b02397e460
feat: WEB_LOADER_TIMEOUT
2025-12-08 11:49:27 -05:00
7e6b8a9a71
refac/fix: docling auth
2025-12-06 08:06:42 -05:00
9a65ed2260
chore: format
2025-12-02 16:06:57 -05:00
b29fdc2a0c
Update milvus_multitenancy.py ( #19695 )
2025-12-02 15:38:06 -05:00
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
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
d19023288e
feat/enh: kb files db migration
2025-12-02 10:53:32 -05:00
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
0a14196afb
Update milvus_multitenancy.py ( #19680 )
2025-12-02 03:57:14 -05:00
743199f2d0
feat/enh: tool server function name filter list
2025-11-25 02:31:34 -05:00
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
9c19d0abd4
refac/breaking: docling params
2025-11-24 16:01:13 -05:00
06f0bfd9f5
fix
2025-11-24 05:58:22 -05:00
662a1fac47
fix: hybrid search
2025-11-24 05:52:18 -05:00
48d1e67e79
chore: format
2025-11-23 20:15:52 -05:00
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
60dbde7e19
chore ( #19389 )
2025-11-23 04:40:05 -05:00
f9c96d03ad
refac
2025-11-22 22:57:27 -05:00
9bfc414d26
refac
2025-11-22 21:33:14 -05:00
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
b8728064d8
feat: add support for Weaviate vector database ( #14747 )
2025-11-20 19:23:46 -05:00
a1d09eae95
chore: format
2025-11-19 03:23:33 -05:00
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
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
2af4c4b3c7
refac
2025-11-18 04:42:09 -05:00
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
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
ee10f372a0
refac/enh: web search domain allow/block filter
2025-11-16 13:52:09 -05:00
64747f7f79
Add Azure Search ( #19104 )
...
Co-authored-by: Tim Baek <tim@openwebui.com >
2025-11-13 19:12:34 -05:00
ad17d35ac4
feat: Add custom API endpoint and user info headers for Perplexity Search ( #31 ) ( #19147 )
...
Co-authored-by: Claude <noreply@anthropic.com >
2025-11-12 22:53:54 -05:00
4673e120c4
refac/fix: mineru params
...
breaking change
2025-11-11 00:30:11 -05:00
bc739de024
refac: rerank
2025-11-09 21:33:50 -05:00
284764e178
Merge pull request #19025 from krishna-medapati/fix-hybrid-search-17046-clean
...
fix: Handle AttributeError in hybrid search with reranking (#17046 )
2025-11-09 20:43:52 -05:00
25c7f101f2
enh: optionally add user headers external websearch
...
Co-Authored-By: Classic298 <27028174+Classic298@users.noreply.github.com >
2025-11-09 16:09:29 -05:00
684324ae9e
fix: Handle AttributeError in hybrid search with reranking ( #17046 )
...
- Split attribute existence checks from document content checks
- Added hasattr() check for metadatas attribute
- Prevents AttributeError when collection_result is missing attributes
- Maintains all original validation logic
Fixes #17046
2025-11-07 23:31:11 +05:30
7faf19dad9
refac
2025-11-06 15:21:06 -05:00
c38f878e1e
fix: firecrawl import
2025-11-06 15:19:08 -05:00
e2b9942648
feat: Optionally forward user headers to external document loader
...
Co-Authored-By: Classic298 <27028174+Classic298@users.noreply.github.com >
2025-11-06 00:05:46 -05:00
415b93c7c3
enh: configurable mistral ocr base url
2025-11-05 23:25:51 -05:00
a4fd26b478
enh/fix: google pse referer header
2025-11-04 13:50:07 -05:00
d14329b285
refac
2025-11-02 18:47:41 -05:00
d98c539d89
refac
2025-11-01 18:48:11 -04:00
c787070dc9
Merge pull request #18765 from mkhludnev/patch-2
...
fix: Don't missguide Tika with mime-type
2025-10-31 14:18:43 -07:00
24aeec9120
Don't missguide Tika with mime-type
...
Fix #18683
* Tika is smart enough to detect content type.
* Windows browsers just misguides Tika providing `application/ms-word` for .rtf files.
2025-10-31 23:12:23 +03:00
3bcf9a442a
fix: make SSL verification async
2025-10-29 16:14:53 +03:00
5e17882488
fix: use trusted env in web search loader
...
Signed-off-by: Wang Weixuan <wangweixvan@gmail.com >
2025-10-28 04:58:00 +08:00
a70bc52c34
chore: format
2025-10-26 19:33:39 -07:00
8197844ff7
refac
2025-10-26 17:22:23 -07:00
7a3f4d85f6
refactor: replace requests with Firecrawl SDK in search and requests Firecrawl SDK in scrape rather than langchain_community FireCrawlLoader
2025-10-26 15:05:35 +08:00
7d29991fa5
fix: pass youtube_proxy as a GenericProxyConfig type object
2025-10-19 02:01:27 +02:00
Timothy Jaeryang Baek