Stephen Hu 5383e254c4 Perf:Remove Useless Convert When BGE Embedding (#8816) ...

### What problem does this PR solve?

FlagModel internal support returns as numpy

### Type of change
- [x] Performance Improvement

2025-07-14 14:02:48 +08:00

..

app

Fix: Improve Memory Usage For Presentation (#8792)

2025-07-11 11:35:25 +08:00

llm

Perf:Remove Useless Convert When BGE Embedding (#8816)

2025-07-14 14:02:48 +08:00

nlp

Fix: better_handle_different_types (#8775)

2025-07-11 18:21:39 +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

Fix: The data set created by API call failed to parse after uploading the file. (#8657)

2025-07-04 12:41:28 +08:00

utils

Fix: add ES re-connect once request timeout. (#8678)

2025-07-07 09:22:25 +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

Refa: limit embedding concurrency and fix chat_with_tool (#8543)

2025-06-27 19:28:41 +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