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

Local Rag Llamaindex

Local Rag Llamaindex is a self-hosted research-paper question-answering application that indexes arXiv papers and returns answers with citations through a FastAPI endpoint.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Local Rag Llamaindex — 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 to create a self-hosted, citation-producing question-answering service over arXiv papers and can operate its Docker or Python-based components.

Who it is for

  • Researchers who want to search and ask questions across a selected set of arXiv papers.
  • Developers building a self-hosted RAG API with local model serving.

Documented uses

  • Download a limited set of arXiv papers matching a search query.
  • Load, chunk, embed and store papers in Qdrant.
  • Retrieve relevant passages for a question and return an LLM-generated answer with source citations.
Before you choose

Requirements & limits

  • The documented ingestion source is arXiv, and the workflow uses a search query and result limit.
  • The Docker Compose stack separates ingestion from the API, vector database and model server.
  • The documented query interface is an API endpoint; no separate user-facing application interface is described.

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 and ingest papers with Docker Compose

Build the project services, start the API stack and index a limited arXiv search into Qdrant.

Before you start

  • Docker and Docker Compose
  • The project repository

Steps

  1. Clone the repository and enter its directory.

  2. Build the images with the command below.

    Documented command
    docker compose build

  3. Start Ollama, Qdrant and the API with the command below.

    Documented command
    docker compose up ollama qdrant api

  4. Run the ingestion service with the command below, changing the search phrase or result limit as needed.

    Documented command
    docker compose run data_ingestion --query "LLM" --max 5 --ingest

Expected outcome

The selected arXiv papers are chunked and stored in Qdrant, and the API service is started on port 8000 for queries.

Guide limitations

  • This setup requires Docker and Docker Compose.
  • The documented ingestion command searches arXiv; it does not describe importing arbitrary local documents.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
Otman404/local-rag-llamaindex · Official homepage title · retained in its source language
How we review sourcesSuggest a correction