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

Local Rag Engine

Local Rag Engine is a self-hosted retrieval-augmented generation application for uploading PDFs and asking questions about their contents. Its Docker Compose stack combines a Streamlit interface and FastAPI backend with Qdrant for vector search and Ollama for local language-model inference.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Local Rag Engine — 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 self-hosted starting point for PDF question-answering and can run Docker Compose on a machine with the recommended memory and disk capacity.

Who it is for

  • People who want to query PDF collections through a locally hosted interface.
  • Developers exploring a Docker-based RAG prototype built with FastAPI, Streamlit, Qdrant and Ollama.

Documented uses

  • Upload PDFs and extract their content for retrieval.
  • Search document content semantically using embeddings and Qdrant.
  • Ask questions about uploaded documents and receive answers from a local Ollama model.
Before you choose

Requirements & limits

The repository is public and identified as MIT-licensed. The documented setup uses Docker Compose and exposes the Streamlit interface at localhost:8501 after the containers start.

  • The first build downloads software and model assets, including an embedding model and a Phi-3 model; the README estimates several gigabytes of downloads and around 10–15 minutes, subject to connection speed.
  • The README recommends at least 8 GB RAM and 10 GB free disk space.
  • The documented document-upload and question-answering workflow is for PDFs.
  • Docker and Docker Compose are the stated setup prerequisites; separate Python and Ollama installations are not required for this container setup.

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

Start the local PDF question-answering app

Launch the Docker Compose stack and use its Streamlit interface to ask questions about uploaded PDFs.

Before you start

  • Docker 20.10 or later
  • Docker Compose 2.0 or later
  • At least 8 GB RAM and 10 GB free disk space are recommended
  • Internet access for the initial build to download dependencies and models

Steps

  1. Clone the repository and change into its directory.

  2. Run docker-compose up --build and wait for the services and models to initialize.

  3. Open http://localhost:8501 in a browser.

  4. Upload PDF documents, wait for processing, then ask questions about them.

Expected outcome

A running Streamlit interface for querying uploaded PDFs with the local RAG stack.

Guide limitations

  • The first build downloads several gigabytes of dependencies and models and may take around 10–15 minutes, depending on the internet connection.
  • The README recommends at least 8 GB of RAM and 10 GB of free disk space.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Vector search

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
Local Rag EngineUpload PDFs and extract their content for retrieval.Docker, Self-hostedThe repository is public and identified as MIT-licensed. The documented setup uses Docker Compose and exposes the Streamlit interface at localhost:8501 after the containers start.
Chatbot with PDF for Semantic SearchPrepare document content as embeddings and save it to a supported vector database.WebThe repository is identified as open source and publicly visible on GitHub.
AI LLM PlaygroundAsk questions about PDF documents through an assistant interface.Web
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
noorjotk/local-rag-engine · Official homepage title · retained in its source language
How we review sourcesSuggest a correction