This public endpoint handles chat interactions that involve responses generated from document retrieval.
It allows users to submit query, which the system processes to provide relevant responses by leveraging documents. You can customize the prompt of the model from the admin panel or complete the existing prompt with a dedicated user message.
Parameters:
query: should be a string.model (optional): specifies the LLM model to use for generating responses. If not provided, the default model configured in the user’s chat settings will be used.workspace_ids (optional): specifies the workspace IDs whose documents will be added to the scope.file_ids (optional): specifies the document IDs that will be added to the scope.chat_session_id (optional): specifies the chat session ID for follow-up.company_scope (optional): specifies if the documents from the user’s company will beadded to the scope.private_scope (optional): specifies if the documents from the user’s private collection will be added to the scope.tool (optional): specifies the tool to use for the chat with doc session choose between ‘VisionDocumentSearch’ and ‘DocumentSearch’, the default is ‘DocumentSearch’.private (optional): specifies whether this chat interaction is private.generation_instructions (optional): specifies additional instructions to concatenate with the prompt for generation. These instructions will be appended to the regular prompt.extra_body (optional): specifies additional parameters for VLLM structured output. guided_* parameters are allowed (guided_choice, guided_regex, guided_json, guided_grammar, guided_whitespace_pattern, guided_decoding_backend).rewrite_query (optional): specifies whether the query will be rewritten to improve the search results, the default is True.WARNING: this endpoint is deprecated and will be removed in a future version. Please use /v3/threads/turns generic endpoints insteadBearer authentication header of the form Bearer <token>, where <token> is your auth token.
Request serializer for document search endpoint.
Search query to find relevant documents
List of workspace IDs whose documents will be added to scope
List of document IDs that will be added to scope
ID of the chat session for context
Model to use for document search
Include documents from company scope
Include documents from private scope
Private search flag
Tool type for document search
VisionDocumentSearch - VisionDocumentSearchDocumentSearch - DocumentSearchVisionDocumentSearch, DocumentSearch Additional instructions to concatenate with the prompt for generation
Additional parameters for VLLM structured output. Only 'guided_*' parameters are allowed (guided_choice, guided_regex, guided_json, guided_grammar, guided_whitespace_pattern, guided_decoding_backend). Standard generation parameters like temperature and max_tokens should not be included as they will be overridden by the generation config.
Rewrite query flag, if True the query will be rewritten to improve the search results