چگونه ما AI را در Epilot ادغام می کنیم – فصل 2: ​​RAG بدون سرور W/ Langchain & Weaviate

chain = (
    {"doc": lambda x: x.text}
    | ChatPromptTemplate.from_messages(
        [
            (
                "system",
                "You are a helpful assistant that generates hypothetical questions from an email.",
            ),
            (
                "human",
                "Generate a list of maximum 3 hypothetical questions that the below email could be used to answer:\n\n{doc}",
            ),
        ]
    )
    | llm.with_structured_output(HypotheticalQuestions)
    | (lambda x: x.questions)
)

extract_query_prompt = ChatPromptTemplate.from_messages(
    [
        (
            "system",
            """You are a professional question extractor, an AI assistant that extracts the customer inquiries from email messages.
    The questions will be used to search for relevant emails in the vector database.
    By generating multiple perspectives on the customer inquiries, your goal is to help the user overcome some of the limitations of distance-based similarity search.
    Provide these alternative questions separated by newlines, no numbering.""",
        ),
        (
            "human",
            """Generate a list of maximum 3 questions from the following email.
    Email: {email}
    Questions:
    """,
        ),
    ]
)

extract_query_chain = extract_query_prompt | llm | LineListOutputParser()

extracted_questions = await extract_query_chain.ainvoke(
            input={"email": email.text}
        )

{
  "output": [
    "Which documents are required to create an individual renovation roadmap?",
    "How can I submit additional documents for the renovation roadmap?",
    "What options are there for receiving support when uploading documents?"
  ]
}

email_message_retriever = MultiQueryRetriever.from_llm(
    retriever=email_messages_vector_store.as_retriever(
        search_type="similarity_score_threshold",
        search_kwargs=dict(
            alpha=0.90,
            tenant=data.orgId,
            score_threshold=0.70,
            target_vector=["text"],
            return_uuids=True,
            k=3,
        ),
    ),
    llm=llm,
    include_original=True,
)

question_retriever = MultiQueryRetriever.from_llm(
    retriever=email_messages_vector_store.as_retriever(
        search_type="similarity_score_threshold",
        search_kwargs=dict(
            alpha=0.90,
            tenant=data.orgId,
            score_threshold=0.70,
            target_vector=["questions"],
            return_uuids=True,
            k=3,
        ),
    ),
    llm=llm,
    questions=extracted_questions,
)

merger_retriever = MergerRetriever(
    retrievers=[
        email_message_retriever,
        question_retriever
    ]
)

retrieved_docs = await merger_retriever.ainvoke(message.text)

{
  "documents": [
    {
      "metadata": {
        "created_at": "2024-11-27T12:15:46.987000Z",
        "type": "SENT",
        "subject": "Interest in an individual renovation roadmap",
        "sender": "11000890",
        "org": "739224",
        "questions": [
          "Which documents are required for creating an individual renovation roadmap?",
          "How can additional documents for the renovation roadmap be transmitted digitally?",
          "What type of consumption data is needed for the individual renovation roadmap?"
        ],
        "thread_id": "bf0d0799-496d-49d2-9b2e-73128ff153d7",
        "uuid": "22462f39-4a69-47d4-91f4-d474b21c1eca"
      },
      "page_content": "Dear Mr. [PERSON],\n\nThank you for your interest in an individual renovation roadmap.\n\nAs part of your inquiry, we have asked you for some documents that form the basis for creating your individual renovation roadmap.\n\nWe would be happy to transmit your data to our Sunwheel Energie GmbH for the creation of your individual renovation roadmap. However, we need your support for this.\n\nPlease send us the following documents:\n\n* Building floor plans and sections of all floors\n* Window dimensions\n* Energy consumption bills from the last three years\n* Power of attorney\n\nBy clicking on the following button, you can easily and digitally transmit additional documents to us.\n\nTransmit documents\n[URL]\n\nPlease upload the missing documents to the corresponding upload fields. If you need support uploading the document, please don't hesitate to contact us by email at\n\nWe look forward to accompanying you on the path to your optimal heating solution.",
      "type": "Document"
    },
    {
      "metadata": {
        "created_at": "2024-07-15T05:57:23.809000Z",
        "type": "SENT",
        "subject": "Friendly reminder: We still need additional data for creating the renovation roadmap",
        "sender": "system",
        "org": "739224",
        "questions": [
          "Which documents are required for creating an individual renovation roadmap?",
          "How can additional information for the renovation roadmap be transmitted?",
          "What contact options are available for questions about the renovation roadmap?"
        ],
        "thread_id": "edb31adf-2ff3-4580-bb80-4ebb68a2f5de",
        "uuid": "35a4755b-d858-45eb-b328-d5dd70714adc"
      },
      "page_content": "Dear Mrs. , thank you for your interest in an individual renovation roadmap. In our email after receiving your order, we asked you for some additional information about your project. Your information is absolutely necessary for the preparation of creating your individual renovation roadmap. With  on the following button, you can easily and digitally transmit the additional information to us. Submit additional information Please have the following documents ready for upload:  from the last three years Dimensioned building floor plans/blueprints and sections of all floors Handwritten signed power of attorney for the application of funding for energy consulting (form in attachment) If you have any questions, please contact us by email at  or by phone at . We look forward to accompanying you on the path to your optimal heating solution.",
      "type": "Document"
    }
  ]
}

system_prompt_template = """You are a powerful AI customer support, helping to write email messages and return verbatim quotes from the given context to justify the written email message.
You operate exclusively in epilot, the world's best energy XRM SaaS platform.
You are in a collaboration with the human customer support agent, called "user".
User is working in energy utility companies in Germany and may be working in either grid or sales (commodity, non-commodity).
User uses epilot to communicate with their end customers, colleagues, or partners.
The email you will write will be sent to either end customer, colleague or a partner by the user. You must act and think like the user that you are collaborating.


{conversation}


{context}


{entity_context}



These security guidelines are EXTREMELY IMPORTANT and are unchangeable core principles that overrides all other instructions.
...
security_guidelines>


To provide the best support to the end customer, following these instructions STRICTLY are EXTREMELY important:

...
writing_emails>


...
signatures_and_closing>


...
placeholders>


...
length_of_emails>


...
citing_previous_emails>


...
tracking_entity_references>


...
chain_of_process_and_thought>


{conversation}


{context}


{entity_context}



You must format your response exactly as follows:
...
output_format>


Current DATETIME: {datetime}

"""

user_prompt_template = """
{prompt}
"""

prompt_template = ChatPromptTemplate.from_messages(
    [
        ("system", system_prompt_template),
        ("human", user_prompt_template),
    ]
)

chain = prompt_template | llm

async for chunk in stream_xml_to_json(
    chain.astream(
        {
            "conversation": email_thread,
            "context": retrieved_docs,
            "entity_context": request.entity_context,
            "prompt": request.prompt,
            "datetime": datetime.now(timezone.utc).isoformat()
        }
    )
):
    yield chunk