Cohere는 기업이 인간과 기계의 상호작용을 개선할 수 있도록 자연어 처리 모델을 제공하는 캐나다 스타트업입니다.

​
Installation and Setup

  • Python SDK 설치:
pip install langchain-cohere
Cohere api key를 발급받아 환경 변수(COHERE_API_KEY)로 설정하세요.

​
Cohere langchain integrations

API설명Endpoint 문서Import사용 예시
Chat챗봇 구축chatfrom langchain_cohere import ChatCoherecohere.ipynb
LLM텍스트 생성generatefrom langchain_cohere.llms import Coherecohere.ipynb
RAG Retriever외부 데이터 소스 연결chat + ragfrom langchain.retrievers import CohereRagRetrievercohere.ipynb
Text Embedding문자열을 벡터로 임베딩embedfrom langchain_cohere import CohereEmbeddingscohere.ipynb
Rerank Retriever관련성에 따라 문자열 순위 지정rerankfrom langchain.retrievers.document_compressors import CohereRerankcohere.ipynb

​
Quick copy examples

​
Chat

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

​
LLM

from langchain_cohere.llms import Cohere

llm = Cohere()
print(llm.invoke("Come up with a pet name"))
Cohere (레거시) LLM model 사용법

​
Tool calling

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 LLM을 사용한 Tool calling은 위와 같이 필요한 tool을 llm에 바인딩하여 수행할 수 있습니다. 다른 방법으로는 아래와 같이 ReAct agent를 사용하여 multi hop tool calling을 지원하는 것입니다.

​
ReAct Agent

이 agent는 논문 ReAct: Synergizing Reasoning and Acting in Language Models을 기반으로 합니다. 
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?",
})
ReAct agent는 여러 tool을 순차적으로 호출하는 데 사용할 수 있습니다.

​
RAG Retriever

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?"))
Cohere RAG Retriever 사용법

​
Text Embedding

from langchain_cohere import CohereEmbeddings

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

​
Reranker

Cohere Reranker 사용법
Edit the source of this page on GitHub.
Connect these docs programmatically to Claude, VSCode, and more via MCP for real-time answers.
⌘I