ragflow

mirror of https://github.com/infiniflow/ragflow.git synced 2026-05-21 16:40:07 +08:00

Files

Jonathan Hill 111cdc77b5 fix: guard LLM response against empty choices (fixes #14711 ) (#14988 )

## Summary

Fixes 10 unguarded `response.choices[0]` accesses that cause
`IndexError` or `AttributeError` when the LLM returns an empty `choices`
list — the scenario described in #14711.

- `rag/llm/cv_model.py`
- `rag/llm/chat_model.py`

Each access site is now guarded with:
```python
if not response.choices:
    raise ValueError("LLM returned empty response")
```

## Verification

Detected and verified by [pact](https://github.com/qizwiz/pact) — a
sheaf-cohomological LLM contract checker using Z3 as a local theory
solver.

**pact sheaf-cohomological proof status after fix:**

| File | Ȟ¹ (after) | Z3 |
|------|-----------|-----|
| `rag/llm/cv_model.py` | 0 | UNSAT ✓ |
| `rag/llm/chat_model.py` | 0 | UNSAT ✓ |

All access sites proven safe (Z3 UNSAT certificate).

The checker was also used to verify the autogen streaming-None fix in
[microsoft/autogen#7711](https://github.com/microsoft/autogen/pull/7711).

## Test plan
- [ ] Existing test suite passes
- [ ] Manually test with a provider that returns empty `choices` under
load (e.g. Vertex AI)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

---------

Signed-off-by: Jonathan Hill <jonathan.f.hill@gmail.com>

2026-05-21 15:37:19 +08:00

advanced_rag

fix: handle missing 'total' key causing KeyError in deep research retrieval (#13942 )

2026-05-09 10:57:51 +08:00

app

Feat: VLM image descriptions in MinerU parser (#14869 ) (#14946 )

2026-05-19 16:08:10 +08:00

flow

refactor: optimize BaseTitleChunker to improve RAG document chunk quality (#14247 )

2026-05-18 10:00:18 +08:00

graphrag

Refactor: enhance graphrag - part 2 (#14972 )