mirror of
https://github.com/onestardao/WFGY.git
synced 2026-04-28 19:50:17 +00:00
178 lines
11 KiB
Markdown
178 lines
11 KiB
Markdown
# LangChain — Guardrails and Fix Patterns
|
||
|
||
Use this when your pipeline is built with **LangChain** (LCEL, Runnable*, Agents, Tools) and you see wrong snippets, unstable reasoning, mixed sources, or silent failures that look fine in logs.
|
||
|
||
**Acceptance targets**
|
||
- ΔS(question, retrieved) ≤ 0.45
|
||
- coverage ≥ 0.70 to the intended section or record
|
||
- λ stays convergent across 3 paraphrases
|
||
|
||
---
|
||
|
||
## Typical breakpoints → exact fixes
|
||
|
||
- Retrieval returns plausible but wrong chunks
|
||
Fix No.1: **Hallucination & Chunk Drift** →
|
||
[Hallucination](https://github.com/onestardao/WFGY/blob/main/ProblemMap/hallucination.md)
|
||
Also review **Retrieval Playbook** →
|
||
[Retrieval Playbook](https://github.com/onestardao/WFGY/blob/main/ProblemMap/retrieval-playbook.md)
|
||
|
||
- High vector similarity, wrong meaning
|
||
Fix No.5: **Embedding ≠ Semantic** →
|
||
[Embedding ≠ Semantic](https://github.com/onestardao/WFGY/blob/main/ProblemMap/embedding-vs-semantic.md)
|
||
|
||
- Hybrid chains with BM25 or HyDE degrade compared to single retriever
|
||
Pattern: **Query Parsing Split** →
|
||
[Query Parsing Split](https://github.com/onestardao/WFGY/blob/main/ProblemMap/patterns/pattern_query_parsing_split.md)
|
||
Apply **Rerankers** for ordering control →
|
||
[Rerankers](https://github.com/onestardao/WFGY/blob/main/ProblemMap/rerankers.md)
|
||
|
||
- Facts exist in the store but never show up
|
||
Pattern: **Vectorstore Fragmentation** →
|
||
[Vectorstore Fragmentation](https://github.com/onestardao/WFGY/blob/main/ProblemMap/patterns/pattern_vectorstore_fragmentation.md)
|
||
|
||
- Citations missing or inconsistent across LCEL steps
|
||
Fix No.8: **Retrieval Traceability** + **Data Contracts** →
|
||
[Retrieval Traceability](https://github.com/onestardao/WFGY/blob/main/ProblemMap/retrieval-traceability.md) ·
|
||
[Data Contracts](https://github.com/onestardao/WFGY/blob/main/ProblemMap/data-contracts.md)
|
||
|
||
- Long Runnable chains flatten style and drift logically
|
||
Fix No.3 and No.9: **Context Drift** and **Entropy Collapse** →
|
||
[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)
|
||
|
||
- Agent loops, role confusion, memory overwrite
|
||
Fix No.13: **Multi-Agent Chaos** →
|
||
[Multi-Agent Problems](https://github.com/onestardao/WFGY/blob/main/ProblemMap/Multi-Agent_Problems.md) ·
|
||
[Role Drift](https://github.com/onestardao/WFGY/blob/main/ProblemMap/multi-agent-chaos/role-drift.md) ·
|
||
[Memory Overwrite](https://github.com/onestardao/WFGY/blob/main/ProblemMap/multi-agent-chaos/memory-overwrite.md)
|
||
|
||
- Model sounds confident but is wrong
|
||
Fix No.4: **Bluffing / Overconfidence** →
|
||
[Bluffing](https://github.com/onestardao/WFGY/blob/main/ProblemMap/bluffing.md)
|
||
|
||
- Model merges two sources into one answer
|
||
Pattern: **Symbolic Constraint Unlock** →
|
||
[Symbolic Constraint Unlock](https://github.com/onestardao/WFGY/blob/main/ProblemMap/patterns/pattern_symbolic_constraint_unlock.md)
|
||
|
||
---
|
||
|
||
## Minimal LCEL pattern with WFGY checks
|
||
|
||
```python
|
||
# Pseudocode. Show the control points you must keep.
|
||
from langchain_core.runnables import RunnablePassthrough, RunnableMap
|
||
|
||
def retrieve(q):
|
||
# k sweep and unified analyzer across dense and sparse
|
||
return retriever.invoke(q, k=10)
|
||
|
||
def assemble(context, q):
|
||
# schema-locked: system -> task -> constraints -> citations -> answer
|
||
return prompt.format(context=context, question=q)
|
||
|
||
def reason(msg):
|
||
# model call runs after cite-then-explain requirement in the prompt
|
||
return llm.invoke(msg)
|
||
|
||
def wfgy_checks(q, context, answer):
|
||
# compute ΔS(question, context) and trace why this snippet
|
||
# enforce thresholds and fail fast when ΔS ≥ 0.60 or λ divergent
|
||
return metrics_and_trace(q, context, answer)
|
||
|
||
chain = (
|
||
{"q": RunnablePassthrough()}
|
||
| RunnableMap({"context": lambda x: retrieve(x["q"]), "q": lambda x: x["q"]})
|
||
| RunnableMap({"msg": lambda x: assemble(x["context"], x["q"]), "q": lambda x: x["q"], "context": lambda x: x["context"]})
|
||
| RunnableMap({"answer": lambda x: reason(x["msg"]), "q": lambda x: x["q"], "context": lambda x: x["context"]})
|
||
| (lambda x: wfgy_checks(x["q"], x["context"], x["answer"]))
|
||
)
|
||
````
|
||
|
||
**What this enforces**
|
||
|
||
* Retrieval is observable and parameterized.
|
||
* Prompt is schema locked with cite first.
|
||
* WFGY check runs after generation and can stop the run when ΔS is high or λ flips.
|
||
* Traces record snippet to citation mapping for audits.
|
||
|
||
Specs and recipes
|
||
[RAG Architecture & Recovery](https://github.com/onestardao/WFGY/blob/main/ProblemMap/rag-architecture-and-recovery.md) ·
|
||
[Retrieval Playbook](https://github.com/onestardao/WFGY/blob/main/ProblemMap/retrieval-playbook.md) ·
|
||
[Retrieval Traceability](https://github.com/onestardao/WFGY/blob/main/ProblemMap/retrieval-traceability.md) ·
|
||
[Data Contracts](https://github.com/onestardao/WFGY/blob/main/ProblemMap/data-contracts.md)
|
||
|
||
---
|
||
|
||
## LangChain-specific gotchas
|
||
|
||
* Mixed embedding functions across write and read paths. Rebuild with explicit metric and normalization.
|
||
See [Embedding ≠ Semantic](https://github.com/onestardao/WFGY/blob/main/ProblemMap/embedding-vs-semantic.md)
|
||
|
||
* RunnableParallel merges outputs without source fences. Add per-source headers and forbid cross-section reuse.
|
||
See [Symbolic Constraint Unlock](https://github.com/onestardao/WFGY/blob/main/ProblemMap/patterns/pattern_symbolic_constraint_unlock.md)
|
||
|
||
* Memory modules re-assert old facts after a refresh. Stamp `mem_rev` and `mem_hash`.
|
||
See [Memory Desync](https://github.com/onestardao/WFGY/blob/main/ProblemMap/patterns/pattern_memory_desync.md)
|
||
|
||
* Agents tool-call retry loops. Add BBCR bridge steps and clamp variance with BBAM in the prompt recipe.
|
||
See [Logic Collapse](https://github.com/onestardao/WFGY/blob/main/ProblemMap/logic-collapse.md)
|
||
|
||
---
|
||
|
||
## When to escalate
|
||
|
||
* ΔS remains ≥ 0.60 after chunk and retrieval fixes
|
||
Work through the playbook and rebuild index parameters.
|
||
[Retrieval Playbook](https://github.com/onestardao/WFGY/blob/main/ProblemMap/retrieval-playbook.md)
|
||
|
||
* Answers flip between runs or sessions
|
||
Verify version skew and session state.
|
||
[Pre-Deploy Collapse](https://github.com/onestardao/WFGY/blob/main/ProblemMap/predeploy-collapse.md)
|
||
|
||
---
|
||
|
||
### 🔗 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 |
|
||
|
||
---
|
||
|
||
### 🧭 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.
|
||
|
||
<div align="center">
|
||
|
||
[](https://github.com/onestardao/WFGY)
|
||
|
||
[](https://github.com/onestardao/WFGY/tree/main/OS)
|
||
|
||
[](https://github.com/onestardao/WFGY/tree/main/OS/BlahBlahBlah)
|
||
|
||
[](https://github.com/onestardao/WFGY/tree/main/OS/BlotBlotBlot)
|
||
|
||
[](https://github.com/onestardao/WFGY/tree/main/OS/BlocBlocBloc)
|
||
|
||
[](https://github.com/onestardao/WFGY/tree/main/OS/BlurBlurBlur)
|
||
|
||
[](https://github.com/onestardao/WFGY/tree/main/OS/BlowBlowBlow)
|
||
|
||
|
||
</div>
|
||
|