The RAG stack
Retrieval-augmented generation grounds an LLM in your own data. A production RAG pipeline is four layers: ingestion, a vector store, orchestration, and evaluation.
GraphCanon updated 2d · 104 views this month
Ingestion & retrieval - parse, chunk, and load documents into a retrievable form.
When not to use: Skip a heavy ingestion framework when your corpus is small and static; a script plus the embedding API is enough.
generative-ai-for-beginners
microsoft/generative-ai-for-beginners
21 Lessons for Getting Started with Generative AI
graphify
Graphify-Labs/graphify
Turn any code or documentation into a queryable knowledge graph
awesome-llm-apps
Shubhamsaboo/awesome-llm-apps
Over 100 runnable AI Agent and RAG apps to clone, tweak, and deploy.
ragflow
infiniflow/ragflow
Retrieval-Augmented Generation engine with agent capabilities
Vector store - persist embeddings and run similarity search at query time.
When not to use: Don't reach for a dedicated vector DB under ~100k vectors; pgvector on your existing Postgres is simpler to operate.
milvus
milvus-io/milvus
High-performance cloud-native vector database
WeKnora
Tencent/WeKnora
Open-source LLM knowledge platform for creating a queryable RAG, autonomous reasoning agent, and self-maintaining Wiki.
qdrant
qdrant/qdrant
High-performance, massive-scale Vector Database and Vector Search Engine
tidb
pingcap/tidb
Scalable, cloud-native database with ACID transactions and vector search support.
Orchestration - assemble retrieval, prompting, and the model into a chain.
When not to use: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves.
AutoGPT
Significant-Gravitas/AutoGPT
AutoGPT is the vision of accessible AI for everyone, to use and to build on.
transformers
huggingface/transformers
Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models
tensorflow
tensorflow/tensorflow
An Open Source Machine Learning Framework for Everyone
prompts.chat
f/prompts.chat
Share, discover, and collect prompts from the community
Evaluation & tracing - measure answer quality, cost, and latency before and after changes.
When not to use: Defer heavyweight eval infra only until you have real traffic - never skip it once users depend on answers.
generative-ai-for-beginners
microsoft/generative-ai-for-beginners
21 Lessons for Getting Started with Generative AI
headroom
headroomlabs-ai/headroom
Compress tool outputs and data to reduce tokens before reaching the LLM.
CL4R1T4S
elder-plinius/CL4R1T4S
Leaked system prompts for various AI agents include ChatGPT, Claude, Gemini among others emphasizing transparency and access.
LibreChat
danny-avila/LibreChat
Enhanced ChatGPT Clone with extensive features and integrations for self-hosting
Common questions
- What is the the rag stack?
- Retrieval-augmented generation grounds an LLM in your own data. A production RAG pipeline is four layers: ingestion, a vector store, orchestration, and evaluation.
- When should I use the the rag stack?
- Use this stack when your constraints match its layers: Data & Retrieval, Vector Databases, LLM Frameworks, Evaluation & Observability. Each step on the page includes when-not-to-use guidance so you do not over-engineer.
- How does GraphCanon pick tools for the rag stack?
- Stack pages are editorial workflows over canonical categories. Representative tools are pulled live from the graph at render time (top adoption in each category), not a fixed marketing list.
- Where can I compare tools in this stack?
- Follow category hubs and head-to-head compare pages linked from each step. Featured comparisons cover the highest-intent pairs (frameworks, vector DBs, agent runtimes). Start at compare hub.
- Is there a machine-readable version of The RAG stack?
- Yes. Append
.mdto `/stacks/rag-pipeline` or fetch `/md/stacks/rag-pipeline` for a markdown twin with steps, when-not notes, and tool links.