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

Docchat

DocChat is a web application that crawls documentation pages from a supplied URL, processes them into a searchable knowledge base, and answers natural-language questions with source-backed responses. It offers vector retrieval with embeddings stored in Qdrant and a vectorless mode that retrieves from a generated documentation tree.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Docchat — 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 DocChat when you want to query the contents of a documentation site conversationally instead of searching through its pages manually.

Who it is for

  • People who need to find answers across a documentation website through natural-language questions.
  • Developers evaluating or setting up a documentation-focused retrieval-augmented generation application.

Documented uses

  • Turn a documentation URL into a searchable collection of its pages.
  • Ask questions about indexed documentation and receive answers grounded in retrieved source material.
  • Choose between embedding-based vector retrieval and a tree-based mode that does not require vector embeddings.
Before you choose

Requirements & limits

  • The vector mode generates embeddings and uses Qdrant; the vectorless mode builds and searches a documentation tree.
  • The crawler recursively visits internal pages up to configured limits and respects robots.txt.
  • The local setup requires several components, including Docker services, a backend API and a background worker.
  • The project describes reuse of existing indexed collections or trees when documentation URLs match.

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 DocChat locally

Prepare the documented local application components for development.

Before you start

  • Node.js (version 20 or later recommended)
  • Docker
  • pnpm
  • The DocChat repository and backend environment values

Steps

  1. Clone the repository and change into its directory.

  2. Copy backend/.env.example to backend/.env and fill in the required variables.

  3. Start the Docker services with docker compose up -d.

  4. Install dependencies with pnpm at the repository root and again in backend/.

  5. From backend/, run the documented Prisma migration and generate commands.

Expected outcome

The documented frontend, API server and background ingestion worker are started as separate local components.

Guide limitations

  • The README points to a separate troubleshooting guide for the full environment-variable descriptions.
  • This setup sequence does not establish that a particular documentation site can be crawled or that a query will succeed.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
18 October 2026
Original website title
avishek0769/DocChat · Official homepage title · retained in its source language
How we review sourcesSuggest a correction