mirror of
https://github.com/onestardao/WFGY.git
synced 2026-04-28 11:40:07 +00:00
9 KiB
9 KiB
Embeddings — Global Fix Map
A hub to stabilize embedding pipelines across stores and retrievers. Use this page to jump to per-tool guardrails and verify fixes with the same acceptance targets.
Quick routes to per-page fixes
- Metric mismatch → metric_mismatch.md
- Normalization and scaling → normalization_and_scaling.md
- Tokenization and casing → tokenization_and_casing.md
- Chunking to embedding contract → chunking_to_embedding_contract.md
- Vectorstore fragmentation → vectorstore_fragmentation.md
- Dimension mismatch and projection → dimension_mismatch_and_projection.md
- Update and index skew → update_and_index_skew.md
- Hybrid retriever weights → hybrid_retriever_weights.md
- Duplication and near-duplicate collapse → duplication_and_near_duplicate_collapse.md
- Poisoning and contamination → poisoning_and_contamination.md
When to use this folder
- High similarity yet wrong meaning.
- Citations do not line up with the retrieved section.
- Hybrid retrievers underperform a single retriever.
- Quality drops after re-embed or re-index.
- Index looks healthy but coverage stays low.
Acceptance targets
- ΔS(question, retrieved) ≤ 0.45
- Coverage of target section ≥ 0.70
- λ remains convergent across 3 paraphrases and 2 seeds
- E_resonance flat on long windows
60-second checklist
- Metrics and analyzer sanity → metric_mismatch.md
- Normalize and rescale vectors → normalization_and_scaling.md
- Unify tokenization and casing → tokenization_and_casing.md
- Lock the chunk→embed contract → chunking_to_embedding_contract.md
- Defragment the store → vectorstore_fragmentation.md
- Fix dimension and projection paths → dimension_mismatch_and_projection.md
- Repair update and index skew → update_and_index_skew.md
- Rebalance hybrid retrievers → hybrid_retriever_weights.md
- Collapse near-duplicates → duplication_and_near_duplicate_collapse.md
- Audit poisoning and contamination → poisoning_and_contamination.md
Map symptoms to structural fixes
- Wrong-meaning hits despite high similarity
→ embedding-vs-semantic.md - Unverifiable citations or snippet drift
→ retrieval-traceability.md · data-contracts.md - Results flip across runs or small paraphrases
→ context-drift.md · entropy-collapse.md · rerankers.md - Hallucination re-entry after correction
→ pattern_hallucination_reentry.md
Verify the fix
- Log ΔS and λ for three paraphrases and two seeds.
- Require coverage ≥ 0.70 and ΔS ≤ 0.45 before publish.
- Keep a small gold set to re-test after any change to metric, tokenizer, or chunking.
🔗 Quick-Start Downloads (60 sec)
| Tool | Link | 3-Step Setup |
|---|---|---|
| WFGY 1.0 PDF | Engine Paper | 1️⃣ Download · 2️⃣ Upload to your LLM · 3️⃣ Ask “Answer using WFGY + <your question>” |
| TXT OS (plain-text OS) | TXTOS.txt | 1️⃣ Download · 2️⃣ Paste into any LLM chat · 3️⃣ 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 → |
| Problem Map 1.0 | Initial 16-mode diagnostic and symbolic fix framework | View → |
| Problem Map 2.0 | RAG-focused failure tree, modular fixes, and pipelines | View → |
| Semantic Clinic Index | Expanded failure catalog: prompt injection, memory bugs, logic drift | View → |
| Semantic Blueprint | Layer-based symbolic reasoning & semantic modulations | View → |
| Benchmark vs GPT-5 | Stress test GPT-5 with full WFGY reasoning suite | View → |
| 🧙♂️ Starter Village 🏡 | New here? Lost in symbols? Click here and let the wizard guide you through | Start → |
👑 Early Stargazers: See the Hall of Fame —
Engineers, hackers, and open source builders who supported WFGY from day one.
⭐ WFGY Engine 2.0 is already unlocked. ⭐ Star the repo to help others discover it and unlock more on the Unlock Board.
