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 Oct 4, 2026
120views 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
dify
langgenius/dify
Build Agentic workflows and RAG pipelines with rich AI model and tool support on one collaborative workspace.
mem0
mem0ai/mem0
Drop-in memory infrastructure for AI agents and apps
JeecgBoot
jeecgboot/JeecgBoot
企业级AI低代码平台，一键生成前后端代码甚至整个系统
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
Milvus is a high-performance, cloud-native vector database for scalable vector ANN search
TencentDB-Agent-Memory
TencentCloud/TencentDB-Agent-Memory
A team-level memory hub for AI Agents, transforming conversations, documents, and code into reusable memory assets.
qdrant
qdrant/qdrant
High-performance, massive-scale Vector Database and Vector Search Engine for AI
cognee
topoteretes/cognee
Cognee is the open-source AI memory platform for agents.
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.
ECC
affaan-m/ECC
Agent harness performance optimization system for AI agents and LLMs
transformers
huggingface/transformers
🤗 Transformers: state-of-the-art machine learning models for text, vision, audio, and multimodal models
tensorflow
tensorflow/tensorflow
An Open Source Machine Learning Framework for Everyone
generative-ai-for-beginners
microsoft/generative-ai-for-beginners
21 Lessons for Getting Started with Generative AI
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, logs, files, and RAG chunks before they reach the LLM.
LibreChat
danny-avila/LibreChat
Enhanced ChatGPT Clone with extensive features and integrations for self-hosting
ray
ray-project/ray
Unified framework for scaling AI and Python applications
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.