Cohere Rerank on LangChain (Integration Guide)

Cohere supports various integrations with LangChain, a large language model (LLM) framework which allows you to quickly create applications based on Cohere’s models. This doc will guide you through how to leverage Rerank with LangChain.

Prerequisites

Running Cohere Rerank with LangChain doesn’t require many prerequisites, consult the top-level document for more information.

Cohere ReRank with LangChain

To use Cohere’s rerank functionality with LangChain, start with instantiating a CohereRerank object as follows: cohere_rerank = CohereRerank(cohere_api_key="{API_KEY}").

You can then use it with LangChain retrievers, embeddings, and RAG. The example below uses the vector DB chroma, for which you will need to install pip install chromadb. Other vector DB’s from this list can also be used. After reranking, we pass the top documents to ChatCohere through its documents argument to get a grounded answer with citations.

PYTHON

from langchain_classic.retrievers import (
    ContextualCompressionRetriever,
)
from langchain_cohere import (
    ChatCohere,
    CohereEmbeddings,
    CohereRerank,
)
from langchain_text_splitters import CharacterTextSplitter
from langchain_community.vectorstores import Chroma
from langchain_community.document_loaders import WebBaseLoader
user_query = "what is Cohere Toolkit?"
# Define the Cohere LLM
llm = ChatCohere(
    cohere_api_key="COHERE_API_KEY", model="command-a-03-2025"
)
# Define the Cohere embedding model
embeddings = CohereEmbeddings(
    cohere_api_key="COHERE_API_KEY", model="embed-english-light-v3.0"
)
# Load text and split into chunks, you can also use data gathered elsewhere in your application
raw_documents = WebBaseLoader(
    "https://docs.cohere.com/docs/cohere-toolkit"
).load()
text_splitter = CharacterTextSplitter(
    chunk_size=1000, chunk_overlap=0
)
documents = text_splitter.split_documents(raw_documents)
# Create a vector store from the documents
db = Chroma.from_documents(documents, embeddings)
# Create Cohere's reranker with the vector DB using Cohere's embeddings as the base retriever
reranker = CohereRerank(
    cohere_api_key="COHERE_API_KEY", model="rerank-english-v3.0"
)
compression_retriever = ContextualCompressionRetriever(
    base_compressor=reranker, base_retriever=db.as_retriever()
)
compressed_docs = compression_retriever.invoke(user_query)
# Print the reranked documents from using the embeddings and reranker
print(compressed_docs)
# Ground the answer in the reranked documents
response = llm.invoke(user_query, documents=compressed_docs)
# Print the answer
print("Answer:")
print(response.content)
# Print the citations that ground the answer in the documents
print("Citations:")
print(response.additional_kwargs.get("citations"))

Using LangChain on Private Deployments

You can use LangChain with privately deployed Cohere models. To use it, specify your model deployment URL in the base_url parameter.

PYTHON

llm = CohereRerank(
    base_url="<YOUR_DEPLOYMENT_URL>",
    cohere_api_key="COHERE_API_KEY",
    model="MODEL_NAME",
)