Cohere

本文介绍了如何开始使用Cohere 聊天模型。

请前往API 参考查看所有属性和方法的详细文档。

设置

集成位于 langchain-cohere 包中。我们可以使用以下命令安装：

pip install -U langchain-cohere

我们还需要获取Cohere API 密钥并设置 COHERE_API_KEY 环境变量：

import getpass
import os
os.environ["COHERE_API_KEY"] = getpass.getpass()

此外，设置LangSmith也很有帮助（但不是必需的），以获得最佳的可观察性。

# os.environ["LANGCHAIN_TRACING_V2"] = "true"
# os.environ["LANGCHAIN_API_KEY"] = getpass.getpass()

用法

ChatCohere 支持所有ChatModel功能：

from langchain_cohere import ChatCohere
from langchain_core.messages import HumanMessage

chat = ChatCohere(model="command")

messages = [HumanMessage(content="1"), HumanMessage(content="2 3")]
chat.invoke(messages)

AIMessage(content='4 && 5 \n6 || 7 \n\nWould you like to play a game of odds and evens?', additional_kwargs={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '2076b614-52b3-4082-a259-cc92cd3d9fea', 'token_count': {'prompt_tokens': 68, 'response_tokens': 23, 'total_tokens': 91, 'billed_tokens': 77}}, response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '2076b614-52b3-4082-a259-cc92cd3d9fea', 'token_count': {'prompt_tokens': 68, 'response_tokens': 23, 'total_tokens': 91, 'billed_tokens': 77}}, id='run-3475e0c8-c89b-4937-9300-e07d652455e1-0')

await chat.ainvoke(messages)

AIMessage(content='4 && 5', additional_kwargs={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': 'f0708a92-f874-46ee-9b93-334d616ad92e', 'token_count': {'prompt_tokens': 68, 'response_tokens': 3, 'total_tokens': 71, 'billed_tokens': 57}}, response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': 'f0708a92-f874-46ee-9b93-334d616ad92e', 'token_count': {'prompt_tokens': 68, 'response_tokens': 3, 'total_tokens': 71, 'billed_tokens': 57}}, id='run-1635e63e-2994-4e7f-986e-152ddfc95777-0')

for chunk in chat.stream(messages):
    print(chunk.content, end="", flush=True)

4 && 5

chat.batch([messages])

[AIMessage(content='4 && 5', additional_kwargs={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '6770ca86-f6c3-4ba3-a285-c4772160612f', 'token_count': {'prompt_tokens': 68, 'response_tokens': 3, 'total_tokens': 71, 'billed_tokens': 57}}, response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '6770ca86-f6c3-4ba3-a285-c4772160612f', 'token_count': {'prompt_tokens': 68, 'response_tokens': 3, 'total_tokens': 71, 'billed_tokens': 57}}, id='run-8d6fade2-1b39-4e31-ab23-4be622dd0027-0')]

链接

您还可以轻松地与提示模板结合，以便轻松构建用户输入。我们可以使用LCEL来实现这一点。

from langchain_core.prompts import ChatPromptTemplate
prompt = ChatPromptTemplate.from_template("Tell me a joke about {topic}")
chain = prompt | chat

chain.invoke({"topic": "bears"})

AIMessage(content='What color socks do bears wear?\n\nThey don’t wear socks, they have bear feet. \n\nHope you laughed! If not, maybe this will help: laughter is the best medicine, and a good sense of humor is infectious!', additional_kwargs={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '6edccf44-9bc8-4139-b30e-13b368f3563c', 'token_count': {'prompt_tokens': 68, 'response_tokens': 51, 'total_tokens': 119, 'billed_tokens': 108}}, response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '6edccf44-9bc8-4139-b30e-13b368f3563c', 'token_count': {'prompt_tokens': 68, 'response_tokens': 51, 'total_tokens': 119, 'billed_tokens': 108}}, id='run-ef7f9789-0d4d-43bf-a4f7-f2a0e27a5320-0')