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

Context Based Question Answering

Context Based Question Answering is an open-source web application that answers questions by extracting relevant snippets from user-provided text or uploaded documents. It uses Haystack for document processing and retrieval, Elasticsearch as its DocumentStore, and pretrained Transformers readers; results include the answer, related context and document title.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Context Based Question Answering — 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 answers should be extracted from a defined body of user-supplied text and returned with context that helps identify the source.

Who it is for

  • People who need to search their own text or PDF, TXT and DOCX documents with natural-language questions.
  • Organizations evaluating a locally run extractive question-answering interface for English or French material.
  • Developers adapting a Haystack- and Transformers-based web QA application.

Documented uses

  • Ask questions about context entered in the application or uploaded as supported files.
  • Retrieve answer snippets with the surrounding context and associated document title.
  • Compare the documented pretrained reader options and select CPU or GPU inference.
Before you choose

Requirements & limits

The project is published as open source under the Apache-2.0 license. The repository README provides local installation instructions and labels the project inactive.

  • The application uses Elasticsearch as its only DocumentStore type; the README's references to other Haystack stores do not describe alternatives used by this system.
  • The documented interface supports English and French, with BERT, RoBERTa, DistilBERT and CamemBERT readers.
  • The README lists Python 3.7, Elasticsearch 7.10 and a pip-based setup, and also documents Docker for running Elasticsearch.
  • The repository describes temporary per-user upload directories and separate Elasticsearch indexes for each user.
  • The repository marks the project inactive, with maintenance as time allows.

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

Prepare a local Python installation

Install the application dependencies and start its documented Elasticsearch service.

Before you start

  • Git
  • Python 3.7 and a virtual environment
  • Elasticsearch 7.10, installed locally or run with Docker
  • Docker engine if choosing the Docker Elasticsearch option

Steps

  1. Clone the repository and change into its directory.

  2. Create and activate a Python 3.7 virtual environment.

  3. Install dependencies with pip install -r requirements.txt.

  4. Start Elasticsearch; the README documents a Docker image and single-node container command as one option.

Expected outcome

The listed dependencies are installed and Elasticsearch is started as the application's DocumentStore service.

Guide limitations

  • This covers dependency setup and Elasticsearch startup, not a complete application launch or question-answering run.
  • The project README marks the project inactive.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
Karthik-Bhaskar/Context-Based-Question-Answering · Official homepage title · retained in its source language
How we review sourcesSuggest a correction