mirror of
https://github.com/onestardao/WFGY.git
synced 2026-04-28 11:40:07 +00:00
134 lines
8 KiB
Markdown
134 lines
8 KiB
Markdown
# 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) | 1️⃣ Download · 2️⃣ Upload to your LLM · 3️⃣ Ask “Answer using WFGY + \<your question>” |
|
||
| **TXT OS (plain-text OS)** | [TXTOS.txt](https://github.com/onestardao/WFGY/blob/main/OS/TXTOS.txt) | 1️⃣ Download · 2️⃣ Paste into any LLM chat · 3️⃣ Type “hello world” — OS boots instantly |
|
||
|
||
---
|
||
|
||
<!-- WFGY_FOOTER_START -->
|
||
|
||
### Explore More
|
||
|
||
| Module | Description | Link |
|
||
| --- | --- | --- |
|
||
| WFGY Core | Canonical framework entry point | [View](https://github.com/onestardao/WFGY/tree/main/core/README.md) |
|
||
| Problem Map | Diagnostic map and navigation hub | [View](https://github.com/onestardao/WFGY/tree/main/ProblemMap/README.md) |
|
||
| Tension Universe Experiments | MVP experiment field | [View](https://github.com/onestardao/WFGY/tree/main/TensionUniverse/Experiments) |
|
||
| Recognition | Where WFGY is referenced or adopted | [View](https://github.com/onestardao/WFGY/blob/main/recognition/README.md) |
|
||
| AI Guide | Anti-hallucination reading protocol for tools | [View](https://github.com/onestardao/WFGY/blob/main/AI_GUIDE.md) |
|
||
|
||
> If this repository helps, starring it improves discovery for other builders.
|
||
> [](https://github.com/onestardao/WFGY)
|
||
|
||
<!-- WFGY_FOOTER_END -->
|
||
|
||
要我直接繼續寫 **`vllm.md`** 嗎？
|