Commit Graph

340 Commits

Author SHA1 Message Date
Sihyeon Jang 3da22af859 fix(utils/middleware): flush pending chat deltas on stream termination
Guarantees the last partial delta chunk is emitted when the SSE stream closes (EOF, break, or `[DONE]` sentinel).

* Buffer `last_delta_data` and track `delta_count`
* Flush automatically once `delta_count >= chunk_size`
* Perform a final flush after the iterator ends

Signed-off-by: Sihyeon Jang <sihyeon.jang@navercorp.com>
2025-08-16 13:03:57 +09:00
Timothy Jaeryang Baek f1c28455ad refac: async webhook request 2025-08-15 00:07:02 +04:00
Timothy Jaeryang Baek b43acc2b3d refac/fix: tag attribute handling 2025-08-14 04:04:34 +04:00
Timothy Jaeryang Baek 3e8d3b08fa refac 2025-08-14 04:04:20 +04:00
Timothy Jaeryang Baek 97448e25ec fix: openai error handling 2025-08-11 17:00:06 +04:00
Timothy Jaeryang Baek fbb8c111ed refac 2025-08-11 00:39:12 +04:00
Timothy Jaeryang Baek 059cc636f6 fix: openai response propagation issue 2025-08-11 00:37:06 +04:00
Timothy Jaeryang Baek 4e9c75be50 enh: CHAT_RESPONSE_STREAM_DELTA_CHUNK_SIZE 2025-08-09 23:49:56 +04:00
Timothy Jaeryang Baek 1a93891d97 feat: stream delta chunk
Co-Authored-By: Jan Kessler <Ithanil@users.noreply.github.com>
2025-08-09 23:43:27 +04:00
Timothy Jaeryang Baek 2f349b5979 refac 2025-08-06 15:06:43 +04:00
Timothy Jaeryang Baek f2cae3d0a7 refac 2025-08-06 15:02:39 +04:00
Timothy Jaeryang Baek 3a1bbcb12e refac 2025-08-06 13:48:43 +04:00
Timothy Jaeryang Baek 2e36540023 refac: tag handling 2025-08-06 13:32:28 +04:00
Tim Jaeryang Baek 58dbd869ba
Merge pull request #16071 from GSAlex/main
fix: Render template variables in folder system prompts
2025-07-28 17:40:47 +04:00
Yang Yang b52d28c94c fix: Render template variables in folder system prompts
Fixes #16019
2025-07-27 23:20:43 +08:00
Timothy Jaeryang Baek bf3c807047 refac 2025-07-22 11:38:47 +04:00
Timothy Jaeryang Baek a638a187bb refac 2025-07-19 19:32:52 +04:00
Timothy Jaeryang Baek ea18ffdade refac/fix 2025-07-19 12:17:35 +04:00
Timothy Jaeryang Baek 2fa8aff82f refac/fix: tag handling 2025-07-18 11:56:40 +04:00
Timothy Jaeryang Baek 83c09f15ac refac/enh: reasoning tag handling 2025-07-16 15:20:03 +04:00
Timothy Jaeryang Baek abe280f0a3 refac/fix: reranking function 2025-07-16 13:56:02 +04:00
Timothy Jaeryang Baek 18bd83413b refac 2025-07-14 14:05:06 +04:00
Timothy Jaeryang Baek 0013f5c1fc refac/enh: forward user info header to reranker 2025-07-14 13:59:10 +04:00
Timothy Jaeryang Baek 80f3c97668 refac: folder chat handling
Co-Authored-By: Classic298 <27028174+Classic298@users.noreply.github.com>
2025-07-13 01:26:56 +04:00
Timothy Jaeryang Baek 0202926e35 refac 2025-07-11 18:09:24 +04:00
Timothy Jaeryang Baek 3b9d86de0b refac 2025-07-11 12:00:21 +04:00
Tim Jaeryang Baek 9d8378d2e2
Merge pull request #15604 from EventHorizon-AI/fix/tool-results
fix: tool results
2025-07-09 12:45:10 +04:00
EntropyYue 5b8007fcb5 fix: tool result frontend 2025-07-09 15:01:19 +08:00
EntropyYue dc0d420af5 fix: tool result 2025-07-09 14:40:53 +08:00
Timothy Jaeryang Baek 3a9d5b0494 refac 2025-07-07 23:51:01 +04:00
Timothy Jaeryang Baek cfcfefb20c refac: tools handling 2025-07-07 11:42:52 +04:00
Timothy Jaeryang Baek 8e95e5267c refac 2025-06-25 13:36:41 +04:00
Timothy Jaeryang Baek 1f123eb100 refac 2025-06-25 12:20:08 +04:00
Timothy Jaeryang Baek f4b92868c4 refac 2025-06-23 12:54:50 +04:00
Timothy Jaeryang Baek ab877e1d7e refac 2025-06-16 17:18:43 +04:00
Timothy Jaeryang Baek 6a5aac43df refac 2025-06-16 15:29:40 +04:00
Tim Jaeryang Baek d6664369a1
Merge pull request #14886 from Constantinople-AI/fix-no-arg-mcp-call
Isolated fix to single section
2025-06-16 15:28:48 +04:00
Timothy Jaeryang Baek ea578af45f refac: use first user message as title instead of 'new chat' 2025-06-16 12:37:41 +04:00
2underscores 88c8ea883c Isolated fix to single section 2025-06-11 19:58:55 +10:00
Timothy Jaeryang Baek b7a91b1963 refac: ollama response 2025-06-10 13:10:31 +04:00
Timothy Jaeryang Baek 8f68b25510 enh/refac: ollama advanced params 2025-06-10 12:48:34 +04:00
Timothy Jaeryang Baek ea8dc333ee refac/fix: multi-replica tasks 2025-06-09 17:21:10 +04:00
Timothy Jaeryang Baek 0c57980e72 refac: tasks 2025-06-08 20:58:31 +04:00
Rodrigo Agundez 41e28a9f6f Use standardized procedure to save and load images 2025-06-08 16:26:58 +08:00
Rodrigo Agundez bb09245792 Inject code to block imports from blacklisted modules
Co-authored-by: KG <kahghi@users.noreply.github.com>
2025-06-05 23:21:37 +08:00
Timothy Jaeryang Baek bbafeca495 refac: reserved `__user__` param format
Deploy to HuggingFace Spaces / check-secret (push) Waiting to run Details
Deploy to HuggingFace Spaces / deploy (push) Blocked by required conditions Details
Create and publish Docker images with specific build args / build-main-image (linux/amd64) (push) Waiting to run Details
Create and publish Docker images with specific build args / build-main-image (linux/arm64) (push) Waiting to run Details
Create and publish Docker images with specific build args / build-cuda-image (linux/amd64) (push) Waiting to run Details
Create and publish Docker images with specific build args / build-cuda-image (linux/arm64) (push) Waiting to run Details
Create and publish Docker images with specific build args / build-cuda126-image (linux/amd64) (push) Waiting to run Details
Create and publish Docker images with specific build args / build-cuda126-image (linux/arm64) (push) Waiting to run Details
Create and publish Docker images with specific build args / build-ollama-image (linux/amd64) (push) Waiting to run Details
Create and publish Docker images with specific build args / build-ollama-image (linux/arm64) (push) Waiting to run Details
Create and publish Docker images with specific build args / merge-main-images (push) Blocked by required conditions Details
Create and publish Docker images with specific build args / merge-cuda-images (push) Blocked by required conditions Details
Create and publish Docker images with specific build args / merge-cuda126-images (push) Blocked by required conditions Details
Create and publish Docker images with specific build args / merge-ollama-images (push) Blocked by required conditions Details
Python CI / Format Backend (3.11.x) (push) Waiting to run Details
Python CI / Format Backend (3.12.x) (push) Waiting to run Details
Frontend Build / Format & Build Frontend (push) Waiting to run Details
Frontend Build / Frontend Unit Tests (push) Waiting to run Details
2025-06-04 15:53:07 +04:00
Timothy Jaeryang Baek d2b5a1614a refac 2025-06-03 21:52:25 +04:00
Timothy Jaeryang Baek 185249623b feat: follow ups backend integration 2025-06-03 18:47:49 +04:00
Timothy Jaeryang Baek be989f3645 refac: better memory error handling 2025-05-30 00:12:28 +04:00
Timothy Jaeryang Baek 4c45d67677 refac/fix: memory 2025-05-30 00:10:52 +04:00
Timothy Jaeryang Baek 4371d2c5a5 enh: better custom param handling 2025-05-29 23:32:14 +04:00
Timothy Jaeryang Baek d43bbcae28 refac/fix: open webui params handling 2025-05-29 12:57:58 +04:00
Timothy Jaeryang Baek 9220afe7b3 feat: custom advanced params 2025-05-29 03:33:11 +04:00
Timothy Jaeryang Baek bb4115fa0e refac: allow all params 2025-05-29 02:56:37 +04:00
Timothy Jaeryang Baek 5c74e56bd0 chore: format 2025-05-27 02:18:43 +04:00
cheadings71 d414662d23 fix: resolve chat engagement TypeError - Fix get_message_list() to return [] instead of None - Fix middleware to use correct metadata message_id - Add safe fallback for missing role field - Ensure assistant messages include role field 2025-05-26 14:35:09 -07:00
Timothy Jaeryang Baek 2d5b82df8c enh: include sources field in non-streaming response 2025-05-26 22:22:37 +04:00
Tim Jaeryang Baek e663b90a9f
Merge pull request #14069 from Ithanil/bm25_weight
feat: Configurable weight for BM25Retriever during hybrid search
2025-05-24 01:13:03 +04:00
Timothy Jaeryang Baek bf97dbe052 refac 2025-05-24 01:12:11 +04:00
Timothy Jaeryang Baek 80eaa24ca8 enh: provide source name in context if available 2025-05-24 00:52:09 +04:00
Timothy Jaeryang Baek 8b5e89eada chore: format 2025-05-24 00:43:38 +04:00
Jan Kessler e70dd33233
rename BM25_WEIGHT -> HYBRID_BM25_WEIGHT 2025-05-23 22:06:44 +02:00
Diwakar Singh Maurya 549237fb05 Show tool call parameters along tool ouput 2025-05-23 17:42:05 +00:00
Timothy Jaeryang Baek a2f12db8d9 refac: memories
Deploy to HuggingFace Spaces / check-secret (push) Waiting to run Details
Deploy to HuggingFace Spaces / deploy (push) Blocked by required conditions Details
Create and publish Docker images with specific build args / build-main-image (linux/amd64) (push) Waiting to run Details
Create and publish Docker images with specific build args / build-main-image (linux/arm64) (push) Waiting to run Details
Create and publish Docker images with specific build args / build-cuda-image (linux/amd64) (push) Waiting to run Details
Create and publish Docker images with specific build args / build-cuda-image (linux/arm64) (push) Waiting to run Details
Create and publish Docker images with specific build args / build-ollama-image (linux/amd64) (push) Waiting to run Details
Create and publish Docker images with specific build args / build-ollama-image (linux/arm64) (push) Waiting to run Details
Create and publish Docker images with specific build args / merge-main-images (push) Blocked by required conditions Details
Create and publish Docker images with specific build args / merge-cuda-images (push) Blocked by required conditions Details
Create and publish Docker images with specific build args / merge-ollama-images (push) Blocked by required conditions Details
Python CI / Format Backend (3.11.x) (push) Waiting to run Details
Python CI / Format Backend (3.12.x) (push) Waiting to run Details
Frontend Build / Format & Build Frontend (push) Waiting to run Details
Frontend Build / Frontend Unit Tests (push) Waiting to run Details
2025-05-23 03:26:14 +04:00
Timothy Jaeryang Baek a68ec8822a enh: filter md image for task generations 2025-05-23 01:33:08 +04:00
Timothy Jaeryang Baek e3e7eb96f6 refac
Deploy to HuggingFace Spaces / check-secret (push) Waiting to run Details
Deploy to HuggingFace Spaces / deploy (push) Blocked by required conditions Details
Create and publish Docker images with specific build args / build-main-image (linux/amd64) (push) Waiting to run Details
Create and publish Docker images with specific build args / build-main-image (linux/arm64) (push) Waiting to run Details
Create and publish Docker images with specific build args / build-cuda-image (linux/amd64) (push) Waiting to run Details
Create and publish Docker images with specific build args / build-cuda-image (linux/arm64) (push) Waiting to run Details
Create and publish Docker images with specific build args / build-ollama-image (linux/amd64) (push) Waiting to run Details
Create and publish Docker images with specific build args / build-ollama-image (linux/arm64) (push) Waiting to run Details
Create and publish Docker images with specific build args / merge-main-images (push) Blocked by required conditions Details
Create and publish Docker images with specific build args / merge-cuda-images (push) Blocked by required conditions Details
Create and publish Docker images with specific build args / merge-ollama-images (push) Blocked by required conditions Details
Frontend Build / Format & Build Frontend (push) Waiting to run Details
Frontend Build / Frontend Unit Tests (push) Waiting to run Details
Python CI / Format Backend (3.11.x) (push) Has been cancelled Details
Python CI / Format Backend (3.12.x) (push) Has been cancelled Details
2025-05-20 23:55:11 +04:00
Jan Kessler 308d8ac04a
make bm25_weight a regular parameter of query_doc.. / get_sources_from_files functions 2025-05-20 11:46:32 +02:00
Timothy Jaeryang Baek 1f38350128 feat: toggle filter middleware 2025-05-16 23:33:02 +04:00
Timothy Jaeryang Baek 7bbeaec93b revert 2025-05-16 22:43:42 +04:00
Timothy Jaeryang Baek 363ac35c09 refac 2025-05-16 22:17:47 +04:00
Tim Jaeryang Baek 50bc6d9b12
Merge pull request #13919 from dongfangzan/main
feat: add switching thinking/non-thinking modes to models
2025-05-16 22:08:04 +04:00
Timothy Jaeryang Baek 07b5e84221 refac 2025-05-16 21:29:50 +04:00
Timothy Jaeryang Baek 528a2cf96a refac 2025-05-16 18:19:28 +04:00
Timothy Jaeryang Baek 2aa5e73728 refac: filter details 2025-05-16 18:01:55 +04:00
Timothy Jaeryang Baek dec9dd1ac0 refac: web search queries 2025-05-16 17:11:42 +04:00
dongfangzan 9b93b81f84 feat: add switching thinking/non-thinking modes to models 2025-05-15 19:56:10 +08:00
hwzhuhao fb2950201a refactor: replace print statements with logging 2025-05-12 22:18:47 +08:00
Timothy Jaeryang Baek 34ec10a78c refac: web search performance
Co-Authored-By: Mabeck <64421281+mmabeck@users.noreply.github.com>
2025-05-10 17:54:41 +04:00
Alexander Grimm a655bb5a63 skip checks in title gen 2025-05-08 06:55:43 +00:00
Alexander Grimm cf5201aada remove files from message for tasks 2025-05-08 06:50:21 +00:00
Serkan Sakar d62353c140 enh: add presence_penalty parameter to openai 2025-05-07 00:56:20 +02:00
Timothy Jaeryang Baek c667d27c38 refac 2025-05-07 02:37:23 +04:00
Timothy Jaeryang Baek 512d475ecc refac: api usage
Deploy to HuggingFace Spaces / check-secret (push) Waiting to run Details
Deploy to HuggingFace Spaces / deploy (push) Blocked by required conditions Details
Create and publish Docker images with specific build args / build-main-image (linux/amd64) (push) Waiting to run Details
Create and publish Docker images with specific build args / build-main-image (linux/arm64) (push) Waiting to run Details
Create and publish Docker images with specific build args / build-cuda-image (linux/amd64) (push) Waiting to run Details
Create and publish Docker images with specific build args / build-cuda-image (linux/arm64) (push) Waiting to run Details
Create and publish Docker images with specific build args / build-ollama-image (linux/amd64) (push) Waiting to run Details
Create and publish Docker images with specific build args / build-ollama-image (linux/arm64) (push) Waiting to run Details
Create and publish Docker images with specific build args / merge-main-images (push) Blocked by required conditions Details
Create and publish Docker images with specific build args / merge-cuda-images (push) Blocked by required conditions Details
Create and publish Docker images with specific build args / merge-ollama-images (push) Blocked by required conditions Details
Python CI / Format Backend (3.11.x) (push) Waiting to run Details
Python CI / Format Backend (3.12.x) (push) Waiting to run Details
Frontend Build / Format & Build Frontend (push) Waiting to run Details
Frontend Build / Frontend Unit Tests (push) Waiting to run Details
2025-05-05 17:43:51 +04:00
Tim Jaeryang Baek 11d599c55d
Merge pull request #13111 from tth37/perf_multi_thread_web_searching
perf: Concurrent processing for web search queries
2025-05-02 03:15:49 -07:00
Timothy Jaeryang Baek 6d81eef425 refac: reasoning detection 2025-05-02 14:04:12 +04:00
Timothy Jaeryang Baek 079af5fffe fix: send webhook notification when user is not active 2025-05-01 09:41:07 +04:00
tth37 cf2d7de873 refac: Implicit asyncio create_task 2025-04-29 00:20:55 +08:00
root 8a9de0a62f Fix bug that never triggers user notification webhooks 2025-04-27 21:31:34 +02:00
Timothy Jaeryang Baek 5030041683 chore: format 2025-04-23 16:05:15 +09:00
tth37 4b451b984b perf: Multi-thread web searching 2025-04-21 22:18:05 +08:00
izumi0004 99ce85f20f
fix: handling tool calls in streamed responses 2025-04-21 00:29:52 +08:00
tth37 79bde6fa47 fix: Align backend <source> tag indexing with frontend citation grouping 2025-04-17 22:27:22 +08:00
Timothy Jaeryang Baek e4c7417522 refac 2025-04-14 02:12:58 -07:00
Timothy Jaeryang Baek ec3b8fab5b refac 2025-04-14 01:08:16 -07:00
Timothy Jaeryang Baek f3fe82da80 fix: ongoing chat stop issue 2025-04-12 20:51:02 -07:00
Timothy Jaeryang Baek 881d81d87f refac: default tool calling behaviour 2025-04-12 17:26:35 -07:00
Timothy Jaeryang Baek 1921420319 refac
Co-Authored-By: dulicon <57261058+dulicon@users.noreply.github.com>
2025-04-10 20:01:07 -07:00
Timothy Jaeryang Baek f10566f3de feat: allow events from pipelines
Co-Authored-By: Anthony Durussel <87324020+anthonydurussel@users.noreply.github.com>
2025-04-10 09:20:18 -07:00
Alexander Grimm 1e7a36478b ~ update to latest change 2025-04-07 15:16:47 +02:00
Alexander Grimm d8a7e9c660 fix: correct document citation 2025-04-07 15:16:47 +02:00