How can use this function: "4/13/2023 - Added new functionality to support questioning multiple documents using the Vector QA agent" ?
Closed this issue · 2 comments
ShadowDawnme commented
How can use this function: "4/13/2023 - Added new functionality to support questioning multiple documents using the Vector QA agent" ?
akshata29 commented
Following are the steps :
- Go to the deployed (or locally running) webapp
- Select SQL NLP
- Select Agent QA
- Assuming the documents are uploaded, select the index (pinecone or redis). That should filter all the documents you have uploaded in that specific vectorstore.
- Select one or multiple documents from the list of all documents
- Start asking question from those multiple documents. It will interact with your data in the vectorstore in agentic manner. Details about that is further available at https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/agent_vectorstore.html
akshata29 commented
Closing - Assuming the instructions/steps are helpful