Together AI 提供 API 来查询 50+ 领先的开源模型 仅需几行代码。

本示例介绍如何使用 LangChain 与 Together AI 模型进行交互。

安装

pip install -U langchain-together

环境

要使用 Together AI，您需要一个 API 密钥，您可以在此处找到： api.together.ai/settings/api-keys。这可以作为初始化参数传入 together_api_key 或设置为环境变量 TOGETHER_API_KEY.

示例

# Querying chat models with Together AI

from langchain_together import ChatTogether

# choose from our 50+ models here: https://docs.together.ai/docs/inference-models
chat = ChatTogether(
    # together_api_key="YOUR_API_KEY",
    model="meta-llama/Llama-3-70b-chat-hf",
)

# stream the response back from the model
stream = chat.stream_events("Tell me fun things to do in NYC", version="v3")
for token in stream.text:
    print(token, end="", flush=True)

# if you don't want to do streaming, you can use the invoke method
# chat.invoke("Tell me fun things to do in NYC")

# Querying code and language models with Together AI

from langchain_together import Together

llm = Together(
    model="codellama/CodeLlama-70b-Python-hf",
    # together_api_key="..."
)

print(llm.invoke("def bubble_sort(): "))