Research & Knowledge Management · Public

MiniRAG

[ACL2026] "MiniRAG: Making RAG Simpler with Small and Open-Sourced Language Models"

Best fitUsers who want source-backed project understanding before installing it.

Check whether this project matches your task before installing it.

What it can doskill, recipe, host_instruction, eval, preflight

Review the portable capability path.

Before continuingVerify in a sandbox

Do not treat a preview pack as a proven local install.

GitHub snapshot2.0k stars

249 forks · 16 contributors

Doramagic.ai Last verification date: 2026-06-25 Verification method: source evidence, semantic profile, public page gate, and static build acceptance.

Official first step Read manual preview Source repository

Publication status · 2026-06-25

What is MiniRAG?

[ACL2026] "MiniRAG: Making RAG Simpler with Small and Open-Sourced Language Models"
Best fit: Users who want source-backed project understanding before installing it.
Not for: Not for users who want to skip sandbox verification or cannot accept configuration, permission, or maintenance overhead.
Capability added to an AI workflow: skill, recipe, host_instruction, eval, preflight
First safe verification step: Verify the smallest path in an isolated environment and keep a rollback path.
Verification state: source, Quick Start, and sandbox install checks are recorded as passed.
Top risk: May increase setup, validation, or first-run risk for the user.
Evidence base: https://github.com/HKUDS/MiniRAG, https://github.com/HKUDS/MiniRAG#readme, Human Manual, Pitfall Log

Quick decision

Use this section to decide whether the project is worth a deeper read.

Best forUsers who want source-backed project understanding before installing it.

Match the project to your task before installing it.

Capabilityskill, recipe, host_instruction, eval, preflight

[ACL2026] "MiniRAG: Making RAG Simpler with Small and Open-Sourced Language Models"

RepositoryHKUDS/MiniRAG

2.0k stars · 249 forks

What it can do

Translate the upstream project into concrete capabilities the user can judge before installing.

MiniRAG Overview & System Architecture

Related topics: Indexing Pipeline & Knowledge Graph Construction, Query & Retrieval Workflow, LLM/Embedding Integrations, API Server & Deployment

Source: https://github.com/HKUDS/MiniRAG / Human Manual

Indexing Pipeline & Knowledge Graph Construction

Related topics: MiniRAG Overview & System Architecture, Query & Retrieval Workflow

Sources: issue [#96](https://github.com/HKUDS/MiniRAG/issues/96), issue [#82](https://github.com/HKUDS/MiniRAG/issues/82), issue [#69](https://github.com/HKUDS/MiniRAG/issues/69), issue [#1](https://github.com/HKUDS/MiniRAG/issues/1), [minirag/api/minirag_server.py:280-340]().

Query & Retrieval Workflow

Related topics: MiniRAG Overview & System Architecture, Indexing Pipeline & Knowledge Graph Construction, LLM/Embedding Integrations, API Server & Deployment

Source: https://github.com/HKUDS/MiniRAG / Human Manual

LLM/Embedding Integrations, API Server & Deployment

Related topics: MiniRAG Overview & System Architecture, Query & Retrieval Workflow

Source: https://github.com/HKUDS/MiniRAG / Human Manual

Doramagic Pitfall Log

Source-linked risks stay visible on the manual page so the preview does not read like a recommendation.

Source: Doramagic discovery, validation, and Project Pack records

Sources: https://github.com/HKUDS/MiniRAG, Human Manual, Project Pack evidence, and downstream validation signals.

Community Discussion Evidence

Project-level external discussion stays visible on the detail page, not only inside the manual.

Stars2.0k stars

Forks249 forks

Contributors16 contributors

Licenseunknown

Community Discussion Evidence

12 source-linked items

Review these external discussions before using MiniRAG with real data or production workflows. They are review inputs, not standalone proof that the project is production-ready.

01
[bug] In hybrid mode, the context is excessively long and fails to be tr
github / github_issue
02
Can MiniRAG load an existing knowledge graph, instead of regenerating it
github / github_issue
03
in the Step1_QA.py file, is it necessary to specify generation parameter
github / github_issue
04
[Performance] MiniRAG underperforms NaiveRAG significantly with Phi-3.5-
github / github_issue
05
speed and time
github / github_issue
06
MiniRAG re-runs entity extraction on existing chunks without cache check
github / github_issue
07
Accuracy is really low
github / github_issue
08
Community source 8
github / github_issue
09
Indicate explicitly minimum or recommended python version
github / github_issue
10
Question: Best practice for evaluating RAG models using the MiniRAG data
github / github_issue
11
Community source 11
github / github_issue
12
get 0 data when indexing
github / github_issue

How to start

Only source-backed commands are shown here. Verify them in an isolated environment first.

Try the prompt first

Test the workflow without installing the upstream project.

preview

Read the Human Manual

Understand inputs, outputs, limits, and failure modes.

manual

Take context to your AI host

Use the compiled assets in your preferred AI environment.

context

Run sandbox verification

Confirm install commands and rollback before using a primary environment.

verify

pip install minirag-hku

Official start command · https://github.com/HKUDS/MiniRAG#readme · verified: yes

Human Manual

The English page must expose the real manual, not a short placeholder.

8+ sections · Human Manual

MiniRAG Manual

[ACL2026] "MiniRAG: Making RAG Simpler with Small and Open-Sourced Language Models"

Open the full manual

https://github.com/HKUDS/MiniRAG Project Manual
Table of Contents
MiniRAG Overview & System Architecture
Related Pages
1. Purpose and Scope
2. System Architecture
3. Installation and Quick Start
Source (recommended for development)

MiniRAG Overview & System Architecture

Related topics: Indexing Pipeline & Knowledge Graph Construction, Query & Retrieval Workflow, LLM/Embedding Integrations, API Server & Deployment

Source: https://github.com/HKUDS/MiniRAG / Human Manual

Indexing Pipeline & Knowledge Graph Construction

Related topics: MiniRAG Overview & System Architecture, Query & Retrieval Workflow

Sources: issue [#96](https://github.com/HKUDS/MiniRAG/issues/96), issue [#82](https://github.com/HKUDS/MiniRAG/issues/82), issue [#69](https://github.com/HKUDS/MiniRAG/issues/69), issue [#1](https://github.com/HKUDS/MiniRAG/issues/1), [minirag/api/minirag_server.py:280-340]().

Query & Retrieval Workflow

Related topics: MiniRAG Overview & System Architecture, Indexing Pipeline & Knowledge Graph Construction, LLM/Embedding Integrations, API Server & Deployment

Source: https://github.com/HKUDS/MiniRAG / Human Manual

LLM/Embedding Integrations, API Server & Deployment

Related topics: MiniRAG Overview & System Architecture, Query & Retrieval Workflow

Source: https://github.com/HKUDS/MiniRAG / Human Manual

Doramagic Pitfall Log

Source-linked risks stay visible on the manual page so the preview does not read like a recommendation.

Source: Doramagic discovery, validation, and Project Pack records

AI Context Pack and portable assets

After deciding to continue, take the project context into your own AI host.

Complete pack plus user-owned assets

These files are planning and verification assets for Claude Code, Codex, Gemini, Cursor, ChatGPT, and other AI hosts.

Download complete pack Read Human Manual

BundleComplete Project Pack AssetAI Context Pack AssetBoundary & Risk Card AssetHuman Manual AssetPitfall Log AssetPrompt Preview AssetQuick Start EvidenceREPO_INSPECTION.json

Preflight checks

Treat this page as a planning asset, not proof that your local environment is ready.

The manual is generated from source-linked project files and Doramagic validation signals.
Community evidence warnings stay visible instead of being converted into marketing claims.
This English page is indexable because the locale quality gate passed and explicit English index approval is enabled.
Use the upstream repository as the final authority for installation commands, license, and version-specific behavior.