Skip to content

Commit

Permalink
Add new integrations in langchain and llamaindex (#192)
Browse files Browse the repository at this point in the history 
* add new integrations langchain llamaindex

* update convention

* standardize chat args

* update code snippets
  • Loading branch information
@mrmer1
mrmer1 authored Oct 16, 2024
1 parent 97c68c7 commit 2c23f4b
Show file tree
Hide file tree
Showing 5 changed files with 522 additions and 103 deletions.
197 changes: 153 additions & 44 deletions fern/pages/integrations/cohere-and-langchain/chat-on-langchain.mdx
View file
Original file line number Diff line number Diff line change
Expand Up @@ -18,24 +18,26 @@ Running Cohere Chat with LangChain doesn't require many prerequisites, consult t

### Cohere Chat with LangChain

To use [Cohere chat](/docs/chat-api) with LangChain, simply create a [ChatCohere](https://github.com/langchain-ai/langchain/blob/master/libs/community/langchain_community/chat_models/cohere.py) object and pass in the message or message history. In the example below, you will need to add your Cohere API key.
To use [Cohere chat](/docs/chat-api) with LangChain, simply create a [ChatCohere](https://python.langchain.com/docs/integrations/chat/cohere/) object and pass in the message or message history. In the example below, you will need to add your Cohere API key.

```python PYTHON
from langchain_community.chat_models import ChatCohere
from langchain_cohere import ChatCohere
from langchain_core.messages import AIMessage, HumanMessage

cohere_chat_model = ChatCohere(cohere_api_key="{API_KEY}")
# Define the Cohere LLM
llm = ChatCohere(cohere_api_key="COHERE_API_KEY",
model="command-r-plus-08-2024")

# Send a chat message without chat history
current_message = [HumanMessage(content="knock knock")]
print(cohere_chat_model(current_message))
print(llm(current_message))

# Send a chat message with chat history, note the last message is the current user message
current_message_and_history = [
HumanMessage(content="knock knock"),
AIMessage(content="Who's there?"),
HumanMessage(content="Tank") ]
print(cohere_chat_model(current_message_and_history))
print(llm(current_message_and_history))
```

### Cohere Agents with LangChain
Expand All @@ -47,29 +49,38 @@ To use Cohere's multi hop agent create a `create_cohere_react_agent` and pass in
For example, using an internet search tool to get essay writing advice from Cohere with citations:

```python PYTHON
from langchain.agents import AgentExecutor
from langchain_cohere.chat_models import ChatCohere
from langchain_cohere import ChatCohere
from langchain_cohere.react_multi_hop.agent import create_cohere_react_agent
from langchain.agents import AgentExecutor
from langchain_community.tools.tavily_search import TavilySearchResults
from langchain_core.prompts import ChatPromptTemplate

# Internet search tool - you can use any tool, and there are lots of community tools in LangChain.
# To use the Tavily tool you will need to set an API key in the TAVILY_API_KEY environment variable.
os.environ["TAVILY_API_KEY"] = "TAVILY_API_KEY"
internet_search = TavilySearchResults()

# Create and run the Cohere agent
# Set a Cohere API key in the COHERE_API_KEY environment variable.
llm = ChatCohere()
# Define the Cohere LLM
llm = ChatCohere(cohere_api_key="COHERE_API_KEY",
model="command-r-plus-08-2024")

# Create an agent
agent = create_cohere_react_agent(
llm=llm,
tools=[internet_search],
prompt=ChatPromptTemplate.from_template("{question}"),
)

# Create an agent executor
agent_executor = AgentExecutor(agent=agent, tools=[internet_search], verbose=True)

response = agent_executor.invoke({
"question": "I want to write an essay. Any tips?",
})
# Generate a response
response = agent_executor.invoke(
{
"question": "I want to write an essay. Any tips?",
}
)

# See Cohere's response
print(response.get("output"))
# Cohere provides exact citations for the sources it used
Expand All @@ -85,65 +96,75 @@ To use Cohere's [retrieval augmented generation (RAG)](/docs/retrieval-augmented
In this example, we use the [wikipedia retriever](https://python.langchain.com/docs/integrations/retrievers/wikipedia) but any [retriever supported by LangChain](https://python.langchain.com/docs/integrations/retrievers) can be used here. In order to set up the wikipedia retriever you need to install the wikipedia python package using `%pip install --upgrade --quiet wikipedia`. With that done, you can execute this code to see how a retriever works:

```python PYTHON
from langchain.retrievers import CohereRagRetriever
from langchain_cohere import CohereRagRetriever
from langchain.retrievers import WikipediaRetriever
from langchain_community.chat_models import ChatCohere
from langchain_cohere import ChatCohere

# User query we will use for the generation
user_query = "What is cohere?"
# Load the cohere chat model
cohere_chat_model = ChatCohere(cohere_api_key="{API_KEY}")
# Create the cohere rag retriever using the chat model
rag = CohereRagRetriever(llm=cohere_chat_model, connectors=[])
# Define the Cohere LLM
llm = ChatCohere(cohere_api_key="COHERE_API_KEY",
model="command-r-plus-08-2024")
# Create the Cohere rag retriever using the chat model
rag = CohereRagRetriever(llm=llm, connectors=[])
# Create the wikipedia retriever
wiki_retriever = WikipediaRetriever()
# Get the relevant documents from wikipedia
wiki_docs = wiki_retriever.get_relevant_documents(user_query )
wiki_docs = wiki_retriever.invoke(user_query)
# Get the cohere generation from the cohere rag retriever
docs = rag.get_relevant_documents(user_query ,source_documents=wiki_docs)
docs = rag.invoke(user_query, documents=wiki_docs)
# Print the documents
print("Documents:")
for doc in docs[:-1]:
print(doc.metadata)
print("\n\n" + doc.page_content)
print("\n\n" + "-" * 30 + "\n\n")
# Print the final generation
# Print the final generation
answer = docs[-1].page_content
print("Answer:")
print(answer)
# Print the final citations
citations = docs[-1].metadata['citations']
print(citations)
# Print the final citations
citations = docs[-1].metadata["citations"]
print("Citations:")
print(docs[-1].__dict__)
```

#### Using Documents

In this example, we take documents (which might be generated in other parts of your application) and pass them into the [CohereRagRetriever](https://github.com/langchain-ai/langchain/blob/master/libs/community/langchain_community/retrievers/cohere_rag_retriever.py) object:

```python PYTHON
from langchain.retrievers import CohereRagRetriever
from langchain_community.chat_models import ChatCohere
from langchain_cohere import CohereRagRetriever
from langchain_cohere import ChatCohere
from langchain_core.documents import Document

# Load the cohere chat model
cohere_chat_model = ChatCohere(cohere_api_key="{API_KEY}")
# Create the cohere rag retriever using the chat model
rag = CohereRagRetriever(llm=cohere_chat_model, connectors=[])
docs = rag.get_relevant_documents(
# Define the Cohere LLM
llm = ChatCohere(cohere_api_key="COHERE_API_KEY",
model="command-r-plus-08-2024")

# Create the Cohere rag retriever using the chat model
rag = CohereRagRetriever(llm=llm, connectors=[])
docs = rag.invoke(
"Does LangChain support cohere RAG?",
source_documents=[
documents=[
Document(page_content="LangChain supports cohere RAG!", metadata={"id": "id-1"}),
Document(page_content="The sky is blue!", metadata={"id": "id-2"}),
],
)

# Print the documents
print("Documents:")
for doc in docs[:-1]:
print(doc.metadata)
print("\n\n" + doc.page_content)
print("\n\n" + "-" * 30 + "\n\n")
# Print the final generation
# Print the final generation
answer = docs[-1].page_content
print("Answer:")
print(answer)
# Print the final citations
# Print the final citations
citations = docs[-1].metadata['citations']
print("Citations:")
print(citations)
```

Expand All @@ -154,24 +175,112 @@ In this example, we create a generation with a [connector](/docs/overview-rag-co
Here's a code sample illustrating how to use a connector:

```python PYTHON
from langchain.retrievers import CohereRagRetriever
from langchain_community.chat_models import ChatCohere
from langchain_cohere import CohereRagRetriever
from langchain_cohere import ChatCohere
from langchain_core.documents import Document

# Load the cohere chat model
cohere_chat_model = ChatCohere(cohere_api_key="{API_KEY}")
# Create the cohere rag retriever using the chat model with the web search connector
rag = CohereRagRetriever(llm=cohere_chat_model, connectors=[{"id": "web-search"}])
docs = rag.get_relevant_documents("Who founded Cohere?")
# Define the Cohere LLM
llm = ChatCohere(cohere_api_key="COHERE_API_KEY",
model="command-r-plus-08-2024")

# Create the Cohere rag retriever using the chat model with the web search connector
rag = CohereRagRetriever(llm=llm, connectors=[{"id": "web-search"}])
docs = rag.invoke("Who founded Cohere?")
# Print the documents
print("Documents:")
for doc in docs[:-1]:
print(doc.metadata)
print("\n\n" + doc.page_content)
print("\n\n" + "-" * 30 + "\n\n")
# Print the final generation
# Print the final generation
answer = docs[-1].page_content
print("Answer:")
print(answer)
# Print the final citations
# Print the final citations
citations = docs[-1].metadata['citations']
print("Citations:")
print(citations)
```
#### Using the `create_stuff_documents_chain` Chain
This chain takes a list of documents and formats them all into a prompt, then passes that prompt to an LLM. It passes ALL documents, so you should make sure it fits within the context window of the LLM you are using.

Note: this feature is currently in beta.

```python PYTHON
from langchain_cohere import ChatCohere
from langchain_core.documents import Document
from langchain_core.prompts import ChatPromptTemplate
from langchain.chains.combine_documents import create_stuff_documents_chain

prompt = ChatPromptTemplate.from_messages(
[("human", "What are everyone's favorite colors:\n\n{context}")]
)

# Define the Cohere LLM
llm = ChatCohere(cohere_api_key="COHERE_API_KEY",
model="command-r-plus-08-2024")

chain = create_stuff_documents_chain(llm, prompt)

docs = [
Document(page_content="Jesse loves red but not yellow"),
Document(page_content = "Jamal loves green but not as much as he loves orange")
]

chain.invoke({"context": docs})
```

### Structured Output Generation
Cohere supports generating JSON objects to structure and organize the model’s responses in a way that can be used in downstream applications.

You can specify the `response_format` parameter to indicate that you want the response in a JSON object format.

```python PYTHON
from langchain_cohere import ChatCohere

# Define the Cohere LLM
llm = ChatCohere(cohere_api_key="COHERE_API_KEY",
model="command-r-plus-08-2024")

res = llm.invoke("John is five years old", response_format={
"type": "json_object",
"schema": {
"title": "Person",
"description": "Identifies the age and name of a person",
"type": "object",
"properties": {
"name": { "type": "string", "description": "Name of the person" },
"age": { "type": "number", "description": "Age of the person" },
},
"required": [
"name",
"age",
],
}
}
)

print(res)
```

### Text Summarization

You can use the `load_summarize_chain` chain to perform text summarization.

```python PYTHON
from langchain_cohere import ChatCohere
from langchain.chains.summarize import load_summarize_chain
from langchain_community.document_loaders import WebBaseLoader

loader = WebBaseLoader("https://docs.cohere.com/docs/cohere-toolkit")
docs = loader.load()

# Define the Cohere LLM
llm = ChatCohere(cohere_api_key="COHERE_API_KEY",
model="command-r-plus-08-2024",
temperature=0)

chain = load_summarize_chain(llm, chain_type="stuff")

chain.invoke({"input_documents": docs})
```
Loading

0 comments on commit 2c23f4b

Please sign in to comment.