LangGraphとElasticsearchを使用したRAGワークフローの構築

pip install --upgrade "langgraph-cli[inmem]"

mkdir lg-agent-demo
cd lg-agent-demo
langgraph new lg-agent-demo

#For Mac
python3 -m venv lg-demo
source lg-demo/bin/activate 
pip install -e .

#For Windows
python3 -m venv lg-demo
lg-demo\Scripts\activate 
pip install -e .

cp .env.example .env

# To separate your traces from other applications
LANGSMITH_PROJECT=retrieval-agent

# LLM choice (set the API key for your selected provider):
ANTHROPIC_API_KEY=your_anthropic_api_key
FIREWORKS_API_KEY=your_fireworks_api_key
OPENAI_API_KEY=your_openai_api_key

# Retrieval provider (configure based on your chosen service):

## Elastic Cloud:
ELASTICSEARCH_URL=https://your_elastic_cloud_url
ELASTICSEARCH_API_KEY=your_elastic_api_key

## Elastic Local:
ELASTICSEARCH_URL=http://host.docker.internal:9200
ELASTICSEARCH_USER=elastic
ELASTICSEARCH_PASSWORD=changeme

## Pinecone:
PINECONE_API_KEY=your_pinecone_api_key
PINECONE_INDEX_NAME=your_pinecone_index_name

## MongoDB Atlas:
MONGODB_URI=your_mongodb_connection_string

# Cohere API key:
COHERE_API_KEY=your_cohere_api_key

# To separate your traces from other applications
LANGSMITH_PROJECT=retrieval-agent
#Retrieval Provider
# Elasticsearch configuration
ELASTICSEARCH_URL=elastic-url:443
ELASTICSEARCH_API_KEY=elastic_api_key
# Cohere API key
COHERE_API_KEY=cohere_api_key

 cd src/retrieval_graph

…
 embedding_model: Annotated[
       str,
       {"__template_metadata__": {"kind": "embeddings"}},
   ] = field(
       default="cohere/embed-english-v3.0",
…
response_model: Annotated[str, {"__template_metadata__": {"kind": "llm"}}] = field(
       default="cohere/command-r-08-2024",
…
query_model: Annotated[str, {"__template_metadata__": {"kind": "llm"}}] = field(
       default="cohere/command-r-08-2024",
       metadata={

cd lg-agent-demo
langgraph dev

{"user_id": "101"}

[
  {    "page_content": "NoveTech Solutions Q1 2025 Report - Revenue: $120.5M, Net Profit: $18.2M, EPS: $2.15. Strong AI software launch and $50M government contract secured."
  },
  {
    "page_content": "NoveTech Solutions Business Highlights - AI-driven analytics software gained 15% market share. Expansion into Southeast Asia with two new offices. Cloud security contract secured."
  },
  {
    "page_content": "NoveTech Solutions Financial Overview - Operating expenses at $85.3M, Gross Margin 29.3%. Stock price rose from $72.5 to $78.3. Market Cap reached $5.2B."
  },
  {
    "page_content": "NoveTech Solutions Challenges - Rising supply chain costs impacting hardware production. Regulatory delays slowing European expansion. Competitive pressure in cybersecurity sector."
  },
  {
    "page_content": "NoveTech Solutions Future Outlook - Expected revenue for Q2 2025: $135M. New AI chatbot and blockchain security platform launch planned. Expansion into Latin America."
  },
  {
    "page_content": "NoveTech Solutions Market Performance - Year-over-Year growth at 12.7%. Stock price increase reflects investor confidence. Cybersecurity and AI sectors remain competitive."
  },
  {
    "page_content": "NoveTech Solutions Strategic Moves - Investing in R&D to enhance AI-driven automation. Strengthening partnerships with enterprise cloud providers. Focusing on data privacy solutions."
  },
  {
    "page_content": "NoveTech Solutions CEO Statement - 'NoveTech Solutions continues to innovate in AI and cybersecurity. Our growth strategy remains strong, and we foresee steady expansion in the coming quarters.'"
  }
]

What was NovaTech Solutions total revenue in Q1 2025?

async def predict_query(
   state: State, *, config: RunnableConfig
) -> dict[str, list[BaseMessage]]:
   logger.info(f"predict_query predict_querypredict_query predict_query predict_query predict_query")  # Log the query

   configuration = Configuration.from_runnable_config(config)
   prompt = ChatPromptTemplate.from_messages(
       [
           ("system", configuration.predict_next_question_prompt),
           ("placeholder", "{messages}"),
       ]
   )
   model = load_chat_model(configuration.response_model)
   user_query = state.queries[-1] if state.queries else "No prior query available"
   logger.info(f"user_query: {user_query}")
   logger.info(f"statemessage: {state.messages}")
   #human_messages = [msg for msg in state.message if isinstance(msg, HumanMessage)]

   message_value = await prompt.ainvoke(
       {
           "messages": state.messages,
           "user_query": user_query,  # Use the most recent query as primary input
           "system_time": datetime.now(tz=timezone.utc).isoformat(),
       },
       config,
   )

   next_question = await model.ainvoke(message_value, config)
   return {"next_question": [next_question]}

async def respond(
   state: State, *, config: RunnableConfig
) -> dict[str, list[BaseMessage]]:
   """Call the LLM powering our "agent"."""
   configuration = Configuration.from_runnable_config(config)
   # Feel free to customize the prompt, model, and other logic!
   prompt = ChatPromptTemplate.from_messages(
       [
           ("system", configuration.response_system_prompt),
           ("placeholder", "{messages}"),
       ]
   )
   model = load_chat_model(configuration.response_model)

   retrieved_docs = format_docs(state.retrieved_docs)
   message_value = await prompt.ainvoke(
       {
           "messages": state.messages,
           "retrieved_docs": retrieved_docs,
           "system_time": datetime.now(tz=timezone.utc).isoformat(),
       },
       config,
   )
   response = await model.ainvoke(message_value, config)
   # We return a list, because this will get added to the existing list
   return {"response": [response]}

builder.add_node(generate_query)
builder.add_node(retrieve)
builder.add_node(respond)
builder.add_node(predict_query)
builder.add_edge("__start__", "generate_query")
builder.add_edge("generate_query", "retrieve")
builder.add_edge("retrieve", "respond")
builder.add_edge("respond", "predict_query")

PREDICT_NEXT_QUESTION_PROMPT = """Given the user query and the retrieved documents, suggest the most likely next question the user might ask.

**Context:**
- Previous Queries:
{previous_queries}

- Latest User Query: {user_query}

- Retrieved Documents:
{retrieved_docs}

**Guidelines:**
1. Do not suggest a question that has already been asked in previous queries.
2. Consider the retrieved documents when predicting the next logical question.
3. If the user's query is already fully answered, suggest a relevant follow-up question.
4. Keep the suggested question natural and conversational.
5. Suggest at least 3 question

System time: {system_time}"""

predict_next_question_prompt: str = field(
       default=prompts.PREDICT_NEXT_QUESTION_PROMPT,
       metadata={"description": "The system prompt used for generating responses."},
   )

response: Annotated[Sequence[AnyMessage], add_messages]
next_question : Annotated[Sequence[AnyMessage], add_messages]

What was NovaTech Solutions total revenue in Q1 2025?