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

Drqa

Drqa is a web-based PDF question-answering application codebase that converts documents into text chunks, embeds and retrieves relevant passages with Qdrant, and uses an LLM such as OpenAI GPT-3 to generate answers. Its Python FastAPI backend handles processing and requests, while its React and TypeScript frontend provides the interface.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Drqa — 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 Drqa as a codebase when you want to configure a PDF question-answering workflow with a separate web frontend, FastAPI backend, vector retrieval and LLM answer generation.

Who it is for

  • Developers building a question-answering interface over PDF collections.
  • Teams adapting a retrieval-augmented generation pipeline for internal knowledge search.

Documented uses

  • Process PDFs into smaller text chunks for question answering.
  • Create embeddings and retrieve relevant document passages from a vector store.
  • Generate answers from retrieved material using an LLM.
Before you choose

Requirements & limits

  • The documented pipeline uses Qdrant for vector retrieval and OpenAI for answer generation.
  • SentenceTransformers is the embedding model identified as used; the README says other embedding models can be substituted.
  • Qdrant may be run locally or used through Qdrant Cloud; cloud setup requires a host URL and API key.
  • The README describes PDF as the current supported document input, with other LangChain loaders as an adaptation rather than a specified implemented feature.

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 Drqa application

Prepare the documented frontend and backend setup with Qdrant and OpenAI credentials.

Before you start

  • A copy of the Drqa repository
  • An OpenAI API key
  • Either Qdrant Cloud credentials, including host URL and API key, or a local Qdrant instance
  • A Python virtual environment and npm

Steps

  1. Create a .env file in backend/app and set QDRANT_HOST, QDRANT_API_KEY and OPENAI_API_KEY.

  2. In the frontend directory, run the command below and then the command below.

    Documented command
    npm install
    Documented command
    npm start

  3. In backend/app, activate a virtual environment, run the command below, and then run the command below.

    Documented command
    pip install -r requirements.txt
    Documented command
    python main.py

Expected outcome

The documented frontend and FastAPI backend start as separate application components.

Guide limitations

  • The README does not specify deployment steps or provide a successful execution test.
  • The described document-question-answering input is PDF; other document loaders are suggested as an adaptation.
Documentation 1 ↗
Evidence and transparency

Sources & review

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