Idriss Sbaaoui de6a8e789a Fix: rerank overflow by enforcing top_k and 64 cap (#14084) ...

### What problem does this PR solve?

This fixes rerank overflow where retrieval could send more documents
than allowed (for example 66 when `page_size=6`), causing provider 400
errors and bypassing the user’s `top_k` intent in rerank-enabled paths.
this pr fixes #14081

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

2026-04-14 10:47:25 +08:00

..

advanced_rag

Refa: async retrieval process. (#12629)

2026-01-15 12:28:49 +08:00

app

Refact: refact on parser structure (#14012)

2026-04-10 10:03:44 +08:00

flow

Fix: markdown parser in pipeline (#14032)

2026-04-10 14:11:14 +08:00

graphrag

Refa: GraphRAG to use async chat methods instead of thread pool execution (#14002)

2026-04-09 19:57:35 +08:00

llm

fix: gpt-5 name-based config clearing from base chat path (#13949)

2026-04-07 11:24:47 +08:00

nlp

Fix: rerank overflow by enforcing top_k and 64 cap (#14084)

2026-04-14 10:47:25 +08:00

prompts

[Security] Fix jinja2 SSTI vulnerability using SandboxedEnvironment (#14068)

2026-04-13 19:24:13 +08:00

res

Feat: Bitbucket connector (#12332)

2025-12-31 17:18:30 +08:00

svr

Disable flask and quart debug (#14042)

2026-04-10 18:01:49 +08:00

utils

fix: support dense_vector from ES fields response (ES 9.x compatibility) (#13972)

2026-04-09 17:44:13 +08:00

__init__.py

Fix: incorrect async chat streamly output (#11679)

2025-12-03 11:15:45 +08:00

benchmark.py

Feat/tenant model (#13072)

2026-03-05 17:27:17 +08:00

raptor.py

fix: correct typo in IterationItem name check and incomplete error message (#13890)

2026-04-02 10:35:28 +08:00

settings.py

Move api.settings to common.settings (#11036)

2025-11-06 09:36:38 +08:00