WFGY/ProblemMap/GlobalFixMap/LocalDeploy_Inference/ollama.md

143 lines
8.7 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.

# Ollama: Guardrails and Fix Patterns
<details>
<summary>🌙 3AM: a dev collapsed mid-debug… 🚑 Welcome to the WFGY Emergency Room</summary>
---
🟥🟥🟥🟥🟥🟥🟥🟥🟥🟥🟥🟥
## 🚑 WFGY Emergency Room
👨‍⚕️ **Now online:**
[**Dr. WFGY in ChatGPT Room**](https://chatgpt.com/share/68b9b7ad-51e4-8000-90ee-a25522da01d7)
This is a **share window** already trained as an ER.
Just open it, drop your bug or screenshot, and talk directly with the doctor.
He will map it to the right Problem Map / Global Fix section, write a minimal prescription, and paste the exact reference link.
If something is unclear, you can even paste a **screenshot of Problem Map content** and ask — the doctor will guide you.
⚠️ Note: for the full reasoning and guardrail behavior you need to be logged in — the share view alone may fallback to a lighter model.
💡 Always free. If it helps, a ⭐ star keeps the ER running.
🌐 Multilingual — start in any language.
🟥🟥🟥🟥🟥🟥🟥🟥🟥🟥🟥🟥
---
</details>
<details>
<summary><strong>🧭 Quick Return to Map</strong></summary>
<br>
> You are in a sub-page of **LocalDeploy_Inference**.
> To reorient, go back here:
>
> - [**LocalDeploy_Inference** — on-prem deployment and model inference](./README.md)
> - [**WFGY Global Fix Map** — main Emergency Room, 300+ structured fixes](../README.md)
> - [**WFGY Problem Map 1.0** — 16 reproducible failure modes](../../README.md)
>
> Think of this page as a desk within a ward.
> If you need the full triage and all prescriptions, return to the Emergency Room lobby.
</details>
Field guide for stabilizing **Ollama-based local inference pipelines**.
Use these checks when models run fine on API providers but collapse, stall, or drift when containerized with Ollama.
## Open these first
* Architecture 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)
* Embedding vs semantic: [embedding-vs-semantic.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/embedding-vs-semantic.md)
* Ordering and deploy race conditions: [bootstrap-ordering.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/bootstrap-ordering.md), [deployment-deadlock.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/deployment-deadlock.md), [predeploy-collapse.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/predeploy-collapse.md)
* Container observability: [eval\_observability.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/eval_observability.md)
---
## Core acceptance
* ΔS(question, retrieved) ≤ 0.45
* Coverage ≥ 0.70 on the target section
* λ remains convergent across 3 paraphrases
* Local runs reproducible across 2+ seeds
---
## Typical Ollama breakpoints and fix
| Symptom | Likely cause | Fix |
| --------------------------------------- | --------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Model boots but stalls on first request | Container not warmed / secrets missing | [bootstrap-ordering.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/bootstrap-ordering.md) |
| Fast API returns, but snippets wrong | Index/hash drift across containers | [retrieval-traceability.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/retrieval-traceability.md), [data-contracts.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/data-contracts.md) |
| Answers diverge run-to-run | λ flips due to context serialization | [context-drift.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/context-drift.md), [entropy-collapse.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/entropy-collapse.md) |
| Works on GPU API, fails locally | Metric / embedding mismatch in Ollama runtime | [embedding-vs-semantic.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/embedding-vs-semantic.md), [vectorstore-fragmentation.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/vectorstore-fragmentation.md) |
| Container OOM or deadlock | Parallel inference with no fence | [deployment-deadlock.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/deployment-deadlock.md), [predeploy-collapse.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/predeploy-collapse.md) |
---
## Fix in 60 seconds
1. **Measure ΔS** between retrieved and anchor.
2. **Probe λ** across 3 paraphrases. If flips, apply BBAM.
3. **Warm boot** with a delay + healthcheck before first request.
4. **Lock index schema** via [data-contracts.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/data-contracts.md).
5. **Verify reproducibility** with two seeds before going live.
---
## Copy-paste local test prompt
```txt
I have WFGY + TXTOS loaded.
Running Ollama locally with container {hash}.
Question: "{user_question}"
Return:
1. ΔS(question,retrieved) and λ across 3 paraphrases
2. Whether index schema matches contract
3. Minimal structural fix if ΔS ≥ 0.60
```
---
### 🔗 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 |
---
<!-- WFGY_FOOTER_START -->
### Explore More
| Layer | Page | What its for |
| --- | --- | --- |
| Proof | [WFGY Recognition Map](/recognition/README.md) | External citations, integrations, and ecosystem proof |
| Engine | [WFGY 1.0](/legacy/README.md) | Original PDF based tension engine |
| Engine | [WFGY 2.0](/core/README.md) | Production tension kernel and math engine for RAG and agents |
| Engine | [WFGY 3.0](/TensionUniverse/EventHorizon/README.md) | TXT based Singularity tension engine, 131 S class set |
| Map | [Problem Map 1.0](/ProblemMap/README.md) | Flagship 16 problem RAG failure checklist and fix map |
| Map | [Problem Map 2.0](/ProblemMap/rag-architecture-and-recovery.md) | RAG focused recovery pipeline |
| Map | [Problem Map 3.0](/ProblemMap/wfgy-rag-16-problem-map-global-debug-card.md) | Global Debug Card, image as a debug protocol layer |
| Map | [Semantic Clinic](/ProblemMap/SemanticClinicIndex.md) | Symptom to family to exact fix |
| Map | [Grandmas Clinic](/ProblemMap/GrandmaClinic/README.md) | Plain language stories mapped to Problem Map 1.0 |
| Onboarding | [Starter Village](/StarterVillage/README.md) | Guided tour for newcomers |
| App | [TXT OS](/OS/README.md) | TXT semantic OS, fast boot |
| App | [Blah Blah Blah](/OS/BlahBlahBlah/README.md) | Abstract and paradox Q and A built on TXT OS |
| App | [Blur Blur Blur](/OS/BlurBlurBlur/README.md) | Text to image with semantic control |
| App | [Blow Blow Blow](/OS/BlowBlowBlow/README.md) | Reasoning game engine and memory demo |
If this repository helped, starring it improves discovery so more builders can find the docs and tools.
[![GitHub Repo stars](https://img.shields.io/github/stars/onestardao/WFGY?style=social)](https://github.com/onestardao/WFGY)
<!-- WFGY_FOOTER_END -->
要我直接繼續寫 **`vllm.md`** 嗎?