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

Go Rag

Go Rag is a self-hosted RAG knowledge-base application with a web interface for ingesting documents and web pages, editing document chunks, searching collections and chatting over selected knowledge bases.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Go Rag — 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 Go Rag when you want to self-host a document-grounded search and chat workflow and manage the knowledge-base content, chunks and retrieval configuration yourself.

Who it is for

  • Teams building searchable knowledge bases from their own documents or web pages.
  • Developers who want to configure and run a RAG application using Docker Compose or its source code.
  • Users who need chunk-level editing or multiple retrieval methods for knowledge-base search.

Documented uses

  • Create separate knowledge bases for different bodies of material.
  • Parse Markdown, PDF and HTML files or web pages into searchable content.
  • Split long documents into chunks and edit those chunks.
  • Retrieve documents using content vectors and generated QA-pair vectors, with reciprocal-rank fusion and reranking.
  • Use chat to ask questions over selected knowledge bases.
Before you choose

Requirements & limits

The project is public and lists an Apache-2.0 license. The repository documents Docker Compose and source-based startup; its source-based instructions call for MySQL and Elasticsearch, and the project lists Qdrant as another vector-data storage option.

  • You need to provide and configure embedding and chat services, plus the relevant storage dependencies.
  • Elasticsearch mode includes BM25 keyword retrieval in addition to vector-based retrieval.
  • You.com web search is optional and requires a YDC_API_KEY; the README says other application functions are unaffected when it is not configured.
  • The README describes a separate companion GUI, wachat, for macOS and Windows; that is distinct from the Go Rag web application.

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 Go Rag with Docker Compose

Prepare the documented configuration and launch the web application with Docker Compose.

Before you start

  • A cloned Go Rag repository.
  • Configuration values for embedding, chat, MySQL and Elasticsearch.

Steps

  1. From the repository directory, copy server/manifest/config/config_demo.yaml to server/manifest/config/config.yaml.

  2. Edit the configuration for the embedding, chat, MySQL and Elasticsearch services you intend to use.

  3. Run the command below.

    Documented command
    docker compose up -d

  4. Open http://localhost:8000 in a browser.

Expected outcome

The README directs users to the Go Rag web interface at localhost:8000 after startup.

Guide limitations

  • The guide documents startup, not the ingestion or retrieval of a particular dataset.
  • The required configuration values and dependencies must be supplied for the selected setup.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
wangle201210/go-rag · Official homepage title · retained in its source language
How we review sourcesSuggest a correction