LangChain Integration

LangChain Integration

Forge integrates seamlessly with LangChain as an OpenAI-compatible LLM provider. Use Forge as your LLM backend to get intelligent routing, memory, and security while building chains and agents with LangChain's orchestration tools.

Setup

pip install langchain langchain-openai

Basic Usage

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="auto",
    api_key="forge_sk_your_key",
    base_url="https://api.optima-forge.com/v1",
)

response = llm.invoke("Explain machine learning in simple terms.")
print(response.content)

With LangChain Chains

from langchain_core.prompts import ChatPromptTemplate
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="auto",
    api_key="forge_sk_your_key",
    base_url="https://api.optima-forge.com/v1",
)

prompt = ChatPromptTemplate.from_messages([
    ("system", "You are a helpful technical writer."),
    ("user", "Write documentation for: {topic}"),
])

chain = prompt | llm
result = chain.invoke({"topic": "REST API authentication"})
print(result.content)

With LangGraph Agents

Use Forge as the LLM backend for LangGraph agent workflows. Forge handles provider routing and failover while LangGraph manages the agent execution graph.

from langgraph.graph import StateGraph, MessagesState
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="auto",
    api_key="forge_sk_your_key",
    base_url="https://api.optima-forge.com/v1",
)

# Define your LangGraph workflow using Forge as the LLM provider
# All LLM calls get Forge routing, caching, and security automatically

Forge Memory with LangChain

You can use Forge's built-in memory alongside or instead of LangChain's memory classes by passing forge extensions in the model kwargs.