OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Memory & RAG

Rag Reactagent

Rag Reactagent is a self-hostable retrieval-augmented question-answering application that indexes local documents and uses a ReAct agent loop to retrieve evidence, call tools and produce cited answers.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Rag Reactagent — OpenViST project profile in Agent Memory & RAG.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when answers need to be grounded in a managed collection of documents and readers need citations or checks against retrieved evidence, especially for questions spanning files or combining semantic and exact-term search.

Who it is for

  • Teams that want to query handbooks, product material, technical documents or project files.
  • Developers exploring RAG, hybrid retrieval, agent tool loops and citation validation.

Documented uses

  • Ask natural-language questions across an uploaded document collection.
  • Find exact codes, identifiers, fields and model details alongside semantic information.
  • Compare or summarize material from multiple documents and inspect answer sources.
  • Set up a locally hosted document assistant with configurable language-model and embedding services.
Before you choose

Requirements & limits

The repository documents a Docker Compose deployment using a published GHCR image and a local web interface. It provides first-login credentials and directs users to configure LLM and embedding services in settings. The project is MIT-licensed.

  • Retrieval uses Qdrant for semantic search and SQLite BM25 for keyword matching, combined through weighted reciprocal rank fusion.
  • A reranker is available as an optional retrieval stage.
  • The agent includes local document search, web search, calculator and document-information tools.
  • Post-generation checks cover citations and numerical consistency; the project also describes evidence-based refusal.
  • The published-image startup path is distinct from source-build and OCR setup instructions.

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 published Docker Compose deployment

Launch the application from its documented GHCR image and open its local web interface.

Before you start

  • Git
  • Docker Compose
  • The project GitHub repository
  • The backend environment template

Steps

  1. Clone the repository and change into its directory.

  2. Copy backend/.env.example to backend/.env.

  3. Run Docker Compose with --env-file backend/.env and -f docker-compose.ghcr.yml up -d.

  4. Open http://localhost:5173 and sign in with the documented first-login credentials.

Expected outcome

The application is available at the local web address; configure LLM and embedding services in settings to use question answering.

Guide limitations

  • The README advises changing the initial password after login.
  • This procedure uses the published image; source-build and OCR setup are separate paths.
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
Rag ReactagentAsk natural-language questions across an uploaded document collection.Self-hosted, Server, WebThe repository documents a Docker Compose deployment using a published GHCR image and a local web interface. It provides first-login credentials and directs users to configure LLM and embedding services in settings. The project is MIT-licensed.
VectaurantFind menu options by describing preferences, such as asking what is vegan or spicy.CLI, Docker, Linux, macOS
Aml Multiagent RagIngest PDF regulations, extract and chunk their text, and build a searchable vector collection.Docker, Self-hostedThe repository is public and specifies the MIT license. The documented setup is self-hosted and requires Python 3.11 or later, Docker Desktop and an OpenAI API key.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
MoMoM101/RAG-ReActAgent · Official homepage title · retained in its source language
How we review sourcesSuggest a correction