Tool to chat with a Pinecone assistant and get structured responses with citations. Use when you need to query an assistant that has access to your knowledge base and want to get back answers with document references and citations.
modelstringThe large language model to use for answer generation. Default is 'gpt-4o'.
filterobjectOptionally filter which documents can be retrieved using metadata fields. Example: {"genre": {"$ne": "documentary"}}
streambooleanIf false, the assistant returns a single JSON response. If true, the assistant returns a stream of responses. Default is false.
messagesRequiredarrayList of messages in the conversation. Must include at least one message with role 'user'.
temperaturenumberControls randomness of model output: lower values make responses more deterministic, higher values increase creativity. Default is 0.0.
json_responsebooleanIf true, the assistant will be instructed to return a JSON response. Cannot be used with streaming. Default is false.
assistant_hostRequiredstringThe host URL for the assistant endpoint (e.g., 'prod-1-data.ke.pinecone.io'). This is the data plane host for your assistant.
assistant_nameRequiredstringThe name of the assistant to chat with.
context_optionsobjectControls the context snippets sent to the LLM.
include_highlightsbooleanIf true, the assistant will be instructed to return highlights from the referenced documents that support its response. Default is false.
dataRequiredData from the action execution
errorstringError if any occurred during the execution of the action
successfulRequiredbooleanWhether or not the action execution was successful or not
API key connection. Risk level 2 of 5.
Free Action
No published Skills explicitly reference this Action yet.