Trying to modify the PDF reader with "Sources" information about genai-stack HOT 4 OPEN

There's a RetrievalQAWithSourcesChain mentioned here https://python.langchain.com/docs/integrations/vectorstores/neo4jvector

I've tried swapping that for from RetrievalQA in pdf_bot.py but not managed to get it to work yet.

from genai-stack.

@tomasonjo correct me if I'm wrong but the main thing is to provide a {metadata: {source: source-link}} to the qa_chain_with_sources ?

from langchain.chains.qa_with_sources import load_qa_with_sources_chain

https://python.langchain.com/docs/use_cases/question_answering/sources

from genai-stack.

Feel free to send a PR

from genai-stack.

To store source information to Neo4j, you would need to use from_documents instead of from_texts method to populate the vector index. You could do this with something like:

from langchain.schema import Document
documents = [Document(content=text, metadata={source:'PDF file name'}) for text in texts]

Any key-value pair in metadata is stored as additional node properties.

from genai-stack.