LangChain is an open-source framework that provides a ready-made agent architecture along with integrations for working with a wide range of models and external tools.
1.1 Usage
Method 1: Direct Parameter Configuration (Recommended)
from langchain_openai import ChatOpenAI
llm = ChatOpenAI(
openai_api_base="https://api.rygen.io/v1",
openai_api_key="your-rygen-api-key",
model="your-model-name"
)
response = llm.invoke("Hi! Can you greet me?")
print(response.content)Method 2: Environment Variables
import os
os.environ["OPENAI_API_BASE"] = "https://api.rygen.io/v1"
os.environ["OPENAI_API_KEY"] = "your-rygen-api-key"
from langchain_openai import ChatOpenAI
llm = ChatOpenAI(model="your-model-name")Method 3: JavaScript / TypeScript
import { ChatOpenAI } from "@langchain/openai";
const llm = new ChatOpenAI({
baseURL: "https://api.rygen.io/v1",
apiKey: "your-rygen-api-key",
model: "your-model-name"
});Method 4: Use in an Agent
from langchain_openai import ChatOpenAI
from langchain.agents import AgentExecutor, create_openai_functions_agent
from langchain import hub
llm = ChatOpenAI(
openai_api_base="https://api.rygen.io/v1",
openai_api_key="your-rygen-api-key",
model="your-model-name"
)
prompt = hub.pull("hwchase17/openai-functions-agent")
agent = create_openai_functions_agent(llm, tools, prompt)
agent_executor = AgentExecutor(agent=agent, tools=tools)
result = agent_executor.invoke({"input": "Ask your question here!"})