Star200+

Workflow recipe

RAG knowledge-base workflow

A workflow for document-heavy agents that ingest files, create searchable knowledge, retrieve relevant context, and answer with grounded sources.

Teams building support, research, internal documentation, or compliance assistants.

Compare recommended skillsBrowse matching skills

Expected outcome

  • Ingest documents
  • Chunk and index content
  • Retrieve context
  • Cite sources in answers

Workflow map

Follow this sequence

01

Ingest

Collect documents, pages, or notes and preserve source metadata.

02

Index

Chunk content and store embeddings in a retrievable format.

03

Retrieve

Fetch only the relevant context for each user question.

04

Answer

Generate grounded responses with citations and confidence checks.

Suggested capabilities

Choose skills for each step

Ranked by relevance to this workflow, quality, GitHub adoption, and maintenance freshness. This is a decision guide, not a single install command.

#1WeKnoraQuality · 98

Repository description

Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

16K starsUnknown licenserag-knowledge
Compare
$ npx skills add Tencent/WeKnora
#2PageIndexQuality · 100

Repository description

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

34K starsMITrag-knowledge
Compare
$ npx skills add VectifyAI/PageIndex
#3QdrantQuality · 100

Repository description

Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

33K starsApache-2.0rag-knowledge
Compare
$ npx skills add qdrant/qdrant
#4RAG TechniquesQuality · 100

Repository description

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.

28K starsUnknown licenserag-knowledge
Compare
$ npx skills add NirDiamant/RAG_Techniques
#5WeaviateQuality · 100

Repository description

Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database​.

17K starsBSD-3-Clauserag-knowledge
Compare
$ npx skills add weaviate/weaviate
#6DocsGPTQuality · 100

Repository description

Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.

18K starsMITrag-knowledge
Compare
$ npx skills add arc53/DocsGPT
#7TxtaiQuality · 100

Repository description

💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows

13K starsApache-2.0rag-knowledge
Compare
$ npx skills add neuml/txtai
#8LancedbQuality · 100

Repository description

Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.

11K starsApache-2.0rag-knowledge
Compare
$ npx skills add lancedb/lancedb

Good fit

  • - Internal docs assistants
  • - Research archives
  • - Support knowledge bases
  • - Policy lookup

Not the right route when

  • - The corpus changes every few seconds
  • - You cannot expose source documents to the agent runtime

Need a runnable bundle?

Skill packs include an install order, audit links, and a machine-readable Agent plan.

Browse packs