rag-architect

原文涵盖的主题

• RAG Architect
• Hard rules
• Embedding model tiers (pattern, not price list)
• Workflow
• 1. Analyze the corpus and pick chunking
• 2. Design the pipeline from requirements
• 3. Evaluate retrieval quality
• 4. Verification loop

Design, tune, and evaluate production RAG pipelines with three deterministic tools. Run the tools against the actual corpus and requirements — do not pick chunk sizes or databases by intuition. 1. Never present model names or vendor prices as current facts. Embedding models and vector-DB pricing rot in months. Recommend a tier (see table below), name a current-generation candidate, and tell the user to verify against the provider's live pricing page. 2. Every design ends with an evaluation run. A RAG design without retrievalevaluator.py numbers is a hypothesis, not a deliverable. 3. Chunking is corpus-driven. Run chunkingoptimizer.py on the real documents before choosing a strategy. | Tier | Current-generation examples (verify before use) | When | |---|---|---| | Fast / self-hosted | all-MiniLM-L6-v2, bge-small | Cost-sensitive, small scale, real-time | | Balanced open | all-mpnet-base-v2, bge-large, e5-large | Quality without API dependency | | Quality API | text-embedding-3-large, voyage-3-large | Accuracy-priority general retrieval | | Code | voyage-code-3, CodeBERT-family | Code search corpora | Pricing discipline: build the cost model with a placeholder table — columns model |

这里只展示节选，请以完整原文和当前要求为准。