2255b91210
Introduces the LightRAG Retrieval-Augmented Generation framework as an Apolo app, including input/output schemas, types, and processors. Adds Helm chart value processing, environment and persistence configurations, and output service discovery for deployment. Includes scripts for generating type schemas and testing support, along with CI and linting setup tailored for the new app. Provides a documentation loader script to ingest markdown files into LightRAG with flexible referencing modes. Relates to MLO-469
55 lines
2.1 KiB
YAML
55 lines
2.1 KiB
YAML
- app_type: lightrag
|
|
name: lightrag
|
|
title: LightRAG
|
|
install_type: workflow
|
|
helm_path: k8s-deploy/lightrag
|
|
app_package_name: apolo_apps_lightrag
|
|
inputs:
|
|
schema_path: .apolo/src/apolo_apps_lightrag/schemas/LightRAGAppInputs.json
|
|
types_name: LightRAGAppInputs
|
|
processor: LightRAGInputsProcessor
|
|
image: ghcr.io/neuro-inc/app-lightrag
|
|
outputs:
|
|
schema_path: .apolo/src/apolo_apps_lightrag/schemas/LightRAGAppOutputs.json
|
|
types_name: LightRAGAppOutputs
|
|
processor: LightRAGOutputsProcessor
|
|
image: ghcr.io/neuro-inc/app-lightrag
|
|
short_description: Advanced RAG framework with graph-enhanced retrieval capabilities
|
|
description: |
|
|
LightRAG is a simple and fast Retrieval-Augmented Generation (RAG) system that incorporates
|
|
graph structure into text indexing and retrieval processes. Unlike traditional RAG approaches,
|
|
LightRAG utilizes both low-level and high-level knowledge discovery to enhance text retrieval.
|
|
It supports both naive and local search methods, making it suitable for comprehensive
|
|
question-answering tasks. The system includes a user-friendly web interface for document
|
|
management and querying, with built-in support for various LLM providers and embedding models.
|
|
pub_date: "2025-06-25T00:00:00+00:00"
|
|
logo: https://storage.googleapis.com/development-421920-assets/app-logos/lightrag-logo.png
|
|
tags:
|
|
- "RAG"
|
|
- "LightRAG"
|
|
- "Knowledge Graph"
|
|
- "Vector Search"
|
|
- "Document Processing"
|
|
- "LLM"
|
|
- "Embeddings"
|
|
- "PostgreSQL"
|
|
- "Graph"
|
|
- "AI"
|
|
- "NLP"
|
|
assets:
|
|
- type: image
|
|
url: https://storage.googleapis.com/development-421920-assets/app-logos/lightrag-banner.png
|
|
- type: video
|
|
url: https://www.youtube.com/watch?v=oageL-1I0GE
|
|
- type: pdf
|
|
url: https://arxiv.org/abs/2410.05779
|
|
urls:
|
|
- name: LightRAG GitHub Repository
|
|
type: documentation
|
|
url: https://github.com/HKUDS/LightRAG
|
|
- name: LightRAG DeepWiki Documentation
|
|
type: documentation
|
|
url: https://deepwiki.com/HKUDS/LightRAG
|
|
- name: LightRAG Official Repository
|
|
type: external
|
|
url: https://github.com/HKUDS/LightRAG
|