Find answers from the community

Updated 9 months ago

Hey all, is there an example anywhere

Hey all, is there an example anywhere within the documentation of a pipeline that first extracts metadata from a user input (probably using pydantic) and then queries a vector database using that user input and the extracted metadata as the metadata filter within the vector database?

2 comments

LLogan M

I think this process is fully automated by the auto retriever
https://docs.llamaindex.ai/en/stable/examples/agent/openai_agent_query_cookbook.html#autoretrieval-from-a-vector-database

But you could also create your own custom query pipeline (more low-level, customizable)
https://docs.llamaindex.ai/en/stable/module_guides/querying/pipeline/root.html

DDS

🙏

Add a reply