Mathias Panzenböck b36d9744ae shortcut metadata_condition if there is none (#12835) ...

### What problem does this PR solve?

If no `metadata_condition` parameter is given then don't load the
metadata of all documents into memory. Instead just pass `doc_ids` as
`None` to the `retrieval()` method, which means to use all documents of
the given datasets.

This is relevant if you have *a lot* of documents!

### Type of change

- [x] Performance Improvement

2026-01-27 12:45:58 +08:00

..

agents.py

Refactor:better handle list agent api desc param (#12733)

2026-01-21 13:09:27 +08:00

chat.py

Align p3 HTTP/SDK tests with current backend behavior (#12563)

2026-01-13 19:22:47 +08:00

dataset.py

Add dataset with table parser type for Infinity and answer question in chat using SQL (#12541)

2026-01-19 19:35:14 +08:00

dify_retrieval.py

Fix: missing parent chunk issue. (#12789)

2026-01-23 12:54:08 +08:00

doc.py

shortcut metadata_condition if there is none (#12835)

2026-01-27 12:45:58 +08:00

files.py

Refa: asyncio.to_thread to ThreadPoolExecutor to break thread limitat… (#12716)

2026-01-20 13:29:37 +08:00

memories.py

Fix : Web API tests by normalizing errors, validation, and uploads (#12620)

2026-01-16 11:09:22 +08:00

messages.py

Feat：memory sdk (#12538)

2026-01-09 17:45:58 +08:00

session.py

Fix: Use tiktoken for proper token counting in OpenAI-compatible endpoint #7850 (#12760)

2026-01-23 09:36:21 +08:00