Ask a question to get started
Enter to send•Shift+Enter new line
VectorDBQA()
BaseRetrievalQA
Chain to use to combine documents.
The key from the model Run's inputs to use as the eval input.
Return the source documents.
The keys to use for the output.
Initialize from llm using default template.
Load chain from chain type.
Optional memory object.
[DEPRECATED] Use callbacks instead.
callbacks
Raise deprecation warning if callback_manager is used.
Vector Database to connect to.
Number of documents to query for.
Search type to use over vectorstore. similarity or mmr.
similarity
mmr
Extra search args.
Validate search type.
Chain for question-answering against a vector database.
Set the chain verbosity.
Asynchronously execute the chain.
Validate and prepare chain outputs, and save info about this run to memory.
Prepare chain inputs, including adding inputs from memory.
Convenience method for executing chain.
Return dictionary representation of agent.
Save the agent.
Utilize the LLM generate method for speed gains.
