Practical overview
When it fits
Use it when you want a locally configured, code-based workflow for preparing your own documents and querying them through vector retrieval.
Who it is for
- Developers building or adapting terminal-based RAG workflows
- NLP researchers working with conversational document retrieval
Documented uses
- Prepare PDF and Markdown collections for retrieval.
- Bring webpages into a document-processing workflow.
- Ask queries against prepared documents through a LangGraph retrieval pipeline.
- Explore message-history caching and query transformation in a Python RAG application.
Requirements & limits
The project is a public GitHub repository with an MIT license. Setup requires a local Python environment and an OpenAI API key.
- Document preparation and query execution are separate steps: processDocs.py prepares inputs, while main.py launches the application.
- The documented stack includes Python 3.12, LangGraph, OpenAI, dependencies in requirements.txt and wkhtmltopdf.
- Webpage and local-file inputs use environment settings and configured directories.
- The README identifies vector-database retrieval but does not name the database implementation.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Set up documents for Langgraphrag
Configure local PDF, Markdown or webpage inputs and run the documented document-preparation stage.
Before you start
- Python 3.12
- A local clone of the repository
- Dependencies installed from requirements.txt and wkhtmltopdf installed
- An OpenAI API key in the .env file
Steps
Clone the repository and enter its directory; create and activate a Python 3.12 virtual environment.
Install requirements and wkhtmltopdf, then copy .env.example to .env and add OPENAI_API_KEY.
For webpages, add comma-separated URLs and configure GET_WEB_PAGES_TO_PDF. For existing PDFs or Markdown files, set the conversion options and place files in the configured INTERMEDIATE_PDF_DIR or DATA_DIR.
From the repository root, run python modules/processDocs.py to set up the documents and webpages.
Expected outcome
The documented document-processing stage prepares the selected inputs for the RAG application.
Guide limitations
- The README says document-processing parameters in .env may need adjustment; it does not specify detailed parameter values.
- This guide covers document setup only, not successful query execution.
Compare options for Retrieval-augmented applications
These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.
| Project | Documented purpose | Platform | Access and requirements |
|---|---|---|---|
| Langgraphrag | Prepare PDF and Markdown collections for retrieval. | CLI, Linux, macOS, Windows | The project is a public GitHub repository with an MIT license. Setup requires a local Python environment and an OpenAI API key. |
| Rag Powered AI Assistant Transforming Data Retrieval And Analysis Across The Web And Pdfs | Retrieve relevant passages from web and PDF content to answer a question. | Web | |
| LangChain in Supabase Edge Functions | Initialize and start a Supabase project locally. | Cloud, Server |
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 17 October 2026
- Original website title
- ranguy9304/LangGraphRAG · Official homepage title · retained in its source language