Migrating from StuffDocumentsChain

StuffDocumentsChain combines documents by concatenating them into a single context window. It is a straightforward and effective strategy for combining documents for question-answering, summarization, and other purposes.

create_stuff_documents_chain is the recommended alternative. It functions the same as StuffDocumentsChain, with better support for streaming and batch functionality. Because it is a simple combination of LCEL primitives, it is also easier to extend and incorporate into other LangChain applications.

Below we will go through both StuffDocumentsChain and create_stuff_documents_chain on a simple example for illustrative purposes.

Let's first load a chat model:

OpenAI

pip install -qU langchain-openai

import getpass
import os

os.environ["OPENAI_API_KEY"] = getpass.getpass()

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(model="gpt-4o-mini")

Anthropic

pip install -qU langchain-anthropic

import getpass
import os

os.environ["ANTHROPIC_API_KEY"] = getpass.getpass()

from langchain_anthropic import ChatAnthropic

llm = ChatAnthropic(model="claude-3-5-sonnet-20240620")

Azure

pip install -qU langchain-openai

import getpass
import os

os.environ["AZURE_OPENAI_API_KEY"] = getpass.getpass()

from langchain_openai import AzureChatOpenAI

llm = AzureChatOpenAI(
    azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
    azure_deployment=os.environ["AZURE_OPENAI_DEPLOYMENT_NAME"],
    openai_api_version=os.environ["AZURE_OPENAI_API_VERSION"],
)

Google

pip install -qU langchain-google-vertexai

# Ensure your VertexAI credentials are configured

from langchain_google_vertexai import ChatVertexAI

llm = ChatVertexAI(model="gemini-1.5-flash")

AWS

pip install -qU langchain-aws

# Ensure your AWS credentials are configured

from langchain_aws import ChatBedrock

llm = ChatBedrock(model="anthropic.claude-3-5-sonnet-20240620-v1:0",
    beta_use_converse_api=True)

Cohere

pip install -qU langchain-cohere

import getpass
import os

os.environ["COHERE_API_KEY"] = getpass.getpass()

from langchain_cohere import ChatCohere

llm = ChatCohere(model="command-r-plus")

NVIDIA

pip install -qU langchain-nvidia-ai-endpoints

import getpass
import os

os.environ["NVIDIA_API_KEY"] = getpass.getpass()

from langchain_nvidia_ai_endpoints import ChatNVIDIA

llm = ChatNVIDIA(model="meta/llama3-70b-instruct")

FireworksAI

pip install -qU langchain-fireworks

import getpass
import os

os.environ["FIREWORKS_API_KEY"] = getpass.getpass()

from langchain_fireworks import ChatFireworks

llm = ChatFireworks(model="accounts/fireworks/models/llama-v3p1-70b-instruct")

Groq

pip install -qU langchain-groq

import getpass
import os

os.environ["GROQ_API_KEY"] = getpass.getpass()

from langchain_groq import ChatGroq

llm = ChatGroq(model="llama3-8b-8192")

MistralAI

pip install -qU langchain-mistralai

import getpass
import os

os.environ["MISTRAL_API_KEY"] = getpass.getpass()

from langchain_mistralai import ChatMistralAI

llm = ChatMistralAI(model="mistral-large-latest")

TogetherAI

pip install -qU langchain-openai

import getpass
import os

os.environ["TOGETHER_API_KEY"] = getpass.getpass()

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    base_url="https://api.together.xyz/v1",
    api_key=os.environ["TOGETHER_API_KEY"],
    model="mistralai/Mixtral-8x7B-Instruct-v0.1",
)

Databricks

pip install -qU databricks-langchain

import getpass
import os

os.environ["DATABRICKS_TOKEN"] = getpass.getpass()

from databricks_langchain import ChatDatabricks

os.environ["DATABRICKS_HOST"] = "https://example.staging.cloud.databricks.com/serving-endpoints"

llm = ChatDatabricks(endpoint="databricks-meta-llama-3-1-70b-instruct")

Example

Let's go through an example where we analyze a set of documents. We first generate some simple documents for illustrative purposes:

from langchain_core.documents import Document

documents = [
    Document(page_content="Apples are red", metadata={"title": "apple_book"}),
    Document(page_content="Blueberries are blue", metadata={"title": "blueberry_book"}),
    Document(page_content="Bananas are yelow", metadata={"title": "banana_book"}),
]

API Reference:Document

Legacy

Details

Below we show an implementation with StuffDocumentsChain. We define the prompt template for a summarization task and instantiate a LLMChain object for this purpose. We define how documents are formatted into the prompt and ensure consistency among the keys in the various prompts.

from langchain.chains import LLMChain, StuffDocumentsChain
from langchain_core.prompts import ChatPromptTemplate, PromptTemplate

# This controls how each document will be formatted. Specifically,
# it will be passed to `format_document` - see that function for more
# details.
document_prompt = PromptTemplate(
    input_variables=["page_content"], template="{page_content}"
)
document_variable_name = "context"
# The prompt here should take as an input variable the
# `document_variable_name`
prompt = ChatPromptTemplate.from_template("Summarize this content: {context}")

llm_chain = LLMChain(llm=llm, prompt=prompt)
chain = StuffDocumentsChain(
    llm_chain=llm_chain,
    document_prompt=document_prompt,
    document_variable_name=document_variable_name,
)

API Reference:LLMChain | StuffDocumentsChain | ChatPromptTemplate | PromptTemplate

We can now invoke our chain:

result = chain.invoke(documents)
result["output_text"]

'This content describes the colors of different fruits: apples are red, blueberries are blue, and bananas are yellow.'

for chunk in chain.stream(documents):
    print(chunk)

{'input_documents': [Document(metadata={'title': 'apple_book'}, page_content='Apples are red'), Document(metadata={'title': 'blueberry_book'}, page_content='Blueberries are blue'), Document(metadata={'title': 'banana_book'}, page_content='Bananas are yelow')], 'output_text': 'This content describes the colors of different fruits: apples are red, blueberries are blue, and bananas are yellow.'}

LCEL

Details

Below we show an implementation using create_stuff_documents_chain:

from langchain.chains.combine_documents import create_stuff_documents_chain
from langchain_core.prompts import ChatPromptTemplate

prompt = ChatPromptTemplate.from_template("Summarize this content: {context}")
chain = create_stuff_documents_chain(llm, prompt)

API Reference:create_stuff_documents_chain | ChatPromptTemplate

Invoking the chain, we obtain a similar result as before:

result = chain.invoke({"context": documents})
result

'This content describes the colors of different fruits: apples are red, blueberries are blue, and bananas are yellow.'

Note that this implementation supports streaming of output tokens:

for chunk in chain.stream({"context": documents}):
    print(chunk, end=" | ")

 | This |  content |  describes |  the |  colors |  of |  different |  fruits | : |  apples |  are |  red | , |  blue | berries |  are |  blue | , |  and |  bananas |  are |  yellow | . |  |

Next steps

Check out the LCEL conceptual docs for more background information.

See these how-to guides for more on question-answering tasks with RAG.

See this tutorial for more LLM-based summarization strategies.