Fast-API Documentation

Theme

LangChain ​ ​

Python LLM application development framework, supports chain calling, Agents, RAG and other advanced features, compatible with OpenAI APIs.

Installation ​ ​

Mac / Linux ​ ​

bash

pip install langchain langchain-openai

Windows ​ ​

cmd

pip install langchain langchain-openai

Requires Python 3.9+

Configuration ​ ​

Directly specify api_key and base_url in your code:

python

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="gpt-4o-mini",
    api_key="sk-xxx",
    base_url="https://www.fast-api.org/v1"
)

Replace sk-xxx with the API Key you obtained from Fast-API.

Usage Example ​ ​

Basic Chat ​ ​

python

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="gpt-4o-mini",
    api_key="sk-yourAPIKey",
    base_url="https://www.fast-api.org/v1"
)

response = llm.invoke("Hello!")
print(response.content)

Multi-turn Conversation ​ ​

python

from langchain_openai import ChatOpenAI
from langchain_core.messages import HumanMessage, SystemMessage

llm = ChatOpenAI(
    model="gpt-4o-mini",
    api_key="sk-yourAPIKey",
    base_url="https://www.fast-api.org/v1"
)

messages = [
    SystemMessage(content="You are a helpful assistant"),
    HumanMessage(content="What is the GIL in Python?")
]

response = llm.invoke(messages)
print(response.content)

FAQ ​ ​

AuthenticationError Prompt ​ ​

Make sure the api_key parameter is filled in correctly, the key starts with sk-.

Connection Timeout ​ ​

Check if base_url is https://www.fast-api.org/v1, and verify network accessibility.

Model Not Found ​ ​

Check if the model parameter is set to a model name supported by Fast-API.

Notes ​ ​

  • base_url must end with /v1: https://www.fast-api.org/v1
  • You can also configure via environment variables OPENAI_API_KEY and OPENAI_API_BASE to avoid hardcoding
  • Supports models such as gpt-4o, gpt-4o-mini, claude-sonnet-4-20250514, etc.