A bit more insight on the thought process of the prompt chain

[maruthiprithivi]

Hi @hwchase17,

I'm trying to build a ChatBot and was trying to understand this part of the code. If you can add more color to why this flow, it would be helpful.

def get_new_chain1(vectorstore) -> Chain:
    WEAVIATE_URL = os.environ["WEAVIATE_URL"]
    client = weaviate.Client(
        url=WEAVIATE_URL,
        additional_headers={"X-OpenAI-Api-Key": os.environ["OPENAI_API_KEY"]},
    )

    _eg_template = """## Example:

    Chat History:
    {chat_history}
    Follow Up Input: {question}
    Standalone question: {answer}"""
    _eg_prompt = PromptTemplate(
        template=_eg_template,
        input_variables=["chat_history", "question", "answer"],
    )

    _prefix = """Given the following conversation and a follow up question, rephrase the follow up question to be a standalone question. You should assume that the question is related to LangChain."""
    _suffix = """## Example:

    Chat History:
    {chat_history}
    Follow Up Input: {question}
    Standalone question:"""
    eg_store = Weaviate(
        client,
        "Rephrase",
        "content",
        attributes=["question", "answer", "chat_history"],
    )
    example_selector = SemanticSimilarityExampleSelector(vectorstore=eg_store, k=4)
    prompt = FewShotPromptTemplate(
        prefix=_prefix,
        suffix=_suffix,
        example_selector=example_selector,
        example_prompt=_eg_prompt,
        input_variables=["question", "chat_history"],
    )
    llm = OpenAI(temperature=0, model_name="text-davinci-003")
    key_word_extractor = LLMChain(llm=llm, prompt=prompt)

    EXAMPLE_PROMPT = PromptTemplate(
        template=">Example:\nContent:\n---------\n{page_content}\n----------\nSource: {source}",
        input_variables=["page_content", "source"],
    )
    template = """You are an AI assistant for the open source library LangChain. The documentation is located at https://langchain.readthedocs.io.
You are given the following extracted parts of a long document and a question. Provide a conversational answer with a hyperlink to the documentation.
You should only use hyperlinks that are explicitly listed as a source in the context. Do NOT make up a hyperlink that is not listed.
If the question includes a request for code, provide a code block directly from the documentation.
If you don't know the answer, just say "Hmm, I'm not sure." Don't try to make up an answer.
If the question is not about LangChain, politely inform them that you are tuned to only answer questions about LangChain.
Question: {question}
=========
{context}
=========
Answer in Markdown:"""
    PROMPT = PromptTemplate(template=template, input_variables=["question", "context"])
    doc_chain = load_qa_chain(
        OpenAI(temperature=0, model_name="text-davinci-003", max_tokens=-1),
        chain_type="stuff",
        prompt=PROMPT,
        document_prompt=EXAMPLE_PROMPT,
    )
    return CustomChain(
        chain=doc_chain, vstore=vectorstore, key_word_extractor=key_word_extractor
    )

And I couldn't find much information on document_prompt in the LangChain documentation.

Thank you!

[dahifi]

document_prompt is a parameter in the load_qa_chain function. Those get injected into the template that is passed on to the model for a response.

You might want to join the Langchain Discord: https://discord.gg/YGRXSt4M