Kevin Hu 24c41d2a61 Perf: make do_cancel quicker. (#8846) ...

### What problem does this PR solve?

### Type of change

- [x] Performance Improvement

2025-07-15 14:35:00 +08:00

..

app

Fix: fixed context loss caused by separating markdown tables from original text (#8844)

2025-07-15 13:03:01 +08:00

llm

Update embedding_model.py (#8836)

2025-07-15 14:04:58 +08:00

nlp

Fix: no chunks parsed out for Law (#8842)

2025-07-15 13:01:56 +08:00

prompts

Refa: refactor prompts into markdown-style structure using Jinja2 (#8667)

2025-07-04 15:59:41 +08:00

res

Perf: ignore concate between rows. (#8507)

2025-06-26 14:55:37 +08:00

svr

Perf: make do_cancel quicker. (#8846)

2025-07-15 14:35:00 +08:00

utils

Perf: Enhance timeout handling. (#8826)

2025-07-15 09:36:45 +08:00

__init__.py

Update comments (#4569)

2025-01-21 20:52:28 +08:00

benchmark.py

Refactor embedding batch_size (#3825)

2024-12-03 16:22:39 +08:00

prompt_template.py

Refa: refactor prompts into markdown-style structure using Jinja2 (#8667)

2025-07-04 15:59:41 +08:00

prompts.py

Fix a small typo in count of used fragments (#8673)

2025-07-04 19:46:31 +08:00

raptor.py

Perf: make do_cancel quicker. (#8846)

2025-07-15 14:35:00 +08:00

settings.py

Feat: make document parsing and embedding batch sizes configurable via environment variables (#8266)

2025-06-16 13:40:47 +08:00