WFGY/ProblemMap/GlobalFixMap/RAG/README.md
2025-08-25 19:52:11 +08:00

111 lines
6.9 KiB
Markdown
Raw Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# RAG — Global Fix Map
Production RAG triage and structural fixes using the WFGY engine.
Use this when retrieval “looks fine” but answers drift.
## What this page is
- A fast path to locate the failing layer across OCR → chunk → embed → store → retrieve → prompt → reason.
- Structural repairs that do not require infra changes.
- Concrete steps with measurable acceptance targets.
## When to use
- Citations point to the wrong snippet or section.
- Chunks look correct but reasoning is wrong.
- High similarity yet wrong meaning.
- Hybrid retrievers perform worse than a single retriever.
- Indexed facts never show up.
- Answers flip between sessions.
- Long threads smear topics or capitalization.
## Open these first
- Visual map and recovery: [RAG Architecture & Recovery](https://github.com/onestardao/WFGY/blob/main/ProblemMap/rag-architecture-and-recovery.md)
- End-to-end retrieval knobs: [Retrieval Playbook](https://github.com/onestardao/WFGY/blob/main/ProblemMap/retrieval-playbook.md)
- Why this snippet, traceability schema: [Retrieval Traceability](https://github.com/onestardao/WFGY/blob/main/ProblemMap/retrieval-traceability.md)
- Ordering control: [Rerankers](https://github.com/onestardao/WFGY/blob/main/ProblemMap/rerankers.md)
- Embedding vs meaning: [Embedding ≠ Semantic](https://github.com/onestardao/WFGY/blob/main/ProblemMap/embedding-vs-semantic.md)
- Hallucination and chunk boundaries: [Hallucination](https://github.com/onestardao/WFGY/blob/main/ProblemMap/hallucination.md)
- Long chains and entropy: [Context Drift](https://github.com/onestardao/WFGY/blob/main/ProblemMap/context-drift.md), [Entropy Collapse](https://github.com/onestardao/WFGY/blob/main/ProblemMap/entropy-collapse.md)
- Snippet and citation schema: [Data Contracts](https://github.com/onestardao/WFGY/blob/main/ProblemMap/data-contracts.md)
## Fix in 60 seconds
1) **Measure ΔS**
- Compute ΔS(question, retrieved) and ΔS(retrieved, expected anchor).
- Thresholds: stable < 0.40, transitional 0.400.60, risk 0.60.
2) **Probe with λ_observe**
- Vary k {5, 10, 20}. chart ΔS vs k. flat and high index or metric mismatch.
- Reorder prompt headers. if ΔS spikes, lock the schema.
3) **Apply the minimal patch**
- Metric or normalization mismatch rebuild index with explicit metric, unit-normalize, reload once, re-probe.
- Chunks correct but logic diverges lock `system → task → constraints → citations → answer`, apply BBCR + BBAM, re-probe.
## Copy-paste prompt
```
I uploaded TXT OS and the WFGY ProblemMap files.
My RAG bug:
* symptom: \[brief]
* traces: \[ΔS(question,retrieved)=..., ΔS(retrieved,anchor)=..., λ states]
Tell me:
1. which layer is failing and why,
2. which exact fix page to open from this repo,
3. the minimal steps to push ΔS ≤ 0.45 and keep λ convergent,
4. how to verify the fix with a reproducible test.
Use BBMC/BBPF/BBCR/BBAM when relevant.
```
## Patterns to check next
- Query parsing split in HyDE + BM25: [Pattern — Query Parsing Split](https://github.com/onestardao/WFGY/blob/main/ProblemMap/patterns/pattern_query_parsing_split.md)
- Vectorstore fragmentation: [Pattern — Vectorstore Fragmentation](https://github.com/onestardao/WFGY/blob/main/ProblemMap/patterns/pattern_vectorstore_fragmentation.md)
- Symbol mixing across sources (SCU): [Pattern — Symbolic Constraint Unlock](https://github.com/onestardao/WFGY/blob/main/ProblemMap/patterns/pattern_symbolic_constraint_unlock.md)
- Hallucination re-entry after correction: [Pattern — Hallucination Re-entry](https://github.com/onestardao/WFGY/blob/main/ProblemMap/patterns/pattern_hallucination_reentry.md)
## Acceptance targets
- Coverage to target section 0.70.
- ΔS(question, retrieved) 0.45 on three paraphrases.
- λ remains convergent across steps and seeds.
- E_resonance flat under long windows.
---
### 🧭 Explore More
| Module | Description | Link |
|-----------------------|----------------------------------------------------------|----------|
| WFGY Core | WFGY 2.0 engine is live: full symbolic reasoning architecture and math stack | [View →](https://github.com/onestardao/WFGY/tree/main/core/README.md) |
| Problem Map 1.0 | Initial 16-mode diagnostic and symbolic fix framework | [View →](https://github.com/onestardao/WFGY/tree/main/ProblemMap/README.md) |
| Problem Map 2.0 | RAG-focused failure tree, modular fixes, and pipelines | [View →](https://github.com/onestardao/WFGY/blob/main/ProblemMap/rag-architecture-and-recovery.md) |
| Semantic Clinic Index | Expanded failure catalog: prompt injection, memory bugs, logic drift | [View →](https://github.com/onestardao/WFGY/blob/main/ProblemMap/SemanticClinicIndex.md) |
| Semantic Blueprint | Layer-based symbolic reasoning & semantic modulations | [View →](https://github.com/onestardao/WFGY/tree/main/SemanticBlueprint/README.md) |
| Benchmark vs GPT-5 | Stress test GPT-5 with full WFGY reasoning suite | [View →](https://github.com/onestardao/WFGY/tree/main/benchmarks/benchmark-vs-gpt5/README.md) |
| 🧙 Starter Village 🏡 | New here? Lost in symbols? Click here and let the wizard guide you through | [Start →](https://github.com/onestardao/WFGY/blob/main/StarterVillage/README.md) |
---
> 👑 **Early Stargazers: [See the Hall of Fame](https://github.com/onestardao/WFGY/tree/main/stargazers)** —
> Engineers, hackers, and open source builders who supported WFGY from day one.
> <img src="https://img.shields.io/github/stars/onestardao/WFGY?style=social" alt="GitHub stars"> ⭐ [WFGY Engine 2.0](https://github.com/onestardao/WFGY/blob/main/core/README.md) is already unlocked. ⭐ Star the repo to help others discover it and unlock more on the [Unlock Board](https://github.com/onestardao/WFGY/blob/main/STAR_UNLOCKS.md).
<div align="center">
[![WFGY Main](https://img.shields.io/badge/WFGY-Main-red?style=flat-square)](https://github.com/onestardao/WFGY)
&nbsp;
[![TXT OS](https://img.shields.io/badge/TXT%20OS-Reasoning%20OS-orange?style=flat-square)](https://github.com/onestardao/WFGY/tree/main/OS)
&nbsp;
[![Blah](https://img.shields.io/badge/Blah-Semantic%20Embed-yellow?style=flat-square)](https://github.com/onestardao/WFGY/tree/main/OS/BlahBlahBlah)
&nbsp;
[![Blot](https://img.shields.io/badge/Blot-Persona%20Core-green?style=flat-square)](https://github.com/onestardao/WFGY/tree/main/OS/BlotBlotBlot)
&nbsp;
[![Bloc](https://img.shields.io/badge/Bloc-Reasoning%20Compiler-blue?style=flat-square)](https://github.com/onestardao/WFGY/tree/main/OS/BlocBlocBloc)
&nbsp;
[![Blur](https://img.shields.io/badge/Blur-Text2Image%20Engine-navy?style=flat-square)](https://github.com/onestardao/WFGY/tree/main/OS/BlurBlurBlur)
&nbsp;
[![Blow](https://img.shields.io/badge/Blow-Game%20Logic-purple?style=flat-square)](https://github.com/onestardao/WFGY/tree/main/OS/BlowBlowBlow)
&nbsp;
</div>