Integrate with LangChain

This integration enables developers to seamlessly incorporate LangChain workflows, to build AI applications on your own infrastructure using DeepFellow. By leveraging LangChain's modular architecture, developers can chain together complex operations, implement retrieval-augmented generation (RAG) patterns, and create multi-step reasoning workflows.

When using LangChain, pass your DeepFellow API key and DeepFellow Server URL to appropriate fields of ChatOpenAI() constructor:

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    api_key="DEEPFELLOW-PROJECT-API-KEY",
    base_url="https://deepfellow-server-host/v1",
    model="llama3-70b",
)

import { ChatOpenAI } from '@langchain/openai';

const llm = new ChatOpenAI({
    configuration: {
        baseURL: 'https://deepfellow-server-host/v1',
        defaultHeaders: {
            Authorization: `Bearer DEEPFELLOW-PROJECT-API-KEY`
        }
    },
    model: 'llama3-70b'
});