Fynn Petersen-Frey
49c378d706
fix(ml): re-enable ARMNN integration ( #7053 )
2024-02-12 13:29:55 -05:00
Mert
0c4df216d7
feat(ml): improve test coverage ( #7041 )
...
* update e2e
* tokenizer tests
* more tests, remove unnecessary code
* fix e2e setting
* add tests for loading model
* update workflow
* fixed test
2024-02-11 17:58:56 -05:00
Mert
c9b7f4e690
chore(ml): make execution provider log info-level ( #7024 )
...
* change debug log to info
* update test
2024-02-11 06:12:11 +00:00
renovate[bot]
f7d0a8ed0a
fix(deps): update dependency fastapi to v0.109.1 [security] ( #6923 )
...
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2024-02-06 12:21:24 +01:00
Mert
79d3342c3d
fix(ml): openvino not working with dynamic axes ( #6871 )
...
* convert to static
* add comment about gross code
* formatting
* fixed test
* fix typing
* cleanup
* formatting
* Revert "formatting"
This reverts commit 073965c47ebb56bd3297
2024-02-03 05:35:26 +00:00
Alex The Bot
07466fa7b7
Version v1.94.1
2024-01-31 19:21:00 +00:00
Alex The Bot
a7ed2b7132
Version v1.94.0
2024-01-31 15:41:53 +00:00
renovate[bot]
2bcba526df
fix(deps): update machine-learning ( #6745 )
...
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2024-01-29 20:43:14 -05:00
Mert
f52994e8ca
fix(ml): model paths not working ( #6705 )
...
* fix str enum string repr
* fixed typing
2024-01-28 20:54:33 +00:00
Mert
a84b6f5fb1
feat(ml): conditionally download .armnn models ( #6650 )
2024-01-28 10:31:59 -05:00
Mert
2249f7d42a
fix(ml): handle missing context_length field ( #6695 )
...
* handle missing `context_length` field
* specify list type
2024-01-27 19:50:50 -05:00
Mert
ca28e1e7a8
fix(ml): error logging ( #6646 )
...
* fix ml error logging
* exclude certain libraries from traceback
2024-01-26 00:26:27 +00:00
renovate[bot]
1c35110806
fix(deps): update dependency orjson to v3.9.12 ( #6600 )
2024-01-23 18:10:10 -05:00
renovate[bot]
871d0c725f
chore(deps): pin dependencies ( #6436 )
...
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2024-01-22 11:08:00 -05:00
Mert
95cfe22866
feat(ml)!: cuda and openvino acceleration ( #5619 )
...
* cuda and openvino ep, refactor, update dockerfile
* updated workflow
* typing fixes
* added tests
* updated ml test gh action
* updated README
* updated docker-compose
* added compute to hwaccel.yml
* updated gh matrix
updated gh matrix
updated gh matrix
updated gh matrix
updated gh matrix
give up
* remove cuda/arm64 build
* add hwaccel image tags to docker-compose
* remove unnecessary quotes
* add suffix to git tag
* fixed kwargs in base model
* armnn ld_library_path
* update pyproject.toml
* add armnn workflow
* formatting
* consolidate hwaccel files, update docker compose
* update hw transcoding docs
* add ml hwaccel docs
* update dev and prod docker-compose
* added armnn prerequisite docs
* support 3.10
* updated docker-compose comments
* formatting
* test coverage
* don't set arena extend strategy for openvino
* working openvino
* formatting
* fix dockerfile
* added type annotation
* add wsl configuration for openvino
* updated lock file
* copy python3
* comment out extends section
* fix platforms
* simplify workflow suffix tagging
* simplify aio transcoding doc
* update docs and workflow for `hwaccel.yml` change
* revert docs
2024-01-21 18:22:39 -05:00
Alex The Bot
4ebb9974ff
Version v1.93.3
2024-01-20 16:03:18 +00:00
Alex The Bot
3dddc6b449
Version v1.93.2
2024-01-19 18:29:04 +00:00
Alex The Bot
d5af357992
Version v1.93.1
2024-01-19 15:01:17 +00:00
Alex The Bot
fa0b7c8563
Version v1.93.0
2024-01-19 02:14:46 +00:00
Mert
68f52818ae
feat(server): separate face clustering job ( #5598 )
...
* separate facial clustering job
* update api
* fixed some tests
* invert clustering
* hdbscan
* update api
* remove commented code
* wip dbscan
* cleanup
removed cluster endpoint
remove commented code
* fixes
updated tests
minor fixes and formatting
fixed queuing
refinements
* scale search range based on library size
* defer non-core faces
* optimizations
removed unused query option
* assign faces individually for correctness
fixed unit tests
remove unused method
* don't select face embedding
update sql
linting
fixed ml typing
* updated job mock
* paginate people query
* select face embeddings because typeorm
* fix setting face detection concurrency
* update sql
formatting
linting
* simplify logic
remove unused imports
* more specific delete signature
* more accurate typing for face stubs
* add migration
formatting
* chore: better typing
* don't select embedding by default
remove unused import
* updated sql
* use normal try/catch
* stricter concurrency typing and enforcement
* update api
* update job concurrency panel to show disabled queues
formatting
* check jobId in queueAll
fix tests
* remove outdated comment
* better facial recognition icon
* wording
wording
formatting
* fixed tests
* fix
* formatting & sql
* try to fix sql check
* more detailed description
* update sql
* formatting
* wording
* update `minFaces` description
---------
Co-authored-by: Jason Rasmussen <jrasm91@gmail.com>
Co-authored-by: Alex Tran <alex.tran1502@gmail.com>
2024-01-18 00:08:48 -05:00
renovate[bot]
d3ff2408bc
chore(deps): update mambaorg/micromamba:bookworm-slim docker digest to 377aafa ( #6434 )
...
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2024-01-16 16:39:31 -05:00
Mert
e2666f0e74
fix(ml): remove unused import ( #6356 )
...
* remove unused import
* formatting
2024-01-13 00:25:26 -05:00
renovate[bot]
20be42cec0
chore(deps): update machine-learning ( #6302 )
...
* chore(deps): update machine-learning
* fix typing, use new lifespan syntax
* wrap in try / finally
* move log
---------
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
Co-authored-by: mertalev <101130780+mertalev@users.noreply.github.com>
2024-01-13 05:00:09 +00:00
Fynn Petersen-Frey
753292956e
feat(ml): ARMNN acceleration ( #5667 )
...
* feat(ml): ARMNN acceleration for CLIP
* wrap ANN as ONNX-Session
* strict typing
* normalize ARMNN CLIP embedding
* mutex to handle concurrent execution
* make inputs contiguous
* fine-grained locking; concurrent network execution
---------
Co-authored-by: mertalev <101130780+mertalev@users.noreply.github.com>
2024-01-11 18:26:46 +01:00
Alex The Bot
df59b2099f
Version v1.92.1
2024-01-08 15:24:38 +00:00
Alex The Bot
319ddfda53
Version v1.92.0
2024-01-08 05:19:11 +00:00
renovate[bot]
3edc87f684
fix(deps): update machine-learning ( #5180 )
...
* fix(deps): update machine-learning
* updated ruff command
* use isinstance
---------
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
Co-authored-by: mertalev <101130780+mertalev@users.noreply.github.com>
2023-12-25 22:37:48 -05:00
renovate[bot]
612590feda
fix(deps): update dependency pillow to v10 [security] ( #5944 )
2023-12-23 14:10:05 +00:00
Mert
19ea0ead85
renovate: use in-range-only strategy for python ( #5937 )
2023-12-23 09:04:36 -05:00
Mert
4dd7412a86
pin python ( #5904 )
2023-12-21 11:54:56 -05:00
Mert
092a23fd7f
feat(server,ml): remove image tagging ( #5903 )
...
* remove image tagging
* updated lock
* fixed tests, improved logging
* be nice
* fixed tests
2023-12-20 20:47:56 -05:00
Alex The Bot
b40859551b
Version v1.91.4
2023-12-19 03:34:19 +00:00
Alex The Bot
08f66c2ae5
Version v1.91.3
2023-12-17 16:57:16 +00:00
Mert
09402eb6d0
fix(ml): disable core dumps ( #5770 )
...
* update dockerfile
* remove sysctl line
2023-12-16 20:30:29 -06:00
Alex The Bot
a15c799ba3
Version v1.91.2
2023-12-16 23:19:58 +00:00
Alex The Bot
0aae9696f6
Version v1.91.1
2023-12-16 17:26:51 +00:00
Mohamed BOUSSAID
7839be3b49
Adding the new models to the whitelist ( #5736 )
2023-12-15 22:45:14 +00:00
Alex The Bot
e9a8daa924
Version v1.91.0
2023-12-15 15:22:37 +00:00
renovate[bot]
e05c7f5b76
chore(deps): update mambaorg/micromamba:bookworm-slim docker digest to 5ea70d2 ( #5707 )
...
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-12-14 23:09:48 -05:00
Mert
d729c863c8
chore(ml): improve shutdown ( #5689 )
2023-12-14 13:51:24 -06:00
renovate[bot]
d2ad01cd2f
chore(deps): update python:3.11-slim-bookworm docker digest to cfd7ed5 ( #5572 )
...
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-12-09 21:15:15 -06:00
Alex The Bot
429ad28810
Version v1.90.2
2023-12-08 14:23:04 +00:00
Alex The Bot
d2fbbe790b
Version v1.90.1
2023-12-08 04:20:27 +00:00
Alex The Bot
c174f0e871
Version v1.90.0
2023-12-07 18:32:45 +00:00
renovate[bot]
259700c45f
chore(deps): update mambaorg/micromamba:bookworm-slim docker digest to e296d47 ( #5487 )
...
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-12-04 19:37:08 -05:00
renovate[bot]
56aed8246d
chore(deps): update python:3.11-slim-bookworm docker digest to cc75851 ( #5462 )
...
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-12-04 13:26:41 -06:00
renovate[bot]
6959cf689b
chore(deps): update python:3.11-bookworm docker digest to ba7a7ac ( #5438 )
...
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-12-02 18:35:23 +00:00
renovate[bot]
cbdcbd3ab4
chore(deps): update python:3.11-slim-bookworm docker digest to 8f82989 ( #5435 )
...
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-12-01 20:24:50 +00:00
renovate[bot]
cb00d45e3d
chore(deps): update python:3.11-bookworm docker digest to 47c1829 ( #5434 )
...
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-12-01 20:13:23 +00:00
renovate[bot]
40964187bb
chore(deps): update python:3.11-slim-bookworm docker digest to 23f5220 ( #5388 )
...
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-12-01 18:36:54 +00:00
renovate[bot]
fe3d951f26
chore(deps): update python:3.11-bookworm docker digest to c56b0c6 ( #5387 )
...
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-12-01 18:36:30 +00:00
Alex The Bot
8b6a79ad9e
Version v1.89.0
2023-11-29 19:20:24 +00:00
renovate[bot]
1fa5e220a1
chore(deps): pin dependencies ( #5367 )
...
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-11-29 02:09:11 +00:00
Mert
6e10d15f2c
pin python ( #5272 )
2023-11-22 19:42:17 -05:00
Alex The Bot
55fa3234fd
Version v1.88.2
2023-11-21 16:09:18 +00:00
Alex Tran
a13052e24c
Revert "Version v1.88.2"
...
This reverts commit bc2c73e499
2023-11-21 09:07:50 -06:00
Alex The Bot
bc2c73e499
Version v1.88.2
2023-11-21 15:01:06 +00:00
Alex The Bot
9cf40afaf0
Version v1.88.1
2023-11-21 03:00:19 +00:00
Alex The Bot
0f596e278c
Version v1.88.0
2023-11-20 20:47:37 +00:00
Mert
ddf04a7eb4
chore(ml): increase spool threshold to 64MiB ( #5176 )
2023-11-20 09:05:35 -06:00
Mert
f7ada7351e
update onnxruntime ( #5175 )
2023-11-20 08:44:45 -06:00
Alex The Bot
ec51a9f6d6
Version v1.87.0
2023-11-18 02:58:26 +00:00
Mert
a6af4892e3
fix(ml): better model unloading ( #3340 )
...
* restart process on inactivity
* formatting
* always update `last_called`
* load models sequentially
* renamed variable, updated docs
* formatting
* made poll env name consistent with model ttl env
2023-11-16 20:42:44 -06:00
Alex The Bot
a7cacafe25
Version v1.86.0
2023-11-14 04:08:18 +00:00
Mert
291159e7fc
fixed tests ( #5017 )
2023-11-13 19:37:39 +00:00
Mert
935f471ccb
chore(ml): use strict mypy ( #5001 )
...
* improved typing
* improved export typing
* strict mypy & check export folder
* formatting
* add formatting checks for export folder
* re-added init call
2023-11-13 10:18:46 -06:00
Mert
328a58ac0d
feat(ml): add face models ( #4952 )
...
added models to config dropdown
fixed downloading
updated tests
use hf for face models
formatting
2023-11-11 19:04:49 -06:00
Alex The Bot
37ab37bffc
Version v1.85.0
2023-11-08 03:20:59 +00:00
Alex The Bot
cf4ec06750
Version v1.84.0
2023-11-01 14:46:59 +00:00
Mert
87a0ba3db3
feat(ml): export clip models to ONNX and host models on Hugging Face ( #4700 )
...
* export clip models
* export to hf
refactored export code
* export mclip, general refactoring
cleanup
* updated conda deps
* do transforms with pillow and numpy, add tokenization config to export, general refactoring
* moved conda dockerfile, re-added poetry
* minor fixes
* updated link
* updated tests
* removed `requirements.txt` from workflow
* fixed mimalloc path
* removed torchvision
* cleaner np typing
* review suggestions
* update default model name
* update test
2023-10-31 05:02:04 -05:00
Alex The Bot
d98a2a5f79
Version v1.83.0
2023-10-28 13:32:48 +00:00
Alex The Bot
31987bc043
Version v1.82.1
2023-10-18 17:14:26 +00:00
Alex The Bot
219f99e516
Version v1.82.0
2023-10-17 01:24:08 +00:00
Mert
d8ecefaea5
chore(ml): removed vit-b check and st warning ( #4422 )
2023-10-10 12:26:30 -05:00
Alex The Bot
126dd45751
Version v1.81.1
2023-10-04 17:53:42 +00:00
Alex The Bot
81d51fbd7e
Version v1.81.0
2023-10-03 20:48:23 +00:00
Alex The Bot
66e860a08e
Version v1.80.0
2023-10-02 14:47:21 +00:00
Alex The Bot
e050121dbf
Version v1.79.1
2023-09-22 01:37:20 +00:00
Alex The Bot
86f5ceb80e
Version v1.79.0
2023-09-21 14:17:00 +00:00
Alex The Bot
a3206bf950
Version v1.78.1
2023-09-14 13:56:33 +00:00
Alex The Bot
b42ca61e1f
Version v1.78.0
2023-09-13 08:24:02 +00:00
Mert
cb437829f3
chore(docs): updated ML documentation ( #4063 )
2023-09-12 13:22:42 +07:00
Mert
258b98c262
fix(ml): load models in separate threads ( #4034 )
...
* load models in thread
* set clip mode logs to debug level
* updated tests
* made fixtures slightly less ugly
* moved responses to json file
* formatting
2023-09-09 16:02:44 +07:00
Alexandre Bouijoux
b8777d7739
Add french documentation ( #4010 )
...
* Copy original README for online editing
* Translate to french
* Add link from other documentations
* Add machine-learning french doc
* Typos
* Missing word
---------
Co-authored-by: Alexandre Bouijoux <alexandre@bouijoux.fr>
2023-09-08 13:48:39 +07:00
Mert
0a24ff90bb
fix(ml): set higher default worker timeout ( #4007 )
2023-09-07 08:27:29 +07:00
Alex The Bot
608543da0b
Version v1.77.0
2023-09-06 03:30:44 +00:00
Mert
3cf0f5f11b
fix(ml): model downloading improvements ( #3988 )
...
* handle ort `NoSuchFile` error, stricter file check
* keep exception order
2023-09-06 08:48:40 +07:00
Mert
b7fd5dcb4a
dev(ml): fixed docker-compose.dev.yml, updated locust ( #3951 )
...
* fixed dev docker compose
* updated locustfile
* deleted old script, moved comments to locustfile
2023-09-01 21:59:17 -04:00
Daniele Ricci
c7d53a5006
docs: remove obsolete environment variables ( #3926 )
...
* Obsolete environment variables
* Review fixes
* Review fixes
* Review fixes
2023-09-01 18:05:45 +07:00
Mert
41461e0d5d
chore(ml): memory optimisations ( #3934 )
2023-08-31 18:30:53 -05:00
Alex The Bot
58ae734fc2
Version v1.76.1
2023-08-30 08:26:04 +00:00
Mert
54b2779b79
chore(ml): improved logging ( #3918 )
...
* fixed `minScore` not being set correctly
* apply to init
* don't send `enabled`
* fix eslint warning
* added logger
* added logging
* refinements
* enable access log for info level
* formatting
* merged strings
---------
Co-authored-by: Alex <alex.tran1502@gmail.com>
2023-08-30 08:22:01 +00:00
Mert
df26e12db6
fix(ml): minScore not being set correctly ( #3916 )
...
* fixed `minScore` not being set correctly
* apply to init
* don't send `enabled`
* fix eslint warning
* better error message
2023-08-30 03:16:00 -05:00
Alex The Bot
49c2d4d115
Version v1.76.0
2023-08-29 19:24:43 +00:00
Mert
bcc36d14a1
feat(ml)!: customizable ML settings ( #3891 )
...
* consolidated endpoints, added live configuration
* added ml settings to server
* added settings dashboard
* updated deps, fixed typos
* simplified modelconfig
updated tests
* Added ml setting accordion for admin page
updated tests
* merge `clipText` and `clipVision`
* added face distance setting
clarified setting
* add clip mode in request, dropdown for face models
* polished ml settings
updated descriptions
* update clip field on error
* removed unused import
* add description for image classification threshold
* pin safetensors for arm wheel
updated poetry lock
* moved dto
* set model type only in ml repository
* revert form-data package install
use fetch instead of axios
* added slotted description with link
updated facial recognition description
clarified effect of disabling tasks
* validation before model load
* removed unnecessary getconfig call
* added migration
* updated api
updated api
updated api
---------
Co-authored-by: Alex Tran <alex.tran1502@gmail.com>
2023-08-29 08:58:00 -05:00
Alex The Bot
f1027d7807
Version v1.75.2
2023-08-26 22:34:54 +00:00
Alex The Bot
cc1fecfffd
Version v1.75.1
2023-08-26 18:31:14 +00:00
Alex The Bot
6fe214a784
Version v1.75.0
2023-08-26 04:44:39 +00:00
Mert
165b91b068
feat(ml)!: switch image classification and CLIP models to ONNX ( #3809 )
2023-08-25 06:28:51 +02:00
Mert
60729a091a
make lazy loading default ( #3797 )
2023-08-20 18:24:14 -05:00
