🚀 LightRAG: Simple and Fast Retrieval-Augmented Generation

🎉 News

• [2026.07]🎯[New Feature]: Add Smart Heading recognition feature for word documents.
• [2026.05]🎯[New Feature]: Merge RagAnything into LightRAG🎉. Multimodal content parsing and extraction via MinerU / Docling services.
• [2026.05]🎯[New Feature]: Introducing four selectable text chunking strategies: Fix, Recursive, Vector, and Paragraph.
• [2026.05]🎯[New Feature]: Role-specific LLM configuration support, 4 distinct roles: EXTRACT, QUERY, KEYWORDS, and VLM, with independent LLM settings.
• [2026.03]🎯[New Feature]: Integrated OpenSearch as a unified storage backend, providing comprehensive support for all four LightRAG storage.
• [2026.03]🎯[New Feature]: Introduced a setup wizard. Support for local deployment of embedding, reranking, and storage backends via Docker.
• [2025.11]🎯[New Feature]: Integrated RAGAS for Evaluation and Langfuse for Tracing. Updated the API to return retrieved contexts alongside query results to support context precision metrics.
• [2025.10]🎯[Scalability Enhancement]: Eliminated processing bottlenecks to support Large-Scale Datasets Efficiently.
• [2025.09]🎯[New Feature] Enhances knowledge graph extraction accuracy for Open-Sourced LLMs such as Qwen3-30B-A3B.
• [2025.08]🎯[New Feature] Reranker is now supported, significantly boosting performance for mixed queries (set as default query mode).
• [2025.08]🎯[New Feature] Added Document Deletion with automatic KG regeneration to ensure optimal query performance.
• [2025.06]🎯[New Release] Our team has released RAG-Anything — an All-in-One Multimodal RAG system for seamless processing of text, images, tables, and equations.
• [2025.06]🎯[New Feature] LightRAG now supports comprehensive multimodal data handling through RAG-Anything integration, enabling seamless document parsing and RAG capabilities across diverse formats including PDFs, images, Office documents, tables, and formulas. Please refer to the new multimodal section for details.
• [2025.03]🎯[New Feature] LightRAG now supports citation functionality, enabling proper source attribution and enhanced document traceability.
• [2025.02]🎯[New Feature] You can now use MongoDB as an all-in-one storage solution for unified data management.
• [2025.02]🎯[New Release] Our team has released VideoRAG-a RAG system for understanding extremely long-context videos
• [2025.01]🎯[New Release] Our team has released MiniRAG making RAG simpler with small models.
• [2025.01]🎯You can now use PostgreSQL as an all-in-one storage solution for data management.
• [2024.11]🎯[New Resource] A comprehensive guide to LightRAG is now available on LearnOpenCV. — explore in-depth tutorials and best practices. Many thanks to the blog author for this excellent contribution!
• [2024.11]🎯[New Feature] Introducing the LightRAG WebUI — an interface that allows you to insert, query, and visualize LightRAG knowledge through an intuitive web-based dashboard.
• [2024.11]🎯[New Feature] You can now use Neo4J for Storage-enabling graph database support.
• [2024.10]🎯[New Feature] We’ve added a link to a LightRAG Introduction Video. — a walkthrough of LightRAG’s capabilities. Thanks to the author for this excellent contribution!
• [2024.10]🎯[New Channel] We have created a Discord channel!💬 Welcome to join our community for sharing, discussions, and collaboration! 🎉🎉

Installation

💡 Using uv for Package Management: This project uses uv for fast and reliable Python package management. Install uv first: curl -LsSf https://astral.sh/uv/install.sh | sh (Unix/macOS) or powershell -c "irm https://astral.sh/uv/install.ps1 | iex" (Windows)

Note: You can also use pip if you prefer, but uv is recommended for better performance and more reliable dependency management.

📦 Offline Deployment: For offline or air-gapped environments, see the Offline Deployment Guide for instructions on pre-installing all dependencies and cache files.

Install LightRAG Server

• Install from PyPI

### Install LightRAG Server as tool using uv (recommended)
uv tool install "lightrag-hku[api]"

### Or using pip
# python -m venv .venv
# source .venv/bin/activate  # Windows: .venv\Scripts\activate
# pip install "lightrag-hku[api]"

# Setup env file
# Obtain the env.example file by downloading it from the GitHub repository root
# or by copying it from a local source checkout.
cp env.example .env  # Update the .env with your LLM and embedding configurations
# Launch the server. It binds to all interfaces (0.0.0.0) by default.
# SECURITY: before exposing it on a network, configure authentication in .env
# (LIGHTRAG_API_KEY, or AUTH_ACCOUNTS together with TOKEN_SECRET), or bind to
# 127.0.0.1 for local-only access; without auth every endpoint is public.
# Note: the Ollama-compatible /api/* routes stay open by default for client
# compatibility; set WHITELIST_PATHS=/health to require auth on them too.
lightrag-server

• Installation from Source

git clone https://github.com/HKUDS/LightRAG.git
cd LightRAG

# Bootstrap the development environment (recommended)
make dev
source .venv/bin/activate  # Activate the virtual environment (Linux/macOS)
# Or on Windows: .venv\Scripts\activate

# make dev installs the test toolchain plus the full offline stack
# (API, storage backends, and provider integrations), then builds the frontend.
# Run make env-base or copy env.example to .env before starting the server.

# Equivalent manual steps with uv
# Note: uv sync automatically creates a virtual environment in .venv/
uv sync --extra test --extra offline
source .venv/bin/activate  # Activate the virtual environment (Linux/macOS)
# Or on Windows: .venv\Scripts\activate

### Or using pip with virtual environment
# python -m venv .venv
# source .venv/bin/activate  # Windows: .venv\Scripts\activate
# pip install -e ".[test,offline]"

# Build front-end artifacts
cd lightrag_webui
bun install --frozen-lockfile
bun run build
cd ..

# setup env file
make env-base  # Or: cp env.example .env and update it manually
# Launch API-WebUI server
lightrag-server

• Launching the LightRAG Server with Docker Compose

git clone https://github.com/HKUDS/LightRAG.git
cd LightRAG
cp env.example .env  # Update the .env with your LLM and embedding configurations
# modify LLM and Embedding settings in .env
docker compose up

Historical versions of LightRAG docker images can be found here: LightRAG Docker Images

Official GHCR images published by GitHub Actions are signed with Sigstore Cosign using GitHub OIDC. See docs/DockerDeployment.md for verification commands.

On Apple Silicon (macOS 26) without Docker Desktop, you can run the same Postgres/Neo4j/Milvus storage stack on Apple’s native container runtime — see docs/AppleContainerSetup.md.

Create .env File With Setup Tool

Instead of editing env.example by hand, use the interactive setup wizard to generate a configured .env and, when needed, docker-compose.final.yml:

make env-base           # Required first step: LLM, embedding, reranker
make env-storage        # Optional: storage backends and database services
make env-server         # Optional: server port, auth, and SSL
make env-base-rewrite   # Optional: force-regenerate wizard-managed compose services
make env-storage-rewrite # Optional: force-regenerate wizard-managed compose services
make env-security-check # Optional: audit the current .env for security risks

For full description of every target see docs/InteractiveSetup.md.

Optional: spaCy Models for docx smart_heading

The native docx parser’s opt-in smart_heading engine parameter uses spaCy for sentence/NER heuristics. The spaCy runtime is already included in the api extra — only the two pinned language models (zh_core_web_sm / en_core_web_sm 3.8.0, GitHub release wheels not published on PyPI) need one extra step:

lightrag-download-cache --spacy --spacy-install

Enable smart_heading per file/rule (e.g. LIGHTRAG_PARSER=docx:native(smart_heading=true)), or globally in .env:

# .docx files routed to the native engine get smart_heading by default;
# opt a file back out with an explicit native(smart_heading=false) rule/hint.
DOCX_SMART_HEADING=true

When the global switch is on (or a LIGHTRAG_PARSER rule carries native(smart_heading=true)), the server verifies the models at startup and fails fast with install guidance if they are missing. Deployments that never enable smart_heading need no models. The main Docker image ships the models pre-installed (the lite image does not); for air-gapped hosts see the Offline Deployment Guide.

About LightRAG

A Lightweight, Graph-Based RAG Framework

LightRAG is a lightweight knowledge-graph RAG framework and an efficient alternative to Microsoft GraphRAG. It adopts a dual-layer architecture to manage both knowledge graphs (KGs) and vector embeddings, effectively bridging the gap between traditional vector-based RAG and graph-based RAG approaches. Designed for high scalability, LightRAG addresses key challenges in large-scale graph indexing and retrieval, including heavy computational overhead, slow response times, and the high cost of incremental updates. While supporting large datasets, LightRAG can still deliver exceptionally high RAG quality, even when paired with a 30B open-source large language model (LLM).

Features & Advantages

• Deep Contextual Understanding: Through graph-structured indexing, LightRAG captures complex semantic dependencies between entities, overcoming the fragmented context limitations typical of traditional chunk-based retrieval methods. Its generation quality and context awareness are particularly outstanding in vertical domains (e.g., legal, financial) that require global comprehension or logical reasoning.
• Exceptional Comprehensiveness & Diversity: LightRAG’s dual-level retrieval mechanism allows it to integrate detailed facts and abstract concepts concurrently. This enables the system to achieve remarkable performance in query result comprehensiveness and diversity, making it highly effective at handling complex, cross-document queries.
• Extreme Retrieval Efficiency & Low Cost: LightRAG does not rely on inefficient community reports or multi-hop reasoning for complex queries. This drastically reduces the number of LLM calls required during both the indexing and querying phases, significantly lowering response latency and LLM computational costs.
• Incremental Updates & Selective Deletion: LightRAG addresses the challenges of incrementally updating and selectively deleting content from graph-based knowledge bases, keeping them current in dynamic data environments. When a document is deleted, the system can use the LLM cache created during indexing to quickly rebuild the affected entities and relationships, substantially improving update efficiency.
• Multiple Document Parsing Engines: LightRAG’s document processing pipeline supports MinerU, Docling, and Native and can be extended with third-party parsers. LightRAG’s Native engine efficiently parses images, tables, and formulas in Word and Markdown documents, making it especially suitable for documents rich in multimodal content. The Native engine also automatically detects and corrects section headings in Word documents, improving content extraction from documents with inconsistent outlines and laying the foundation for section-aware text chunking.
• Multiple Text Chunking Strategies: LightRAG supports four text chunking strategies: Fixed-length (F), Recursive character (R), Vector semantic (V), and Paragraph semantic (P). The LightRAG-native Paragraph semantic (P) strategy aligns chunk boundaries with the document’s native semantic boundaries—headings, paragraphs, and tables—as closely as possible. This reduces problems such as mismatched headings and content or missing header rows when long tables are split.
• Multiple Storage Backends: LightRAG’s default KV, vector, and graph stores use in-memory databases with local file persistence, making them well suited for quickly evaluating the project. LightRAG also supports a wide range of commonly used storage backends for production deployments with large datasets.

Multimodal Capability Upgrades

Traditional RAG systems lack an effective way to process multimodal content such as images, formulas, and tables in documents. Starting with v1.5, LightRAG seamlessly integrates multimodal processing into its document pipeline and query flow. Through the knowledge graph, LightRAG connects multimodal content with the body text and can use that information when answering queries to produce more accurate and reliable responses. This capability can substantially improve RAG quality for documents rich in multimodal content, such as operation manuals and academic papers.

LightRAG API Server

The LightRAG server offers not only a web-based UI for exploring LightRAG functionalities but also a comprehensive REST API. For more information about the LightRAG server, please refer to LightRAG Server.

Key Configuration Guide

Selecting LLM Models

LightRAG requires LLM/VLMs of four different roles during its workflow. You should configure models with different capabilities and speeds for different roles to strike a balance between performance and processing speed. LightRAG has higher capability requirements for Large Language Models (LLMs) than traditional RAG because it requires LLMs to perform complex entity-relation extraction tasks from documents. During the query phase, the LLM needs to process a large volume of retrieved information, including entities, relationships, and text chunks. This requires the model to have the capability of generating high-quality responses in long, noisy contexts.

Recommended models by role:

• Extraction LLM (EXTRACT): Entity-relation extraction runs on every text chunk, so a fast, cost-effective mainstream model is enough — a non-thinking model (reasoning/thinking mode disabled) is strongly recommended to avoid slow, expensive extraction. Good hosted options include GPT-5.6-luna, Claude Haiku, or Gemini-mini internationally, and DeepSeek-V4-lite or Kimi in China. For local deployment, Qwen3-30B-A3B-Instruct is a reasonable minimum.
• Query LLM (QUERY): This model writes the final answer from long, noisy retrieved context, so it should be stronger than the extraction model in order to maximize answer quality. Choose a higher-tier model from the same families; a thinking-capable model is fine here.
• Keyword LLM (KEYWORD): A lightweight, latency-sensitive step that must use a non-thinking model to keep query latency low; a fast model comparable to the extraction one is sufficient.
• VLM (VLM): Any mainstream multimodal model with image-input support works. For local deployment, consider Qwen3.6-35B-A3B.

Within your acceptable latency and cost budget, prefer the highest-scoring model available (based on public benchmarks/leaderboards). For detailed model configurations, please refer to RoleSpecificLLMConfiguration.md

Selecting Query Modes

LightRAG supports five query modes:

• local: Focuses on precise matching of local contexts and specific entities. It retrieves candidate entities and their directly associated attributes from the knowledge graph. This mode is suitable for Q&A targeting specific objects, concrete concepts, or detailed facts, providing highly relevant and detailed local context support.
• global: Focuses on macro themes, cross-document reasoning, and deep relationships between entities. It retrieves relationship chains covering broad themes and concepts. This mode is suitable for queries that require summarization across multiple contexts, trend analysis, or understanding complex semantic dependencies.
• hybrid: Merges the retrieval results of both local and global modes. It performs comprehensive reasoning and generation by simultaneously recalling specific entities and global relationship contexts.
• naive: Traditional RAG retrieval based on text chunks. It does not use a knowledge graph and relies directly on vector similarity to retrieve from the original text chunks.
• mix: Fully-featured mode that merges retrieval results from local, global, and naive modes to provide the most comprehensive and rich retrieval results.

The default query mode for LightRAG is mix. Using mix mode generally yields the most ideal query results. The mix mode takes slightly longer than naive, while other query modes are roughly comparable in latency.

Embedding Models

When choosing an Embedding model, pay attention to its multilingual support capabilities. Since LightRAG’s retrieval quality has limited dependency on the Embedding model, it is recommended to choose low-dimensional and fast models. Any mainstream, up-to-date embedding model works well; for local deployment, BAAI/bge-m3 is a solid choice. We highly recommend deploying the Embedding model locally to achieve the best performance.

Important Note: The Embedding model must be determined before document indexing, and the same model must be used in the query phase. Once selected, embedding models generally cannot be changed. If changed, you will need to re-embed all text chunks, entities, and relationships. LightRAG does not currently provide a re-embedding tool. Some storage backends (e.g., PostgreSQL) require the vector dimension to be defined when creating tables for the first time, so changing the Embedding model requires deleting vector-related tables so LightRAG can recreate them.

Enabling Reranking

Enabling the Rerank option during the query phase can significantly improve query quality. However, enabling Rerank typically introduces a 1–2 second delay. To minimize latency, it is highly recommended to deploy the Rerank model locally. Any mainstream, up-to-date reranker works; for local deployment, BAAI/bge-reranker-v2-m3 is recommended. For configuration details, please refer to the .env.example file. Unlike Embedding models, the Rerank model can be changed at any time during the query phase.

Document Processing Pipeline Configuration

The default pipeline configuration in LightRAG does not allow the system to perform at its best. The quality of document parsing greatly impacts document indexing and querying. Therefore, we recommend configuring the pipeline to enable the MinerU parsing engine and activating the pipeline’s image analysis features. Suggested configuration:

LIGHTRAG_PARSER=*:native-iteP,*:mineru-iteP,*:legacy-R

VLM_PROCESS_ENABLE=true
VLM_LLM_MODEL=<your_vlm_model_name>

Since the cloud-based MinerU service has limitations on usage, file size, and page count, it is recommended to use a locally deployed MinerU. For details on configuring the file processing pipeline, please refer to FileProcessingPipeline.md

Concurrency Optimization for File Processing

For large-scale document processing, you need to improve concurrency. Key environment variables related to concurrent file processing include:

• MAX_ASYNC_LLM/EXTRACT_ASYNC_LLM: Controls the maximum concurrency for LLM models.
• MAX_PARALLEL_INSERT: Controls the maximum number of files processed in parallel. Processing of text, tables, formulas, and images within a single file will also occur concurrently. MAX_PARALLEL_INSERT should ideally be set to about 1/3 of MAX_ASYNC_LLM.
• MAX_PARALLEL_PARSE_MINERU: Controls the number of parallel files processed for MinerU parsing.
• MAX_PARALLEL_PARSE_DOCLING: Controls the number of parallel files processed for Docling parsing.
• EMBEDDING_FUNC_MAX_ASYNC: Controls the maximum concurrency for embedding models.
• EMBEDDING_BATCH_NUM: Controls the number of texts included in each embedding model request (how many embeddings per batch). Increasing this number can significantly reduce the number of API calls to the embedding model and speed up data persistence in the embedding storage.

# Sample Configuration
MAX_ASYNC_LLM=8
MAX_PARALLEL_INSERT=3
EMBEDDING_FUNC_MAX_ASYNC=16
EMBEDDING_BATCH_NUM=32

Selecting Backend Storage

LightRAG requires four types of backend storage:

• KV_STORAGE: Used to save LLM response caches, text chunking results, entity-relation extraction results, etc.
• VECTOR_STORAGE: Used to store vector information for text chunks, entities, and relationships.
• GRAPH_STORAGE: Used to save the knowledge graph.
• DOC_STATUS_STORAGE: Used to store the document list.

By default, LightRAG’s storage backends are file-persisted, in-memory databases. These default storages are intended only for development and debugging, and are not suitable for production. In a production environment, if you prefer a single backend to handle all four storage types, you can choose PostgreSQL, MongoDB, or OpenSearch. Alternatively, you can select specialized databases for vector or graph storage, such as using Milvus or Qdrant for vector storage, and Neo4j or Memgraph for graph storage.

Other Important Configurations for Document Processing

During the document insertion stage, you may also want to adjust the following environment variables based on your needs:

• SUMMARY_LANGUAGE: Controls the language used by the LLM when outputting entity-relation names and summaries, e.g., Chinese, English.
• ENTITY_EXTRACTION_USE_JSON: Controls whether the LLM outputs entity-relation extractions in JSON format. Using JSON format typically yields more stable results, but it consumes more tokens and can be slightly slower.
• ENABLE_CONTENT_HEADINGS: Controls whether the section heading information of a text chunk is sent to the LLM during the query stage (enabled by default, providing more context for the LLM).
• FORCE_LLM_SUMMARY_ON_MERGE / MAX_SOURCE_IDS_PER_RELATION: Controls the maximum number of text chunks an entity/relation can be associated with.
• SOURCE_IDS_LIMIT_METHOD: Controls whether to keep updating the entity/relation description once an entity/relation exceeds its associated text chunk limit (by default it stops updating, because at that point the entity-relation description is already rich enough and further updates add little value; skipping updates can greatly speed up knowledge base construction).
• DEFAULT_MAX_FILE_PATHS: Controls the maximum number of source files an entity/relation can be associated with; once this limit is exceeded, new file names are no longer written to the vector storage.

Resolving LLM Timeouts During Entity-Relation Extraction

LLM timeouts during entity-relation extraction usually trace back to one of three causes. Identify the cause, then apply the matching remedy (the parameters can be combined):

• The model is slow. A model running below ~50 tokens/second may be unable to finish a chunk that contains many entities and relations before the request times out. Increase the timeout via *_LLM_TIMEOUT — either the global LLM_TIMEOUT or the role-specific EXTRACT_LLM_TIMEOUT for the extraction phase. Note that the effective execution timeout is twice the configured value, so EXTRACT_LLM_TIMEOUT=300 allows up to 600 seconds.
• The chunk produces too many entities and relations. Reference/bibliography chunks, for example, can make the model emit an enormous number of records that cannot complete in time. Cap the output length with OPENAI_LLM_MAX_TOKENS or OPENAI_LLM_MAX_COMPLETION_TOKENS (the correct parameter name depends on the LLM provider — see env.example). A useful sizing rule is max_output_tokens < LLM_TIMEOUT × tokens_per_second (e.g., 9000 < 240s × 50 tps).
• The model gets stuck in an output loop. Some models (locally deployed Qwen models in particular) occasionally fall into an endless-output loop on certain text. When this is intermittent, simply re-processing the document once usually resolves it.
• References specifically (P chunking strategy). When using the paragraph-semantic (P) chunking strategy (e.g., LIGHTRAG_PARSER=...-iteP), set CHUNK_P_DROP_REFERENCES=true to automatically drop matching reference blocks before chunking. This prevents references from generating a flood of low-value entities and relations, a common source of timeouts. It can also be enabled per file via the filename hint paper.[-P(drop_rf=true)].pdf; related detection knobs (CHUNK_P_REFERENCES_TAIL_N, CHUNK_P_REFERENCES_HEADINGS) are documented in env.example.

Other Important Configurations for Document Querying

During the document query stage, you may also want to adjust the following environment variables based on your needs:

• MAX_ENTITY_TOKENS / MAX_RELATION_TOKENS / MAX_TOTAL_TOKENS: Controls the token length of the retrieved content sent to the LLM context. The retrieved content consists of three parts: entities, relations, and text chunks. The lengths of entities and relations can be controlled independently, while the text chunk length is determined by subtracting the entity and relation lengths from the total length.
• ENABLE_CONTENT_HEADINGS: Controls whether the section heading where a text chunk resides is sent to the LLM; enabled by default, providing richer context for the LLM and improving answer quality.
• ENABLE_LLM_CACHE: Whether to cache query results. Enabled by default; identical query questions, query modes, and LLM model parameters will return the same result.

Using LightRAG As SDK

⚠️ For integration into your project, we strongly recommend using the REST API provided by the LightRAG Server. The LightRAG SDK is primarily intended for embedded applications or academic research and evaluation purposes.

Install LightRAG SDK

• Install from source code

cd LightRAG
# 注意: uv sync 会自动在 .venv/ 目录创建虚拟环境
uv sync
source .venv/bin/activate  # 激活虚拟环境 (Linux/macOS)
# Windows 系统: .venv\Scripts\activate

# 或: pip install -e .

• Install from PyPI

uv pip install lightrag-hku
# 或: pip install lightrag-hku

LightRAG SDK Sample Code

To get started with LightRAG core, refer to the sample codes available in the examples folder. Additionally, a video demo demonstration is provided to guide you through the local setup process. If you already possess an OpenAI API key, you can run the demo right away:

### you should run the demo code with project folder
cd LightRAG
### provide your API-KEY for OpenAI
export OPENAI_API_KEY="sk-...your_opeai_key..."
### download the demo document of "A Christmas Carol" by Charles Dickens
curl https://raw.githubusercontent.com/gusye1234/nano-graphrag/main/tests/mock_data.txt > ./book.txt
### run the demo code
python examples/lightrag_openai_demo.py

For a streaming response implementation example, please see examples/lightrag_openai_compatible_demo.py. Prior to execution, ensure you modify the sample code’s LLM and embedding configurations accordingly.

Note 1: When running the demo program, please be aware that different test scripts may use different embedding models. If you switch to a different embedding model, you must clear the data directory (./dickens); otherwise, the program may encounter errors. If you wish to retain the LLM cache, you can preserve the kv_store_llm_response_cache.json file while clearing the data directory.

Note 2: Only lightrag_openai_demo.py and lightrag_openai_compatible_demo.py are officially supported sample codes. Other sample files are community contributions that haven’t undergone full testing and optimization.

Notes on SDK Usage

For detailed instructions on using the SDK, please refer to docs/ProgramingWithCore.md. Some LightRAG features are not exposed via the REST API and are accessible only through the SDK. These features are typically experimental and may not be compatible with future versions.

Replicating Findings in the Paper

LightRAG consistently outperforms NaiveRAG, RQ-RAG, HyDE, and GraphRAG across agriculture, computer science, legal, and mixed domains. For the full evaluation methodology, prompts, and reproduce steps, see docs/Reproduce.md.

Overall Performance Table

📚 Documentation and Tools

Reference Documentation (docs/)

Entries marked 🇨🇳 also ship a Chinese translation as *-zh.md in the same folder.

Deployment and Setup

Server and API

Document Processing

Models and Storage

SDK and Development

Maintenance Tools (lightrag/tools/)

Storage-facing tools read .env and environment variables exactly like the server does, so run them from the project root with the same configuration. Several of them rewrite storage in place — check the linked guide for whether the server (and any other writer) has to be stopped first; rebuild_vdb requires it.

rebuild_vdb.py — lightrag-rebuild-vdb — README_REBUILD_VDB.md

Drops and rebuilds every vector storage from its authoritative source (graph nodes/edges and the text_chunks KV store). The recovery path after a failed vector write, and after changing the embedding model or dimension. Also offers a read-only consistency check.

clean_llm_query_cache.py — lightrag-clean-llmqc — README_CLEAN_LLM_QUERY_CACHE.md

Deletes query-mode LLM cache entries (mix:*, hybrid:*, local:*, global:*, naive:*) while preserving the expensive extraction cache.

migrate_llm_cache.py — python -m lightrag.tools.migrate_llm_cache — README_MIGRATE_LLM_CACHE.md

Migrates default-mode caches (extraction, summary, multimodal analysis) between KV storage backends, preserving workspace isolation.

kg_integrity_repair.py — python -m lightrag.tools.kg_integrity_repair [--apply] — README_KG_INTEGRITY_REPAIR.md

Audits the whole graph for contributions missing from the full_entities / full_relations recovery anchors, reports irrecoverable orphans, and optionally repairs the anchors so delete/retry can discover them again.

source_conflict_repair.py — python -m lightrag.tools.source_conflict_repair list / ... repair — README_SOURCE_CONFLICT_REPAIR.md

Lists documents that claim the same canonical source key, and demotes the candidates the operator did not choose to duplicates. It never picks a winner on its own and never deletes content.

download_cache.py — lightrag-download-cache [--spacy --spacy-install] — OfflineDeployment.md

Pre-downloads the tiktoken encodings and the pinned spaCy models required for offline deployment and the docx smart_heading engine parameter.

hash_password.py — lightrag-hash-password [--username USER] — LightRAG-API-Server.md

Generates a bcrypt value ready to paste into AUTH_ACCOUNTS.

check_initialization.py — python -m lightrag.tools.check_initialization --demo — ProgramingWithCore.md

SDK diagnostic: verifies that a LightRAG instance is fully initialized, catching the common “forgot await rag.initialize_storages()“ mistake.

🔗 Related Projects

Ecosystem & Extensions

🤝 Contribution

📖 Citation

@article{guo2024lightrag,
title={LightRAG: Simple and Fast Retrieval-Augmented Generation},
author={Zirui Guo and Lianghao Xia and Yanhua Yu and Tu Ao and Chao Huang},
year={2024},
eprint={2410.05779},
archivePrefix={arXiv},
primaryClass={cs.IR}
}