Get desktop application:
View/edit binary Protocol Buffers messages
============================================================== AssistantService ==============================================================
CreateAssistantRequest, GetAssistantResponse, ModifyAssistantResponse
Used in:
ResponseFormat response_format = 8;
union of Code, FileSearch, Function
Used in: , , , ,
Used in: , , , ,
Used in:
maxItems = 20
Used in:
maxItem = 1
Used in: , , ,
The ID of the run to cancel.
The ID of the thread to which this run belongs.
The ID of the file batch to cancel.
The ID of the vector store that the file batch belongs to.
Used in: ,
Used in: ,
Used in: ,
The ID of the [thread](/docs/api-reference/threads) to create a message for.
optional
for internal use
ToolChoice tool_choice = 18;
ResponseFormat response_format = 19;
============================================================== ThreadService - Run ==============================================================
>= 256
>= 256
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.
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 a tool. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool. due to language characteristics, we cannot make `tool_choice` as arbitrary type of `string` and `object`. So we choose to define `ToolChoice` as object type. ToolChoice tool_choice = 14;
message ToolChoice { AssistantToolType type = 1; ToolChoiceFunction function = 2; message ToolChoiceFunction { string name = 1; } }
ResponseFormat response_format = 15;
============================================================== VectorStore - FileBatch ==============================================================
The ID of the vector store for which to create a File Batch.
The ID of the vector store for which to create a File.
The ID of the assistant to delete.
The ID of the file to use for this request.
The ID of the thread to delete.
The ID of the file to delete.
The ID of the vector store that the file belongs to.
always `vector_store.file.deleted`
The ID of the vector store to delete.
DownloadFileResponse is type of string, thus it cannot be defined in proto files
The ID of the file to use for this request.
Used in: ,
UploadFileResponse, RetrieveFileResponse
Used in:
Used in: , ,
The ID of the assistant to retrieve.
The ID of the message to retrieve.
The ID of the [thread](/docs/api-reference/threads) to which this message belongs.
The ID of the run to retrieve.
The ID of the [thread](/docs/api-reference/threads) that was run.
The ID of the run to which the run step belongs.
The ID of the run step to retrieve.
The ID of the thread to which the run and run step belongs.
The ID of the thread to retrieve.
The ID of the file batch being retrieved.
The ID of the vector store that the file batch belongs to.
The ID of the file being retrieved.
The ID of the vector store that the file belongs to.
The ID of the vector store to retrieve.
Used in: ,
Used in:
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.
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, ending with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.
A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.
Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order.
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.
The ID of the file batch that the files belong to.
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, ending with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.
Filter by file status. One of `in_progress`, `completed`, `failed`, `cancelled`.
A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.
Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order.
The ID of the vector store that the files belong to.
============================================================== File ==============================================================
Only return files with the given purpose.
always `list`
============================================================== ThreadService - Message ==============================================================
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.
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, ending with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.
A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.
Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order.
Filter messages by the run ID that generated them.
The ID of the [thread](/docs/api-reference/threads) the messages belong to.
Used in: , , , , , ,
default
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.
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, ending with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.
A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.
Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order.
The ID of the run the run steps belong to.
The ID of the thread the run and run steps belong to.
always `list`
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.
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, ending with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.
A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.
Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order.
The ID of the thread the run belongs to.
always `list`
============================================================== VectorStore - File ==============================================================
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.
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, ending with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.
Filter by file status. One of `in_progress`, `completed`, `failed`, `cancelled`.
A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.
Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order.
The ID of the vector store that the files belong to.
============================================================== VectorStore ==============================================================
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.
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, ending with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.
A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.
Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order.
Used in: ,
CreateMessageResponse, RetrieveMessageResponse, ModifyMessageResponse
Used in:
Used in:
for image file only
for text only
Used in:
Used in:
union of citation and file path
Used in:
for citation only
Used in:
for file path only
Used in:
Used in:
A citation within the message that points to a specific quote from a specific File associated with the assistant or the message. Generated when the assistant uses the "file_search" tool to search files.
A URL for the file that's generated when the assistant used the code_interpreter tool to generate a file.
Used in:
Used in:
Used in: ,
ResponseFormat response_format = 8;
The ID of the message to modify.
The ID of the thread to which this message belongs.
The ID of the run to modify.
The ID of the [thread](/docs/api-reference/threads) that was run.
only used internally
only used internally
The ID of the thread to modify. Only the `metadata` can be modified.
The ID of the file being retrieved.
The ID of the vector store that the file belongs to.
The ID of the vector store to modify.
The ID of the file to use for this request.
custom detail data for AgentFinish
CreateThreadAndRunResponse, CreateRunResponse, RetrieveRunObject, ModifyRunResponse, SubmitToolOutputsResponse, GetRunResponse
Used in:
always `thread.run`
could be zero so it has be `optional`
could be zero so it has be `optional`
"auto" or JSON string of ToolChoice
"auto" or JSON string of ResponseFormat
Used in: ,
Used in:
Used in:
Used in: ,
Used in:
Used in: , , ,
GetRunStepResponse
Used in:
union of RunStepDetailsMessageCreationObject and RunStepDetailsToolCallObject
Used in: ,
for message creation only
for tool calls only
Used in:
union of CodeInterpreterToolCall, FileSearchToolCall, FunctionToolCall
Used in:
Used in:
union of CodeOutputLogsObject and CodeOutputImageObject
Used in:
only for CodeOutputLogsObject
only for CodeOutputImageObject
Used in:
Used in:
Used in:
(message has no fields)
Used in:
Used in: ,
Used in: ,
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.
The ID of the run that requires the tool output submission.
The ID of the [thread](/docs/api-reference/threads) to which this run belongs.
If true, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a data: [DONE] message.
Used in:
============================================================== ThreadService - Thread ==============================================================
CreateThreadRequest, GetThreadResponse, ModifyThreadResponse
Used in:
Used in:
Used in: , ,
fine-tune, assistants
Used in: , ,
Anchor timestamp after which the expiration policy applies. Supported anchors: last_active_at.
The number of days after the anchor time that the vector store will expire.
Used in:
CreateVectorStoreFileBatchResponse, GetVectorStoreFileBatchResponse, CancelVectorStoreFileBatchResponse
Used in: ,
Used in: , , ,
CreateVectorFileResponse
Used in: ,
extra field for summary which doesn't exist in original API
Used in: , , ,
CreateVectorStoreResponse, GetVectorStoreResponse, ModifyVectorStoreResponse
Used in:
always `vector_store`
The Unix timestamp (in seconds) for when the vector store will expire.
The Unix timestamp (in seconds) for when the vector store was last active.
this is a extra field for storing text summary of containing documents. And it's not in the original OpenAI's API design.
Used in: ,