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

Haystack Rag App

Haystack Rag App is an open-source example of a retrieval-augmented generation application, with a React web interface for uploading and searching documents and a Haystack backend for generative question-answering.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Haystack Rag App — 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 runnable reference for a document-grounded search and question-answering workflow, or a starting point for adapting a Haystack-based RAG application.

Who it is for

  • Developers exploring a document-search and question-answering application built with Haystack.
  • Teams prototyping a RAG interface that connects OpenSearch retrieval with an OpenAI generator.

Documented uses

  • Upload a collection of PDF, TXT, or Markdown files for indexing.
  • Search the uploaded documents and ask questions about their contents.
  • Study an application architecture that separates a React UI, indexing and query services, OpenSearch, and an nginx proxy.
Before you choose

Requirements & limits

The repository is public, open source, and licensed under Apache-2.0. The documented setup runs the application with Docker Compose and requires an OpenAI API key and an OpenSearch password.

  • It supports PDF, TXT, and Markdown documents.
  • Uploads are indexed synchronously, and the frontend imposes a 110 MB per-upload limit.
  • The Docker Compose setup starts the interface, backend services, OpenSearch, and nginx proxy together.

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 document-search application with Docker Compose

Configure the example and bring up its web interface and supporting services.

Before you start

  • A clone of the public repository
  • Docker Compose
  • An OpenAI API key
  • An OpenSearch password

Steps

  1. Copy .env.example to .env in the project directory.

  2. Set OPENSEARCH_PASSWORD and add OPENAI_API_KEY in .env; the OpenSearch host URL can remain unchanged for the Docker Compose setup.

  3. Run docker-compose up from the project directory.

  4. After the containers are running, open http://localhost:8080 in a browser.

Expected outcome

The application UI is available for uploading documents and querying the indexed collection.

Guide limitations

  • The supported file formats are PDF, TXT, and Markdown.
  • The frontend limits a single upload to 110 MB.
  • Files are indexed synchronously, so larger uploads can take longer.
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
Haystack Rag AppUpload a collection of PDF, TXT, or Markdown files for indexing.Cloud, Server, WebThe repository is public, open source, and licensed under Apache-2.0. The documented setup runs the application with Docker Compose and requires an OpenAI API key and an OpenSearch password.
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
17 October 2026
Original website title
deepset-ai/haystack-rag-app · Official homepage title · retained in its source language
How we review sourcesSuggest a correction