Building the Future with LLMs, LangChain, and Pinecone

Please add any questions you have relating to the March 16 workshop, Building the Future with LLMs, LangChain, and Pinecone.

Thank you for the event!
Question: Is there a way to use semantic search and a vector database so that an application figures out how to structure a API request? A use-case could be to build an application that can take a query from a user such as “Could you mark this task as complete in {{internal application}}”, the application would then search how to do that programmatically.

Is there a recorded session for us to review the video?

1 Like