Cohere
Cohere 是一家加拿大初创公司，提供自然语言处理模型，帮助公司改善人机交互。
安装与设置
- 安装Python SDK：
pip install langchain-cohere
获取一个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 |
|---|---|---|---|---|
| 聊天 | 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 | 连接到外部数据源 | chat + rag | from langchain.retrievers import CohereRagRetriever | cohere.ipynb |
| 文本嵌入 | 将字符串嵌入为向量 | embed | from langchain_cohere import CohereEmbeddings | cohere.ipynb |
| Rerank Retriever | 根据相关性对字符串进行排序 | rerank | from langchain.retrievers.document_compressors import CohereRerank | cohere.ipynb |
快速复制示例
聊天
from langchain_cohere import ChatCohere
from langchain_core.messages import HumanMessage
chat = ChatCohere()
messages = [HumanMessage(content="knock knock")]
print(chat.invoke(messages))
API Reference:ChatCohere | HumanMessage
使用Cohere 聊天模型
LLM
from langchain_cohere.llms import Cohere
llm = Cohere()
print(llm.invoke("Come up with a pet name"))
API Reference:Cohere
使用Cohere（旧版）LLM模型
工具调用
from langchain_cohere import ChatCohere
from langchain_core.messages import (
HumanMessage,
ToolMessage,
)
from langchain_core.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)
使用Cohere LLM进行工具调用可以通过将必要的工具绑定到llm来完成，如上所示。 另一种方法是支持使用ReAct代理进行多跳工具调用，如下所示。
ReAct 代理
该代理基于论文 ReAct: Synergizing Reasoning and Acting in Language Models。
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.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?",
})
API Reference:TavilySearchResults | ChatCohere | create_cohere_react_agent | ChatPromptTemplate | AgentExecutor
ReAct代理可以用于依次调用多个工具。
RAG 检索器
from langchain_cohere import ChatCohere
from langchain.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."]))
API Reference:CohereEmbeddings
使用Cohere 文本嵌入模型
重新排序器
使用Cohere Reranker