Friendli 通过可扩展、高效的部署选项，专为高需求 AI 工作负载量身定制，提升 AI 应用程序性能并优化成本节省。本教程将指导您如何使用 LangChain 集成
ChatFriendli 进行聊天应用程序开发。ChatFriendli 提供了一种灵活的方法来生成对话式 AI 响应，支持同步和异步调用。
设置
请确保已安装langchain_community 和 friendli-client。
复制
向 AI 提问
pip install -U langchain-community friendli-client.
FRIENDLI_TOKEN 环境变量。
复制
向 AI 提问
import getpass
import os
if "FRIENDLI_TOKEN" not in os.environ:
os.environ["FRIENDLI_TOKEN"] = getpass.getpass("Friendi Personal Access Token: ")
mixtral-8x7b-instruct-v0-1。您可以在 docs.friendli.ai 查阅可用模型。
复制
向 AI 提问
from langchain_community.chat_models.friendli import ChatFriendli
chat = ChatFriendli(model="meta-llama-3.1-8b-instruct", max_tokens=100, temperature=0)
用法
FrienliChat 支持 ChatModel 的所有方法，包括异步 API。 您还可以使用 invoke、batch、generate 和 stream 功能。复制
向 AI 提问
from langchain.messages import HumanMessage, SystemMessage
system_message = SystemMessage(content="Answer questions as short as you can.")
human_message = HumanMessage(content="Tell me a joke.")
messages = [system_message, human_message]
chat.invoke(messages)
复制
向 AI 提问
AIMessage(content="Why don't eggs tell jokes? They'd crack each other up.", additional_kwargs={}, response_metadata={}, id='run-d47c1056-54e8-4ea9-ad63-07cf74b834b7-0')
复制
向 AI 提问
chat.batch([messages, messages])
复制
向 AI 提问
[AIMessage(content="Why don't eggs tell jokes? They'd crack each other up.", additional_kwargs={}, response_metadata={}, id='run-36775b84-2a7a-48f0-8c68-df23ffffe4b2-0'),
AIMessage(content="Why don't eggs tell jokes? They'd crack each other up.", additional_kwargs={}, response_metadata={}, id='run-b204be41-bc06-4d3a-9f74-e66ab1e60e4f-0')]
复制
向 AI 提问
chat.generate([messages, messages])
复制
向 AI 提问
LLMResult(generations=[[ChatGeneration(text="Why don't eggs tell jokes? They'd crack each other up.", message=AIMessage(content="Why don't eggs tell jokes? They'd crack each other up.", additional_kwargs={}, response_metadata={}, id='run-2e4cb949-8c51-40d5-92a0-cd0ac577db83-0'))], [ChatGeneration(text="Why don't eggs tell jokes? They'd crack each other up.", message=AIMessage(content="Why don't eggs tell jokes? They'd crack each other up.", additional_kwargs={}, response_metadata={}, id='run-afcdd1be-463c-4e50-9731-7a9f5958e396-0'))]], llm_output={}, run=[RunInfo(run_id=UUID('2e4cb949-8c51-40d5-92a0-cd0ac577db83')), RunInfo(run_id=UUID('afcdd1be-463c-4e50-9731-7a9f5958e396'))], type='LLMResult')
复制
向 AI 提问
for chunk in chat.stream(messages):
print(chunk.content, end="", flush=True)
复制
向 AI 提问
Why don't eggs tell jokes? They'd crack each other up.
ainvoke、abatch、agenerate 和 astream。
复制
向 AI 提问
await chat.ainvoke(messages)
复制
向 AI 提问
AIMessage(content="Why don't eggs tell jokes? They'd crack each other up.", additional_kwargs={}, response_metadata={}, id='run-ba8062fb-68af-47b8-bd7b-d1e01b914744-0')
复制
向 AI 提问
await chat.abatch([messages, messages])
复制
向 AI 提问
[AIMessage(content="Why don't eggs tell jokes? They'd crack each other up.", additional_kwargs={}, response_metadata={}, id='run-5d2c77ab-2637-45da-8bbe-1b1f18a22369-0'),
AIMessage(content="Why don't eggs tell jokes? They'd crack each other up.", additional_kwargs={}, response_metadata={}, id='run-f1338470-8b52-4d6e-9428-a694a08ae484-0')]
复制
向 AI 提问
await chat.agenerate([messages, messages])
复制
向 AI 提问
LLMResult(generations=[[ChatGeneration(text="Why don't eggs tell jokes? They'd crack each other up.", message=AIMessage(content="Why don't eggs tell jokes? They'd crack each other up.", additional_kwargs={}, response_metadata={}, id='run-d4e44569-39cc-40cc-93fc-de53e599fd51-0'))], [ChatGeneration(text="Why don't eggs tell jokes? They'd crack each other up.", message=AIMessage(content="Why don't eggs tell jokes? They'd crack each other up.", additional_kwargs={}, response_metadata={}, id='run-54647cc2-bee3-4154-ad00-2e547993e6d7-0'))]], llm_output={}, run=[RunInfo(run_id=UUID('d4e44569-39cc-40cc-93fc-de53e599fd51')), RunInfo(run_id=UUID('54647cc2-bee3-4154-ad00-2e547993e6d7'))], type='LLMResult')
复制
向 AI 提问
async for chunk in chat.astream(messages):
print(chunk.content, end="", flush=True)
复制
向 AI 提问
Why don't eggs tell jokes? They'd crack each other up.
以编程方式连接这些文档到 Claude、VSCode 等，通过 MCP 获取实时答案。