Threads

Create thread

client.Beta.Threads.New(ctx, body) (*Thread, error)

post /threads

Create a thread.

Parameters

• body BetaThreadNewParams

  • Messages param.Field[[]BetaThreadNewParamsMessage]

    A list of messages to start the thread with.

    • Content BetaThreadNewParamsMessageContentUnion

      The text contents of the message.

      • string

      • type BetaThreadNewParamsMessageContentArrayOfContentParts []MessageContentPartParamUnionResp

        An array of content parts with a defined type, each can be of type text or images can be passed with image_url or image_file. Image types are only supported on Vision-compatible models.

        • type ImageFileContentBlock struct{…}

          References an image File in the content of a message.

          • ImageFile ImageFile

            • FileID string

              The File ID of the image in the message content. Set purpose="vision" when uploading the File if you need to later display the file content.

            • Detail ImageFileDetail

              Specifies the detail level of the image if specified by the user. low uses fewer tokens, you can opt in to high resolution using high.

              • const ImageFileDetailAuto ImageFileDetail = "auto"

              • const ImageFileDetailLow ImageFileDetail = "low"

              • const ImageFileDetailHigh ImageFileDetail = "high"

          • Type ImageFile

            Always image_file.

            • const ImageFileImageFile ImageFile = "image_file"

        • type ImageURLContentBlock struct{…}

          References an image URL in the content of a message.

          • ImageURL ImageURL

            • URL string

              The external URL of the image, must be a supported image types: jpeg, jpg, png, gif, webp.

            • Detail ImageURLDetail

              Specifies the detail level of the image. low uses fewer tokens, you can opt in to high resolution using high. Default value is auto

              • const ImageURLDetailAuto ImageURLDetail = "auto"

              • const ImageURLDetailLow ImageURLDetail = "low"

              • const ImageURLDetailHigh ImageURLDetail = "high"

          • Type ImageURL

            The type of the content part.

            • const ImageURLImageURL ImageURL = "image_url"

        • type TextContentBlockParam struct{…}

          The text content that is part of a message.

          • Text string

            Text content to be sent to the model

          • Type Text

            Always text.

            • const TextText Text = "text"

    • Role string

      The role of the entity that is creating the message. Allowed values include:

      • user: Indicates the message is sent by an actual user and should be used in most cases to represent user-generated messages.

      • assistant: Indicates the message is generated by the assistant. Use this value to insert messages from the assistant into the conversation.

      • const BetaThreadNewParamsMessageRoleUser BetaThreadNewParamsMessageRole = "user"

      • const BetaThreadNewParamsMessageRoleAssistant BetaThreadNewParamsMessageRole = "assistant"

    • Attachments []BetaThreadNewParamsMessageAttachment

      A list of files attached to the message, and the tools they should be added to.

      • FileID string

        The ID of the file to attach to the message.

      • Tools []BetaThreadNewParamsMessageAttachmentToolUnion

        The tools to add this file to.

        • type CodeInterpreterTool struct{…}

          • Type CodeInterpreter

            The type of tool being defined: code_interpreter

            • const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"

        • type BetaThreadNewParamsMessageAttachmentToolFileSearch struct{…}

          • Type FileSearch

            The type of tool being defined: file_search

            • const FileSearchFileSearch FileSearch = "file_search"

    • Metadata Metadata

      Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

      Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

  • Metadata param.Field[Metadata]

    Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

    Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

  • ToolResources param.Field[BetaThreadNewParamsToolResources]

    A set of resources that are made available to the assistant's tools in this thread. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.

    • CodeInterpreter BetaThreadNewParamsToolResourcesCodeInterpreter

      • FileIDs []string

        A list of file IDs made available to the code_interpreter tool. There can be a maximum of 20 files associated with the tool.

    • FileSearch BetaThreadNewParamsToolResourcesFileSearch

      • VectorStoreIDs []string

        The vector store attached to this thread. There can be a maximum of 1 vector store attached to the thread.

      • VectorStores []BetaThreadNewParamsToolResourcesFileSearchVectorStore

        A helper to create a vector store with file_ids and attach it to this thread. There can be a maximum of 1 vector store attached to the thread.

        • ChunkingStrategy BetaThreadNewParamsToolResourcesFileSearchVectorStoreChunkingStrategyUnion

          The chunking strategy used to chunk the file(s). If not set, will use the auto strategy.

          • type BetaThreadNewParamsToolResourcesFileSearchVectorStoreChunkingStrategyAuto struct{…}

            The default strategy. This strategy currently uses a max_chunk_size_tokens of 800 and chunk_overlap_tokens of 400.

            • Type Auto

              Always auto.

              • const AutoAuto Auto = "auto"

          • type BetaThreadNewParamsToolResourcesFileSearchVectorStoreChunkingStrategyStatic struct{…}

            • Static BetaThreadNewParamsToolResourcesFileSearchVectorStoreChunkingStrategyStaticStatic

              • ChunkOverlapTokens int64

                The number of tokens that overlap between chunks. The default value is 400.

                Note that the overlap must not exceed half of max_chunk_size_tokens.

              • MaxChunkSizeTokens int64

                The maximum number of tokens in each chunk. The default value is 800. The minimum value is 100 and the maximum value is 4096.

            • Type Static

              Always static.

              • const StaticStatic Static = "static"

        • FileIDs []string

          A list of file IDs to add to the vector store. For vector stores created before Nov 2025, there can be a maximum of 10,000 files in a vector store. For vector stores created starting in Nov 2025, the limit is 100,000,000 files.

        • Metadata Metadata

          Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

          Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

Returns

• type Thread struct{…}

  Represents a thread that contains messages.

  • ID string

    The identifier, which can be referenced in API endpoints.

  • CreatedAt int64

    The Unix timestamp (in seconds) for when the thread was created.

  • Metadata Metadata

    Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

    Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

  • Object Thread

    The object type, which is always thread.

    • const ThreadThread Thread = "thread"

  • ToolResources ThreadToolResources

    A set of resources that are made available to the assistant's tools in this thread. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.

    • CodeInterpreter ThreadToolResourcesCodeInterpreter

      • FileIDs []string

        A list of file IDs made available to the code_interpreter tool. There can be a maximum of 20 files associated with the tool.

    • FileSearch ThreadToolResourcesFileSearch

      • VectorStoreIDs []string

        The vector store attached to this thread. There can be a maximum of 1 vector store attached to the thread.

Example

package main

import (
  "context"
  "fmt"

  "github.com/openai/openai-go"
  "github.com/openai/openai-go/option"
)

func main() {
  client := openai.NewClient(
    option.WithAPIKey("My API Key"),
  )
  thread, err := client.Beta.Threads.New(context.TODO(), openai.BetaThreadNewParams{

  })
  if err != nil {
    panic(err.Error())
  }
  fmt.Printf("%+v\n", thread.ID)
}

Response

{
  "id": "id",
  "created_at": 0,
  "metadata": {
    "foo": "string"
  },
  "object": "thread",
  "tool_resources": {
    "code_interpreter": {
      "file_ids": [
        "string"
      ]
    },
    "file_search": {
      "vector_store_ids": [
        "string"
      ]
    }
  }
}

Create thread and run

client.Beta.Threads.NewAndRun(ctx, body) (*Run, error)

post /threads/runs

Create a thread and run it in one request.

Parameters

• body BetaThreadNewAndRunParams

  • AssistantID param.Field[string]

    The ID of the assistant to use to execute this run.

  • Instructions param.Field[string]

    Override the default system message of the assistant. This is useful for modifying the behavior on a per-run basis.

  • MaxCompletionTokens param.Field[int64]

    The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status incomplete. See incomplete_details for more info.

  • MaxPromptTokens param.Field[int64]

    The maximum number of prompt tokens that may be used over the course of the run. The run will make a best effort to use only the number of prompt tokens specified, across multiple turns of the run. If the run exceeds the number of prompt tokens specified, the run will end with status incomplete. See incomplete_details for more info.

  • Metadata param.Field[Metadata]

    Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

    Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

  • Model param.Field[ChatModel]

    The ID of the Model to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used.

    • string

    • type ChatModel string

      • const ChatModelGPT5_6Sol ChatModel = "gpt-5.6-sol"

      • const ChatModelGPT5_6Terra ChatModel = "gpt-5.6-terra"

      • const ChatModelGPT5_6Luna ChatModel = "gpt-5.6-luna"

      • const ChatModelGPT5_4 ChatModel = "gpt-5.4"

      • const ChatModelGPT5_4Mini ChatModel = "gpt-5.4-mini"

      • const ChatModelGPT5_4Nano ChatModel = "gpt-5.4-nano"

      • const ChatModelGPT5_4Mini2026_03_17 ChatModel = "gpt-5.4-mini-2026-03-17"

      • const ChatModelGPT5_4Nano2026_03_17 ChatModel = "gpt-5.4-nano-2026-03-17"

      • const ChatModelGPT5_3ChatLatest ChatModel = "gpt-5.3-chat-latest"

      • const ChatModelGPT5_2 ChatModel = "gpt-5.2"

      • const ChatModelGPT5_2_2025_12_11 ChatModel = "gpt-5.2-2025-12-11"

      • const ChatModelGPT5_2ChatLatest ChatModel = "gpt-5.2-chat-latest"

      • const ChatModelGPT5_2Pro ChatModel = "gpt-5.2-pro"

      • const ChatModelGPT5_2Pro2025_12_11 ChatModel = "gpt-5.2-pro-2025-12-11"

      • const ChatModelGPT5_1 ChatModel = "gpt-5.1"

      • const ChatModelGPT5_1_2025_11_13 ChatModel = "gpt-5.1-2025-11-13"

      • const ChatModelGPT5_1Codex ChatModel = "gpt-5.1-codex"

      • const ChatModelGPT5_1Mini ChatModel = "gpt-5.1-mini"

      • const ChatModelGPT5_1ChatLatest ChatModel = "gpt-5.1-chat-latest"

      • const ChatModelGPT5 ChatModel = "gpt-5"

      • const ChatModelGPT5Mini ChatModel = "gpt-5-mini"

      • const ChatModelGPT5Nano ChatModel = "gpt-5-nano"

      • const ChatModelGPT5_2025_08_07 ChatModel = "gpt-5-2025-08-07"

      • const ChatModelGPT5Mini2025_08_07 ChatModel = "gpt-5-mini-2025-08-07"

      • const ChatModelGPT5Nano2025_08_07 ChatModel = "gpt-5-nano-2025-08-07"

      • const ChatModelGPT5ChatLatest ChatModel = "gpt-5-chat-latest"

      • const ChatModelGPT4_1 ChatModel = "gpt-4.1"

      • const ChatModelGPT4_1Mini ChatModel = "gpt-4.1-mini"

      • const ChatModelGPT4_1Nano ChatModel = "gpt-4.1-nano"

      • const ChatModelGPT4_1_2025_04_14 ChatModel = "gpt-4.1-2025-04-14"

      • const ChatModelGPT4_1Mini2025_04_14 ChatModel = "gpt-4.1-mini-2025-04-14"

      • const ChatModelGPT4_1Nano2025_04_14 ChatModel = "gpt-4.1-nano-2025-04-14"

      • const ChatModelO4Mini ChatModel = "o4-mini"

      • const ChatModelO4Mini2025_04_16 ChatModel = "o4-mini-2025-04-16"

      • const ChatModelO3 ChatModel = "o3"

      • const ChatModelO3_2025_04_16 ChatModel = "o3-2025-04-16"

      • const ChatModelO3Mini ChatModel = "o3-mini"

      • const ChatModelO3Mini2025_01_31 ChatModel = "o3-mini-2025-01-31"

      • const ChatModelO1 ChatModel = "o1"

      • const ChatModelO1_2024_12_17 ChatModel = "o1-2024-12-17"

      • const ChatModelO1Preview ChatModel = "o1-preview"

      • const ChatModelO1Preview2024_09_12 ChatModel = "o1-preview-2024-09-12"

      • const ChatModelO1Mini ChatModel = "o1-mini"

      • const ChatModelO1Mini2024_09_12 ChatModel = "o1-mini-2024-09-12"

      • const ChatModelGPT4o ChatModel = "gpt-4o"

      • const ChatModelGPT4o2024_11_20 ChatModel = "gpt-4o-2024-11-20"

      • const ChatModelGPT4o2024_08_06 ChatModel = "gpt-4o-2024-08-06"

      • const ChatModelGPT4o2024_05_13 ChatModel = "gpt-4o-2024-05-13"

      • const ChatModelGPT4oAudioPreview ChatModel = "gpt-4o-audio-preview"

      • const ChatModelGPT4oAudioPreview2024_10_01 ChatModel = "gpt-4o-audio-preview-2024-10-01"

      • const ChatModelGPT4oAudioPreview2024_12_17 ChatModel = "gpt-4o-audio-preview-2024-12-17"

      • const ChatModelGPT4oAudioPreview2025_06_03 ChatModel = "gpt-4o-audio-preview-2025-06-03"

      • const ChatModelGPT4oMiniAudioPreview ChatModel = "gpt-4o-mini-audio-preview"

      • const ChatModelGPT4oMiniAudioPreview2024_12_17 ChatModel = "gpt-4o-mini-audio-preview-2024-12-17"

      • const ChatModelGPT4oSearchPreview ChatModel = "gpt-4o-search-preview"

      • const ChatModelGPT4oMiniSearchPreview ChatModel = "gpt-4o-mini-search-preview"

      • const ChatModelGPT4oSearchPreview2025_03_11 ChatModel = "gpt-4o-search-preview-2025-03-11"

      • const ChatModelGPT4oMiniSearchPreview2025_03_11 ChatModel = "gpt-4o-mini-search-preview-2025-03-11"

      • const ChatModelChatgpt4oLatest ChatModel = "chatgpt-4o-latest"

      • const ChatModelCodexMiniLatest ChatModel = "codex-mini-latest"

      • const ChatModelGPT4oMini ChatModel = "gpt-4o-mini"

      • const ChatModelGPT4oMini2024_07_18 ChatModel = "gpt-4o-mini-2024-07-18"

      • const ChatModelGPT4Turbo ChatModel = "gpt-4-turbo"

      • const ChatModelGPT4Turbo2024_04_09 ChatModel = "gpt-4-turbo-2024-04-09"

      • const ChatModelGPT4_0125Preview ChatModel = "gpt-4-0125-preview"

      • const ChatModelGPT4TurboPreview ChatModel = "gpt-4-turbo-preview"

      • const ChatModelGPT4_1106Preview ChatModel = "gpt-4-1106-preview"

      • const ChatModelGPT4VisionPreview ChatModel = "gpt-4-vision-preview"

      • const ChatModelGPT4 ChatModel = "gpt-4"

      • const ChatModelGPT4_0314 ChatModel = "gpt-4-0314"

      • const ChatModelGPT4_0613 ChatModel = "gpt-4-0613"

      • const ChatModelGPT4_32k ChatModel = "gpt-4-32k"

      • const ChatModelGPT4_32k0314 ChatModel = "gpt-4-32k-0314"

      • const ChatModelGPT4_32k0613 ChatModel = "gpt-4-32k-0613"

      • const ChatModelGPT3_5Turbo ChatModel = "gpt-3.5-turbo"

      • const ChatModelGPT3_5Turbo16k ChatModel = "gpt-3.5-turbo-16k"

      • const ChatModelGPT3_5Turbo0301 ChatModel = "gpt-3.5-turbo-0301"

      • const ChatModelGPT3_5Turbo0613 ChatModel = "gpt-3.5-turbo-0613"

      • const ChatModelGPT3_5Turbo1106 ChatModel = "gpt-3.5-turbo-1106"

      • const ChatModelGPT3_5Turbo0125 ChatModel = "gpt-3.5-turbo-0125"

      • const ChatModelGPT3_5Turbo16k0613 ChatModel = "gpt-3.5-turbo-16k-0613"

  • ParallelToolCalls param.Field[bool]

    Whether to enable parallel function calling during tool use.

  • ResponseFormat param.Field[AssistantResponseFormatOptionUnion]

    Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.

    Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

    Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.

    Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

  • ``

  • Temperature param.Field[float64]

    What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

  • Thread param.Field[BetaThreadNewAndRunParamsThread]

    Options to create a new thread. If no thread is provided when running a request, an empty thread will be created.

    • Messages []BetaThreadNewAndRunParamsThreadMessage

      A list of messages to start the thread with.

      • Content BetaThreadNewAndRunParamsThreadMessageContentUnion

        The text contents of the message.

        • string

        • []MessageContentPartParamUnion

          • type ImageFileContentBlock struct{…}

            References an image File in the content of a message.

            • ImageFile ImageFile

              • FileID string

                The File ID of the image in the message content. Set purpose="vision" when uploading the File if you need to later display the file content.

              • Detail ImageFileDetail

                Specifies the detail level of the image if specified by the user. low uses fewer tokens, you can opt in to high resolution using high.

                • const ImageFileDetailAuto ImageFileDetail = "auto"

                • const ImageFileDetailLow ImageFileDetail = "low"

                • const ImageFileDetailHigh ImageFileDetail = "high"

            • Type ImageFile

              Always image_file.

              • const ImageFileImageFile ImageFile = "image_file"

          • type ImageURLContentBlock struct{…}

            References an image URL in the content of a message.

            • ImageURL ImageURL

              • URL string

                The external URL of the image, must be a supported image types: jpeg, jpg, png, gif, webp.

              • Detail ImageURLDetail

                Specifies the detail level of the image. low uses fewer tokens, you can opt in to high resolution using high. Default value is auto

                • const ImageURLDetailAuto ImageURLDetail = "auto"

                • const ImageURLDetailLow ImageURLDetail = "low"

                • const ImageURLDetailHigh ImageURLDetail = "high"

            • Type ImageURL

              The type of the content part.

              • const ImageURLImageURL ImageURL = "image_url"

          • type TextContentBlockParam struct{…}

            The text content that is part of a message.

            • Text string

              Text content to be sent to the model

            • Type Text

              Always text.

              • const TextText Text = "text"

      • Role string

        The role of the entity that is creating the message. Allowed values include:

        • user: Indicates the message is sent by an actual user and should be used in most cases to represent user-generated messages.

        • assistant: Indicates the message is generated by the assistant. Use this value to insert messages from the assistant into the conversation.

        • const BetaThreadNewAndRunParamsThreadMessageRoleUser BetaThreadNewAndRunParamsThreadMessageRole = "user"

        • const BetaThreadNewAndRunParamsThreadMessageRoleAssistant BetaThreadNewAndRunParamsThreadMessageRole = "assistant"

      • Attachments []BetaThreadNewAndRunParamsThreadMessageAttachment

        A list of files attached to the message, and the tools they should be added to.

        • FileID string

          The ID of the file to attach to the message.

        • Tools []BetaThreadNewAndRunParamsThreadMessageAttachmentToolUnion

          The tools to add this file to.

          • type CodeInterpreterTool struct{…}

            • Type CodeInterpreter

              The type of tool being defined: code_interpreter

              • const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"

          • BetaThreadNewAndRunParamsThreadMessageAttachmentToolFileSearch

            • Type FileSearch

              The type of tool being defined: file_search

              • const FileSearchFileSearch FileSearch = "file_search"

      • Metadata Metadata

        Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

        Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

    • Metadata Metadata

      Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

      Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

    • ToolResources BetaThreadNewAndRunParamsThreadToolResources

      A set of resources that are made available to the assistant's tools in this thread. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.

      • CodeInterpreter BetaThreadNewAndRunParamsThreadToolResourcesCodeInterpreter

        • FileIDs []string

          A list of file IDs made available to the code_interpreter tool. There can be a maximum of 20 files associated with the tool.

      • FileSearch BetaThreadNewAndRunParamsThreadToolResourcesFileSearch

        • VectorStoreIDs []string

          The vector store attached to this thread. There can be a maximum of 1 vector store attached to the thread.

        • VectorStores []BetaThreadNewAndRunParamsThreadToolResourcesFileSearchVectorStore

          A helper to create a vector store with file_ids and attach it to this thread. There can be a maximum of 1 vector store attached to the thread.

          • ChunkingStrategy BetaThreadNewAndRunParamsThreadToolResourcesFileSearchVectorStoreChunkingStrategyUnion

            The chunking strategy used to chunk the file(s). If not set, will use the auto strategy.

            • BetaThreadNewAndRunParamsThreadToolResourcesFileSearchVectorStoreChunkingStrategyAuto

              • Type Auto

                Always auto.

                • const AutoAuto Auto = "auto"

            • BetaThreadNewAndRunParamsThreadToolResourcesFileSearchVectorStoreChunkingStrategyStatic

              • Static BetaThreadNewAndRunParamsThreadToolResourcesFileSearchVectorStoreChunkingStrategyStaticStatic

                • ChunkOverlapTokens int64

                  The number of tokens that overlap between chunks. The default value is 400.

                  Note that the overlap must not exceed half of max_chunk_size_tokens.

                • MaxChunkSizeTokens int64

                  The maximum number of tokens in each chunk. The default value is 800. The minimum value is 100 and the maximum value is 4096.

              • Type Static

                Always static.

                • const StaticStatic Static = "static"

          • FileIDs []string

            A list of file IDs to add to the vector store. For vector stores created before Nov 2025, there can be a maximum of 10,000 files in a vector store. For vector stores created starting in Nov 2025, the limit is 100,000,000 files.

          • Metadata Metadata

            Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

            Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

  • ToolChoice param.Field[AssistantToolChoiceOptionUnion]

    Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

  • ToolResources param.Field[BetaThreadNewAndRunParamsToolResources]

    A set of resources that are used by the assistant's tools. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.

    • CodeInterpreter BetaThreadNewAndRunParamsToolResourcesCodeInterpreter

      • FileIDs []string

        A list of file IDs made available to the code_interpreter tool. There can be a maximum of 20 files associated with the tool.

    • FileSearch BetaThreadNewAndRunParamsToolResourcesFileSearch

      • VectorStoreIDs []string

        The ID of the vector store attached to this assistant. There can be a maximum of 1 vector store attached to the assistant.

  • Tools param.Field[[]AssistantToolUnion]

    Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis.

    • type CodeInterpreterTool struct{…}

    • type FileSearchTool struct{…}

      • Type FileSearch

        The type of tool being defined: file_search

        • const FileSearchFileSearch FileSearch = "file_search"

      • FileSearch FileSearchToolFileSearch

        Overrides for the file search tool.

        • MaxNumResults int64

          The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

          Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

        • RankingOptions FileSearchToolFileSearchRankingOptions

          The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

          See the file search tool documentation for more information.

          • ScoreThreshold float64

            The score threshold for the file search. All values must be a floating point number between 0 and 1.

          • Ranker string

            The ranker to use for the file search. If not specified will use the auto ranker.

            • const FileSearchToolFileSearchRankingOptionsRankerAuto FileSearchToolFileSearchRankingOptionsRanker = "auto"

            • const FileSearchToolFileSearchRankingOptionsRankerDefault2024_08_21 FileSearchToolFileSearchRankingOptionsRanker = "default_2024_08_21"

    • type FunctionTool struct{…}

      • Function FunctionDefinition

        • Name string

          The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Description string

          A description of what the function does, used by the model to choose when and how to call the function.

        • Parameters FunctionParameters

          The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

          Omitting parameters defines a function with an empty parameter list.

        • Strict bool

          Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

      • Type Function

        The type of tool being defined: function

        • const FunctionFunction Function = "function"

  • TopP param.Field[float64]

    An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

    We generally recommend altering this or temperature but not both.

  • TruncationStrategy param.Field[BetaThreadNewAndRunParamsTruncationStrategy]

    Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.

    • Type string

      The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.

      • const BetaThreadNewAndRunParamsTruncationStrategyTypeAuto BetaThreadNewAndRunParamsTruncationStrategyType = "auto"

      • const BetaThreadNewAndRunParamsTruncationStrategyTypeLastMessages BetaThreadNewAndRunParamsTruncationStrategyType = "last_messages"

    • LastMessages int64

      The number of most recent messages from the thread when constructing the context for the run.

Returns

• type Run struct{…}

  Represents an execution run on a thread.

  • ID string

    The identifier, which can be referenced in API endpoints.

  • AssistantID string

    The ID of the assistant used for execution of this run.

  • CancelledAt int64

    The Unix timestamp (in seconds) for when the run was cancelled.

  • CompletedAt int64

    The Unix timestamp (in seconds) for when the run was completed.

  • CreatedAt int64

    The Unix timestamp (in seconds) for when the run was created.

  • ExpiresAt int64

    The Unix timestamp (in seconds) for when the run will expire.

  • FailedAt int64

    The Unix timestamp (in seconds) for when the run failed.

  • IncompleteDetails RunIncompleteDetails

    Details on why the run is incomplete. Will be null if the run is not incomplete.

    • Reason string

      The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.

      • const RunIncompleteDetailsReasonMaxCompletionTokens RunIncompleteDetailsReason = "max_completion_tokens"

      • const RunIncompleteDetailsReasonMaxPromptTokens RunIncompleteDetailsReason = "max_prompt_tokens"

  • Instructions string

    The instructions that the assistant used for this run.

  • LastError RunLastError

    The last error associated with this run. Will be null if there are no errors.

    • Code string

      One of server_error, rate_limit_exceeded, or invalid_prompt.

      • const RunLastErrorCodeServerError RunLastErrorCode = "server_error"

      • const RunLastErrorCodeRateLimitExceeded RunLastErrorCode = "rate_limit_exceeded"

      • const RunLastErrorCodeInvalidPrompt RunLastErrorCode = "invalid_prompt"

    • Message string

      A human-readable description of the error.

  • MaxCompletionTokens int64

    The maximum number of completion tokens specified to have been used over the course of the run.

  • MaxPromptTokens int64

    The maximum number of prompt tokens specified to have been used over the course of the run.

  • Metadata Metadata

    Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

    Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

  • Model string

    The model that the assistant used for this run.

  • Object ThreadRun

    The object type, which is always thread.run.

    • const ThreadRunThreadRun ThreadRun = "thread.run"

  • ParallelToolCalls bool

    Whether to enable parallel function calling during tool use.

  • RequiredAction RunRequiredAction

    Details on the action required to continue the run. Will be null if no action is required.

    • SubmitToolOutputs RunRequiredActionSubmitToolOutputs

      Details on the tool outputs needed for this run to continue.

      • ToolCalls []RequiredActionFunctionToolCall

        A list of the relevant tool calls.

        • ID string

          The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.

        • Function RequiredActionFunctionToolCallFunction

          The function definition.

          • Arguments string

            The arguments that the model expects you to pass to the function.

          • Name string

            The name of the function.

        • Type Function

          The type of tool call the output is required for. For now, this is always function.

          • const FunctionFunction Function = "function"

    • Type SubmitToolOutputs

      For now, this is always submit_tool_outputs.

      • const SubmitToolOutputsSubmitToolOutputs SubmitToolOutputs = "submit_tool_outputs"

  • ResponseFormat AssistantResponseFormatOptionUnion

    Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.

    Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

    Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.

    Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

    • type Auto string

      auto is the default value

      • const AutoAuto Auto = "auto"

    • type ResponseFormatText struct{…}

      Default response format. Used to generate text responses.

      • Type Text

        The type of response format being defined. Always text.

        • const TextText Text = "text"

    • type ResponseFormatJSONObject struct{…}

      JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.

      • Type JSONObject

        The type of response format being defined. Always json_object.

        • const JSONObjectJSONObject JSONObject = "json_object"

    • type ResponseFormatJSONSchema struct{…}

      JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

      • JSONSchema ResponseFormatJSONSchemaJSONSchema

        Structured Outputs configuration options, including a JSON Schema.

        • Name string

          The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Description string

          A description of what the response format is for, used by the model to determine how to respond in the format.

        • Schema map[string, any]

          The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

        • Strict bool

          Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.

      • Type JSONSchema

        The type of response format being defined. Always json_schema.

        • const JSONSchemaJSONSchema JSONSchema = "json_schema"

  • StartedAt int64

    The Unix timestamp (in seconds) for when the run was started.

  • Status RunStatus

    The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.

    • const RunStatusQueued RunStatus = "queued"

    • const RunStatusInProgress RunStatus = "in_progress"

    • const RunStatusRequiresAction RunStatus = "requires_action"

    • const RunStatusCancelling RunStatus = "cancelling"

    • const RunStatusCancelled RunStatus = "cancelled"

    • const RunStatusFailed RunStatus = "failed"

    • const RunStatusCompleted RunStatus = "completed"

    • const RunStatusIncomplete RunStatus = "incomplete"

    • const RunStatusExpired RunStatus = "expired"

  • ThreadID string

    The ID of the thread that was executed on as a part of this run.

  • ToolChoice AssistantToolChoiceOptionUnion

    Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

    • type AssistantToolChoiceOptionAuto string

      none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.

      • const AssistantToolChoiceOptionAutoNone AssistantToolChoiceOptionAuto = "none"

      • const AssistantToolChoiceOptionAutoAuto AssistantToolChoiceOptionAuto = "auto"

      • const AssistantToolChoiceOptionAutoRequired AssistantToolChoiceOptionAuto = "required"

    • type AssistantToolChoice struct{…}

      Specifies a tool the model should use. Use to force the model to call a specific tool.

      • Type AssistantToolChoiceType

        The type of the tool. If type is function, the function name must be set

        • const AssistantToolChoiceTypeFunction AssistantToolChoiceType = "function"

        • const AssistantToolChoiceTypeCodeInterpreter AssistantToolChoiceType = "code_interpreter"

        • const AssistantToolChoiceTypeFileSearch AssistantToolChoiceType = "file_search"

      • Function AssistantToolChoiceFunction

        • Name string

          The name of the function to call.

  • Tools []AssistantToolUnion

    The list of tools that the assistant used for this run.

    • type CodeInterpreterTool struct{…}

      • Type CodeInterpreter

        The type of tool being defined: code_interpreter

        • const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"

    • type FileSearchTool struct{…}

      • Type FileSearch

        The type of tool being defined: file_search

        • const FileSearchFileSearch FileSearch = "file_search"

      • FileSearch FileSearchToolFileSearch

        Overrides for the file search tool.

        • MaxNumResults int64

          The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

          Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

        • RankingOptions FileSearchToolFileSearchRankingOptions

          The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

          See the file search tool documentation for more information.

          • ScoreThreshold float64

            The score threshold for the file search. All values must be a floating point number between 0 and 1.

          • Ranker string

            The ranker to use for the file search. If not specified will use the auto ranker.

            • const FileSearchToolFileSearchRankingOptionsRankerAuto FileSearchToolFileSearchRankingOptionsRanker = "auto"

            • const FileSearchToolFileSearchRankingOptionsRankerDefault2024_08_21 FileSearchToolFileSearchRankingOptionsRanker = "default_2024_08_21"

    • type FunctionTool struct{…}

      • Function FunctionDefinition

        • Name string

          The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Description string

          A description of what the function does, used by the model to choose when and how to call the function.

        • Parameters FunctionParameters

          The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

          Omitting parameters defines a function with an empty parameter list.

        • Strict bool

          Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

      • Type Function

        The type of tool being defined: function

        • const FunctionFunction Function = "function"

  • TruncationStrategy RunTruncationStrategy

    Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.

    • Type string

      The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.

      • const RunTruncationStrategyTypeAuto RunTruncationStrategyType = "auto"

      • const RunTruncationStrategyTypeLastMessages RunTruncationStrategyType = "last_messages"

    • LastMessages int64

      The number of most recent messages from the thread when constructing the context for the run.

  • Usage RunUsage

    Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).

    • CompletionTokens int64

      Number of completion tokens used over the course of the run.

    • PromptTokens int64

      Number of prompt tokens used over the course of the run.

    • TotalTokens int64

      Total number of tokens used (prompt + completion).

  • Temperature float64

    The sampling temperature used for this run. If not set, defaults to 1.

  • TopP float64

    The nucleus sampling value used for this run. If not set, defaults to 1.

Example

package main

import (
  "context"
  "fmt"

  "github.com/openai/openai-go"
  "github.com/openai/openai-go/option"
)

func main() {
  client := openai.NewClient(
    option.WithAPIKey("My API Key"),
  )
  run, err := client.Beta.Threads.NewAndRun(context.TODO(), openai.BetaThreadNewAndRunParams{
    AssistantID: "assistant_id",
  })
  if err != nil {
    panic(err.Error())
  }
  fmt.Printf("%+v\n", run.ID)
}

Response

{
  "id": "id",
  "assistant_id": "assistant_id",
  "cancelled_at": 0,
  "completed_at": 0,
  "created_at": 0,
  "expires_at": 0,
  "failed_at": 0,
  "incomplete_details": {
    "reason": "max_completion_tokens"
  },
  "instructions": "instructions",
  "last_error": {
    "code": "server_error",
    "message": "message"
  },
  "max_completion_tokens": 256,
  "max_prompt_tokens": 256,
  "metadata": {
    "foo": "string"
  },
  "model": "model",
  "object": "thread.run",
  "parallel_tool_calls": true,
  "required_action": {
    "submit_tool_outputs": {
      "tool_calls": [
        {
          "id": "id",
          "function": {
            "arguments": "arguments",
            "name": "name"
          },
          "type": "function"
        }
      ]
    },
    "type": "submit_tool_outputs"
  },
  "response_format": "auto",
  "started_at": 0,
  "status": "queued",
  "thread_id": "thread_id",
  "tool_choice": "none",
  "tools": [
    {
      "type": "code_interpreter"
    }
  ],
  "truncation_strategy": {
    "type": "auto",
    "last_messages": 1
  },
  "usage": {
    "completion_tokens": 0,
    "prompt_tokens": 0,
    "total_tokens": 0
  },
  "temperature": 0,
  "top_p": 0
}

Retrieve thread

client.Beta.Threads.Get(ctx, threadID) (*Thread, error)

get /threads/{thread_id}

Retrieves a thread.

Parameters

• threadID string

Returns

• type Thread struct{…}

  Represents a thread that contains messages.

  • ID string

    The identifier, which can be referenced in API endpoints.

  • CreatedAt int64

    The Unix timestamp (in seconds) for when the thread was created.

  • Metadata Metadata

    Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

    Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

  • Object Thread

    The object type, which is always thread.

    • const ThreadThread Thread = "thread"

  • ToolResources ThreadToolResources

    A set of resources that are made available to the assistant's tools in this thread. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.

    • CodeInterpreter ThreadToolResourcesCodeInterpreter

      • FileIDs []string

        A list of file IDs made available to the code_interpreter tool. There can be a maximum of 20 files associated with the tool.

    • FileSearch ThreadToolResourcesFileSearch

      • VectorStoreIDs []string

        The vector store attached to this thread. There can be a maximum of 1 vector store attached to the thread.

Example

package main

import (
  "context"
  "fmt"

  "github.com/openai/openai-go"
  "github.com/openai/openai-go/option"
)

func main() {
  client := openai.NewClient(
    option.WithAPIKey("My API Key"),
  )
  thread, err := client.Beta.Threads.Get(context.TODO(), "thread_id")
  if err != nil {
    panic(err.Error())
  }
  fmt.Printf("%+v\n", thread.ID)
}

Response

{
  "id": "id",
  "created_at": 0,
  "metadata": {
    "foo": "string"
  },
  "object": "thread",
  "tool_resources": {
    "code_interpreter": {
      "file_ids": [
        "string"
      ]
    },
    "file_search": {
      "vector_store_ids": [
        "string"
      ]
    }
  }
}

Modify thread

client.Beta.Threads.Update(ctx, threadID, body) (*Thread, error)

post /threads/{thread_id}

Modifies a thread.

Parameters

• threadID string

• body BetaThreadUpdateParams

  • Metadata param.Field[Metadata]

    Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

    Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

  • ToolResources param.Field[BetaThreadUpdateParamsToolResources]

    A set of resources that are made available to the assistant's tools in this thread. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.

    • CodeInterpreter BetaThreadUpdateParamsToolResourcesCodeInterpreter

      • FileIDs []string

        A list of file IDs made available to the code_interpreter tool. There can be a maximum of 20 files associated with the tool.

    • FileSearch BetaThreadUpdateParamsToolResourcesFileSearch

      • VectorStoreIDs []string

        The vector store attached to this thread. There can be a maximum of 1 vector store attached to the thread.

Returns

• type Thread struct{…}

  Represents a thread that contains messages.

  • ID string

    The identifier, which can be referenced in API endpoints.

  • CreatedAt int64

    The Unix timestamp (in seconds) for when the thread was created.

  • Metadata Metadata

    Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

    Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

  • Object Thread

    The object type, which is always thread.

    • const ThreadThread Thread = "thread"

  • ToolResources ThreadToolResources

    A set of resources that are made available to the assistant's tools in this thread. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.

    • CodeInterpreter ThreadToolResourcesCodeInterpreter

      • FileIDs []string

        A list of file IDs made available to the code_interpreter tool. There can be a maximum of 20 files associated with the tool.

    • FileSearch ThreadToolResourcesFileSearch

      • VectorStoreIDs []string

        The vector store attached to this thread. There can be a maximum of 1 vector store attached to the thread.

Example

package main

import (
  "context"
  "fmt"

  "github.com/openai/openai-go"
  "github.com/openai/openai-go/option"
)

func main() {
  client := openai.NewClient(
    option.WithAPIKey("My API Key"),
  )
  thread, err := client.Beta.Threads.Update(
    context.TODO(),
    "thread_id",
    openai.BetaThreadUpdateParams{

    },
  )
  if err != nil {
    panic(err.Error())
  }
  fmt.Printf("%+v\n", thread.ID)
}

Response

{
  "id": "id",
  "created_at": 0,
  "metadata": {
    "foo": "string"
  },
  "object": "thread",
  "tool_resources": {
    "code_interpreter": {
      "file_ids": [
        "string"
      ]
    },
    "file_search": {
      "vector_store_ids": [
        "string"
      ]
    }
  }
}

Delete thread

client.Beta.Threads.Delete(ctx, threadID) (*ThreadDeleted, error)

delete /threads/{thread_id}

Delete a thread.

Parameters

• threadID string

Returns

• type ThreadDeleted struct{…}

  • ID string

  • Deleted bool

  • Object ThreadDeleted

    • const ThreadDeletedThreadDeleted ThreadDeleted = "thread.deleted"

Example

package main

import (
  "context"
  "fmt"

  "github.com/openai/openai-go"
  "github.com/openai/openai-go/option"
)

func main() {
  client := openai.NewClient(
    option.WithAPIKey("My API Key"),
  )
  threadDeleted, err := client.Beta.Threads.Delete(context.TODO(), "thread_id")
  if err != nil {
    panic(err.Error())
  }
  fmt.Printf("%+v\n", threadDeleted.ID)
}

Response

{
  "id": "id",
  "deleted": true,
  "object": "thread.deleted"
}

Domain Types

Assistant Response Format Option

• type AssistantResponseFormatOptionUnion interface{…}

  Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.

  Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

  Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.

  Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

  • type Auto string

    auto is the default value

    • const AutoAuto Auto = "auto"

  • type ResponseFormatText struct{…}

    Default response format. Used to generate text responses.

    • Type Text

      The type of response format being defined. Always text.

      • const TextText Text = "text"

  • type ResponseFormatJSONObject struct{…}

    JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.

    • Type JSONObject

      The type of response format being defined. Always json_object.

      • const JSONObjectJSONObject JSONObject = "json_object"

  • type ResponseFormatJSONSchema struct{…}

    JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

    • JSONSchema ResponseFormatJSONSchemaJSONSchema

      Structured Outputs configuration options, including a JSON Schema.

      • Name string

        The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

      • Description string

        A description of what the response format is for, used by the model to determine how to respond in the format.

      • Schema map[string, any]

        The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

      • Strict bool

        Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.

    • Type JSONSchema

      The type of response format being defined. Always json_schema.

      • const JSONSchemaJSONSchema JSONSchema = "json_schema"

Assistant Tool Choice

• type AssistantToolChoice struct{…}

  Specifies a tool the model should use. Use to force the model to call a specific tool.

  • Type AssistantToolChoiceType

    The type of the tool. If type is function, the function name must be set

    • const AssistantToolChoiceTypeFunction AssistantToolChoiceType = "function"

    • const AssistantToolChoiceTypeCodeInterpreter AssistantToolChoiceType = "code_interpreter"

    • const AssistantToolChoiceTypeFileSearch AssistantToolChoiceType = "file_search"

  • Function AssistantToolChoiceFunction

    • Name string

      The name of the function to call.

Assistant Tool Choice Function

• type AssistantToolChoiceFunction struct{…}

  • Name string

    The name of the function to call.

Assistant Tool Choice Option

• type AssistantToolChoiceOptionUnion interface{…}

  Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

  • type AssistantToolChoiceOptionAuto string

    none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.

    • const AssistantToolChoiceOptionAutoNone AssistantToolChoiceOptionAuto = "none"

    • const AssistantToolChoiceOptionAutoAuto AssistantToolChoiceOptionAuto = "auto"

    • const AssistantToolChoiceOptionAutoRequired AssistantToolChoiceOptionAuto = "required"

  • type AssistantToolChoice struct{…}

    Specifies a tool the model should use. Use to force the model to call a specific tool.

    • Type AssistantToolChoiceType

      The type of the tool. If type is function, the function name must be set

      • const AssistantToolChoiceTypeFunction AssistantToolChoiceType = "function"

      • const AssistantToolChoiceTypeCodeInterpreter AssistantToolChoiceType = "code_interpreter"

      • const AssistantToolChoiceTypeFileSearch AssistantToolChoiceType = "file_search"

    • Function AssistantToolChoiceFunction

      • Name string

        The name of the function to call.

Thread

• type Thread struct{…}

  Represents a thread that contains messages.

  • ID string

    The identifier, which can be referenced in API endpoints.

  • CreatedAt int64

    The Unix timestamp (in seconds) for when the thread was created.

  • Metadata Metadata

    Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

    Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

  • Object Thread

    The object type, which is always thread.

    • const ThreadThread Thread = "thread"

  • ToolResources ThreadToolResources

    A set of resources that are made available to the assistant's tools in this thread. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.

    • CodeInterpreter ThreadToolResourcesCodeInterpreter

      • FileIDs []string

        A list of file IDs made available to the code_interpreter tool. There can be a maximum of 20 files associated with the tool.

    • FileSearch ThreadToolResourcesFileSearch

      • VectorStoreIDs []string

        The vector store attached to this thread. There can be a maximum of 1 vector store attached to the thread.

Thread Deleted

• type ThreadDeleted struct{…}

  • ID string

  • Deleted bool

  • Object ThreadDeleted

    • const ThreadDeletedThreadDeleted ThreadDeleted = "thread.deleted"

Runs

List runs

client.Beta.Threads.Runs.List(ctx, threadID, query) (*CursorPage[Run], error)

get /threads/{thread_id}/runs

Returns a list of runs belonging to a thread.

Parameters

• threadID string

• query BetaThreadRunListParams

  • After param.Field[string]

    A cursor for use in pagination. after is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.

  • Before param.Field[string]

    A cursor for use in pagination. before is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.

  • Limit param.Field[int64]

    A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.

  • Order param.Field[BetaThreadRunListParamsOrder]

    Sort order by the created_at timestamp of the objects. asc for ascending order and desc for descending order.

    • const BetaThreadRunListParamsOrderAsc BetaThreadRunListParamsOrder = "asc"

    • const BetaThreadRunListParamsOrderDesc BetaThreadRunListParamsOrder = "desc"

Returns

• type Run struct{…}

  Represents an execution run on a thread.

  • ID string

    The identifier, which can be referenced in API endpoints.

  • AssistantID string

    The ID of the assistant used for execution of this run.

  • CancelledAt int64

    The Unix timestamp (in seconds) for when the run was cancelled.

  • CompletedAt int64

    The Unix timestamp (in seconds) for when the run was completed.

  • CreatedAt int64

    The Unix timestamp (in seconds) for when the run was created.

  • ExpiresAt int64

    The Unix timestamp (in seconds) for when the run will expire.

  • FailedAt int64

    The Unix timestamp (in seconds) for when the run failed.

  • IncompleteDetails RunIncompleteDetails

    Details on why the run is incomplete. Will be null if the run is not incomplete.

    • Reason string

      The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.

      • const RunIncompleteDetailsReasonMaxCompletionTokens RunIncompleteDetailsReason = "max_completion_tokens"

      • const RunIncompleteDetailsReasonMaxPromptTokens RunIncompleteDetailsReason = "max_prompt_tokens"

  • Instructions string

    The instructions that the assistant used for this run.

  • LastError RunLastError

    The last error associated with this run. Will be null if there are no errors.

    • Code string

      One of server_error, rate_limit_exceeded, or invalid_prompt.

      • const RunLastErrorCodeServerError RunLastErrorCode = "server_error"

      • const RunLastErrorCodeRateLimitExceeded RunLastErrorCode = "rate_limit_exceeded"

      • const RunLastErrorCodeInvalidPrompt RunLastErrorCode = "invalid_prompt"

    • Message string

      A human-readable description of the error.

  • MaxCompletionTokens int64

    The maximum number of completion tokens specified to have been used over the course of the run.

  • MaxPromptTokens int64

    The maximum number of prompt tokens specified to have been used over the course of the run.

  • Metadata Metadata

    Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

    Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

  • Model string

    The model that the assistant used for this run.

  • Object ThreadRun

    The object type, which is always thread.run.

    • const ThreadRunThreadRun ThreadRun = "thread.run"

  • ParallelToolCalls bool

    Whether to enable parallel function calling during tool use.

  • RequiredAction RunRequiredAction

    Details on the action required to continue the run. Will be null if no action is required.

    • SubmitToolOutputs RunRequiredActionSubmitToolOutputs

      Details on the tool outputs needed for this run to continue.

      • ToolCalls []RequiredActionFunctionToolCall

        A list of the relevant tool calls.

        • ID string

          The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.

        • Function RequiredActionFunctionToolCallFunction

          The function definition.

          • Arguments string

            The arguments that the model expects you to pass to the function.

          • Name string

            The name of the function.

        • Type Function

          The type of tool call the output is required for. For now, this is always function.

          • const FunctionFunction Function = "function"

    • Type SubmitToolOutputs

      For now, this is always submit_tool_outputs.

      • const SubmitToolOutputsSubmitToolOutputs SubmitToolOutputs = "submit_tool_outputs"

  • ResponseFormat AssistantResponseFormatOptionUnion

    Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.

    Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

    Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.

    Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

    • type Auto string

      auto is the default value

      • const AutoAuto Auto = "auto"

    • type ResponseFormatText struct{…}

      Default response format. Used to generate text responses.

      • Type Text

        The type of response format being defined. Always text.

        • const TextText Text = "text"

    • type ResponseFormatJSONObject struct{…}

      JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.

      • Type JSONObject

        The type of response format being defined. Always json_object.

        • const JSONObjectJSONObject JSONObject = "json_object"

    • type ResponseFormatJSONSchema struct{…}

      JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

      • JSONSchema ResponseFormatJSONSchemaJSONSchema

        Structured Outputs configuration options, including a JSON Schema.

        • Name string

          The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Description string

          A description of what the response format is for, used by the model to determine how to respond in the format.

        • Schema map[string, any]

          The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

        • Strict bool

          Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.

      • Type JSONSchema

        The type of response format being defined. Always json_schema.

        • const JSONSchemaJSONSchema JSONSchema = "json_schema"

  • StartedAt int64

    The Unix timestamp (in seconds) for when the run was started.

  • Status RunStatus

    The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.

    • const RunStatusQueued RunStatus = "queued"

    • const RunStatusInProgress RunStatus = "in_progress"

    • const RunStatusRequiresAction RunStatus = "requires_action"

    • const RunStatusCancelling RunStatus = "cancelling"

    • const RunStatusCancelled RunStatus = "cancelled"

    • const RunStatusFailed RunStatus = "failed"

    • const RunStatusCompleted RunStatus = "completed"

    • const RunStatusIncomplete RunStatus = "incomplete"

    • const RunStatusExpired RunStatus = "expired"

  • ThreadID string

    The ID of the thread that was executed on as a part of this run.

  • ToolChoice AssistantToolChoiceOptionUnion

    Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

    • type AssistantToolChoiceOptionAuto string

      none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.

      • const AssistantToolChoiceOptionAutoNone AssistantToolChoiceOptionAuto = "none"

      • const AssistantToolChoiceOptionAutoAuto AssistantToolChoiceOptionAuto = "auto"

      • const AssistantToolChoiceOptionAutoRequired AssistantToolChoiceOptionAuto = "required"

    • type AssistantToolChoice struct{…}

      Specifies a tool the model should use. Use to force the model to call a specific tool.

      • Type AssistantToolChoiceType

        The type of the tool. If type is function, the function name must be set

        • const AssistantToolChoiceTypeFunction AssistantToolChoiceType = "function"

        • const AssistantToolChoiceTypeCodeInterpreter AssistantToolChoiceType = "code_interpreter"

        • const AssistantToolChoiceTypeFileSearch AssistantToolChoiceType = "file_search"

      • Function AssistantToolChoiceFunction

        • Name string

          The name of the function to call.

  • Tools []AssistantToolUnion

    The list of tools that the assistant used for this run.

    • type CodeInterpreterTool struct{…}

      • Type CodeInterpreter

        The type of tool being defined: code_interpreter

        • const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"

    • type FileSearchTool struct{…}

      • Type FileSearch

        The type of tool being defined: file_search

        • const FileSearchFileSearch FileSearch = "file_search"

      • FileSearch FileSearchToolFileSearch

        Overrides for the file search tool.

        • MaxNumResults int64

          The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

          Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

        • RankingOptions FileSearchToolFileSearchRankingOptions

          The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

          See the file search tool documentation for more information.

          • ScoreThreshold float64

            The score threshold for the file search. All values must be a floating point number between 0 and 1.

          • Ranker string

            The ranker to use for the file search. If not specified will use the auto ranker.

            • const FileSearchToolFileSearchRankingOptionsRankerAuto FileSearchToolFileSearchRankingOptionsRanker = "auto"

            • const FileSearchToolFileSearchRankingOptionsRankerDefault2024_08_21 FileSearchToolFileSearchRankingOptionsRanker = "default_2024_08_21"

    • type FunctionTool struct{…}

      • Function FunctionDefinition

        • Name string

          The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Description string

          A description of what the function does, used by the model to choose when and how to call the function.

        • Parameters FunctionParameters

          The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

          Omitting parameters defines a function with an empty parameter list.

        • Strict bool

          Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

      • Type Function

        The type of tool being defined: function

        • const FunctionFunction Function = "function"

  • TruncationStrategy RunTruncationStrategy

    Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.

    • Type string

      The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.

      • const RunTruncationStrategyTypeAuto RunTruncationStrategyType = "auto"

      • const RunTruncationStrategyTypeLastMessages RunTruncationStrategyType = "last_messages"

    • LastMessages int64

      The number of most recent messages from the thread when constructing the context for the run.

  • Usage RunUsage

    Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).

    • CompletionTokens int64

      Number of completion tokens used over the course of the run.

    • PromptTokens int64

      Number of prompt tokens used over the course of the run.

    • TotalTokens int64

      Total number of tokens used (prompt + completion).

  • Temperature float64

    The sampling temperature used for this run. If not set, defaults to 1.

  • TopP float64

    The nucleus sampling value used for this run. If not set, defaults to 1.

Example

package main

import (
  "context"
  "fmt"

  "github.com/openai/openai-go"
  "github.com/openai/openai-go/option"
)

func main() {
  client := openai.NewClient(
    option.WithAPIKey("My API Key"),
  )
  page, err := client.Beta.Threads.Runs.List(
    context.TODO(),
    "thread_id",
    openai.BetaThreadRunListParams{

    },
  )
  if err != nil {
    panic(err.Error())
  }
  fmt.Printf("%+v\n", page)
}

Response

{
  "data": [
    {
      "id": "id",
      "assistant_id": "assistant_id",
      "cancelled_at": 0,
      "completed_at": 0,
      "created_at": 0,
      "expires_at": 0,
      "failed_at": 0,
      "incomplete_details": {
        "reason": "max_completion_tokens"
      },
      "instructions": "instructions",
      "last_error": {
        "code": "server_error",
        "message": "message"
      },
      "max_completion_tokens": 256,
      "max_prompt_tokens": 256,
      "metadata": {
        "foo": "string"
      },
      "model": "model",
      "object": "thread.run",
      "parallel_tool_calls": true,
      "required_action": {
        "submit_tool_outputs": {
          "tool_calls": [
            {
              "id": "id",
              "function": {
                "arguments": "arguments",
                "name": "name"
              },
              "type": "function"
            }
          ]
        },
        "type": "submit_tool_outputs"
      },
      "response_format": "auto",
      "started_at": 0,
      "status": "queued",
      "thread_id": "thread_id",
      "tool_choice": "none",
      "tools": [
        {
          "type": "code_interpreter"
        }
      ],
      "truncation_strategy": {
        "type": "auto",
        "last_messages": 1
      },
      "usage": {
        "completion_tokens": 0,
        "prompt_tokens": 0,
        "total_tokens": 0
      },
      "temperature": 0,
      "top_p": 0
    }
  ],
  "first_id": "run_abc123",
  "has_more": false,
  "last_id": "run_abc456",
  "object": "list"
}

Create run

client.Beta.Threads.Runs.New(ctx, threadID, params) (*Run, error)

post /threads/{thread_id}/runs

Create a run.

Parameters

• threadID string

• params BetaThreadRunNewParams

  • AssistantID param.Field[string]

    Body param: The ID of the assistant to use to execute this run.

  • Include param.Field[[]RunStepInclude]

    Query param: A list of additional fields to include in the response. Currently the only supported value is step_details.tool_calls[*].file_search.results[*].content to fetch the file search result content.

    See the file search tool documentation for more information.

    • const RunStepIncludeStepDetailsToolCallsFileSearchResultsContent RunStepInclude = "step_details.tool_calls[*].file_search.results[*].content"

  • AdditionalInstructions param.Field[string]

    Body param: Appends additional instructions at the end of the instructions for the run. This is useful for modifying the behavior on a per-run basis without overriding other instructions.

  • AdditionalMessages param.Field[[]BetaThreadRunNewParamsAdditionalMessage]

    Body param: Adds additional messages to the thread before creating the run.

    • Content BetaThreadRunNewParamsAdditionalMessageContentUnion

      The text contents of the message.

      • string

      • []MessageContentPartParamUnion

        • type ImageFileContentBlock struct{…}

          References an image File in the content of a message.

          • ImageFile ImageFile

            • FileID string

              The File ID of the image in the message content. Set purpose="vision" when uploading the File if you need to later display the file content.

            • Detail ImageFileDetail

              Specifies the detail level of the image if specified by the user. low uses fewer tokens, you can opt in to high resolution using high.

              • const ImageFileDetailAuto ImageFileDetail = "auto"

              • const ImageFileDetailLow ImageFileDetail = "low"

              • const ImageFileDetailHigh ImageFileDetail = "high"

          • Type ImageFile

            Always image_file.

            • const ImageFileImageFile ImageFile = "image_file"

        • type ImageURLContentBlock struct{…}

          References an image URL in the content of a message.

          • ImageURL ImageURL

            • URL string

              The external URL of the image, must be a supported image types: jpeg, jpg, png, gif, webp.

            • Detail ImageURLDetail

              Specifies the detail level of the image. low uses fewer tokens, you can opt in to high resolution using high. Default value is auto

              • const ImageURLDetailAuto ImageURLDetail = "auto"

              • const ImageURLDetailLow ImageURLDetail = "low"

              • const ImageURLDetailHigh ImageURLDetail = "high"

          • Type ImageURL

            The type of the content part.

            • const ImageURLImageURL ImageURL = "image_url"

        • type TextContentBlockParam struct{…}

          The text content that is part of a message.

          • Text string

            Text content to be sent to the model

          • Type Text

            Always text.

            • const TextText Text = "text"

    • Role string

      The role of the entity that is creating the message. Allowed values include:

      • user: Indicates the message is sent by an actual user and should be used in most cases to represent user-generated messages.

      • assistant: Indicates the message is generated by the assistant. Use this value to insert messages from the assistant into the conversation.

      • const BetaThreadRunNewParamsAdditionalMessageRoleUser BetaThreadRunNewParamsAdditionalMessageRole = "user"

      • const BetaThreadRunNewParamsAdditionalMessageRoleAssistant BetaThreadRunNewParamsAdditionalMessageRole = "assistant"

    • Attachments []BetaThreadRunNewParamsAdditionalMessageAttachment

      A list of files attached to the message, and the tools they should be added to.

      • FileID string

        The ID of the file to attach to the message.

      • Tools []BetaThreadRunNewParamsAdditionalMessageAttachmentToolUnion

        The tools to add this file to.

        • type CodeInterpreterTool struct{…}

          • Type CodeInterpreter

            The type of tool being defined: code_interpreter

            • const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"

        • BetaThreadRunNewParamsAdditionalMessageAttachmentToolFileSearch

          • Type FileSearch

            The type of tool being defined: file_search

            • const FileSearchFileSearch FileSearch = "file_search"

    • Metadata Metadata

      Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

      Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

  • Instructions param.Field[string]

    Body param: Overrides the instructions of the assistant. This is useful for modifying the behavior on a per-run basis.

  • MaxCompletionTokens param.Field[int64]

    Body param: The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status incomplete. See incomplete_details for more info.

  • MaxPromptTokens param.Field[int64]

    Body param: The maximum number of prompt tokens that may be used over the course of the run. The run will make a best effort to use only the number of prompt tokens specified, across multiple turns of the run. If the run exceeds the number of prompt tokens specified, the run will end with status incomplete. See incomplete_details for more info.

  • Metadata param.Field[Metadata]

    Body param: Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

    Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

  • Model param.Field[ChatModel]

    Body param: The ID of the Model to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used.

    • string

    • type ChatModel string

      • const ChatModelGPT5_6Sol ChatModel = "gpt-5.6-sol"

      • const ChatModelGPT5_6Terra ChatModel = "gpt-5.6-terra"

      • const ChatModelGPT5_6Luna ChatModel = "gpt-5.6-luna"

      • const ChatModelGPT5_4 ChatModel = "gpt-5.4"

      • const ChatModelGPT5_4Mini ChatModel = "gpt-5.4-mini"

      • const ChatModelGPT5_4Nano ChatModel = "gpt-5.4-nano"

      • const ChatModelGPT5_4Mini2026_03_17 ChatModel = "gpt-5.4-mini-2026-03-17"

      • const ChatModelGPT5_4Nano2026_03_17 ChatModel = "gpt-5.4-nano-2026-03-17"

      • const ChatModelGPT5_3ChatLatest ChatModel = "gpt-5.3-chat-latest"

      • const ChatModelGPT5_2 ChatModel = "gpt-5.2"

      • const ChatModelGPT5_2_2025_12_11 ChatModel = "gpt-5.2-2025-12-11"

      • const ChatModelGPT5_2ChatLatest ChatModel = "gpt-5.2-chat-latest"

      • const ChatModelGPT5_2Pro ChatModel = "gpt-5.2-pro"

      • const ChatModelGPT5_2Pro2025_12_11 ChatModel = "gpt-5.2-pro-2025-12-11"

      • const ChatModelGPT5_1 ChatModel = "gpt-5.1"

      • const ChatModelGPT5_1_2025_11_13 ChatModel = "gpt-5.1-2025-11-13"

      • const ChatModelGPT5_1Codex ChatModel = "gpt-5.1-codex"

      • const ChatModelGPT5_1Mini ChatModel = "gpt-5.1-mini"

      • const ChatModelGPT5_1ChatLatest ChatModel = "gpt-5.1-chat-latest"

      • const ChatModelGPT5 ChatModel = "gpt-5"

      • const ChatModelGPT5Mini ChatModel = "gpt-5-mini"

      • const ChatModelGPT5Nano ChatModel = "gpt-5-nano"

      • const ChatModelGPT5_2025_08_07 ChatModel = "gpt-5-2025-08-07"

      • const ChatModelGPT5Mini2025_08_07 ChatModel = "gpt-5-mini-2025-08-07"

      • const ChatModelGPT5Nano2025_08_07 ChatModel = "gpt-5-nano-2025-08-07"

      • const ChatModelGPT5ChatLatest ChatModel = "gpt-5-chat-latest"

      • const ChatModelGPT4_1 ChatModel = "gpt-4.1"

      • const ChatModelGPT4_1Mini ChatModel = "gpt-4.1-mini"

      • const ChatModelGPT4_1Nano ChatModel = "gpt-4.1-nano"

      • const ChatModelGPT4_1_2025_04_14 ChatModel = "gpt-4.1-2025-04-14"

      • const ChatModelGPT4_1Mini2025_04_14 ChatModel = "gpt-4.1-mini-2025-04-14"

      • const ChatModelGPT4_1Nano2025_04_14 ChatModel = "gpt-4.1-nano-2025-04-14"

      • const ChatModelO4Mini ChatModel = "o4-mini"

      • const ChatModelO4Mini2025_04_16 ChatModel = "o4-mini-2025-04-16"

      • const ChatModelO3 ChatModel = "o3"

      • const ChatModelO3_2025_04_16 ChatModel = "o3-2025-04-16"

      • const ChatModelO3Mini ChatModel = "o3-mini"

      • const ChatModelO3Mini2025_01_31 ChatModel = "o3-mini-2025-01-31"

      • const ChatModelO1 ChatModel = "o1"

      • const ChatModelO1_2024_12_17 ChatModel = "o1-2024-12-17"

      • const ChatModelO1Preview ChatModel = "o1-preview"

      • const ChatModelO1Preview2024_09_12 ChatModel = "o1-preview-2024-09-12"

      • const ChatModelO1Mini ChatModel = "o1-mini"

      • const ChatModelO1Mini2024_09_12 ChatModel = "o1-mini-2024-09-12"

      • const ChatModelGPT4o ChatModel = "gpt-4o"

      • const ChatModelGPT4o2024_11_20 ChatModel = "gpt-4o-2024-11-20"

      • const ChatModelGPT4o2024_08_06 ChatModel = "gpt-4o-2024-08-06"

      • const ChatModelGPT4o2024_05_13 ChatModel = "gpt-4o-2024-05-13"

      • const ChatModelGPT4oAudioPreview ChatModel = "gpt-4o-audio-preview"

      • const ChatModelGPT4oAudioPreview2024_10_01 ChatModel = "gpt-4o-audio-preview-2024-10-01"

      • const ChatModelGPT4oAudioPreview2024_12_17 ChatModel = "gpt-4o-audio-preview-2024-12-17"

      • const ChatModelGPT4oAudioPreview2025_06_03 ChatModel = "gpt-4o-audio-preview-2025-06-03"

      • const ChatModelGPT4oMiniAudioPreview ChatModel = "gpt-4o-mini-audio-preview"

      • const ChatModelGPT4oMiniAudioPreview2024_12_17 ChatModel = "gpt-4o-mini-audio-preview-2024-12-17"

      • const ChatModelGPT4oSearchPreview ChatModel = "gpt-4o-search-preview"

      • const ChatModelGPT4oMiniSearchPreview ChatModel = "gpt-4o-mini-search-preview"

      • const ChatModelGPT4oSearchPreview2025_03_11 ChatModel = "gpt-4o-search-preview-2025-03-11"

      • const ChatModelGPT4oMiniSearchPreview2025_03_11 ChatModel = "gpt-4o-mini-search-preview-2025-03-11"

      • const ChatModelChatgpt4oLatest ChatModel = "chatgpt-4o-latest"

      • const ChatModelCodexMiniLatest ChatModel = "codex-mini-latest"

      • const ChatModelGPT4oMini ChatModel = "gpt-4o-mini"

      • const ChatModelGPT4oMini2024_07_18 ChatModel = "gpt-4o-mini-2024-07-18"

      • const ChatModelGPT4Turbo ChatModel = "gpt-4-turbo"

      • const ChatModelGPT4Turbo2024_04_09 ChatModel = "gpt-4-turbo-2024-04-09"

      • const ChatModelGPT4_0125Preview ChatModel = "gpt-4-0125-preview"

      • const ChatModelGPT4TurboPreview ChatModel = "gpt-4-turbo-preview"

      • const ChatModelGPT4_1106Preview ChatModel = "gpt-4-1106-preview"

      • const ChatModelGPT4VisionPreview ChatModel = "gpt-4-vision-preview"

      • const ChatModelGPT4 ChatModel = "gpt-4"

      • const ChatModelGPT4_0314 ChatModel = "gpt-4-0314"

      • const ChatModelGPT4_0613 ChatModel = "gpt-4-0613"

      • const ChatModelGPT4_32k ChatModel = "gpt-4-32k"

      • const ChatModelGPT4_32k0314 ChatModel = "gpt-4-32k-0314"

      • const ChatModelGPT4_32k0613 ChatModel = "gpt-4-32k-0613"

      • const ChatModelGPT3_5Turbo ChatModel = "gpt-3.5-turbo"

      • const ChatModelGPT3_5Turbo16k ChatModel = "gpt-3.5-turbo-16k"

      • const ChatModelGPT3_5Turbo0301 ChatModel = "gpt-3.5-turbo-0301"

      • const ChatModelGPT3_5Turbo0613 ChatModel = "gpt-3.5-turbo-0613"

      • const ChatModelGPT3_5Turbo1106 ChatModel = "gpt-3.5-turbo-1106"

      • const ChatModelGPT3_5Turbo0125 ChatModel = "gpt-3.5-turbo-0125"

      • const ChatModelGPT3_5Turbo16k0613 ChatModel = "gpt-3.5-turbo-16k-0613"

  • ParallelToolCalls param.Field[bool]

    Body param: Whether to enable parallel function calling during tool use.

  • ReasoningEffort param.Field[ReasoningEffort]

    Body param: Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, xhigh, and max. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. Not all reasoning models support every value. See the reasoning guide for model-specific support.

  • ResponseFormat param.Field[AssistantResponseFormatOptionUnion]

    Body param: Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.

    Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

    Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.

    Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

  • ``

  • Temperature param.Field[float64]

    Body param: What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

  • ToolChoice param.Field[AssistantToolChoiceOptionUnion]

    Body param: Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

  • Tools param.Field[[]AssistantToolUnion]

    Body param: Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis.

    • type CodeInterpreterTool struct{…}

    • type FileSearchTool struct{…}

      • Type FileSearch

        The type of tool being defined: file_search

        • const FileSearchFileSearch FileSearch = "file_search"

      • FileSearch FileSearchToolFileSearch

        Overrides for the file search tool.

        • MaxNumResults int64

          The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

          Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

        • RankingOptions FileSearchToolFileSearchRankingOptions

          The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

          See the file search tool documentation for more information.

          • ScoreThreshold float64

            The score threshold for the file search. All values must be a floating point number between 0 and 1.

          • Ranker string

            The ranker to use for the file search. If not specified will use the auto ranker.

            • const FileSearchToolFileSearchRankingOptionsRankerAuto FileSearchToolFileSearchRankingOptionsRanker = "auto"

            • const FileSearchToolFileSearchRankingOptionsRankerDefault2024_08_21 FileSearchToolFileSearchRankingOptionsRanker = "default_2024_08_21"

    • type FunctionTool struct{…}

      • Function FunctionDefinition

        • Name string

          The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Description string

          A description of what the function does, used by the model to choose when and how to call the function.

        • Parameters FunctionParameters

          The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

          Omitting parameters defines a function with an empty parameter list.

        • Strict bool

          Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

      • Type Function

        The type of tool being defined: function

        • const FunctionFunction Function = "function"

  • TopP param.Field[float64]

    Body param: An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

    We generally recommend altering this or temperature but not both.

  • TruncationStrategy param.Field[BetaThreadRunNewParamsTruncationStrategy]

    Body param: Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.

    • Type string

      The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.

      • const BetaThreadRunNewParamsTruncationStrategyTypeAuto BetaThreadRunNewParamsTruncationStrategyType = "auto"

      • const BetaThreadRunNewParamsTruncationStrategyTypeLastMessages BetaThreadRunNewParamsTruncationStrategyType = "last_messages"

    • LastMessages int64

      The number of most recent messages from the thread when constructing the context for the run.

Returns

• type Run struct{…}

  Represents an execution run on a thread.

  • ID string

    The identifier, which can be referenced in API endpoints.

  • AssistantID string

    The ID of the assistant used for execution of this run.

  • CancelledAt int64

    The Unix timestamp (in seconds) for when the run was cancelled.

  • CompletedAt int64

    The Unix timestamp (in seconds) for when the run was completed.

  • CreatedAt int64

    The Unix timestamp (in seconds) for when the run was created.

  • ExpiresAt int64

    The Unix timestamp (in seconds) for when the run will expire.

  • FailedAt int64

    The Unix timestamp (in seconds) for when the run failed.

  • IncompleteDetails RunIncompleteDetails

    Details on why the run is incomplete. Will be null if the run is not incomplete.

    • Reason string

      The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.

      • const RunIncompleteDetailsReasonMaxCompletionTokens RunIncompleteDetailsReason = "max_completion_tokens"

      • const RunIncompleteDetailsReasonMaxPromptTokens RunIncompleteDetailsReason = "max_prompt_tokens"

  • Instructions string

    The instructions that the assistant used for this run.

  • LastError RunLastError

    The last error associated with this run. Will be null if there are no errors.

    • Code string

      One of server_error, rate_limit_exceeded, or invalid_prompt.

      • const RunLastErrorCodeServerError RunLastErrorCode = "server_error"

      • const RunLastErrorCodeRateLimitExceeded RunLastErrorCode = "rate_limit_exceeded"

      • const RunLastErrorCodeInvalidPrompt RunLastErrorCode = "invalid_prompt"

    • Message string

      A human-readable description of the error.

  • MaxCompletionTokens int64

    The maximum number of completion tokens specified to have been used over the course of the run.

  • MaxPromptTokens int64

    The maximum number of prompt tokens specified to have been used over the course of the run.

  • Metadata Metadata

    Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

    Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

  • Model string

    The model that the assistant used for this run.

  • Object ThreadRun

    The object type, which is always thread.run.

    • const ThreadRunThreadRun ThreadRun = "thread.run"

  • ParallelToolCalls bool

    Whether to enable parallel function calling during tool use.

  • RequiredAction RunRequiredAction

    Details on the action required to continue the run. Will be null if no action is required.

    • SubmitToolOutputs RunRequiredActionSubmitToolOutputs

      Details on the tool outputs needed for this run to continue.

      • ToolCalls []RequiredActionFunctionToolCall

        A list of the relevant tool calls.

        • ID string

          The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.

        • Function RequiredActionFunctionToolCallFunction

          The function definition.

          • Arguments string

            The arguments that the model expects you to pass to the function.

          • Name string

            The name of the function.

        • Type Function

          The type of tool call the output is required for. For now, this is always function.

          • const FunctionFunction Function = "function"

    • Type SubmitToolOutputs

      For now, this is always submit_tool_outputs.

      • const SubmitToolOutputsSubmitToolOutputs SubmitToolOutputs = "submit_tool_outputs"

  • ResponseFormat AssistantResponseFormatOptionUnion

    Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.

    Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

    Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.

    Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

    • type Auto string

      auto is the default value

      • const AutoAuto Auto = "auto"

    • type ResponseFormatText struct{…}

      Default response format. Used to generate text responses.

      • Type Text

        The type of response format being defined. Always text.

        • const TextText Text = "text"

    • type ResponseFormatJSONObject struct{…}

      JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.

      • Type JSONObject

        The type of response format being defined. Always json_object.

        • const JSONObjectJSONObject JSONObject = "json_object"

    • type ResponseFormatJSONSchema struct{…}

      JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

      • JSONSchema ResponseFormatJSONSchemaJSONSchema

        Structured Outputs configuration options, including a JSON Schema.

        • Name string

          The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Description string

          A description of what the response format is for, used by the model to determine how to respond in the format.

        • Schema map[string, any]

          The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

        • Strict bool

          Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.

      • Type JSONSchema

        The type of response format being defined. Always json_schema.

        • const JSONSchemaJSONSchema JSONSchema = "json_schema"

  • StartedAt int64

    The Unix timestamp (in seconds) for when the run was started.

  • Status RunStatus

    The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.

    • const RunStatusQueued RunStatus = "queued"

    • const RunStatusInProgress RunStatus = "in_progress"

    • const RunStatusRequiresAction RunStatus = "requires_action"

    • const RunStatusCancelling RunStatus = "cancelling"

    • const RunStatusCancelled RunStatus = "cancelled"

    • const RunStatusFailed RunStatus = "failed"

    • const RunStatusCompleted RunStatus = "completed"

    • const RunStatusIncomplete RunStatus = "incomplete"

    • const RunStatusExpired RunStatus = "expired"

  • ThreadID string

    The ID of the thread that was executed on as a part of this run.

  • ToolChoice AssistantToolChoiceOptionUnion

    Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

    • type AssistantToolChoiceOptionAuto string

      none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.

      • const AssistantToolChoiceOptionAutoNone AssistantToolChoiceOptionAuto = "none"

      • const AssistantToolChoiceOptionAutoAuto AssistantToolChoiceOptionAuto = "auto"

      • const AssistantToolChoiceOptionAutoRequired AssistantToolChoiceOptionAuto = "required"

    • type AssistantToolChoice struct{…}

      Specifies a tool the model should use. Use to force the model to call a specific tool.

      • Type AssistantToolChoiceType

        The type of the tool. If type is function, the function name must be set

        • const AssistantToolChoiceTypeFunction AssistantToolChoiceType = "function"

        • const AssistantToolChoiceTypeCodeInterpreter AssistantToolChoiceType = "code_interpreter"

        • const AssistantToolChoiceTypeFileSearch AssistantToolChoiceType = "file_search"

      • Function AssistantToolChoiceFunction

        • Name string

          The name of the function to call.

  • Tools []AssistantToolUnion

    The list of tools that the assistant used for this run.

    • type CodeInterpreterTool struct{…}

      • Type CodeInterpreter

        The type of tool being defined: code_interpreter

        • const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"

    • type FileSearchTool struct{…}

      • Type FileSearch

        The type of tool being defined: file_search

        • const FileSearchFileSearch FileSearch = "file_search"

      • FileSearch FileSearchToolFileSearch

        Overrides for the file search tool.

        • MaxNumResults int64

          The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

          Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

        • RankingOptions FileSearchToolFileSearchRankingOptions

          The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

          See the file search tool documentation for more information.

          • ScoreThreshold float64

            The score threshold for the file search. All values must be a floating point number between 0 and 1.

          • Ranker string

            The ranker to use for the file search. If not specified will use the auto ranker.

            • const FileSearchToolFileSearchRankingOptionsRankerAuto FileSearchToolFileSearchRankingOptionsRanker = "auto"

            • const FileSearchToolFileSearchRankingOptionsRankerDefault2024_08_21 FileSearchToolFileSearchRankingOptionsRanker = "default_2024_08_21"

    • type FunctionTool struct{…}

      • Function FunctionDefinition

        • Name string

          The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Description string

          A description of what the function does, used by the model to choose when and how to call the function.

        • Parameters FunctionParameters

          The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

          Omitting parameters defines a function with an empty parameter list.

        • Strict bool

          Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

      • Type Function

        The type of tool being defined: function

        • const FunctionFunction Function = "function"

  • TruncationStrategy RunTruncationStrategy

    Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.

    • Type string

      The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.

      • const RunTruncationStrategyTypeAuto RunTruncationStrategyType = "auto"

      • const RunTruncationStrategyTypeLastMessages RunTruncationStrategyType = "last_messages"

    • LastMessages int64

      The number of most recent messages from the thread when constructing the context for the run.

  • Usage RunUsage

    Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).

    • CompletionTokens int64

      Number of completion tokens used over the course of the run.

    • PromptTokens int64

      Number of prompt tokens used over the course of the run.

    • TotalTokens int64

      Total number of tokens used (prompt + completion).

  • Temperature float64

    The sampling temperature used for this run. If not set, defaults to 1.

  • TopP float64

    The nucleus sampling value used for this run. If not set, defaults to 1.

Example

package main

import (
  "context"
  "fmt"

  "github.com/openai/openai-go"
  "github.com/openai/openai-go/option"
)

func main() {
  client := openai.NewClient(
    option.WithAPIKey("My API Key"),
  )
  run, err := client.Beta.Threads.Runs.New(
    context.TODO(),
    "thread_id",
    openai.BetaThreadRunNewParams{
      AssistantID: "assistant_id",
    },
  )
  if err != nil {
    panic(err.Error())
  }
  fmt.Printf("%+v\n", run.ID)
}

Response

{
  "id": "id",
  "assistant_id": "assistant_id",
  "cancelled_at": 0,
  "completed_at": 0,
  "created_at": 0,
  "expires_at": 0,
  "failed_at": 0,
  "incomplete_details": {
    "reason": "max_completion_tokens"
  },
  "instructions": "instructions",
  "last_error": {
    "code": "server_error",
    "message": "message"
  },
  "max_completion_tokens": 256,
  "max_prompt_tokens": 256,
  "metadata": {
    "foo": "string"
  },
  "model": "model",
  "object": "thread.run",
  "parallel_tool_calls": true,
  "required_action": {
    "submit_tool_outputs": {
      "tool_calls": [
        {
          "id": "id",
          "function": {
            "arguments": "arguments",
            "name": "name"
          },
          "type": "function"
        }
      ]
    },
    "type": "submit_tool_outputs"
  },
  "response_format": "auto",
  "started_at": 0,
  "status": "queued",
  "thread_id": "thread_id",
  "tool_choice": "none",
  "tools": [
    {
      "type": "code_interpreter"
    }
  ],
  "truncation_strategy": {
    "type": "auto",
    "last_messages": 1
  },
  "usage": {
    "completion_tokens": 0,
    "prompt_tokens": 0,
    "total_tokens": 0
  },
  "temperature": 0,
  "top_p": 0
}

Retrieve run

client.Beta.Threads.Runs.Get(ctx, threadID, runID) (*Run, error)

get /threads/{thread_id}/runs/{run_id}

Retrieves a run.

Parameters

• threadID string

• runID string

Returns

• type Run struct{…}

  Represents an execution run on a thread.

  • ID string

    The identifier, which can be referenced in API endpoints.

  • AssistantID string

    The ID of the assistant used for execution of this run.

  • CancelledAt int64

    The Unix timestamp (in seconds) for when the run was cancelled.

  • CompletedAt int64

    The Unix timestamp (in seconds) for when the run was completed.

  • CreatedAt int64

    The Unix timestamp (in seconds) for when the run was created.

  • ExpiresAt int64

    The Unix timestamp (in seconds) for when the run will expire.

  • FailedAt int64

    The Unix timestamp (in seconds) for when the run failed.

  • IncompleteDetails RunIncompleteDetails

    Details on why the run is incomplete. Will be null if the run is not incomplete.

    • Reason string

      The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.

      • const RunIncompleteDetailsReasonMaxCompletionTokens RunIncompleteDetailsReason = "max_completion_tokens"

      • const RunIncompleteDetailsReasonMaxPromptTokens RunIncompleteDetailsReason = "max_prompt_tokens"

  • Instructions string

    The instructions that the assistant used for this run.

  • LastError RunLastError

    The last error associated with this run. Will be null if there are no errors.

    • Code string

      One of server_error, rate_limit_exceeded, or invalid_prompt.

      • const RunLastErrorCodeServerError RunLastErrorCode = "server_error"

      • const RunLastErrorCodeRateLimitExceeded RunLastErrorCode = "rate_limit_exceeded"

      • const RunLastErrorCodeInvalidPrompt RunLastErrorCode = "invalid_prompt"

    • Message string

      A human-readable description of the error.

  • MaxCompletionTokens int64

    The maximum number of completion tokens specified to have been used over the course of the run.

  • MaxPromptTokens int64

    The maximum number of prompt tokens specified to have been used over the course of the run.

  • Metadata Metadata

    Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

    Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

  • Model string

    The model that the assistant used for this run.

  • Object ThreadRun

    The object type, which is always thread.run.

    • const ThreadRunThreadRun ThreadRun = "thread.run"

  • ParallelToolCalls bool

    Whether to enable parallel function calling during tool use.

  • RequiredAction RunRequiredAction

    Details on the action required to continue the run. Will be null if no action is required.

    • SubmitToolOutputs RunRequiredActionSubmitToolOutputs

      Details on the tool outputs needed for this run to continue.

      • ToolCalls []RequiredActionFunctionToolCall

        A list of the relevant tool calls.

        • ID string

          The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.

        • Function RequiredActionFunctionToolCallFunction

          The function definition.

          • Arguments string

            The arguments that the model expects you to pass to the function.

          • Name string

            The name of the function.

        • Type Function

          The type of tool call the output is required for. For now, this is always function.

          • const FunctionFunction Function = "function"

    • Type SubmitToolOutputs

      For now, this is always submit_tool_outputs.

      • const SubmitToolOutputsSubmitToolOutputs SubmitToolOutputs = "submit_tool_outputs"

  • ResponseFormat AssistantResponseFormatOptionUnion

    Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.

    Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

    Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.

    Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

    • type Auto string

      auto is the default value

      • const AutoAuto Auto = "auto"

    • type ResponseFormatText struct{…}

      Default response format. Used to generate text responses.

      • Type Text

        The type of response format being defined. Always text.

        • const TextText Text = "text"

    • type ResponseFormatJSONObject struct{…}

      JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.

      • Type JSONObject

        The type of response format being defined. Always json_object.

        • const JSONObjectJSONObject JSONObject = "json_object"

    • type ResponseFormatJSONSchema struct{…}

      JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

      • JSONSchema ResponseFormatJSONSchemaJSONSchema

        Structured Outputs configuration options, including a JSON Schema.

        • Name string

          The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Description string

          A description of what the response format is for, used by the model to determine how to respond in the format.

        • Schema map[string, any]

          The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

        • Strict bool

          Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.

      • Type JSONSchema

        The type of response format being defined. Always json_schema.

        • const JSONSchemaJSONSchema JSONSchema = "json_schema"

  • StartedAt int64

    The Unix timestamp (in seconds) for when the run was started.

  • Status RunStatus

    The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.

    • const RunStatusQueued RunStatus = "queued"

    • const RunStatusInProgress RunStatus = "in_progress"

    • const RunStatusRequiresAction RunStatus = "requires_action"

    • const RunStatusCancelling RunStatus = "cancelling"

    • const RunStatusCancelled RunStatus = "cancelled"

    • const RunStatusFailed RunStatus = "failed"

    • const RunStatusCompleted RunStatus = "completed"

    • const RunStatusIncomplete RunStatus = "incomplete"

    • const RunStatusExpired RunStatus = "expired"

  • ThreadID string

    The ID of the thread that was executed on as a part of this run.

  • ToolChoice AssistantToolChoiceOptionUnion

    Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

    • type AssistantToolChoiceOptionAuto string

      none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.

      • const AssistantToolChoiceOptionAutoNone AssistantToolChoiceOptionAuto = "none"

      • const AssistantToolChoiceOptionAutoAuto AssistantToolChoiceOptionAuto = "auto"

      • const AssistantToolChoiceOptionAutoRequired AssistantToolChoiceOptionAuto = "required"

    • type AssistantToolChoice struct{…}

      Specifies a tool the model should use. Use to force the model to call a specific tool.

      • Type AssistantToolChoiceType

        The type of the tool. If type is function, the function name must be set

        • const AssistantToolChoiceTypeFunction AssistantToolChoiceType = "function"

        • const AssistantToolChoiceTypeCodeInterpreter AssistantToolChoiceType = "code_interpreter"

        • const AssistantToolChoiceTypeFileSearch AssistantToolChoiceType = "file_search"

      • Function AssistantToolChoiceFunction

        • Name string

          The name of the function to call.

  • Tools []AssistantToolUnion

    The list of tools that the assistant used for this run.

    • type CodeInterpreterTool struct{…}

      • Type CodeInterpreter

        The type of tool being defined: code_interpreter

        • const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"

    • type FileSearchTool struct{…}

      • Type FileSearch

        The type of tool being defined: file_search

        • const FileSearchFileSearch FileSearch = "file_search"

      • FileSearch FileSearchToolFileSearch

        Overrides for the file search tool.

        • MaxNumResults int64

          The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

          Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

        • RankingOptions FileSearchToolFileSearchRankingOptions

          The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

          See the file search tool documentation for more information.

          • ScoreThreshold float64

            The score threshold for the file search. All values must be a floating point number between 0 and 1.

          • Ranker string

            The ranker to use for the file search. If not specified will use the auto ranker.

            • const FileSearchToolFileSearchRankingOptionsRankerAuto FileSearchToolFileSearchRankingOptionsRanker = "auto"

            • const FileSearchToolFileSearchRankingOptionsRankerDefault2024_08_21 FileSearchToolFileSearchRankingOptionsRanker = "default_2024_08_21"

    • type FunctionTool struct{…}

      • Function FunctionDefinition

        • Name string

          The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Description string

          A description of what the function does, used by the model to choose when and how to call the function.

        • Parameters FunctionParameters

          The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

          Omitting parameters defines a function with an empty parameter list.

        • Strict bool

          Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

      • Type Function

        The type of tool being defined: function

        • const FunctionFunction Function = "function"

  • TruncationStrategy RunTruncationStrategy

    Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.

    • Type string

      The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.

      • const RunTruncationStrategyTypeAuto RunTruncationStrategyType = "auto"

      • const RunTruncationStrategyTypeLastMessages RunTruncationStrategyType = "last_messages"

    • LastMessages int64

      The number of most recent messages from the thread when constructing the context for the run.

  • Usage RunUsage

    Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).

    • CompletionTokens int64

      Number of completion tokens used over the course of the run.

    • PromptTokens int64

      Number of prompt tokens used over the course of the run.

    • TotalTokens int64

      Total number of tokens used (prompt + completion).

  • Temperature float64

    The sampling temperature used for this run. If not set, defaults to 1.

  • TopP float64

    The nucleus sampling value used for this run. If not set, defaults to 1.

Example

package main

import (
  "context"
  "fmt"

  "github.com/openai/openai-go"
  "github.com/openai/openai-go/option"
)

func main() {
  client := openai.NewClient(
    option.WithAPIKey("My API Key"),
  )
  run, err := client.Beta.Threads.Runs.Get(
    context.TODO(),
    "thread_id",
    "run_id",
  )
  if err != nil {
    panic(err.Error())
  }
  fmt.Printf("%+v\n", run.ID)
}

Response

{
  "id": "id",
  "assistant_id": "assistant_id",
  "cancelled_at": 0,
  "completed_at": 0,
  "created_at": 0,
  "expires_at": 0,
  "failed_at": 0,
  "incomplete_details": {
    "reason": "max_completion_tokens"
  },
  "instructions": "instructions",
  "last_error": {
    "code": "server_error",
    "message": "message"
  },
  "max_completion_tokens": 256,
  "max_prompt_tokens": 256,
  "metadata": {
    "foo": "string"
  },
  "model": "model",
  "object": "thread.run",
  "parallel_tool_calls": true,
  "required_action": {
    "submit_tool_outputs": {
      "tool_calls": [
        {
          "id": "id",
          "function": {
            "arguments": "arguments",
            "name": "name"
          },
          "type": "function"
        }
      ]
    },
    "type": "submit_tool_outputs"
  },
  "response_format": "auto",
  "started_at": 0,
  "status": "queued",
  "thread_id": "thread_id",
  "tool_choice": "none",
  "tools": [
    {
      "type": "code_interpreter"
    }
  ],
  "truncation_strategy": {
    "type": "auto",
    "last_messages": 1
  },
  "usage": {
    "completion_tokens": 0,
    "prompt_tokens": 0,
    "total_tokens": 0
  },
  "temperature": 0,
  "top_p": 0
}

Modify run

client.Beta.Threads.Runs.Update(ctx, threadID, runID, body) (*Run, error)

post /threads/{thread_id}/runs/{run_id}

Modifies a run.

Parameters

• threadID string

• runID string

• body BetaThreadRunUpdateParams

  • Metadata param.Field[Metadata]

    Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

    Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

Returns

• type Run struct{…}

  Represents an execution run on a thread.

  • ID string

    The identifier, which can be referenced in API endpoints.

  • AssistantID string

    The ID of the assistant used for execution of this run.

  • CancelledAt int64

    The Unix timestamp (in seconds) for when the run was cancelled.

  • CompletedAt int64

    The Unix timestamp (in seconds) for when the run was completed.

  • CreatedAt int64

    The Unix timestamp (in seconds) for when the run was created.

  • ExpiresAt int64

    The Unix timestamp (in seconds) for when the run will expire.

  • FailedAt int64

    The Unix timestamp (in seconds) for when the run failed.

  • IncompleteDetails RunIncompleteDetails

    Details on why the run is incomplete. Will be null if the run is not incomplete.

    • Reason string

      The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.

      • const RunIncompleteDetailsReasonMaxCompletionTokens RunIncompleteDetailsReason = "max_completion_tokens"

      • const RunIncompleteDetailsReasonMaxPromptTokens RunIncompleteDetailsReason = "max_prompt_tokens"

  • Instructions string

    The instructions that the assistant used for this run.

  • LastError RunLastError

    The last error associated with this run. Will be null if there are no errors.

    • Code string

      One of server_error, rate_limit_exceeded, or invalid_prompt.

      • const RunLastErrorCodeServerError RunLastErrorCode = "server_error"

      • const RunLastErrorCodeRateLimitExceeded RunLastErrorCode = "rate_limit_exceeded"

      • const RunLastErrorCodeInvalidPrompt RunLastErrorCode = "invalid_prompt"

    • Message string

      A human-readable description of the error.

  • MaxCompletionTokens int64

    The maximum number of completion tokens specified to have been used over the course of the run.

  • MaxPromptTokens int64

    The maximum number of prompt tokens specified to have been used over the course of the run.

  • Metadata Metadata

    Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

    Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

  • Model string

    The model that the assistant used for this run.

  • Object ThreadRun

    The object type, which is always thread.run.

    • const ThreadRunThreadRun ThreadRun = "thread.run"

  • ParallelToolCalls bool

    Whether to enable parallel function calling during tool use.

  • RequiredAction RunRequiredAction

    Details on the action required to continue the run. Will be null if no action is required.

    • SubmitToolOutputs RunRequiredActionSubmitToolOutputs

      Details on the tool outputs needed for this run to continue.

      • ToolCalls []RequiredActionFunctionToolCall

        A list of the relevant tool calls.

        • ID string

          The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.

        • Function RequiredActionFunctionToolCallFunction

          The function definition.

          • Arguments string

            The arguments that the model expects you to pass to the function.

          • Name string

            The name of the function.

        • Type Function

          The type of tool call the output is required for. For now, this is always function.

          • const FunctionFunction Function = "function"

    • Type SubmitToolOutputs

      For now, this is always submit_tool_outputs.

      • const SubmitToolOutputsSubmitToolOutputs SubmitToolOutputs = "submit_tool_outputs"

  • ResponseFormat AssistantResponseFormatOptionUnion

    Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.

    Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

    Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.

    Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

    • type Auto string

      auto is the default value

      • const AutoAuto Auto = "auto"

    • type ResponseFormatText struct{…}

      Default response format. Used to generate text responses.

      • Type Text

        The type of response format being defined. Always text.

        • const TextText Text = "text"

    • type ResponseFormatJSONObject struct{…}

      JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.

      • Type JSONObject

        The type of response format being defined. Always json_object.

        • const JSONObjectJSONObject JSONObject = "json_object"

    • type ResponseFormatJSONSchema struct{…}

      JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

      • JSONSchema ResponseFormatJSONSchemaJSONSchema

        Structured Outputs configuration options, including a JSON Schema.

        • Name string

          The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Description string

          A description of what the response format is for, used by the model to determine how to respond in the format.

        • Schema map[string, any]

          The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

        • Strict bool

          Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.

      • Type JSONSchema

        The type of response format being defined. Always json_schema.

        • const JSONSchemaJSONSchema JSONSchema = "json_schema"

  • StartedAt int64

    The Unix timestamp (in seconds) for when the run was started.

  • Status RunStatus

    The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.

    • const RunStatusQueued RunStatus = "queued"

    • const RunStatusInProgress RunStatus = "in_progress"

    • const RunStatusRequiresAction RunStatus = "requires_action"

    • const RunStatusCancelling RunStatus = "cancelling"

    • const RunStatusCancelled RunStatus = "cancelled"

    • const RunStatusFailed RunStatus = "failed"

    • const RunStatusCompleted RunStatus = "completed"

    • const RunStatusIncomplete RunStatus = "incomplete"

    • const RunStatusExpired RunStatus = "expired"

  • ThreadID string

    The ID of the thread that was executed on as a part of this run.

  • ToolChoice AssistantToolChoiceOptionUnion

    Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

    • type AssistantToolChoiceOptionAuto string

      none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.

      • const AssistantToolChoiceOptionAutoNone AssistantToolChoiceOptionAuto = "none"

      • const AssistantToolChoiceOptionAutoAuto AssistantToolChoiceOptionAuto = "auto"

      • const AssistantToolChoiceOptionAutoRequired AssistantToolChoiceOptionAuto = "required"

    • type AssistantToolChoice struct{…}

      Specifies a tool the model should use. Use to force the model to call a specific tool.

      • Type AssistantToolChoiceType

        The type of the tool. If type is function, the function name must be set

        • const AssistantToolChoiceTypeFunction AssistantToolChoiceType = "function"

        • const AssistantToolChoiceTypeCodeInterpreter AssistantToolChoiceType = "code_interpreter"

        • const AssistantToolChoiceTypeFileSearch AssistantToolChoiceType = "file_search"

      • Function AssistantToolChoiceFunction

        • Name string

          The name of the function to call.

  • Tools []AssistantToolUnion

    The list of tools that the assistant used for this run.

    • type CodeInterpreterTool struct{…}

      • Type CodeInterpreter

        The type of tool being defined: code_interpreter

        • const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"

    • type FileSearchTool struct{…}

      • Type FileSearch

        The type of tool being defined: file_search

        • const FileSearchFileSearch FileSearch = "file_search"

      • FileSearch FileSearchToolFileSearch

        Overrides for the file search tool.

        • MaxNumResults int64

          The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

          Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

        • RankingOptions FileSearchToolFileSearchRankingOptions

          The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

          See the file search tool documentation for more information.

          • ScoreThreshold float64

            The score threshold for the file search. All values must be a floating point number between 0 and 1.

          • Ranker string

            The ranker to use for the file search. If not specified will use the auto ranker.

            • const FileSearchToolFileSearchRankingOptionsRankerAuto FileSearchToolFileSearchRankingOptionsRanker = "auto"

            • const FileSearchToolFileSearchRankingOptionsRankerDefault2024_08_21 FileSearchToolFileSearchRankingOptionsRanker = "default_2024_08_21"

    • type FunctionTool struct{…}

      • Function FunctionDefinition

        • Name string

          The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Description string

          A description of what the function does, used by the model to choose when and how to call the function.

        • Parameters FunctionParameters

          The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

          Omitting parameters defines a function with an empty parameter list.

        • Strict bool

          Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

      • Type Function

        The type of tool being defined: function

        • const FunctionFunction Function = "function"

  • TruncationStrategy RunTruncationStrategy

    Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.

    • Type string

      The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.

      • const RunTruncationStrategyTypeAuto RunTruncationStrategyType = "auto"

      • const RunTruncationStrategyTypeLastMessages RunTruncationStrategyType = "last_messages"

    • LastMessages int64

      The number of most recent messages from the thread when constructing the context for the run.

  • Usage RunUsage

    Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).

    • CompletionTokens int64

      Number of completion tokens used over the course of the run.

    • PromptTokens int64

      Number of prompt tokens used over the course of the run.

    • TotalTokens int64

      Total number of tokens used (prompt + completion).

  • Temperature float64

    The sampling temperature used for this run. If not set, defaults to 1.

  • TopP float64

    The nucleus sampling value used for this run. If not set, defaults to 1.

Example

package main

import (
  "context"
  "fmt"

  "github.com/openai/openai-go"
  "github.com/openai/openai-go/option"
)

func main() {
  client := openai.NewClient(
    option.WithAPIKey("My API Key"),
  )
  run, err := client.Beta.Threads.Runs.Update(
    context.TODO(),
    "thread_id",
    "run_id",
    openai.BetaThreadRunUpdateParams{

    },
  )
  if err != nil {
    panic(err.Error())
  }
  fmt.Printf("%+v\n", run.ID)
}

Response

{
  "id": "id",
  "assistant_id": "assistant_id",
  "cancelled_at": 0,
  "completed_at": 0,
  "created_at": 0,
  "expires_at": 0,
  "failed_at": 0,
  "incomplete_details": {
    "reason": "max_completion_tokens"
  },
  "instructions": "instructions",
  "last_error": {
    "code": "server_error",
    "message": "message"
  },
  "max_completion_tokens": 256,
  "max_prompt_tokens": 256,
  "metadata": {
    "foo": "string"
  },
  "model": "model",
  "object": "thread.run",
  "parallel_tool_calls": true,
  "required_action": {
    "submit_tool_outputs": {
      "tool_calls": [
        {
          "id": "id",
          "function": {
            "arguments": "arguments",
            "name": "name"
          },
          "type": "function"
        }
      ]
    },
    "type": "submit_tool_outputs"
  },
  "response_format": "auto",
  "started_at": 0,
  "status": "queued",
  "thread_id": "thread_id",
  "tool_choice": "none",
  "tools": [
    {
      "type": "code_interpreter"
    }
  ],
  "truncation_strategy": {
    "type": "auto",
    "last_messages": 1
  },
  "usage": {
    "completion_tokens": 0,
    "prompt_tokens": 0,
    "total_tokens": 0
  },
  "temperature": 0,
  "top_p": 0
}

Submit tool outputs to run

client.Beta.Threads.Runs.SubmitToolOutputs(ctx, threadID, runID, body) (*Run, error)

post /threads/{thread_id}/runs/{run_id}/submit_tool_outputs

When a run has the status: "requires_action" and required_action.type is submit_tool_outputs, this endpoint can be used to submit the outputs from the tool calls once they're all completed. All outputs must be submitted in a single request.

Parameters

• threadID string

• runID string

• body BetaThreadRunSubmitToolOutputsParams

  • ToolOutputs param.Field[[]BetaThreadRunSubmitToolOutputsParamsToolOutput]

    A list of tools for which the outputs are being submitted.

    • Output string

      The output of the tool call to be submitted to continue the run.

    • ToolCallID string

      The ID of the tool call in the required_action object within the run object the output is being submitted for.

  • ``

Returns

• type Run struct{…}

  Represents an execution run on a thread.

  • ID string

    The identifier, which can be referenced in API endpoints.

  • AssistantID string

    The ID of the assistant used for execution of this run.

  • CancelledAt int64

    The Unix timestamp (in seconds) for when the run was cancelled.

  • CompletedAt int64

    The Unix timestamp (in seconds) for when the run was completed.

  • CreatedAt int64

    The Unix timestamp (in seconds) for when the run was created.

  • ExpiresAt int64

    The Unix timestamp (in seconds) for when the run will expire.

  • FailedAt int64

    The Unix timestamp (in seconds) for when the run failed.

  • IncompleteDetails RunIncompleteDetails

    Details on why the run is incomplete. Will be null if the run is not incomplete.

    • Reason string

      The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.

      • const RunIncompleteDetailsReasonMaxCompletionTokens RunIncompleteDetailsReason = "max_completion_tokens"

      • const RunIncompleteDetailsReasonMaxPromptTokens RunIncompleteDetailsReason = "max_prompt_tokens"

  • Instructions string

    The instructions that the assistant used for this run.

  • LastError RunLastError

    The last error associated with this run. Will be null if there are no errors.

    • Code string

      One of server_error, rate_limit_exceeded, or invalid_prompt.

      • const RunLastErrorCodeServerError RunLastErrorCode = "server_error"

      • const RunLastErrorCodeRateLimitExceeded RunLastErrorCode = "rate_limit_exceeded"

      • const RunLastErrorCodeInvalidPrompt RunLastErrorCode = "invalid_prompt"

    • Message string

      A human-readable description of the error.

  • MaxCompletionTokens int64

    The maximum number of completion tokens specified to have been used over the course of the run.

  • MaxPromptTokens int64

    The maximum number of prompt tokens specified to have been used over the course of the run.

  • Metadata Metadata

    Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

    Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

  • Model string

    The model that the assistant used for this run.

  • Object ThreadRun

    The object type, which is always thread.run.

    • const ThreadRunThreadRun ThreadRun = "thread.run"

  • ParallelToolCalls bool

    Whether to enable parallel function calling during tool use.

  • RequiredAction RunRequiredAction

    Details on the action required to continue the run. Will be null if no action is required.

    • SubmitToolOutputs RunRequiredActionSubmitToolOutputs

      Details on the tool outputs needed for this run to continue.

      • ToolCalls []RequiredActionFunctionToolCall

        A list of the relevant tool calls.

        • ID string

          The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.

        • Function RequiredActionFunctionToolCallFunction

          The function definition.

          • Arguments string

            The arguments that the model expects you to pass to the function.

          • Name string

            The name of the function.

        • Type Function

          The type of tool call the output is required for. For now, this is always function.

          • const FunctionFunction Function = "function"

    • Type SubmitToolOutputs

      For now, this is always submit_tool_outputs.

      • const SubmitToolOutputsSubmitToolOutputs SubmitToolOutputs = "submit_tool_outputs"

  • ResponseFormat AssistantResponseFormatOptionUnion

    Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.

    Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

    Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.

    Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

    • type Auto string

      auto is the default value

      • const AutoAuto Auto = "auto"

    • type ResponseFormatText struct{…}

      Default response format. Used to generate text responses.

      • Type Text

        The type of response format being defined. Always text.

        • const TextText Text = "text"

    • type ResponseFormatJSONObject struct{…}

      JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.

      • Type JSONObject

        The type of response format being defined. Always json_object.

        • const JSONObjectJSONObject JSONObject = "json_object"

    • type ResponseFormatJSONSchema struct{…}

      JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

      • JSONSchema ResponseFormatJSONSchemaJSONSchema

        Structured Outputs configuration options, including a JSON Schema.

        • Name string

          The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Description string

          A description of what the response format is for, used by the model to determine how to respond in the format.

        • Schema map[string, any]

          The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

        • Strict bool

          Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.

      • Type JSONSchema

        The type of response format being defined. Always json_schema.

        • const JSONSchemaJSONSchema JSONSchema = "json_schema"

  • StartedAt int64

    The Unix timestamp (in seconds) for when the run was started.

  • Status RunStatus

    The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.

    • const RunStatusQueued RunStatus = "queued"

    • const RunStatusInProgress RunStatus = "in_progress"

    • const RunStatusRequiresAction RunStatus = "requires_action"

    • const RunStatusCancelling RunStatus = "cancelling"

    • const RunStatusCancelled RunStatus = "cancelled"

    • const RunStatusFailed RunStatus = "failed"

    • const RunStatusCompleted RunStatus = "completed"

    • const RunStatusIncomplete RunStatus = "incomplete"

    • const RunStatusExpired RunStatus = "expired"

  • ThreadID string

    The ID of the thread that was executed on as a part of this run.

  • ToolChoice AssistantToolChoiceOptionUnion

    Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

    • type AssistantToolChoiceOptionAuto string

      none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.

      • const AssistantToolChoiceOptionAutoNone AssistantToolChoiceOptionAuto = "none"

      • const AssistantToolChoiceOptionAutoAuto AssistantToolChoiceOptionAuto = "auto"

      • const AssistantToolChoiceOptionAutoRequired AssistantToolChoiceOptionAuto = "required"

    • type AssistantToolChoice struct{…}

      Specifies a tool the model should use. Use to force the model to call a specific tool.

      • Type AssistantToolChoiceType

        The type of the tool. If type is function, the function name must be set

        • const AssistantToolChoiceTypeFunction AssistantToolChoiceType = "function"

        • const AssistantToolChoiceTypeCodeInterpreter AssistantToolChoiceType = "code_interpreter"

        • const AssistantToolChoiceTypeFileSearch AssistantToolChoiceType = "file_search"

      • Function AssistantToolChoiceFunction

        • Name string

          The name of the function to call.

  • Tools []AssistantToolUnion

    The list of tools that the assistant used for this run.

    • type CodeInterpreterTool struct{…}

      • Type CodeInterpreter

        The type of tool being defined: code_interpreter

        • const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"

    • type FileSearchTool struct{…}

      • Type FileSearch

        The type of tool being defined: file_search

        • const FileSearchFileSearch FileSearch = "file_search"

      • FileSearch FileSearchToolFileSearch

        Overrides for the file search tool.

        • MaxNumResults int64

          The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

          Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

        • RankingOptions FileSearchToolFileSearchRankingOptions

          The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

          See the file search tool documentation for more information.

          • ScoreThreshold float64

            The score threshold for the file search. All values must be a floating point number between 0 and 1.

          • Ranker string

            The ranker to use for the file search. If not specified will use the auto ranker.

            • const FileSearchToolFileSearchRankingOptionsRankerAuto FileSearchToolFileSearchRankingOptionsRanker = "auto"

            • const FileSearchToolFileSearchRankingOptionsRankerDefault2024_08_21 FileSearchToolFileSearchRankingOptionsRanker = "default_2024_08_21"

    • type FunctionTool struct{…}

      • Function FunctionDefinition

        • Name string

          The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Description string

          A description of what the function does, used by the model to choose when and how to call the function.

        • Parameters FunctionParameters

          The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

          Omitting parameters defines a function with an empty parameter list.

        • Strict bool

          Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

      • Type Function

        The type of tool being defined: function

        • const FunctionFunction Function = "function"

  • TruncationStrategy RunTruncationStrategy

    Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.

    • Type string

      The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.

      • const RunTruncationStrategyTypeAuto RunTruncationStrategyType = "auto"

      • const RunTruncationStrategyTypeLastMessages RunTruncationStrategyType = "last_messages"

    • LastMessages int64

      The number of most recent messages from the thread when constructing the context for the run.

  • Usage RunUsage

    Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).

    • CompletionTokens int64

      Number of completion tokens used over the course of the run.

    • PromptTokens int64

      Number of prompt tokens used over the course of the run.

    • TotalTokens int64

      Total number of tokens used (prompt + completion).

  • Temperature float64

    The sampling temperature used for this run. If not set, defaults to 1.

  • TopP float64

    The nucleus sampling value used for this run. If not set, defaults to 1.

Example

package main

import (
  "context"
  "fmt"

  "github.com/openai/openai-go"
  "github.com/openai/openai-go/option"
)

func main() {
  client := openai.NewClient(
    option.WithAPIKey("My API Key"),
  )
  run, err := client.Beta.Threads.Runs.SubmitToolOutputs(
    context.TODO(),
    "thread_id",
    "run_id",
    openai.BetaThreadRunSubmitToolOutputsParams{
      ToolOutputs: []openai.BetaThreadRunSubmitToolOutputsParamsToolOutput{openai.BetaThreadRunSubmitToolOutputsParamsToolOutput{

      }},
    },
  )
  if err != nil {
    panic(err.Error())
  }
  fmt.Printf("%+v\n", run.ID)
}

Response

{
  "id": "id",
  "assistant_id": "assistant_id",
  "cancelled_at": 0,
  "completed_at": 0,
  "created_at": 0,
  "expires_at": 0,
  "failed_at": 0,
  "incomplete_details": {
    "reason": "max_completion_tokens"
  },
  "instructions": "instructions",
  "last_error": {
    "code": "server_error",
    "message": "message"
  },
  "max_completion_tokens": 256,
  "max_prompt_tokens": 256,
  "metadata": {
    "foo": "string"
  },
  "model": "model",
  "object": "thread.run",
  "parallel_tool_calls": true,
  "required_action": {
    "submit_tool_outputs": {
      "tool_calls": [
        {
          "id": "id",
          "function": {
            "arguments": "arguments",
            "name": "name"
          },
          "type": "function"
        }
      ]
    },
    "type": "submit_tool_outputs"
  },
  "response_format": "auto",
  "started_at": 0,
  "status": "queued",
  "thread_id": "thread_id",
  "tool_choice": "none",
  "tools": [
    {
      "type": "code_interpreter"
    }
  ],
  "truncation_strategy": {
    "type": "auto",
    "last_messages": 1
  },
  "usage": {
    "completion_tokens": 0,
    "prompt_tokens": 0,
    "total_tokens": 0
  },
  "temperature": 0,
  "top_p": 0
}

Cancel a run

client.Beta.Threads.Runs.Cancel(ctx, threadID, runID) (*Run, error)

post /threads/{thread_id}/runs/{run_id}/cancel

Cancels a run that is in_progress.

Parameters

• threadID string

• runID string

Returns

• type Run struct{…}

  Represents an execution run on a thread.

  • ID string

    The identifier, which can be referenced in API endpoints.

  • AssistantID string

    The ID of the assistant used for execution of this run.

  • CancelledAt int64

    The Unix timestamp (in seconds) for when the run was cancelled.

  • CompletedAt int64

    The Unix timestamp (in seconds) for when the run was completed.

  • CreatedAt int64

    The Unix timestamp (in seconds) for when the run was created.

  • ExpiresAt int64

    The Unix timestamp (in seconds) for when the run will expire.

  • FailedAt int64

    The Unix timestamp (in seconds) for when the run failed.

  • IncompleteDetails RunIncompleteDetails

    Details on why the run is incomplete. Will be null if the run is not incomplete.

    • Reason string

      The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.

      • const RunIncompleteDetailsReasonMaxCompletionTokens RunIncompleteDetailsReason = "max_completion_tokens"

      • const RunIncompleteDetailsReasonMaxPromptTokens RunIncompleteDetailsReason = "max_prompt_tokens"

  • Instructions string

    The instructions that the assistant used for this run.

  • LastError RunLastError

    The last error associated with this run. Will be null if there are no errors.

    • Code string

      One of server_error, rate_limit_exceeded, or invalid_prompt.

      • const RunLastErrorCodeServerError RunLastErrorCode = "server_error"

      • const RunLastErrorCodeRateLimitExceeded RunLastErrorCode = "rate_limit_exceeded"

      • const RunLastErrorCodeInvalidPrompt RunLastErrorCode = "invalid_prompt"

    • Message string

      A human-readable description of the error.

  • MaxCompletionTokens int64

    The maximum number of completion tokens specified to have been used over the course of the run.

  • MaxPromptTokens int64

    The maximum number of prompt tokens specified to have been used over the course of the run.

  • Metadata Metadata

    Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

    Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

  • Model string

    The model that the assistant used for this run.

  • Object ThreadRun

    The object type, which is always thread.run.

    • const ThreadRunThreadRun ThreadRun = "thread.run"

  • ParallelToolCalls bool

    Whether to enable parallel function calling during tool use.

  • RequiredAction RunRequiredAction

    Details on the action required to continue the run. Will be null if no action is required.

    • SubmitToolOutputs RunRequiredActionSubmitToolOutputs

      Details on the tool outputs needed for this run to continue.

      • ToolCalls []RequiredActionFunctionToolCall

        A list of the relevant tool calls.

        • ID string

          The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.

        • Function RequiredActionFunctionToolCallFunction

          The function definition.

          • Arguments string

            The arguments that the model expects you to pass to the function.

          • Name string

            The name of the function.

        • Type Function

          The type of tool call the output is required for. For now, this is always function.

          • const FunctionFunction Function = "function"

    • Type SubmitToolOutputs

      For now, this is always submit_tool_outputs.

      • const SubmitToolOutputsSubmitToolOutputs SubmitToolOutputs = "submit_tool_outputs"

  • ResponseFormat AssistantResponseFormatOptionUnion

    Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.

    Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

    Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.

    Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

    • type Auto string

      auto is the default value

      • const AutoAuto Auto = "auto"

    • type ResponseFormatText struct{…}

      Default response format. Used to generate text responses.

      • Type Text

        The type of response format being defined. Always text.

        • const TextText Text = "text"

    • type ResponseFormatJSONObject struct{…}

      JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.

      • Type JSONObject

        The type of response format being defined. Always json_object.

        • const JSONObjectJSONObject JSONObject = "json_object"

    • type ResponseFormatJSONSchema struct{…}

      JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

      • JSONSchema ResponseFormatJSONSchemaJSONSchema

        Structured Outputs configuration options, including a JSON Schema.

        • Name string

          The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Description string

          A description of what the response format is for, used by the model to determine how to respond in the format.

        • Schema map[string, any]

          The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

        • Strict bool

          Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.

      • Type JSONSchema

        The type of response format being defined. Always json_schema.

        • const JSONSchemaJSONSchema JSONSchema = "json_schema"

  • StartedAt int64

    The Unix timestamp (in seconds) for when the run was started.

  • Status RunStatus

    The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.

    • const RunStatusQueued RunStatus = "queued"

    • const RunStatusInProgress RunStatus = "in_progress"

    • const RunStatusRequiresAction RunStatus = "requires_action"

    • const RunStatusCancelling RunStatus = "cancelling"

    • const RunStatusCancelled RunStatus = "cancelled"

    • const RunStatusFailed RunStatus = "failed"

    • const RunStatusCompleted RunStatus = "completed"

    • const RunStatusIncomplete RunStatus = "incomplete"

    • const RunStatusExpired RunStatus = "expired"

  • ThreadID string

    The ID of the thread that was executed on as a part of this run.

  • ToolChoice AssistantToolChoiceOptionUnion

    Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

    • type AssistantToolChoiceOptionAuto string

      none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.

      • const AssistantToolChoiceOptionAutoNone AssistantToolChoiceOptionAuto = "none"

      • const AssistantToolChoiceOptionAutoAuto AssistantToolChoiceOptionAuto = "auto"

      • const AssistantToolChoiceOptionAutoRequired AssistantToolChoiceOptionAuto = "required"

    • type AssistantToolChoice struct{…}

      Specifies a tool the model should use. Use to force the model to call a specific tool.

      • Type AssistantToolChoiceType

        The type of the tool. If type is function, the function name must be set

        • const AssistantToolChoiceTypeFunction AssistantToolChoiceType = "function"

        • const AssistantToolChoiceTypeCodeInterpreter AssistantToolChoiceType = "code_interpreter"

        • const AssistantToolChoiceTypeFileSearch AssistantToolChoiceType = "file_search"

      • Function AssistantToolChoiceFunction

        • Name string

          The name of the function to call.

  • Tools []AssistantToolUnion

    The list of tools that the assistant used for this run.

    • type CodeInterpreterTool struct{…}

      • Type CodeInterpreter

        The type of tool being defined: code_interpreter

        • const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"

    • type FileSearchTool struct{…}

      • Type FileSearch

        The type of tool being defined: file_search

        • const FileSearchFileSearch FileSearch = "file_search"

      • FileSearch FileSearchToolFileSearch

        Overrides for the file search tool.

        • MaxNumResults int64

          The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

          Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

        • RankingOptions FileSearchToolFileSearchRankingOptions

          The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

          See the file search tool documentation for more information.

          • ScoreThreshold float64

            The score threshold for the file search. All values must be a floating point number between 0 and 1.

          • Ranker string

            The ranker to use for the file search. If not specified will use the auto ranker.

            • const FileSearchToolFileSearchRankingOptionsRankerAuto FileSearchToolFileSearchRankingOptionsRanker = "auto"

            • const FileSearchToolFileSearchRankingOptionsRankerDefault2024_08_21 FileSearchToolFileSearchRankingOptionsRanker = "default_2024_08_21"

    • type FunctionTool struct{…}

      • Function FunctionDefinition

        • Name string

          The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Description string

          A description of what the function does, used by the model to choose when and how to call the function.

        • Parameters FunctionParameters

          The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

          Omitting parameters defines a function with an empty parameter list.

        • Strict bool

          Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

      • Type Function

        The type of tool being defined: function

        • const FunctionFunction Function = "function"

  • TruncationStrategy RunTruncationStrategy

    Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.

    • Type string

      The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.

      • const RunTruncationStrategyTypeAuto RunTruncationStrategyType = "auto"

      • const RunTruncationStrategyTypeLastMessages RunTruncationStrategyType = "last_messages"

    • LastMessages int64

      The number of most recent messages from the thread when constructing the context for the run.

  • Usage RunUsage

    Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).

    • CompletionTokens int64

      Number of completion tokens used over the course of the run.

    • PromptTokens int64

      Number of prompt tokens used over the course of the run.

    • TotalTokens int64

      Total number of tokens used (prompt + completion).

  • Temperature float64

    The sampling temperature used for this run. If not set, defaults to 1.

  • TopP float64

    The nucleus sampling value used for this run. If not set, defaults to 1.

Example

package main

import (
  "context"
  "fmt"

  "github.com/openai/openai-go"
  "github.com/openai/openai-go/option"
)

func main() {
  client := openai.NewClient(
    option.WithAPIKey("My API Key"),
  )
  run, err := client.Beta.Threads.Runs.Cancel(
    context.TODO(),
    "thread_id",
    "run_id",
  )
  if err != nil {
    panic(err.Error())
  }
  fmt.Printf("%+v\n", run.ID)
}

Response

{
  "id": "id",
  "assistant_id": "assistant_id",
  "cancelled_at": 0,
  "completed_at": 0,
  "created_at": 0,
  "expires_at": 0,
  "failed_at": 0,
  "incomplete_details": {
    "reason": "max_completion_tokens"
  },
  "instructions": "instructions",
  "last_error": {
    "code": "server_error",
    "message": "message"
  },
  "max_completion_tokens": 256,
  "max_prompt_tokens": 256,
  "metadata": {
    "foo": "string"
  },
  "model": "model",
  "object": "thread.run",
  "parallel_tool_calls": true,
  "required_action": {
    "submit_tool_outputs": {
      "tool_calls": [
        {
          "id": "id",
          "function": {
            "arguments": "arguments",
            "name": "name"
          },
          "type": "function"
        }
      ]
    },
    "type": "submit_tool_outputs"
  },
  "response_format": "auto",
  "started_at": 0,
  "status": "queued",
  "thread_id": "thread_id",
  "tool_choice": "none",
  "tools": [
    {
      "type": "code_interpreter"
    }
  ],
  "truncation_strategy": {
    "type": "auto",
    "last_messages": 1
  },
  "usage": {
    "completion_tokens": 0,
    "prompt_tokens": 0,
    "total_tokens": 0
  },
  "temperature": 0,
  "top_p": 0
}

Domain Types

Required Action Function Tool Call

• type RequiredActionFunctionToolCall struct{…}

  Tool call objects

  • ID string

    The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.

  • Function RequiredActionFunctionToolCallFunction

    The function definition.

    • Arguments string

      The arguments that the model expects you to pass to the function.

    • Name string

      The name of the function.

  • Type Function

    The type of tool call the output is required for. For now, this is always function.

    • const FunctionFunction Function = "function"

Run

• type Run struct{…}

  Represents an execution run on a thread.

  • ID string

    The identifier, which can be referenced in API endpoints.

  • AssistantID string

    The ID of the assistant used for execution of this run.

  • CancelledAt int64

    The Unix timestamp (in seconds) for when the run was cancelled.

  • CompletedAt int64

    The Unix timestamp (in seconds) for when the run was completed.

  • CreatedAt int64

    The Unix timestamp (in seconds) for when the run was created.

  • ExpiresAt int64

    The Unix timestamp (in seconds) for when the run will expire.

  • FailedAt int64

    The Unix timestamp (in seconds) for when the run failed.

  • IncompleteDetails RunIncompleteDetails

    Details on why the run is incomplete. Will be null if the run is not incomplete.

    • Reason string

      The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.

      • const RunIncompleteDetailsReasonMaxCompletionTokens RunIncompleteDetailsReason = "max_completion_tokens"

      • const RunIncompleteDetailsReasonMaxPromptTokens RunIncompleteDetailsReason = "max_prompt_tokens"

  • Instructions string

    The instructions that the assistant used for this run.

  • LastError RunLastError

    The last error associated with this run. Will be null if there are no errors.

    • Code string

      One of server_error, rate_limit_exceeded, or invalid_prompt.

      • const RunLastErrorCodeServerError RunLastErrorCode = "server_error"

      • const RunLastErrorCodeRateLimitExceeded RunLastErrorCode = "rate_limit_exceeded"

      • const RunLastErrorCodeInvalidPrompt RunLastErrorCode = "invalid_prompt"

    • Message string

      A human-readable description of the error.

  • MaxCompletionTokens int64

    The maximum number of completion tokens specified to have been used over the course of the run.

  • MaxPromptTokens int64

    The maximum number of prompt tokens specified to have been used over the course of the run.

  • Metadata Metadata

    Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

    Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

  • Model string

    The model that the assistant used for this run.

  • Object ThreadRun

    The object type, which is always thread.run.

    • const ThreadRunThreadRun ThreadRun = "thread.run"

  • ParallelToolCalls bool

    Whether to enable parallel function calling during tool use.

  • RequiredAction RunRequiredAction

    Details on the action required to continue the run. Will be null if no action is required.

    • SubmitToolOutputs RunRequiredActionSubmitToolOutputs

      Details on the tool outputs needed for this run to continue.

      • ToolCalls []RequiredActionFunctionToolCall

        A list of the relevant tool calls.

        • ID string

          The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.

        • Function RequiredActionFunctionToolCallFunction

          The function definition.

          • Arguments string

            The arguments that the model expects you to pass to the function.

          • Name string

            The name of the function.

        • Type Function

          The type of tool call the output is required for. For now, this is always function.

          • const FunctionFunction Function = "function"

    • Type SubmitToolOutputs

      For now, this is always submit_tool_outputs.

      • const SubmitToolOutputsSubmitToolOutputs SubmitToolOutputs = "submit_tool_outputs"

  • ResponseFormat AssistantResponseFormatOptionUnion

    Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.

    Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

    Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.

    Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

    • type Auto string

      auto is the default value

      • const AutoAuto Auto = "auto"

    • type ResponseFormatText struct{…}

      Default response format. Used to generate text responses.

      • Type Text

        The type of response format being defined. Always text.

        • const TextText Text = "text"

    • type ResponseFormatJSONObject struct{…}

      JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.

      • Type JSONObject

        The type of response format being defined. Always json_object.

        • const JSONObjectJSONObject JSONObject = "json_object"

    • type ResponseFormatJSONSchema struct{…}

      JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

      • JSONSchema ResponseFormatJSONSchemaJSONSchema

        Structured Outputs configuration options, including a JSON Schema.

        • Name string

          The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Description string

          A description of what the response format is for, used by the model to determine how to respond in the format.

        • Schema map[string, any]

          The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

        • Strict bool

          Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.

      • Type JSONSchema

        The type of response format being defined. Always json_schema.

        • const JSONSchemaJSONSchema JSONSchema = "json_schema"

  • StartedAt int64

    The Unix timestamp (in seconds) for when the run was started.

  • Status RunStatus

    The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.

    • const RunStatusQueued RunStatus = "queued"

    • const RunStatusInProgress RunStatus = "in_progress"

    • const RunStatusRequiresAction RunStatus = "requires_action"

    • const RunStatusCancelling RunStatus = "cancelling"

    • const RunStatusCancelled RunStatus = "cancelled"

    • const RunStatusFailed RunStatus = "failed"

    • const RunStatusCompleted RunStatus = "completed"

    • const RunStatusIncomplete RunStatus = "incomplete"

    • const RunStatusExpired RunStatus = "expired"

  • ThreadID string

    The ID of the thread that was executed on as a part of this run.

  • ToolChoice AssistantToolChoiceOptionUnion

    Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

    • type AssistantToolChoiceOptionAuto string

      none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.

      • const AssistantToolChoiceOptionAutoNone AssistantToolChoiceOptionAuto = "none"

      • const AssistantToolChoiceOptionAutoAuto AssistantToolChoiceOptionAuto = "auto"

      • const AssistantToolChoiceOptionAutoRequired AssistantToolChoiceOptionAuto = "required"

    • type AssistantToolChoice struct{…}

      Specifies a tool the model should use. Use to force the model to call a specific tool.

      • Type AssistantToolChoiceType

        The type of the tool. If type is function, the function name must be set

        • const AssistantToolChoiceTypeFunction AssistantToolChoiceType = "function"

        • const AssistantToolChoiceTypeCodeInterpreter AssistantToolChoiceType = "code_interpreter"

        • const AssistantToolChoiceTypeFileSearch AssistantToolChoiceType = "file_search"

      • Function AssistantToolChoiceFunction

        • Name string

          The name of the function to call.

  • Tools []AssistantToolUnion

    The list of tools that the assistant used for this run.

    • type CodeInterpreterTool struct{…}

      • Type CodeInterpreter

        The type of tool being defined: code_interpreter

        • const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"

    • type FileSearchTool struct{…}

      • Type FileSearch

        The type of tool being defined: file_search

        • const FileSearchFileSearch FileSearch = "file_search"

      • FileSearch FileSearchToolFileSearch

        Overrides for the file search tool.

        • MaxNumResults int64

          The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

          Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

        • RankingOptions FileSearchToolFileSearchRankingOptions

          The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

          See the file search tool documentation for more information.

          • ScoreThreshold float64

            The score threshold for the file search. All values must be a floating point number between 0 and 1.

          • Ranker string

            The ranker to use for the file search. If not specified will use the auto ranker.

            • const FileSearchToolFileSearchRankingOptionsRankerAuto FileSearchToolFileSearchRankingOptionsRanker = "auto"

            • const FileSearchToolFileSearchRankingOptionsRankerDefault2024_08_21 FileSearchToolFileSearchRankingOptionsRanker = "default_2024_08_21"

    • type FunctionTool struct{…}

      • Function FunctionDefinition

        • Name string

          The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Description string

          A description of what the function does, used by the model to choose when and how to call the function.

        • Parameters FunctionParameters

          The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

          Omitting parameters defines a function with an empty parameter list.

        • Strict bool

          Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

      • Type Function

        The type of tool being defined: function

        • const FunctionFunction Function = "function"

  • TruncationStrategy RunTruncationStrategy

    Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.

    • Type string

      The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.

      • const RunTruncationStrategyTypeAuto RunTruncationStrategyType = "auto"

      • const RunTruncationStrategyTypeLastMessages RunTruncationStrategyType = "last_messages"

    • LastMessages int64

      The number of most recent messages from the thread when constructing the context for the run.

  • Usage RunUsage

    Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).

    • CompletionTokens int64

      Number of completion tokens used over the course of the run.

    • PromptTokens int64

      Number of prompt tokens used over the course of the run.

    • TotalTokens int64

      Total number of tokens used (prompt + completion).

  • Temperature float64

    The sampling temperature used for this run. If not set, defaults to 1.

  • TopP float64

    The nucleus sampling value used for this run. If not set, defaults to 1.

Run Status

• type RunStatus string

  The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.

  • const RunStatusQueued RunStatus = "queued"

  • const RunStatusInProgress RunStatus = "in_progress"

  • const RunStatusRequiresAction RunStatus = "requires_action"

  • const RunStatusCancelling RunStatus = "cancelling"

  • const RunStatusCancelled RunStatus = "cancelled"

  • const RunStatusFailed RunStatus = "failed"

  • const RunStatusCompleted RunStatus = "completed"

  • const RunStatusIncomplete RunStatus = "incomplete"

  • const RunStatusExpired RunStatus = "expired"

Steps

List run steps

client.Beta.Threads.Runs.Steps.List(ctx, threadID, runID, query) (*CursorPage[RunStep], error)

get /threads/{thread_id}/runs/{run_id}/steps

Returns a list of run steps belonging to a run.

Parameters

• threadID string

• runID string

• query BetaThreadRunStepListParams

  • After param.Field[string]

    A cursor for use in pagination. after is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.

  • Before param.Field[string]

    A cursor for use in pagination. before is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.

  • Include param.Field[[]RunStepInclude]

    A list of additional fields to include in the response. Currently the only supported value is step_details.tool_calls[*].file_search.results[*].content to fetch the file search result content.

    See the file search tool documentation for more information.

    • const RunStepIncludeStepDetailsToolCallsFileSearchResultsContent RunStepInclude = "step_details.tool_calls[*].file_search.results[*].content"

  • Limit param.Field[int64]

    A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.

  • Order param.Field[BetaThreadRunStepListParamsOrder]

    Sort order by the created_at timestamp of the objects. asc for ascending order and desc for descending order.

    • const BetaThreadRunStepListParamsOrderAsc BetaThreadRunStepListParamsOrder = "asc"

    • const BetaThreadRunStepListParamsOrderDesc BetaThreadRunStepListParamsOrder = "desc"

Returns

• type RunStep struct{…}

  Represents a step in execution of a run.

  • ID string

    The identifier of the run step, which can be referenced in API endpoints.

  • AssistantID string

    The ID of the assistant associated with the run step.

  • CancelledAt int64

    The Unix timestamp (in seconds) for when the run step was cancelled.

  • CompletedAt int64

    The Unix timestamp (in seconds) for when the run step completed.

  • CreatedAt int64

    The Unix timestamp (in seconds) for when the run step was created.

  • ExpiredAt int64

    The Unix timestamp (in seconds) for when the run step expired. A step is considered expired if the parent run is expired.

  • FailedAt int64

    The Unix timestamp (in seconds) for when the run step failed.

  • LastError RunStepLastError

    The last error associated with this run step. Will be null if there are no errors.

    • Code string

      One of server_error or rate_limit_exceeded.

      • const RunStepLastErrorCodeServerError RunStepLastErrorCode = "server_error"

      • const RunStepLastErrorCodeRateLimitExceeded RunStepLastErrorCode = "rate_limit_exceeded"

    • Message string

      A human-readable description of the error.

  • Metadata Metadata

    Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

    Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

  • Object ThreadRunStep

    The object type, which is always thread.run.step.

    • const ThreadRunStepThreadRunStep ThreadRunStep = "thread.run.step"

  • RunID string

    The ID of the run that this run step is a part of.

  • Status RunStepStatus

    The status of the run step, which can be either in_progress, cancelled, failed, completed, or expired.

    • const RunStepStatusInProgress RunStepStatus = "in_progress"

    • const RunStepStatusCancelled RunStepStatus = "cancelled"

    • const RunStepStatusFailed RunStepStatus = "failed"

    • const RunStepStatusCompleted RunStepStatus = "completed"

    • const RunStepStatusExpired RunStepStatus = "expired"

  • StepDetails RunStepStepDetailsUnion

    The details of the run step.

    • type MessageCreationStepDetails struct{…}

      Details of the message creation by the run step.

      • MessageCreation MessageCreationStepDetailsMessageCreation

        • MessageID string

          The ID of the message that was created by this run step.

      • Type MessageCreation

        Always message_creation.

        • const MessageCreationMessageCreation MessageCreation = "message_creation"

    • type ToolCallsStepDetails struct{…}

      Details of the tool call.

      • ToolCalls []ToolCallUnion

        An array of tool calls the run step was involved in. These can be associated with one of three types of tools: code_interpreter, file_search, or function.

        • type CodeInterpreterToolCall struct{…}

          Details of the Code Interpreter tool call the run step was involved in.

          • ID string

            The ID of the tool call.

          • CodeInterpreter CodeInterpreterToolCallCodeInterpreter

            The Code Interpreter tool call definition.

            • Input string

              The input to the Code Interpreter tool call.

            • Outputs []CodeInterpreterToolCallCodeInterpreterOutputUnion

              The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (logs) or images (image). Each of these are represented by a different object type.

              • type CodeInterpreterToolCallCodeInterpreterOutputLogs struct{…}

                Text output from the Code Interpreter tool call as part of a run step.

                • Logs string

                  The text output from the Code Interpreter tool call.

                • Type Logs

                  Always logs.

                  • const LogsLogs Logs = "logs"

              • type CodeInterpreterToolCallCodeInterpreterOutputImage struct{…}

                • Image CodeInterpreterToolCallCodeInterpreterOutputImageImage

                  • FileID string

                    The file ID of the image.

                • Type Image

                  Always image.

                  • const ImageImage Image = "image"

          • Type CodeInterpreter

            The type of tool call. This is always going to be code_interpreter for this type of tool call.

            • const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"

        • type FileSearchToolCall struct{…}

          • ID string

            The ID of the tool call object.

          • FileSearch FileSearchToolCallFileSearch

            For now, this is always going to be an empty object.

            • RankingOptions FileSearchToolCallFileSearchRankingOptions

              The ranking options for the file search.

              • Ranker string

                The ranker to use for the file search. If not specified will use the auto ranker.

                • const FileSearchToolCallFileSearchRankingOptionsRankerAuto FileSearchToolCallFileSearchRankingOptionsRanker = "auto"

                • const FileSearchToolCallFileSearchRankingOptionsRankerDefault2024_08_21 FileSearchToolCallFileSearchRankingOptionsRanker = "default_2024_08_21"

              • ScoreThreshold float64

                The score threshold for the file search. All values must be a floating point number between 0 and 1.

            • Results []FileSearchToolCallFileSearchResult

              The results of the file search.

              • FileID string

                The ID of the file that result was found in.

              • FileName string

                The name of the file that result was found in.

              • Score float64

                The score of the result. All values must be a floating point number between 0 and 1.

              • Content []FileSearchToolCallFileSearchResultContent

                The content of the result that was found. The content is only included if requested via the include query parameter.

                • Text string

                  The text content of the file.

                • Type string

                  The type of the content.

                  • const FileSearchToolCallFileSearchResultContentTypeText FileSearchToolCallFileSearchResultContentType = "text"

          • Type FileSearch

            The type of tool call. This is always going to be file_search for this type of tool call.

            • const FileSearchFileSearch FileSearch = "file_search"

        • type FunctionToolCall struct{…}

          • ID string

            The ID of the tool call object.

          • Function FunctionToolCallFunction

            The definition of the function that was called.

            • Arguments string

              The arguments passed to the function.

            • Name string

              The name of the function.

            • Output string

              The output of the function. This will be null if the outputs have not been submitted yet.

          • Type Function

            The type of tool call. This is always going to be function for this type of tool call.

            • const FunctionFunction Function = "function"

      • Type ToolCalls

        Always tool_calls.

        • const ToolCallsToolCalls ToolCalls = "tool_calls"

  • ThreadID string

    The ID of the thread that was run.

  • Type RunStepType

    The type of run step, which can be either message_creation or tool_calls.

    • const RunStepTypeMessageCreation RunStepType = "message_creation"

    • const RunStepTypeToolCalls RunStepType = "tool_calls"

  • Usage RunStepUsage

    Usage statistics related to the run step. This value will be null while the run step's status is in_progress.

    • CompletionTokens int64

      Number of completion tokens used over the course of the run step.

    • PromptTokens int64

      Number of prompt tokens used over the course of the run step.

    • TotalTokens int64

      Total number of tokens used (prompt + completion).

Example

package main

import (
  "context"
  "fmt"

  "github.com/openai/openai-go"
  "github.com/openai/openai-go/option"
)

func main() {
  client := openai.NewClient(
    option.WithAPIKey("My API Key"),
  )
  page, err := client.Beta.Threads.Runs.Steps.List(
    context.TODO(),
    "thread_id",
    "run_id",
    openai.BetaThreadRunStepListParams{

    },
  )
  if err != nil {
    panic(err.Error())
  }
  fmt.Printf("%+v\n", page)
}

Response

{
  "data": [
    {
      "id": "id",
      "assistant_id": "assistant_id",
      "cancelled_at": 0,
      "completed_at": 0,
      "created_at": 0,
      "expired_at": 0,
      "failed_at": 0,
      "last_error": {
        "code": "server_error",
        "message": "message"
      },
      "metadata": {
        "foo": "string"
      },
      "object": "thread.run.step",
      "run_id": "run_id",
      "status": "in_progress",
      "step_details": {
        "message_creation": {
          "message_id": "message_id"
        },
        "type": "message_creation"
      },
      "thread_id": "thread_id",
      "type": "message_creation",
      "usage": {
        "completion_tokens": 0,
        "prompt_tokens": 0,
        "total_tokens": 0
      }
    }
  ],
  "first_id": "step_abc123",
  "has_more": false,
  "last_id": "step_abc456",
  "object": "list"
}

Retrieve run step

client.Beta.Threads.Runs.Steps.Get(ctx, threadID, runID, stepID, query) (*RunStep, error)

get /threads/{thread_id}/runs/{run_id}/steps/{step_id}

Retrieves a run step.

Parameters

• threadID string

• runID string

• stepID string

• query BetaThreadRunStepGetParams

  • Include param.Field[[]RunStepInclude]

    A list of additional fields to include in the response. Currently the only supported value is step_details.tool_calls[*].file_search.results[*].content to fetch the file search result content.

    See the file search tool documentation for more information.

    • const RunStepIncludeStepDetailsToolCallsFileSearchResultsContent RunStepInclude = "step_details.tool_calls[*].file_search.results[*].content"

Returns

• type RunStep struct{…}

  Represents a step in execution of a run.

  • ID string

    The identifier of the run step, which can be referenced in API endpoints.

  • AssistantID string

    The ID of the assistant associated with the run step.

  • CancelledAt int64

    The Unix timestamp (in seconds) for when the run step was cancelled.

  • CompletedAt int64

    The Unix timestamp (in seconds) for when the run step completed.

  • CreatedAt int64

    The Unix timestamp (in seconds) for when the run step was created.

  • ExpiredAt int64

    The Unix timestamp (in seconds) for when the run step expired. A step is considered expired if the parent run is expired.

  • FailedAt int64

    The Unix timestamp (in seconds) for when the run step failed.

  • LastError RunStepLastError

    The last error associated with this run step. Will be null if there are no errors.

    • Code string

      One of server_error or rate_limit_exceeded.

      • const RunStepLastErrorCodeServerError RunStepLastErrorCode = "server_error"

      • const RunStepLastErrorCodeRateLimitExceeded RunStepLastErrorCode = "rate_limit_exceeded"

    • Message string

      A human-readable description of the error.

  • Metadata Metadata

    Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

    Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

  • Object ThreadRunStep

    The object type, which is always thread.run.step.

    • const ThreadRunStepThreadRunStep ThreadRunStep = "thread.run.step"

  • RunID string

    The ID of the run that this run step is a part of.

  • Status RunStepStatus

    The status of the run step, which can be either in_progress, cancelled, failed, completed, or expired.

    • const RunStepStatusInProgress RunStepStatus = "in_progress"

    • const RunStepStatusCancelled RunStepStatus = "cancelled"

    • const RunStepStatusFailed RunStepStatus = "failed"

    • const RunStepStatusCompleted RunStepStatus = "completed"

    • const RunStepStatusExpired RunStepStatus = "expired"

  • StepDetails RunStepStepDetailsUnion

    The details of the run step.

    • type MessageCreationStepDetails struct{…}

      Details of the message creation by the run step.

      • MessageCreation MessageCreationStepDetailsMessageCreation

        • MessageID string

          The ID of the message that was created by this run step.

      • Type MessageCreation

        Always message_creation.

        • const MessageCreationMessageCreation MessageCreation = "message_creation"

    • type ToolCallsStepDetails struct{…}

      Details of the tool call.

      • ToolCalls []ToolCallUnion

        An array of tool calls the run step was involved in. These can be associated with one of three types of tools: code_interpreter, file_search, or function.

        • type CodeInterpreterToolCall struct{…}

          Details of the Code Interpreter tool call the run step was involved in.

          • ID string

            The ID of the tool call.

          • CodeInterpreter CodeInterpreterToolCallCodeInterpreter

            The Code Interpreter tool call definition.

            • Input string

              The input to the Code Interpreter tool call.

            • Outputs []CodeInterpreterToolCallCodeInterpreterOutputUnion

              The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (logs) or images (image). Each of these are represented by a different object type.

              • type CodeInterpreterToolCallCodeInterpreterOutputLogs struct{…}

                Text output from the Code Interpreter tool call as part of a run step.

                • Logs string

                  The text output from the Code Interpreter tool call.

                • Type Logs

                  Always logs.

                  • const LogsLogs Logs = "logs"

              • type CodeInterpreterToolCallCodeInterpreterOutputImage struct{…}

                • Image CodeInterpreterToolCallCodeInterpreterOutputImageImage

                  • FileID string

                    The file ID of the image.

                • Type Image

                  Always image.

                  • const ImageImage Image = "image"

          • Type CodeInterpreter

            The type of tool call. This is always going to be code_interpreter for this type of tool call.

            • const CodeInterpreterCodeInterpreter CodeInterpreter = "code_interpreter"

        • type FileSearchToolCall struct{…}

          • ID string

            The ID of the tool call object.

          • FileSearch FileSearchToolCallFileSearch

            For now, this is always going to be an empty object.

            • RankingOptions FileSearchToolCallFileSearchRankingOptions

              The ranking options for the file search.

              • Ranker string

                The ranker to use for the file search. If not specified will use the auto ranker.

                • const FileSearchToolCallFileSearchRankingOptionsRankerAuto FileSearchToolCallFileSearchRankingOptionsRanker = "auto"

                • const FileSearchToolCallFileSearchRankingOptionsRankerDefault2024_08_21 FileSearchToolCallFileSearchRankingOptionsRanker = "default_2024_08_21"

              • ScoreThreshold float64

                The score threshold for the file search. All values must be a floating point number between 0 and 1.

            • Results []FileSearchToolCallFileSearchResult

              The results of the file search.

              • FileID string

                The ID of the file that result was found in.

              • FileName string

                The name of the file that result was found in.

              • Score float64

                The score of the result. All values must be a floating point number between 0 and 1.

              • Content []FileSearchToolCallFileSearchResultContent

                The content of the result that was found. The content is only included if requested via the include query parameter.

                • Text string

                  The text content of the file.

                • Type string

                  The type of the content.

                  • const FileSearchToolCallFileSearchResultContentTypeText FileSearchToolCallFileSearchResultContentType = "text"

          • Type FileSearch

            The type of tool call. This is always going to be file_search for this type of tool call.

            • const FileSearchFileSearch FileSearch = "file_search"

        • type FunctionToolCall struct{…}

          • ID string

            The ID of the tool call object.

          • Function FunctionToolCallFunction

            The definition of the function that was called.

            • Arguments string

              The arguments passed to the function.

            • Name string

              The name of the function.

            • Output string

              The output of the function. This will be null if the outputs have not been submitted yet.

          • Type Function

            The type of tool call. This is always going to be function for this type of tool call.

            • const FunctionFunction Function = "function"

      • Type ToolCalls

        Always tool_calls.

        • const ToolCallsToolCalls ToolCalls = "tool_calls"

  • ThreadID string

    The ID of the thread that was run.

  • Type RunStepType

    The type of run step, which can be either message_creation or tool_calls.

    • const RunStepTypeMessageCreation RunStepType = "message_creation"

    • const RunStepTypeToolCalls RunStepType = "tool_calls"

  • Usage RunStepUsage

    Usage statistics related to the run step. This value will be null while the run step's status is in_progress.

    • CompletionTokens int64

      Number of completion tokens used over the course of the run step.

    • PromptTokens int64

      Number of prompt tokens used over the course of the run step.

    • TotalTokens int64

      Total number of tokens used (prompt + completion).