ai-rag-patterns
/ai-rag-patterns
Prowadzi budowę funkcji odpowiadających na pytania z prywatnych danych i dokumentów: architektura RAG, chunking, wyszukiwanie hybrydowe, re-ranking, bazy wektorowe, ewaluacja oraz RAG agentowy i multimodalny.
- Autor
- peterbamuhigire ↗
- Repozytorium
- chwezi-dev-engine ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 24.10.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 9
- Skrypty
- 0
- Komentarze HTML
- 2
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 24.10.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
- SKILL.md zawiera komentarze HTML (2). Nie widać ich w podglądzie Markdown, a model je czyta.
Co robi i kiedy
Prowadzi budowę funkcji odpowiadających na pytania z prywatnych danych i dokumentów: architektura RAG, chunking, wyszukiwanie hybrydowe, re-ranking, bazy wektorowe, ewaluacja oraz RAG agentowy i multimodalny.
Oryginalny opis (EN)
Use when building features that answer questions from private data, documents, policies, or time-sensitive information — RAG architecture, chunking, hybrid search, re-ranking, vector databases, evaluation, agentic and multimodal RAG, and bounded iterative retrieval for context-starved subagents.
Jak działa
- Operating contract
- Inputs
- Outputs
- Capability and permission boundaries
- Degraded mode
- Decision rules
- Anti-Patterns
- Use When
- Evidence Produced
- References
Podgląd SKILL.md
--- name: ai-rag-patterns description: Use when building features that answer questions from private data, documents, policies, or time-sensitive information — RAG architecture, chunking, hybrid search, re-ranking, vector databases, evaluation, agentic and multimodal RAG, and bounded iterative retrieval for context-starved subagents. metadata: portable: true compatible_with: - claude-code - codex --- # RAG Patterns — Retrieval-Augmented Generation ## Operating contract ## Inputs | Input | Required | Purpose | |---|---|---| | Domain evidence | yes | question set, authoritative corpus, tenancy and access rules, freshness target, citation needs, and evaluation set | ## Outputs - Produce: retrieval architecture, ingestion/chunking policy, index and filter contract, grounded-answer schema, and evaluation report. ## Capability and permission boundaries Default to read-only analysis. Read only scoped records; redact secrets and regulated data. Writes, execution, network calls, production configuration, customer communication, billing changes, and delegation require explicit authority and an identified owner. Never widen tenant, time-window, or system scope implicitly. ## Degraded mode When required telemetry, evidence, execution, network access, or write authority is unavailable, return a partial result with each unassessed item labelled, preserve the safest existing state, and state the evidence or approval needed to continue. Never convert missing evidence into a pass. ## Decision rules | Condition | Action | |---|---| | Scope, owner, or threshold is missing | Stop the affected decision and request it | | Evidence is incomplete but read-only analysis is safe | Produce a qualified partial result and gap list | | A mutation exceeds authority or tenant boundary | Block it and route for approval | | Evidence meets the stated threshold | Issue the output with provenance and owner | ## Anti-Patterns - Treating absent evidence as success. Fix: mark the check unassessed and name the missing source. - Expanding one tenant or workflow to all tenants. Fix: enforce supplied scope at every query and action. - Performing a production write during analysis. Fix: emit a reviewed change plan until authority is explicit. - Reporting a metric without population, window, or source. Fix: attach all three. - Hiding a failed threshold inside an average. Fix: report failure slices and the remediation owner. Acknowledgement: Shared by Peter Bamuhigire, techguypeter.com, +256 784 464178. <!-- dual-compat-start --> ## Use When - Use when building features that answer questions from private data, documents, policies, or time-sensitive information — RAG architecture, chunking strategies, hybrid search, re-ranking, vector databases, evaluation, agentic RAG, multimodal RAG... ## Evidence Produced | Category | Artifact | Format | Example | |----------|----------|--------|---------| | Correctness | RAG retrieval evaluation report | Markdown doc covering recall / precision / answer-quality on a fixed eval set | `docs/ai/rag-eval-2026-04-16.md` | | Data safety | Index ingestion + tenancy isolation note | Markdown doc covering chunking, source filtering, and per-tenant index segregation | `docs/ai/rag-tenancy-note.md` | ## References - Use the `references/` directory for deep detail after reading the core workflow below. - [references/curated-corpus-worked-example.md](references/curated-corpus-worked-example.md): small curated corpus with BM25 ranking, per-domain score floors, calibrated abstention and a graded, fingerprinted golden set. <!-- dual-compat-end --> ## Overview RAG solves the core LLM limitation: they only know what they were trained on. Use RAG to inject private data (invoices, menus, policies, reports) into every AI response. **Core principle:** RAG = look up a database + LLM synthesises the results. The LLM never needs to "know" your data. --- ## When to Use RAG | Condition | Action | |---|---| | Knowledge base < 200K tokens (~500 pages) | Include everything in context — no RAG needed | | Knowledge base > 200K tokens | Use RAG | | Data changes frequently (menus, prices, stock) | RAG (update documents, not model) | | Data is private/confidential | RAG (keeps data out of training pipelines) | | Need source citations | RAG (chunks are traceable to source) | | Model needs brand voice / domain jargon | Fine-tune instead | --- ## RAG vs Fine-Tuning | Factor | RAG | Fine-Tuning | |---|---|---| | Up-to-date content | ✅ Yes (add docs anytime) | ❌ Stale until retrained | | Hallucinations | ✅ Lower (document-grounded) | ❌ Higher | | Source citations | ✅ Yes | ❌ No | | Brand voice control | ❌ Weak | ✅ Strong | | Domain jargon | ❌ Weak | ✅ Strong | | Up-front cost | ✅ Lower | ❌ High | **Default: start with RAG.** Fine-tune only when RAG + prompt engineering cannot deliver the required tone or vocabulary. --- ## Additional Guidance Guidance is split across two reference files so this entrypoint stays compact. **[references/skill-deep-dive.md](references/skill-deep-dive.md)** — architecture, chunking, retrieval, schema: - `Pipeline Architecture` - `Chunking Strategies` - `Embedding Model Selection` - `Vector Database Selection` - `Retrieval Algorithms` - `Re-Ranking` - `Full RAG Query Algorithm` - `Query Rewriting (Multi-Turn)` - `RAG Schema (Multi-Tenant)` - `Evaluation Framework` - `Production Patterns` - `Agentic RAG` - `Multimodal RAG`, `Edge Cases`, `Cost Optimisation`, `Sources` **[references/production-rag.md](references/production-rag.md)** — the progression from draft to production and the gates before shipping: - `RAG Maturity Model` — Naive → Advanced → Modular - `Query Transformation` — HyDE, Multi-Query, Step-Back - `Contextual Compression` - `Self-RAG` - `RAGAS Evaluation` — 4 metrics with production thresholds - `Embedding Pipeline` — batching, upserts, re-embed triggers, $/1M-token table - `Cost Management Decision Tree` — concrete dollar figures per branch - `Failure Mode Playbook` — empty, irrelevant, hallucinated, stale - `Gates Before Shipping` **[references/iterative-retrieval.md](references/iterative-retrieval.md)** — load when a context-starved subagent must explore a codebase or workspace before working: bounded DISPATCH-EVALUATE-REFINE-LOOP (max 3 cycles), relevance banding, explicit gap lists, and terminology learning. Load the production file when building a RAG system that has to pass evaluation gates, survive multi-tenant review, or hit a cost budget under load. When answers depend on structured records about a specific customer, order or account (not documents), or when embedding, prompt and model versions must be managed like an ML system, load `python-ml-predictive` reference `ml-system-architecture-fti.md` (feature/training/inference pipelines, entity-keyed retrieval, version coupling). ## Multi-Tenant Addendum This skill describes RAG patterns in general. When the RAG feature ships inside a multi-tenant SaaS, the production answer is `ai-rag-multi-tenant` — per-tenant ingestion pipelines, vector store partitioning, tier-specific chunking and embedding models, defence-in-depth retrieval security, and citation grounding tied to live sources. Cross-references: - `ai-rag-multi-tenant` — multi-tenant RAG end-to-end. - `ai-tenant-isolation-patterns` — vector-store partitioning tradeoffs and data-bleed tests. - `ai-on-saas-architecture` — KB service as a control-plane service. - `ai-hallucination-slo-and-grounding` — citation grounding + faithfulness SLO. - `ai-model-gateway` — gateway-mediated retrieval calls. - `saas-tenant-data-portability-and-erasure` — KB erasure cascade for embeddings. - [Catalog metadata for AI](../../backend-databases/database-design-engineering/references/metadata-catalog-and-lineage-design.md) — load when retrieval or an agent draws on data-catalog or data-contract metadata: classification-first filtering, ODCS `context` block, provenance. ## Consolidated Child References - Load [references/routing.md](references/routing.md) to map retired AI child skill slugs to their reference modules.
Pliki w paczce (9)
- SKILL.md 8 KB
- references/curated-corpus-worked-example.md 5 KB
- references/iterative-retrieval.md 5 KB
- references/production-rag.md 15 KB
- references/routing.md 1 KB
- references/skill-deep-dive.md 15 KB
- references/ai-rag-multi-tenant/entrypoint.md 11 KB
- references/ai-rag-multi-tenant/references/per-tenant-ingestion-pipeline.md 5 KB
- references/ai-rag-multi-tenant/references/retrieval-security-patterns.md 4 KB
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · peterbamuhigire/chwezi-dev-engine | 100 | MIT |
| Muvon/octomind-tap | 90 | Apache-2.0 |
Migawka bazy z 13.11.2026 · wersja paczki 3aa222dadf31 (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 100rag-skills
Wspiera budowę, debugowanie i ulepszanie systemów RAG: chunking, wybór bazy wektorowej, hybrid search, reranking, multimodalny RAG i opóźnienia wyszukiwania. - 100rag-patterns
Opisuje wzorce architektury RAG: strategie chunkingu, pipeline'y wyszukiwania, reranking, wyszukiwanie hybrydowe, ewaluację i projekt systemu produkcyjnego. - 100rag-engineer
Projektuje systemy RAG dla aplikacji LLM: dobiera modele embeddingów i bazy wektorowe, ustawia chunking i optymalizuje wyszukiwanie semantyczne oraz pobieranie dokumentów. - 100rag-engineer
Projektuje systemy RAG dla aplikacji LLM: dobiera modele embeddingów i bazy wektorowe, ustawia chunking i optymalizuje wyszukiwanie. - 100rag-engineer
Projektuje systemy RAG dla aplikacji LLM: dobiera modele embeddingów i bazy wektorowe, ustawia chunking i optymalizuje wyszukiwanie. - 100rag-architect
Projektuje i wdraża produkcyjne systemy RAG: chunking, embeddingi, magazyny wektorowe, wyszukiwanie hybrydowe, reranking i ocena jakości wyszukiwania.