Commit Graph

35 Commits

Author SHA1 Message Date
Josh Hawkins
24ac9f3e5a
Use sqlite-vec extension instead of chromadb for embeddings (#14163)
* swap sqlite_vec for chroma in requirements

* load sqlite_vec in embeddings manager

* remove chroma and revamp Embeddings class for sqlite_vec

* manual minilm onnx inference

* remove chroma in clip model

* migrate api from chroma to sqlite_vec

* migrate event cleanup from chroma to sqlite_vec

* migrate embedding maintainer from chroma to sqlite_vec

* genai description for sqlite_vec

* load sqlite_vec in main thread db

* extend the SqliteQueueDatabase class and use peewee db.execute_sql

* search with Event type for similarity

* fix similarity search

* install and add comment about transformers

* fix normalization

* add id filter

* clean up

* clean up

* fully remove chroma and add transformers env var

* readd uvicorn for fastapi

* readd tokenizer parallelism env var

* remove chroma from docs

* remove chroma from UI

* try removing custom pysqlite3 build

* hard code limit

* optimize queries

* revert explore query

* fix query

* keep building pysqlite3

* single pass fetch and process

* remove unnecessary re-embed

* update deps

* move SqliteVecQueueDatabase to db directory

* make search thumbnail take up full size of results box

* improve typing

* improve model downloading and add status screen

* daemon downloading thread

* catch case when semantic search is disabled

* fix typing

* build sqlite_vec from source

* resolve conflict

* file permissions

* try build deps

* remove sources

* sources

* fix thread start

* include git in build

* reorder embeddings after detectors are started

* build with sqlite amalgamation

* non-platform specific

* use wget instead of curl

* remove unzip -d

* remove sqlite_vec from requirements and load the compiled version

* fix build

* avoid race in db connection

* add scale_factor and bias to description zscore normalization
2024-10-07 14:30:45 -06:00
Josh Hawkins
68465aed49
Increase healthcheck start period to 5 minutes (#13968) 2024-09-25 15:14:10 -06:00
Nicolas Mowen
2362d0e838
Override onnx clip loading (#13800)
* Set caching options for hardware providers

* Always use CPU for searching

* Use new install strategy to remove onnxruntime and then install post wheels
2024-09-17 13:24:35 -06:00
Nicolas Mowen
90d7fc6bc5
Install no deps separately for wheel (#13799)
* Install no deps separately for wheel

* Fix order

* fix arg
2024-09-17 11:04:51 -06:00
Nicolas Mowen
5ff476c6f9
Configurable ffmpeg (#13722)
* Install multiple ffmpeg versions and add config to make it configurable

* Update docs

* Run ffprobe too

* Cleanup

* Apply config to go2rtc as well

* Fix ffmpeg bin

* Docs

* Restore path

* Cleanup env var

* Fix ffmpeg path for encoding

* Fix export

* Formatting
2024-09-13 15:14:51 -05:00
Jason Hunter
36cbffcc5e Semantic Search for Detections (#11899)
* Initial re-implementation of semantic search

* put docker-compose back and make reindex match docs

* remove debug code and fix import

* fix docs

* manually build pysqlite3 as binaries are only available for x86-64

* update comment in build_pysqlite3.sh

* only embed objects

* better error handling when genai fails

* ask ollama to pull requested model at startup

* update ollama docs

* address some PR review comments

* fix lint

* use IPC to write description, update docs for reindex

* remove gemini-pro-vision from docs as it will be unavailable soon

* fix OpenAI doc available models

* fix api error in gemini and metadata for embeddings
2024-08-29 20:19:50 -06:00
Nicolas Mowen
599dd7eecb
Build libusb for coral compatibility (#12681) 2024-07-30 16:32:32 -06:00
Nicolas Mowen
18b8e19847
Fix audio model download again (#12207)
* Fix audio model download again

* Update Dockerfile
2024-06-29 12:55:55 -06:00
Nicolas Mowen
48a87b16b8
Fix yamnet model download (#12200) 2024-06-29 09:35:34 -05:00
Nicolas Mowen
00e235867a
Downgrade go2rtc (#12139) 2024-06-24 08:26:32 -05:00
Nicolas Mowen
c72d304515
Update go2rtc (#12063) 2024-06-19 08:46:23 -06:00
Blake Blackshear
7031c47fb2
fix tempio install for arm64 (#11691) 2024-06-02 08:47:11 -05:00
Blake Blackshear
e431031112
improve tls implementation (#11690)
* improve tls implementation

* update docs
2024-06-02 06:48:28 -06:00
Nicolas Mowen
7bed854ff7
remove libusb build (#11571) 2024-05-27 16:52:19 -06:00
Blake Blackshear
bfeb7b8a96
upgrade to latest openvino version (#11563) 2024-05-27 14:49:35 -06:00
Blake Blackshear
1133202cbd
Auth! (#11347)
* reload the window on 401

* backend apis for auth

* add login page

* re-enable web linter

* fix login page routing

* bypass csrf for internal auth endpoint

* disable healthcheck in devcontainer target

* include login page in vite build

* redirect to login page on 401

* implement config for users and settings

* implement JWT actual secret

* add brute force protection on login

* add support for redirecting from auth failures on api calls

* return location for redirect

* default cookie name should pass regex test

* set hash iterations to current OWASP recommendation

* move users to database instead of config

* config option to reset admin password on startup

* user management UI

* check for deleted user on refresh

* validate username and fixes

* remove password constraint

* cleanup

* fix user check on refresh

* web fixes

* implement auth via new external port

* use x-forwarded-for to rate limit login attempts by ip

* implement logout and profile

* fixes

* lint fixes

* add support for user passthru from upstream proxies

* add support for specifying a logout url

* add documentation

* Update docs/docs/configuration/authentication.md

Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>

* Update docs/docs/configuration/authentication.md

Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>

---------

Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
2024-05-18 10:36:13 -06:00
Nicolas Mowen
97f5ba0145
Update go2rtc and implement stream probe to only show 2 way talk when supported (#11407)
* Support two way talk validation

* Fix handling

* Use go2rtc stream info to infer audio output

* Update go2rtc

* Update bundle policy

* Formatting
2024-05-17 07:30:22 -06:00
Marc Altmann
50ee447e52
Fix aarch64 build (#11289)
* fix aarch64 build

* change order of packages
2024-05-09 07:22:34 -06:00
harakas
44d8cdbba1
AMD GPU support with the rocm detector and YOLOv8 pretrained model download (#9762)
* ROCm AMD/GPU based build and detector, WIP

* detectors/rocm: separate yolov8 postprocessing into own function; fix box scaling; use cv2.dnn.blobForImage for preprocessing; assert on required model parameters

* AMD/ROCm: add couple of more ultralytics models; comments

* docker/rocm: make imported model files readable by all

* docker/rocm: readme about running on AMD GPUs

* docker/rocm: updated README

* docker/rocm: updated README

* docker/rocm: updated README

* detectors/rocm: separated preprocessing functions into yolo_utils.py

* detector/plugins: added onnx cpu plugin

* docker/rocm: updated container with limite label sets

* example detectors view

* docker/rocm: updated README.md

* docker/rocm: update README.md

* docker/rocm: do not set HSA_OVERRIDE_GFX_VERSION at all for the general version as the empty value broke rocm

* detectors: simplified/optimized yolov8_postprocess

* detector/yolo_utils: indentation, remove unused variable

* detectors/rocm: default option to conserve cpu usage at the expense of latency

* detectors/yolo_utils: use nms to prefilter overlapping boxes if too many detected

* detectors/edgetpu_tfl: add support for yolov8

* util/download_models: script to download yolov8 model files

* docker/main: add download-models overlay into s6 startup

* detectors/rocm: assume models are in /config/model_cache/yolov8/

* docker/rocm: compile onnx files into mxr files at startup

* switch model download into bash script

* detectors/rocm: automatically override HSA_OVERRIDE_GFX_VERSION for couple of known chipsets

* docs: rocm detector first notes

* typos

* describe builds (harakas temporary)

* docker/rocm: also build a version for gfx1100

* docker/rocm: use cp instead of tar

* docker.rocm: remove README as it is now in detector config

* frigate/detectors: renamed yolov8_preprocess->preprocess, pass input tensor element type

* docker/main: use newer openvino (2023.3.0)

* detectors: implement class aggregation

* update yolov8 model

* add openvino/yolov8 support for label aggregation

* docker: remove pointless s6/timeout-up files

* Revert "detectors: implement class aggregation"

This reverts commit dcfe6bbf6f.

* detectors/openvino: remove class aggregation

* detectors: increase yolov8 postprocessing score trershold to 0.5

* docker/rocm: separate rocm distributed files into its own build stage

* Update object_detectors.md

* updated CODEOWNERS file for rocm

* updated build names for documentation

* Revert "docker/main: use newer openvino (2023.3.0)"

This reverts commit dee95de908.

* reverrted openvino detector

* reverted edgetpu detector

* scratched rocm docs from any mention of edgetpu or openvino

* Update docs/docs/configuration/object_detectors.md

Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>

* renamed frigate.detectors.yolo_utils.py -> frigate.detectors.util.py

* clarified rocm example performance

* Improved wording and clarified text

* Mentioned rocm detector for AMD GPUs

* applied ruff formating

* applied ruff suggested fixes

* docker/rocm: fix missing argument resulting in larger docker image sizes

* docs/configuration/object_detectors: fix links to yolov8 release files

---------

Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
2024-02-10 06:41:46 -06:00
Stephen Advincula
f6a4c2a7b3 bump go2rtc to 1.8.5 (#9487) 2024-02-06 06:52:20 -06:00
Pierre Belanger
15f79d91e3 Remove deprecated RTMP port 1935 (#9137) 2024-01-31 12:56:11 +00:00
Blake Blackshear
bdebb99b5a Use new UI (#8983)
* fixup build

* swap frontends
2024-01-31 12:56:11 +00:00
Sergey Krashevich
ea247ca816
go2rtc 1.8.4 (#8691) 2023-11-21 01:07:54 +00:00
Blake Blackshear
4879de263b
Docs improvements (#8641)
* go all in on ruff

* upgrade docusaurus

* add netlify toml

* broken link

* fix netlify toml

* start filling out guide

* add debian setup detail

* simplify bash command
2023-11-18 08:04:43 -06:00
Nicolas Mowen
97c15f7ef3
Update go2rtc to 1.8.3 (#8627) 2023-11-16 01:24:26 +00:00
Nicolas Mowen
d0036b2f77
Update go2rtc to 1.8.2 (#8459)
* Update go2rtc to 1.8.2

* Update docs for 1.8.2
2023-11-09 06:43:06 -06:00
Sergey Krashevich
cac37e484d
Upd: go2rtc v1.8.1 (#8166)
* go2rtc v1.8.0

* 1.8.1
2023-10-16 06:42:24 -05:00
Felipe Santos
97e5a98b95
Fix jetson docker build with old apt key (#8112)
* Fix jetson docker build with old apt key

* Fix CI
2023-10-09 18:16:05 -05:00
Felipe Santos
3a460133d4
Add docker healthcheck (#8006)
* Add docker healthcheck

* Fix unknown start-interval

* Add HEALTHCHECK for tensorrt and bump default start-period

* Move healthcheck to deps stage
2023-10-07 09:21:03 -05:00
Nicolas Mowen
080d7a2d88
Update go2rtc to 1.7.1 (#7657)
* Update go2rtc to 1.7.0

* Update docs references

* Add docs for homekit restream

* Exit with better error message when substitution is not correct

* Formatting

* Fix pin

* Update go2rtc dep

* Update go2rtc docs references

* Fix name

* Mute player by default

* Remove homekit mention
2023-09-21 06:52:46 -06:00
Sergey Krashevich
ef6b464d0e
Update libusb version to v1.0.26 in Dockerfile (#7585) 2023-09-01 07:01:06 -05:00
Sergey Krashevich
eaf7078d98
Refactor Dockerfile to use scratch as base image and add go2rtc binary using ADD command (#7321) 2023-07-28 21:33:21 -05:00
Nate Meyer
b42e995f0f
Update OpenVINO 2022.3.1 (#7319)
* Use build platform for running OpenVino model conversion

* Update OpenVINO to 2022.3.1 and upgrade numpy
2023-07-28 19:27:53 -05:00
Andrew Reiter
a96a951e23
Nvidia Jetson ffmpeg + TensorRT support (#6458)
* Non-Jetson changes

Required for later commits:
- Allow base image to be overridden (and don't assume its WORKDIR)
- Ensure python3.9
- Map hwaccel decode presets as strings instead of lists
Not required:
- Fix existing documentation
- Simplify hwaccel scale logic

* Prepare for multi-arch tensorrt build

* Add tensorrt images for Jetson boards

* Add Jetson ffmpeg hwaccel

* Update docs

* Add CODEOWNERS

* CI

* Change default model from yolov7-tiny-416 to yolov7-320

In my experience the tiny models perform markedly worse without being
much faster

* fixup! Update docs
2023-07-26 05:50:41 -05:00
Nicolas Mowen
dc44a6c3b4
Community Supported Boards Framework (#7114)
* Make main frigate build non rpi specific and build rpi using base image

* Add boards to sidebar

* Fix docker build

* Fix docs build

* Update pr branch for testing

* remove target from rpi build

* Remove manual build

* Add push build for rpi

* fix typos, improve wording

* Add arm build for rpi

* Cleanup and add default github ref name

* Cleanup docker build file system

* Setup to use docker bake

* Add ci/cd for bake

* Fix path

* Fix devcontainer

* Set targets

* Fix build

* Fix syntax

* Add wheels target

* Move dev container to trt

* Update key and fix rpi local

* Move requirements files and set intermediate targets

* Add back --load

* Update docs for community board development

* Update installation docs to reflect different builds available

* Update docs with official and community supported headers

* Update codeowners docs

* Update docs

* Assemble main and standard builds

* Change order of pushes

* Remove community board after successful build

* Fix rpi bake file names
2023-07-23 16:45:29 -05:00