Skip to main content


This template performs RAG on semi-structured data, such as a PDF with text and tables.

See this cookbook as a reference.

Environment Setup​

Set the OPENAI_API_KEY environment variable to access the OpenAI models.

This uses Unstructured for PDF parsing, which requires some system-level package installations.

On Mac, you can install the necessary packages with the following:

brew install tesseract poppler


To use this package, you should first have the LangChain CLI installed:

pip install -U langchain-cli

To create a new LangChain project and install this as the only package, you can do:

langchain app new my-app --package rag-semi-structured

If you want to add this to an existing project, you can just run:

langchain app add rag-semi-structured

And add the following code to your file:

from rag_semi_structured import chain as rag_semi_structured_chain

add_routes(app, rag_semi_structured_chain, path="/rag-semi-structured")

(Optional) Let's now configure LangSmith. LangSmith will help us trace, monitor and debug LangChain applications. You can sign up for LangSmith here. If you don't have access, you can skip this section

export LANGCHAIN_API_KEY=<your-api-key>
export LANGCHAIN_PROJECT=<your-project> # if not specified, defaults to "default"

If you are inside this directory, then you can spin up a LangServe instance directly by:

langchain serve

This will start the FastAPI app with a server is running locally at http://localhost:8000

We can see all templates at We can access the playground at

We can access the template from code with:

from langserve.client import RemoteRunnable

runnable = RemoteRunnable("http://localhost:8000/rag-semi-structured")

For more details on how to connect to the template, refer to the Jupyter notebook rag_semi_structured.

Help us out by providing feedback on this documentation page: