Following the tutorial (PART 1-4), I noticed that the model answered with "not enough information to answer". Looking at "docs" I get this output:
[Document(page_content='Conversatin samples:\n[\n {\n "role": "system",', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'})]
Seems like docs = retriever.get_relevant_documents("What is Task Decomposition?") is not generating a correct page_content.
If I invoke the chain for the whole context, aka splits, not docs I do get a meaningful answer.
chain.invoke({"context":splits,"question":"What is Task Decomposition?"})
Note: I'm using using googles API, but I would expect that to be irrelevant.
Following the tutorial (PART 1-4), I noticed that the model answered with "not enough information to answer". Looking at "docs" I get this output:
[Document(page_content='Conversatin samples:\n[\n {\n "role": "system",', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'})]Seems likedocs = retriever.get_relevant_documents("What is Task Decomposition?")is not generating a correct page_content. If I invoke the chain for the whole context, aka splits, not docs I do get a meaningful answer.chain.invoke({"context":splits,"question":"What is Task Decomposition?"})Note: I'm using using googles API, but I would expect that to be irrelevant.