Cohere Embed on LangChain (Integration Guide)

1
from langchain_cohere import CohereEmbeddings
2
3
# Define the Cohere embedding model
4
embeddings = CohereEmbeddings(
5
    cohere_api_key="COHERE_API_KEY", model="embed-v4.0"
6
)
7
8
# Embed a document
9
text = "This is a test document."
10
query_result = embeddings.embed_query(text)
11
print(query_result[:5], "...")
12
doc_result = embeddings.embed_documents([text])
13
print(doc_result[0][:5], "...")

1
from langchain_cohere import (
2
    ChatCohere,
3
    CohereEmbeddings,
4
    CohereRerank,
5
    CohereRagRetriever,
6
)
7
from langchain.text_splitter import CharacterTextSplitter
8
from langchain_community.vectorstores import Chroma
9
from langchain_community.document_loaders import WebBaseLoader
10
11
user_query = "what is Cohere Toolkit?"
12
13
llm = ChatCohere(
14
    cohere_api_key="COHERE_API_KEY",
15
    model="command-a-03-2025",
16
    temperature=0,
17
)
18
19
embeddings = CohereEmbeddings(
20
    cohere_api_key="COHERE_API_KEY", model="embed-v4.0"
21
)
22
23
# Load text files and split into chunks, you can also use data gathered elsewhere in your application
24
raw_documents = WebBaseLoader(
25
    "https://docs.cohere.com/docs/cohere-toolkit"
26
).load()
27
28
text_splitter = CharacterTextSplitter(chunk_size=500, chunk_overlap=0)
29
documents = text_splitter.split_documents(raw_documents)
30
# Create a vector store from the documents
31
db = Chroma.from_documents(documents, embeddings)
32
input_docs = db.as_retriever().invoke(user_query)
33
34
# Create the cohere rag retriever using the chat model
35
rag = CohereRagRetriever(llm=llm)
36
docs = rag.invoke(
37
    user_query,
38
    documents=input_docs,
39
)
40
# Print the documents
41
print("Documents:")
42
for doc in docs[:-1]:
43
    print(doc.metadata)
44
    print("\n\n" + doc.page_content)
45
    print("\n\n" + "-" * 30 + "\n\n")
46
# Print the final generation
47
answer = docs[-1].page_content
48
print("Answer:")
49
print(answer)
50
# Print the final citations
51
citations = docs[-1].metadata["citations"]
52
print("Citations:")
53
print(citations)

1
from langchain_aws import BedrockEmbeddings
2
3
# Replace the profile name with the one created in the setup.
4
embeddings = BedrockEmbeddings(
5
    credentials_profile_name="{PROFILE-NAME}",
6
    region_name="us-east-1",
7
    model_id="cohere.embed-english-v3",
8
)
9
10
embeddings.embed_query("This is a content of the document")

1
llm = CohereEmbeddings(
2
    base_url="<YOUR_DEPLOYMENT_URL>",
3
    cohere_api_key="COHERE_API_KEY",
4
    model="MODEL_NAME",
5
)