本指南提供了快速入门概述，帮助您开始使用 ChatBaseten 聊天模型.

Baseten provides inference designed for production applications. Built on the Baseten Inference Stack, these APIs deliver enterprise-grade performance and reliability for leading open-source or custom models: https://www.baseten.co/library/.

概述

详情

功能特性

Model APIs only support text input, while some dedicated deployments support image and audio input depending on model. Check the Baseten model library for details: https://www.baseten.co/library/

设置

要访问 Baseten 模型，您需要创建一个 Baseten 账户，获取 API 密钥，并安装 langchain-baseten 集成包。

前往 Baseten 网站 创建账户并生成 API 密钥。完成此操作后，设置 BASETEN_API_KEY 环境变量：

凭证

if "BASETEN_API_KEY" not in os.environ:
    os.environ["BASETEN_API_KEY"] = getpass.getpass("Enter your Baseten API key: ")

要启用自动化 追踪 您的模型调用，请设置您的 LangSmith API 密钥：

os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")
os.environ["LANGSMITH_TRACING"] = "true"

安装

LangChain Baseten 集成位于 langchain-baseten package:

    pip install -U langchain-baseten
    

    uv add langchain-baseten
    

实例化

Baseten 提供两种访问聊天模型的方式：

1. **模型 API**：用于访问最新、最流行的开源模型。
2. **专用 URL**：使用具有专用资源的特定模型部署。

两种方法都支持自动端点规范化。

from langchain_baseten import ChatBaseten

# Option 1: Use Model APIs with model slug
model = ChatBaseten(
    model="moonshotai/Kimi-K2-Instruct-0905",  # Choose from available model slugs: https://docs.baseten.co/development/model-apis/overview#supported-models
    api_key="your-api-key",  # Or set BASETEN_API_KEY env var
)

from langchain_baseten import ChatBaseten

# Option 2: Use dedicated deployments with model url
model = ChatBaseten(
    model_url="https://model-<id>.api.baseten.co/environments/production/predict",
    api_key="your-api-key",  # Or set BASETEN_API_KEY env var
)

调用

# Use the chat model
response = model.invoke("Hello, how are you?")
print(response.content)

Hello! I'm doing well, thank you for asking! How about you?

您还可以使用消息对象进行更复杂的对话：

    messages = [
        {"role": "system", "content": "You are a poetry expert"},
        {"role": "user", "content": "Write a haiku about spring"},
    ]
    response = model.invoke(messages)
    print(response)
    

content='Buds yawn open wide—\na robin stitches the hush\nwith threads of first light.' additional_kwargs={} response_metadata={'token_usage': {'completion_tokens': 26, 'prompt_tokens': 14, 'total_tokens': 40}, 'model_name': 'moonshotai/Kimi-K2-Instruct-0905', 'finish_reason': 'stop', 'model_provider': 'baseten'} id='run--6f7d1db7-daae-4628-a40a-2ab7323e8f15-0'