LangGraph

1.1 API Configuration

LangGraph extends LangChain and connects to LLMs via ChatOpenAI. Set openai_api_base to point to any OpenAI-compatible endpoint:

Basic Configuration

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    openai_api_base="https://api.hpc-ai.com/inference/v1",
    api_key="sk-your-hpc-ai-api-key",
    model="minimax/minimax-m2.5"
)

Environment Variables

import os
from langchain_openai import ChatOpenAI

os.environ["OPENAI_API_BASE"] = "https://api.hpc-ai.com/inference/v1"
os.environ["OPENAI_API_KEY"] = "sk-your-hpc-ai-api-key"

llm = ChatOpenAI(model="minimax/minimax-m2.5")

1.2 Using in LangGraph

from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

# Configure custom LLM
llm = ChatOpenAI(
    openai_api_base="https://api.hpc-ai.com/inference/v1",
    api_key="sk-your-hpc-ai-api-key",
    model="minimax/minimax-m2.5",
    temperature=0.7
)

# Create agent
agent = create_react_agent(llm, tools=[])

# Invoke agent
result = agent.invoke({"messages": [("user", "Hello")]})
print(result)

1.3 References

• LangChain Integration: https://python.langchain.com/docs/integrations/llms/openai/