Commit Graph
497 Commits
Author SHA1 Message Date
Timothy Jaeryang Baek ecbdef732b enh: PDF_LOADER_MODE 2026-01-21 23:51:36 +04:00
9d642f6354 Added support for connecting to self hosted weaviate deployments using connect_to_custom replacing connect_to_local, which is better suited for cases where HTTP and GRPC are hosted on different ingresses. (#20620)
Co-authored-by: Tim Baek <tim@openwebui.com>
Co-authored-by: joaoback <156559121+joaoback@users.noreply.github.com>
Co-authored-by: rohithshenoyg@gmail.com <rohithshenoyg@gmail.com>
2026-01-17 21:48:52 +04:00
Kailey Wong e26f6acc3b fix: use proper X-Api-Key header format when docling api key provided (#20652) 2026-01-15 10:44:35 +04:00
Timothy Jaeryang Baek 5990c51ab5 chore: format 2026-01-09 22:27:53 +04:00
Timothy Jaeryang Baek 3c986adeda enh: kb metadata search 2026-01-09 22:21:00 +04:00
Timothy Jaeryang Baek e67891a374 refac 2026-01-08 00:42:29 +04:00
Classic298 614cb56420 feat: Add configurable DDGS backend selection with UI support (#20366)
* init

* Update WebSearch.svelte

* reorder
2026-01-05 03:05:56 +04:00
Timothy Jaeryang Baek e4a5b06ca6 enh: embedding_batch_size for local embedding engine 2026-01-01 16:06:42 +04:00
Timothy Jaeryang Baek f7f8a263b9 feat: JINA_API_BASE_URL 2026-01-01 02:17:47 +04:00
Timothy Jaeryang Baek 89ad1c68d1 enh: FIRECRAWL_TIMEOUT 2026-01-01 02:07:22 +04:00
Timothy Jaeryang Baek dfc5dad631 enh: REQUESTS_VERIFY 2026-01-01 01:27:07 +04:00
Classic298 464846d4a3 fix: retry Brave Search on HTTP 429 rate limit with 1s delay (#20255)
* Update brave.py

* Update brave.py
2025-12-30 17:37:44 +04:00
Timothy Jaeryang Baek b1d0f00d8c refac/enh: db session sharing 2025-12-29 00:21:18 +04:00
Dechao Sun 25db8225f8 openWebUI supports openGauss vector store (#20179) 2025-12-26 18:32:05 +04:00
Timothy Jaeryang Baek fe653a1336 refac 2025-12-20 18:12:03 +04:00
Timothy Jaeryang Baek d4bd938a77 refac: ollama web 2025-12-20 17:54:13 +04:00
okamototk 37085ed42b chore: update langchain 1.2.0 (#19991)
* chore: update langchain 1.2.0

* chore: format
2025-12-20 08:50:44 -05:00
2e7c7d635d fix: prevent ExternalReranker from blocking event loop during RAG queries (#20049)
* fix: prevent ExternalReranker from blocking event loop during RAG queries (#120)

Co-authored-by: Tim Baek <tim@openwebui.com>
Co-authored-by: Claude <noreply@anthropic.com>
Fixes #19900

* Merge pull request open-webui#19030 from open-webui/dev (#122)

Co-authored-by: Tim Baek <tim@openwebui.com>
Co-authored-by: Claude <noreply@anthropic.com>
Fixes #19900

---------

Co-authored-by: Tim Baek <tim@openwebui.com>
Co-authored-by: Claude <noreply@anthropic.com>
2025-12-20 08:43:40 -05:00
Timothy Jaeryang Baek afaa404fe4 enh: mineru api timeout 2025-12-20 17:39:33 +04:00
Timothy Jaeryang Baekandzengxy b5bd8704fe fix: bocha filter list
Co-Authored-By: zengxy <11961641+zengxy@users.noreply.github.com>
2025-12-20 17:24:24 +04:00
823b9a6dd9 chore/perf: Remove old SRC level log env vars with no impact (#20045)
* Update openai.py

* Update env.py

* Merge pull request open-webui#19030 from open-webui/dev (#119)

Co-authored-by: Tim Baek <tim@openwebui.com>
Co-authored-by: Claude <noreply@anthropic.com>

---------

Co-authored-by: Tim Baek <tim@openwebui.com>
Co-authored-by: Claude <noreply@anthropic.com>
2025-12-20 08:16:14 -05:00
Boris Bocquet bc681f8258 feat : new environment variable SEARXNG_LANGUAGE , in the persistent config, that you can also edit in Admin > Web Search pannel in case you choose Searxng. This is used in the request to searxng as the "search language" (arguement "language"). Before this feature, it was set to en-US only. Now default is "all". (#19909) 2025-12-14 12:38:47 -05:00
Timothy Jaeryang Baek b02397e460 feat: WEB_LOADER_TIMEOUT 2025-12-08 11:49:27 -05:00
Timothy Jaeryang Baek 7e6b8a9a71 refac/fix: docling auth 2025-12-06 08:06:42 -05:00
Timothy Jaeryang Baek 9a65ed2260 chore: format 2025-12-02 16:06:57 -05:00
Classic298 b29fdc2a0c Update milvus_multitenancy.py (#19695) 2025-12-02 15:38:06 -05:00
Classic298andTim Baek 12f237ff80 fix: Update milvus.py (#19602)
* Update milvus.py

* Update milvus.py

* Update milvus.py

* Update milvus.py

* Update milvus.py

---------

Co-authored-by: Tim Baek <tim@openwebui.com>
2025-12-02 15:30:31 -05:00
Henne a7e614ca4c feat: Adds document intelligence model configuration (#19692)
* Adds document intelligence model configuration

Enables the configuration of the Document Intelligence model to be used by the RAG pipeline.

This allows users to specify the model they want to use for document processing, providing flexibility and control over the extraction process.

* Added Titel to Document Intelligence Model Config

Added Titel to Document Intelligence Model Config
2025-12-02 14:41:09 -05:00
Timothy Jaeryang Baek d19023288e feat/enh: kb files db migration 2025-12-02 10:53:32 -05:00
PocciaandTim Baek 6e531679f4 fix/adjust web search to properly block domains (#19670)
Co-authored-by: Tim Baek <tim@openwebui.com>
2025-12-02 04:17:32 -05:00
Classic298 0a14196afb Update milvus_multitenancy.py (#19680) 2025-12-02 03:57:14 -05:00
Timothy Jaeryang Baek 743199f2d0 feat/enh: tool server function name filter list 2025-11-25 02:31:34 -05:00
Timothy Jaeryang BaekandClassic298 2328dc284e feat/enh: async embedding processing setting
Co-Authored-By: Classic298 <27028174+Classic298@users.noreply.github.com>
2025-11-25 01:55:43 -05:00
Timothy Jaeryang Baek 9c19d0abd4 refac/breaking: docling params 2025-11-24 16:01:13 -05:00
Timothy Jaeryang Baek 06f0bfd9f5 fix 2025-11-24 05:58:22 -05:00
Timothy Jaeryang Baek 662a1fac47 fix: hybrid search 2025-11-24 05:52:18 -05:00
Timothy Jaeryang Baek 48d1e67e79 chore: format 2025-11-23 20:15:52 -05:00
Classic298 99f0fe7f32 chore: user header forward minimize code changes throughout codebase (#19392)
* Update external.py

* remove unused imports

* Update ollama.py

* Update ollama.py

* Update ollama.py

* Update openai.py
2025-11-23 16:48:03 -05:00
Classic298 60dbde7e19 chore (#19389) 2025-11-23 04:40:05 -05:00
Timothy Jaeryang Baek f9c96d03ad refac 2025-11-22 22:57:27 -05:00
Timothy Jaeryang Baek 9bfc414d26 refac 2025-11-22 21:33:14 -05:00
Classic298andClaude 902c6cfbea perf: 50x performance improvement for external embeddings (#19296)
* Update utils.py (#77)

Co-authored-by: Claude <noreply@anthropic.com>

* refactor: address code review feedback for embedding performance improvements (#92)

Co-authored-by: Claude <noreply@anthropic.com>

* fix: prevent sentence transformers from blocking async event loop (#95)

Co-authored-by: Claude <noreply@anthropic.com>

---------

Co-authored-by: Claude <noreply@anthropic.com>
2025-11-22 20:54:59 -05:00
Diwakar b8728064d8 feat: add support for Weaviate vector database (#14747) 2025-11-20 19:23:46 -05:00
Timothy Jaeryang Baek a1d09eae95 chore: format 2025-11-19 03:23:33 -05:00
Seth Argyle 720af637e6 fix: Use get_index() instead of list_indexes() in has_collection() to… (#19238)
* fix: Use get_index() instead of list_indexes() in has_collection() to handle pagination

Fixes #19233

  Replace list_indexes() pagination scan with direct get_index() lookup
  in has_collection() method. The previous implementation only checked
  the first ~1,000 indexes due to unhandled pagination, causing RAG
  queries to fail for indexes beyond the first page.

  Benefits:
  - Handles buckets with any number of indexes (no pagination needed)
  - ~8x faster (0.19s vs 1.53s in testing)
  - Proper exception handling for ResourceNotFoundException
  - Scales to millions of indexes

* Update s3vector.py

Unneeded exception handling removed to match original OWUI code
2025-11-19 00:19:10 -05:00
Jacob LeksanandTim Baek 07ef295a77 feat: Adding file metadata to hybrid search (#19095)
* Added metadata to hybrid search

* And config and env plus refac

* consistency

---------

Co-authored-by: Tim Baek <tim@openwebui.com>
2025-11-18 15:29:07 -05:00
Timothy Jaeryang Baek 2af4c4b3c7 refac 2025-11-18 04:42:09 -05:00
Timothy Jaeryang BaekandClassic298 02238d3113 feat/security: Add SSRF protection with configurable blocklist
Co-Authored-By: Classic298 <27028174+Classic298@users.noreply.github.com>
2025-11-18 04:40:55 -05:00
lazarivandMoritz 6cdb13d5cb feat: pgvector hnsw index type (#19158)
* Adding hnsw index type for pgvector, allowing vector dimensions larger than 2000

* remove some variable assignments

* Make USE_HALFVEC variable configurable

* Simplify USE_HALFVEC handling

* Raise runtime error if the index requires rebuilt

---------

Co-authored-by: Moritz <moritz.mueller2@tu-dresden.de>
2025-11-18 04:14:43 -05:00
Timothy Jaeryang Baek ee10f372a0 refac/enh: web search domain allow/block filter 2025-11-16 13:52:09 -05:00