3 people fea6b6e999 fix(rag): derive url file suffix from content-type media type in load_from_url (#42364) ...

Co-authored-by: coderdailyone <codecookie@proton.me>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>

2026-09-17 02:56:58 +00:00

..

cleaner

fix(rag): stop the document cleaner from stripping valid characters ï, ¿, ¾ (#39215)

2026-07-27 02:53:33 +00:00

data_post_processor

feat: knowledge add more trace (#38959)

2026-07-24 02:27:16 +00:00

datasource

test: migrate RAG retrieval sessions and ORM models to SQLite (#40512)

2026-09-10 04:15:40 +00:00

docstore

chore: avoid duplicate token counting during dataset indexing (#39466)

2026-07-23 10:56:03 +00:00

embedding

chore: avoid duplicate token counting during dataset indexing (#39466)

2026-07-23 10:56:03 +00:00

entities

refactor(api): migrate dataset endpoints to BaseModel (#37957)

2026-07-09 04:22:30 +00:00

extractor

fix(rag): derive url file suffix from content-type media type in load_from_url (#42364)

2026-09-17 02:56:58 +00:00

index_processor

fix(api): skip invalid markdown image URLs (#41343)

2026-09-04 08:17:33 +00:00

models

chore: reorg imports (#35308)

2026-04-16 08:50:02 +00:00

pipeline

chore: use from __future__ import annotations (#30254)

2026-01-06 23:57:20 +09:00

rerank

feat(api): track credit usage contexts (#41181)

2026-08-25 10:21:32 +00:00

retrieval

fix: dataset hitcount deadlock (#41979)

2026-09-09 02:37:26 +00:00

splitter

fix: preserve spaces during recursive text splitting (#39498)

2026-07-27 03:21:26 +00:00

summary_index

feat(api): track credit usage contexts (#41181)

2026-08-25 10:21:32 +00:00

__init__.py

Feat/dify rag (#2528)

2024-02-22 23:31:57 +08:00