---
title: "The RAG stack"
type: "stack"
slug: "rag-pipeline"
canonical_url: "https://www.graphcanon.com/stacks/rag-pipeline"
---

# 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.

## 1. Data & Retrieval

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.

- [graphrag](/tools/microsoft-graphrag.md) - A modular graph-based Retrieval-Augmented Generation (RAG) system (★ 34,239)
- [ChatGLM2-6B](/tools/zai-org-chatglm2-6b.md) - ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型 (★ 15,560)
- [easy-dataset](/tools/conardli-easy-dataset.md) - A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval (★ 14,605)
- [orama](/tools/oramasearch-orama.md) - 🌌  A complete search engine and RAG pipeline in your browser, server or edge network with support for full-text, vector, and hybrid search  (★ 10,468)

## 2. Vector Databases

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.

- [ECC](/tools/affaan-m-ecc.md) - The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Code (★ 226,953)
- [hermes-agent](/tools/nousresearch-hermes-agent.md) - The agent that grows with you (★ 210,874)
- [ollama](/tools/ollama-ollama.md) - Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. (★ 175,657)
- [langflow](/tools/langflow-ai-langflow.md) - Langflow is a powerful tool for building and deploying AI-powered agents and workflows. (★ 151,298)

## 3. LLM Frameworks

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](/tools/affaan-m-ecc.md) - The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Code (★ 226,953)
- [hermes-agent](/tools/nousresearch-hermes-agent.md) - The agent that grows with you (★ 210,874)
- [AutoGPT](/tools/significant-gravitas-autogpt.md) - AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on w (★ 185,418)
- [ollama](/tools/ollama-ollama.md) - Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. (★ 175,657)

## 4. Evaluation & Observability

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.

- [toon](/tools/toon-format-toon.md) - 🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK. (★ 24,792)
- [VAR](/tools/foundationvision-var.md) - [NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeli (★ 8,706)
- [LLM4Decompile](/tools/albertan017-llm4decompile.md) - Reverse Engineering: Decompiling Binary Code with Large Language Models (★ 6,741)
- [tree-of-thought-llm](/tools/princeton-nlp-tree-of-thought-llm.md) - [NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models (★ 6,025)

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon/categories`](/api/graphcanon/categories)
- LLM index: [/llms.txt](/llms.txt)
- Full corpus: [/llms-full.txt](/llms-full.txt)

_GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_