Cohere 集成

Cohere 是一家加拿大初创公司，提供自然语言处理模型 帮助企业提升人机交互体验。

Cohere 是一家加拿大初创公司，提供自然语言处理模型 帮助企业提升人机交互体验。

安装与配置

• 安装 Python SDK :

pip

pip install langchain-cohere

获取 Cohere api key 并将其设置为环境变量（COHERE_API_KEY）

Cohere LangChain 集成

API	描述	端点文档	导入	示例用法
Chat	构建聊天机器人	chat	from langchain_cohere import ChatCohere	cohere.ipynb
LLM	生成文本	generate	from langchain_cohere.llms import Cohere	cohere.ipynb
RAG Retriever	连接外部数据源	chat + rag	from langchain_classic.retrievers import CohereRagRetriever	cohere.ipynb
Text Embedding	将字符串转换为向量	embed	from langchain_cohere import CohereEmbeddings	cohere.ipynb
Rerank Retriever	基于相关性排序字符串	rerank	from langchain_classic.retrievers.document_compressors import CohereRerank	cohere.ipynb

快速示例

聊天

from langchain_cohere import ChatCohere
from langchain.messages import HumanMessage
chat = ChatCohere()
messages = [HumanMessage(content="knock knock")]
print(chat.invoke(messages))

使用 Cohere chat model

LLM

from langchain_cohere.llms import Cohere

llm = Cohere()
print(llm.invoke("Come up with a pet name"))

使用 Cohere (遗留) LLM model

工具调用

from langchain_cohere import ChatCohere
from langchain.messages import (
    HumanMessage,
    ToolMessage,
)
from langchain.tools import tool

@tool
def magic_function(number: int) -> int:
    """Applies a magic operation to an integer

    Args:
        number: Number to have magic operation performed on
    """
    return number + 10

def invoke_tools(tool_calls, messages):
    for tool_call in tool_calls:
        selected_tool = {"magic_function":magic_function}[
            tool_call["name"].lower()
        ]
        tool_output = selected_tool.invoke(tool_call["args"])
        messages.append(ToolMessage(tool_output, tool_call_id=tool_call["id"]))
    return messages

tools = [magic_function]

llm = ChatCohere()
llm_with_tools = llm.bind_tools(tools=tools)
messages = [
    HumanMessage(
        content="What is the value of magic_function(2)?"
    )
]

res = llm_with_tools.invoke(messages)
while res.tool_calls:
    messages.append(res)
    messages = invoke_tools(res.tool_calls, messages)
    res = llm_with_tools.invoke(messages)

print(res.content)

Cohere LLM 的工具调用可通过绑定必要工具实现（如上所示）。另一种方式是通过 ReAct 智能体支持多步工具调用（如下所示）。

ReAct 智能体

该智能体基于论文 ReAct: Synergizing Reasoning and Acting in Language Models。

langchain-community包已不再维护。从langchain_community导入的示例可能过时或无法使用。请谨慎使用。

from langchain_community.tools.tavily_search import TavilySearchResults
from langchain_cohere import ChatCohere, create_cohere_react_agent
from langchain_core.prompts import ChatPromptTemplate
from langchain_classic.agents import AgentExecutor

llm = ChatCohere()

internet_search = TavilySearchResults(max_results=4)
internet_search.name = "internet_search"
internet_search.description = "Route a user query to the internet"

prompt = ChatPromptTemplate.from_template("{input}")

agent = create_cohere_react_agent(
    llm,
    [internet_search],
    prompt
)

agent_executor = AgentExecutor(agent=agent, tools=[internet_search], verbose=True)

agent_executor.invoke({
    "input": "In what year was the company that was founded as Sound of Music added to the S&P 500?",
})

ReAct 智能体可用于按顺序调用多个工具。

RAG 检索器

from langchain_cohere import ChatCohere
from langchain_classic.retrievers import CohereRagRetriever
from langchain_core.documents import Document

rag = CohereRagRetriever(llm=ChatCohere())
print(rag.invoke("What is cohere ai?"))

使用 Cohere RAG Retriever

文本嵌入

from langchain_cohere import CohereEmbeddings

embeddings = CohereEmbeddings(model="embed-english-light-v3.0")
print(embeddings.embed_documents(["This is a test document."]))

使用 Cohere Text Embeddings model

重排序器

使用 Cohere Reranker

---

官方原文：src/oss/python/integrations/providers/cohere.mdx · 非官方翻译，译文由 AI 生成，以英文原文为准。