Create README.md

This commit is contained in:
PSBigBig 2025-08-27 12:23:15 +08:00 committed by GitHub
parent db398e0f87
commit eed1fc64ac
No known key found for this signature in database
GPG key ID: B5690EEEBB952194

View file

@ -0,0 +1,144 @@
# Vector DBs & Stores — Global Fix Map
A hub to stabilize retrieval pipelines across popular vector stores.
Use this page to jump to per-tool guardrails and verify fixes with the same acceptance targets.
---
## Quick routes to per-store pages
- FAISS → [faiss.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/GlobalFixMap/VectorDBs_and_Stores/faiss.md)
- Chroma → [chroma.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/GlobalFixMap/VectorDBs_and_Stores/chroma.md)
- Qdrant → [qdrant.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/GlobalFixMap/VectorDBs_and_Stores/qdrant.md)
- Weaviate → [weaviate.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/GlobalFixMap/VectorDBs_and_Stores/weaviate.md)
- Milvus → [milvus.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/GlobalFixMap/VectorDBs_and_Stores/milvus.md)
- pgvector → [pgvector.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/GlobalFixMap/VectorDBs_and_Stores/pgvector.md)
- Redis (Search/Vec) → [redis.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/GlobalFixMap/VectorDBs_and_Stores/redis.md)
- Elasticsearch (kNN / dense) → [elasticsearch.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/GlobalFixMap/VectorDBs_and_Stores/elasticsearch.md)
- Pinecone → [pinecone.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/GlobalFixMap/VectorDBs_and_Stores/pinecone.md)
---
## When to use this folder
- High similarity but wrong meaning.
- Citations dont line up with the retrieved section.
- Hybrid retrievers underperform a single retriever.
- Query casing / analyzer / metric mismatches after deploy.
- Index looks healthy yet coverage remains low.
---
## Acceptance targets for any store
- ΔS(question, retrieved) ≤ **0.45**
- Coverage of target section ≥ **0.70**
- λ\_observe stays **convergent** across 3 paraphrases
- E\_resonance flat on long windows
---
## Map symptoms → structural fixes (Problem Map)
- **Embedding ≠ Semantic**
Wrong-meaning hits despite high similarity.
→ [embedding-vs-semantic.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/embedding-vs-semantic.md)
- **Retrieval traceability**
Snippet/section mismatch or unverifiable citations.
→ [retrieval-traceability.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/retrieval-traceability.md)
Payload schema: → [data-contracts.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/data-contracts.md)
- **Ordering / version skew**
Old index or analyzer used at runtime.
→ [bootstrap-ordering.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/bootstrap-ordering.md) ·
[predeploy-collapse.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/predeploy-collapse.md)
- **Hybrid collapse / query split**
HyDE vs BM25 disagreement, reranker blind spots.
→ Pattern: [patterns/pattern_query_parsing_split.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/patterns/pattern_query_parsing_split.md)
→ Knobs: [rerankers.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/rerankers.md)
---
## 60-second fix checklist (store-agnostic)
1) **Lock metrics & analyzers**
Pin distance metric, tokenizer/casing, and normalization on both write and read.
2) **Contract the snippet**
Require `{snippet_id, section_id, source_url, offsets, tokens}`.
3) **Probe ΔS and λ**
Log ΔS(question, retrieved) and λ per step; alert at ΔS ≥ 0.60.
4) **Verify coverage**
Run a 10-question eval on the target section; require coverage ≥ 0.70.
5) **Reranking pass**
If hybrid disagrees, add a rerank step and re-measure ΔS.
---
## Copy-paste prompt for a quick audit
```
I uploaded TXT OS and the WFGY Problem Map pages.
My stack uses <store> with metric \<cosine|l2|dot>, analyzer <...>, and normalization <...>.
Do:
1. Report ΔS(question, retrieved) and λ states across retrieve → rerank → reason.
2. If ΔS ≥ 0.60, point to one minimal structural fix:
embedding-vs-semantic, retrieval-traceability, data-contracts, rerankers.
3. Return JSON:
{ "citations":\[...], "ΔS":0.xx, "λ":"→|←|<>|×", "next\_fix":"..." }
```
---
### 🔗 Quick-Start Downloads (60 sec)
| Tool | Link | 3-Step Setup |
|------|------|--------------|
| **WFGY 1.0 PDF** | [Engine Paper](https://github.com/onestardao/WFGY/blob/main/I_am_not_lizardman/WFGY_All_Principles_Return_to_One_v1.0_PSBigBig_Public.pdf) | 1⃣ Download · 2⃣ Upload to your LLM · 3⃣ Ask “Answer using WFGY + <your question>” |
| **TXT OS (plain-text OS)** | [TXTOS.txt](https://github.com/onestardao/WFGY/blob/main/OS/TXTOS.txt) | 1⃣ Download · 2⃣ Paste into any LLM chat · 3⃣ Type “hello world” — OS boots instantly |
---
### 🧭 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)**
> <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>