  PVBLIC FoundationandGitHub
|
cf3635ba25
|
Update mistral.py
1. Intelligent Error Handling
Added _is_retryable_error() method to distinguish retryable vs non-retryable errors
Prevents unnecessary retries on client errors (4xx) that won't succeed
Caps retry delay at 30 seconds to prevent excessive waiting
2. Optimized Timeout Configuration
Upload: Capped at 2 minutes (was using full 5-minute timeout)
URL requests: 30 seconds (should be fast)
OCR processing: Full timeout (can take time)
Cleanup: 30 seconds (should be quick)
3. Enhanced Connection Pool
Increased connection limits: 20 total, 10 per host
Longer DNS cache TTL (10 minutes vs 5 minutes)
Increased keepalive timeout (60s vs 30s)
Added async DNS resolver for better performance
Granular timeout controls (connect, read, total)
4. Concurrency Control for Batch Processing
Added semaphore-based concurrency control (default: 5 concurrent)
Prevents API overwhelming while maintaining throughput
Configurable concurrency limit per workload
5. Memory Efficient Result Processing
Early exit for empty content validation
Better error metadata for debugging
Added content length tracking
Streamlined page processing logic
6. General Performance Improvements
Better error logging with truncated responses
Optimized metadata creation
Improved debug logging efficiency
|
2025-05-30 20:06:29 -07:00 |
|
 Timothy Jaeryang Baek
|
b2befd486f
|
refac
|
2025-05-30 01:24:54 +04:00 |
|
|
Timothy Jaeryang Baek
|
9306ae5972
|
refac
|
2025-05-30 01:19:56 +04:00 |
|
|
Timothy Jaeryang Baek
|
036ce12dd9
|
doc: changelog
|
2025-05-30 01:14:38 +04:00 |
|
|
Tim Jaeryang BaekandGitHub
|
d6c3f93cfd
|
Merge pull request #14509 from r0mdau/fix/audio-format
fix: only trust codec_name for audio conversion
|
2025-05-30 01:12:22 +04:00 |
|
 Romain Dauby
|
b12a493fe5
|
fix: only trust codec_name for audio conversion
Some files have .wav extension with incompatible OpenAI codec
|
2025-05-29 16:57:23 -04:00 |
|
|
Timothy Jaeryang Baek
|
e1e2c096e2
|
refac: PLEASE follow existing convention
|
2025-05-30 00:34:18 +04:00 |
|
|
Tim Jaeryang BaekandGitHub
|
ff353578db
|
Merge pull request #14370 from daw/feat/add-azure-openai-embeddings-option
feat:Add Azure OpenAI embedding support
|
2025-05-30 00:18:55 +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
|
7dc7d5c028
|
refac: PLEASE FOLLOW EXISTING CONVENTION
|
2025-05-29 03:47:02 +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
|
551597b9cc
|
chore: format
|
2025-05-29 02:36:33 +04:00 |
|
|
Timothy Jaeryang Baek
|
cb4299eb98
|
refac
|
2025-05-29 02:33:40 +04:00 |
|
|
Tim Jaeryang BaekandGitHub
|
042c37ea34
|
Merge pull request #14311 from Hisma/marker-api-content-extraction
feat: Marker api content extraction support
|
2025-05-29 02:21:13 +04:00 |
|
|
Timothy Jaeryang Baek
|
85a384fab5
|
enh: load tool by url
|
2025-05-29 02:08:54 +04:00 |
|
|
Timothy Jaeryang Baek
|
4461122a0e
|
fix: /api/v1/retrieval/query/collection endpoint
|
2025-05-28 18:45:47 +04:00 |
|
 notyusheng
|
efedb7ab1f
|
chore: removed duplicate css elements
|
2025-05-28 08:31:11 -04:00 |
|
|
Timothy Jaeryang Baek
|
d81886e315
|
refac
|
2025-05-28 01:42:42 +04:00 |
|
|
Timothy Jaeryang Baek
|
7effb04782
|
refac
|
2025-05-28 01:41:49 +04:00 |
|
|
Timothy Jaeryang Baek
|
f5fefb49d5
|
refac
|
2025-05-28 01:38:24 +04:00 |
|
|
Timothy Jaeryang Baek
|
e4a53e0a3c
|
refac
|
2025-05-28 01:34:53 +04:00 |
|
|
Tim Jaeryang BaekandGitHub
|
100a764293
|
Merge pull request #14402 from torisetxd/parallelized-model-fetching
perf: Parallelize base model fetching
|
2025-05-27 16:56:44 +04:00 |
|
|
Timothy Jaeryang Baek
|
1d216b82ba
|
refac
|
2025-05-27 16:48:17 +04:00 |
|
 torisetandGitHub
|
9eccce2444
|
Added proper type hints to new functions
Forgot about that...
|
2025-05-27 15:44:20 +03:00 |
|
|
torisetandGitHub
|
27de981246
|
Parallelize base model fetching
|
2025-05-27 15:35:16 +03:00 |
|
|
Timothy Jaeryang Baek
|
40bea00e3d
|
refac
|
2025-05-27 16:06:00 +04:00 |
|
|
Timothy Jaeryang Baek
|
b944acd3ff
|
refac: function cache
|
2025-05-27 14:39:35 +04:00 |
|
 Gunwoo Hur
|
14c3d0c2d1
|
Prevent duplicate function module loads with caching helper and refactor
|
2025-05-27 18:08:58 +09:00 |
|
 Hisma
|
e12a79c0e2
|
fix: handle json output format correctly
|
2025-05-27 01:12:03 -04:00 |
|
|
Hisma
|
a9405cc101
|
feat: Marker api content extraction support
|
2025-05-27 00:44:07 -04:00 |
|
|
Timothy Jaeryang Baek
|
efb54aa2e4
|
fix: image generation
|
2025-05-27 02:48:22 +04:00 |
|
|
Timothy Jaeryang Baek
|
5c74e56bd0
|
chore: format
|
2025-05-27 02:18:43 +04:00 |
|
|
Tim Jaeryang BaekandGitHub
|
1cb8fa0f03
|
Merge pull request #14362 from PVBLIC-F/fix/chat-engagement-critical
Fix/chat engagement critical
|
2025-05-27 02:17:34 +04:00 |
|
|
cheadings71
|
256034e285
|
Update misc.py
Before fix: Chat engagement failed with TypeError and KeyError
After fix: Chat works smoothly with automatic title generation and proper history
|
2025-05-26 14:55:48 -07:00 |
|
|
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
|
940a437631
|
refac
|
2025-05-27 01:16:11 +04:00 |
|
|
Timothy Jaeryang Baek
|
aaff204e7b
|
refac
|
2025-05-27 00:56:59 +04:00 |
|
|
Timothy Jaeryang Baek
|
2c7ccc69fe
|
enh: allow custom openapi json url
|
2025-05-27 00:20:47 +04:00 |
|
|
Timothy Jaeryang Baek
|
a38e44e870
|
enh: external tool server custom name/description support
|
2025-05-27 00:10:33 +04:00 |
|
|
Timothy Jaeryang Baek
|
b4caad928e
|
feat: load function from url
|
2025-05-26 23:52:22 +04:00 |
|
|
Tim Jaeryang BaekandGitHub
|
6062174602
|
Merge pull request #14228 from suleimanelkhoury/s3-tags-allowed-characters
fix: S3 allowed characters in Tags.
|
2025-05-26 22:43:21 +04:00 |
|
|
Timothy Jaeryang Baek
|
2d5b82df8c
|
enh: include sources field in non-streaming response
|
2025-05-26 22:22:37 +04:00 |
|
|
Timothy Jaeryang Baek
|
ffa51ece0c
|
refac: pinned chat endpoint
|
2025-05-26 22:15:21 +04:00 |
|
|
Timothy Jaeryang Baek
|
fc5dfd3536
|
refac
|
2025-05-26 22:02:40 +04:00 |
|
|
Tim Jaeryang BaekandGitHub
|
5d7c89964c
|
Merge pull request #14314 from fl0w1nd/dev
fix: Correctly handle toggle filters to prevent unintended activation
|
2025-05-26 21:58:57 +04:00 |
|
 Timothy Jaeryang BaekandJason Baker
|
4da75a9e78
|
feat: GZip, Brotli, ZStd compression middleware support
Co-Authored-By: Jason Baker <jason.th.baker@gmail.com>
|
2025-05-26 14:18:29 +04:00 |
|