OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

Ollama Pdf Rag

Ollama Pdf Rag is a self-hosted PDF question-answering application that uses Ollama, LangChain and ChromaDB for retrieval-augmented generation. It provides a Next.js web interface with a FastAPI backend, a Streamlit interface, and Jupyter notebooks for experimentation.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Ollama Pdf Rag — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want a locally run PDF question-answering workflow and are prepared to install Ollama, models, and the app's software dependencies.

Who it is for

  • People who want to ask questions across their own PDF documents using locally run models.
  • Developers exploring or adapting a local retrieval-augmented generation application.

Documented uses

  • Upload and query multiple PDFs through the Next.js interface, with answers accompanied by source citations.
  • Use a Streamlit interface to upload a PDF or select a sample document and ask questions.
  • Access documented PDF upload, listing, deletion, model-listing and query functions through the FastAPI backend.
  • Experiment with the RAG implementation using the included Jupyter notebooks.
Before you choose

Requirements & limits

The repository is public and MIT-licensed. The application is self-hosted and requires local setup, including Ollama and model downloads.

  • The Next.js and Streamlit interfaces are separate options; the Next.js path pairs a web frontend with FastAPI.
  • The README describes local processing and identifies llama3.2 and nomic-embed-text as example chat and embedding models.
  • The REST API offers programmatic PDF and query operations alongside the graphical interfaces.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the Next.js and FastAPI interface

Prepare the documented local web interface and its backend.

Before you start

  • Ollama installed, with a chat model such as llama3.2 and the nomic-embed-text embedding model pulled.
  • Python, pnpm, and the repository's requirements.txt dependencies.

Steps

  1. Clone the repository and enter its directory.

  2. Create and activate a Python virtual environment, then install dependencies from requirements.txt.

  3. Enter web-ui, install packages with pnpm install, and run pnpm db:migrate.

  4. Start the backend with python run_api.py, then start the frontend with cd web-ui && pnpm dev.

Expected outcome

The README lists the frontend at localhost:3000 and the FastAPI backend at localhost:8001.

Guide limitations

  • The README documents setup and launch instructions; this guide does not verify successful operation.
  • This setup requires both local services and the Ollama model runtime.
Documentation 1 ↗
Source-based practical guide

Start the Streamlit interface

Launch the documented Streamlit app for PDF chat.

Before you start

  • Ollama installed and running, with a chat model and the nomic-embed-text embedding model pulled.
  • A Python environment with the repository dependencies installed.

Steps

  1. Clone the repository and install its Python dependencies in a virtual environment.

  2. Start the app with python run.py.

  3. Use the file uploader or choose the sample PDF, select an available Ollama model, and ask a question.

Expected outcome

The README says the Streamlit interface runs at localhost:8501 and supports chatting with a PDF.

Guide limitations

  • The README documents the workflow; it is not an independent execution test.
  • The documented Streamlit workflow describes uploading one PDF at a time.
Documentation 1 ↗
COMPARE OPTIONS

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.

ProjectDocumented purposePlatformAccess and requirements
Ollama Pdf RagUpload and query multiple PDFs through the Next.js interface, with answers accompanied by source citations.Self-hosted, WebThe repository is public and MIT-licensed. The application is self-hosted and requires local setup, including Ollama and model downloads.
Rag Powered AI Assistant Transforming Data Retrieval And Analysis Across The Web And PdfsRetrieve relevant passages from web and PDF content to answer a question.Web
LangChain in Supabase Edge FunctionsInitialize and start a Supabase project locally.Cloud, Server
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
9 October 2026
Original website title
tonykipkemboi/ollama_pdf_rag · Official homepage title · retained in its source language
How we review sourcesSuggest a correction