LangChain / LlamaIndex

Use 221 models in LangChain and LlamaIndex by pointing the OpenAI-compatible API endpoint to Chuizi.AI.

Prerequisites

Python 3.9+
A Chuizi.AI account with an API key (starts with ck-)

LangChain Configuration

Installation

terminal

bash

pip install langchain-openai

Basic Usage

example.py

python

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    openai_api_base="https://api.chuizi.ai/v1",
    openai_api_key="ck-your-key-here",
    model="anthropic/claude-sonnet-4-6",
)

response = llm.invoke("What is RAG?")
print(response.content)

Using in a Chain

example.py

python

from langchain_core.prompts import ChatPromptTemplate

prompt = ChatPromptTemplate.from_messages([
    ("system", "You are a helpful AI assistant."),
    ("user", "{input}"),
])

chain = prompt | llm
response = chain.invoke({"input": "Explain LangChain"})
print(response.content)

Embeddings

example.py

python

from langchain_openai import OpenAIEmbeddings

embeddings = OpenAIEmbeddings(
    openai_api_base="https://api.chuizi.ai/v1",
    openai_api_key="ck-your-key-here",
    model="openai/text-embedding-3-small",
)

result = embeddings.embed_query("Hello world")

LlamaIndex Configuration

Installation

terminal

bash

pip install llama-index-llms-openai llama-index-embeddings-openai

Basic Usage

example.py

python

from llama_index.llms.openai import OpenAI

llm = OpenAI(
    api_base="https://api.chuizi.ai/v1",
    api_key="ck-your-key-here",
    model="anthropic/claude-sonnet-4-6",
)

response = llm.complete("What is a vector database?")
print(response)

Set as Global Default

example.py

python

from llama_index.core import Settings

Settings.llm = OpenAI(
    api_base="https://api.chuizi.ai/v1",
    api_key="ck-your-key-here",
    model="anthropic/claude-sonnet-4-6",
)

Verify the Configuration

Run any of the code examples above. If you receive a successful response, the configuration is correct.

Common Issues

Model Name Format

In both LangChain and LlamaIndex, use the provider/model format, such as anthropic/claude-sonnet-4-6.

Parameter Name Differences

LangChain uses openai_api_base, while LlamaIndex uses api_base. Be careful not to mix them up.

Framework Version Compatibility

Use LangChain 0.2+ and LlamaIndex 0.10+ for best results. Older versions may have slightly different parameter names.

Next Steps

Embeddings API — vector embedding reference for RAG pipelines
Choose a Model — compare models for RAG and agent tasks
Structured Output — get JSON responses for data extraction