* Run ONNX models on a Mac's Neural Engine through lighter's plugin provider
lighter's lighter.sh/ane device places an ONNX Runtime plugin execution
provider in the container. When it is present, the ONNX session setup
registers it once and opens sessions on its Neural Engine device, the same
place CUDA, ROCm and OpenVINO are chosen, so the onnx detector (and any
model that is not pinned to the CPU) runs there with no configuration. The
hardware probe reports it as an onnx unit.
* docs: hardware decode on an Apple Silicon Mac under lighter
A community section on the video decoding page: lighter's lighter.sh/video
device, hwaccel_args -c:v h264_v4l2m2m, and why the Raspberry Pi presets
decode a single-stream camera in software. The detector docs link to it.
* docs: set the lighter decoder per camera when codecs are mixed
* docs: the ONNX detector on a Mac's Neural Engine under lighter
* Format the Neural Engine provider setup
* Fall back to the default providers when the Neural Engine cannot load a model
* Apple Silicon ffmpeg presets for lighter's media engine, recommended when it is present
The CUDA execution provider returns an identical vector for every image when jina-clip-v2 is built below ORT_ENABLE_EXTENDED, so every thumbnail embedding written on a GPU was the same normalized garbage and semantic search returned the same results for any query. Reproduced on two different NVIDIA cards, across onnxruntime 1.22 and 1.24, and on both the 0.17 and 0.18 CUDA stacks, so it isn't specific to any of those. ORT_ENABLE_ALL isn't an option because it fails to build on CPU with a SimplifiedLayerNormFusion error, leaving EXTENDED as the only level that works on both providers. jinav1 is unaffected and stays on BASIC.
* Pin ruff
* Add python upgrade fixes
This enables python upgrade checks in ruff to look for deprecated types and patterns. This namely fixes:
- usage of deprecated `Typing` which is now built in
- some specific exceptions which are caught and have new aliases
Some specific UP checks were also ignored as they are stylistic / unimportant and likely to cause bugs
* Remove async blocking calls
Use asyncio.to_thread on two remaining blocking calls to fix hanging event thread loop. Enable this specific rule to block it in the future.
* Use proper logging mechanism
* Correctly format logs
* Raise with context
When raising an exception include the from context to improve debugging
* Cleanup
* serialize OpenVINO inference per process to prevent concurrent-inference segfault
* clean up
* add max scaling meta to login page
* add more detect section field messages
* fix icon layout in settings field messages
* tweak edit icon color
* start audio transcription post processor when enabled on any camera
* Fetch embed key whenever an error occurs in case the llama server was restarted
* mypy
* add tooltips for colored dots in settings menu
* add ability to reorder cameras from management pane
* add ability to reorder birdseye
* add reordering save text to camera management view
* Include NPU in latency performance hint
* Implement turbo for NPU on object detection
* hide order fields
* drop auto-derived field paths from camera value when unset globally
* use correct field type for export hwaccel args
* add debug replay to detail actions menu
* clarify debug replay in docs
* guard get_current_frame_time against missing camera state
* Implement debug reply from export
* Refactor debug replay to use sources for dynamic playback
* Mypy
* fix debug export replay source timestamp handling
* skip replay cameras in stats immediately
* broadcast debug replay state over ws and buffer pre-OPEN sends
- push debug replay session state over the job_state ws topic so the status bar reacts instantly to start/stop without polling
- fix child-effect-before-parent-effect race in WsProvider that silently dropped initial snapshot requests on cold load
* fix debug replay test hang
---------
Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
On multi-GPU systems, OpenVINO enumerates devices as "GPU.0", "GPU.1",
etc. rather than a single "GPU". The exact string match in
is_openvino_gpu_npu_available() fails to recognize these suffixed device
names, causing enrichments (face recognition, semantic search) to
silently fall back to CPU-only inference via ONNXModelRunner instead of
using OpenVINOModelRunner on GPU.
Switch from exact match to prefix match so both single-GPU ("GPU") and
multi-GPU ("GPU.0", "GPU.1") device names are correctly detected, along
with any future suffixed variants for NPU and other accelerators.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* Update to ROCm 7.2.3
* Add inference time for 9060XT
* Update times
* Update hardware info for latest ROCm
* Add env vars to save kernels and miopen database
* re-enable face recognition for ROCm
* Update
* Save LLVM cache
* Update version
* Create scaffolding for case management (#21293)
* implement case management for export apis (#21295)
* refactor vainfo to search for first GPU (#21296)
use existing LibvaGpuSelector to pick appropritate libva device
* Case management UI (#21299)
* Refactor export cards to match existing cards in other UI pages
* Show cases separately from exports
* Add proper filtering and display of cases
* Add ability to edit and select cases for exports
* Cleanup typing
* Hide if no unassigned
* Cleanup hiding logic
* fix scrolling
* Improve layout
* Camera connection quality indicator (#21297)
* add camera connection quality metrics and indicator
* formatting
* move stall calcs to watchdog
* clean up
* change watchdog to 1s and separately track time for ffmpeg retry_interval
* implement status caching to reduce message volume
* Export filter UI (#21322)
* Get started on export filters
* implement basic filter
* Implement filtering and adjust api
* Improve filter handling
* Improve navigation
* Cleanup
* handle scrolling
* Refactor temperature reporting for detectors and implement Hailo temp reading (#21395)
* Add Hailo temperature retrieval
* Refactor `get_hailo_temps()` to use ctxmanager
* Show Hailo temps in system UI
* Move hailo_platform import to get_hailo_temps
* Refactor temperatures calculations to use within detector block
* Adjust webUI to handle new location
---------
Co-authored-by: tigattack <10629864+tigattack@users.noreply.github.com>
* Camera-specific hwaccel settings for timelapse exports (correct base) (#21386)
* added hwaccel_args to camera.record.export config struct
* populate camera.record.export.hwaccel_args with a cascade up to camera then global if 'auto'
* use new hwaccel args in export
* added documentation for camera-specific hwaccel export
* fix c/p error
* missed an import
* fleshed out the docs and comments a bit
* ruff lint
* separated out the tips in the doc
* fix documentation
* fix and simplify reference config doc
* Add support for GPU and NPU temperatures (#21495)
* Add rockchip temps
* Add support for GPU and NPU temperatures in the frontend
* Add support for Nvidia temperature
* Improve separation
* Adjust graph scaling
* Exports Improvements (#21521)
* Add images to case folder view
* Add ability to select case in export dialog
* Add to mobile review too
* Add API to handle deleting recordings (#21520)
* Add recording delete API
* Re-organize recordings apis
* Fix import
* Consolidate query types
* Add media sync API endpoint (#21526)
* add media cleanup functions
* add endpoint
* remove scheduled sync recordings from cleanup
* move to utils dir
* tweak import
* remove sync_recordings and add config migrator
* remove sync_recordings
* docs
* remove key
* clean up docs
* docs fix
* docs tweak
* Media sync API refactor and UI (#21542)
* generic job infrastructure
* types and dispatcher changes for jobs
* save data in memory only for completed jobs
* implement media sync job and endpoints
* change logs to debug
* websocket hook and types
* frontend
* i18n
* docs tweaks
* endpoint descriptions
* tweak docs
* use same logging pattern in sync_recordings as the other sync functions (#21625)
* Fix incorrect counting in sync_recordings (#21626)
* Update go2rtc to v1.9.13 (#21648)
Co-authored-by: Eugeny Tulupov <eugeny.tulupov@spirent.com>
* Refactor Time-Lapse Export (#21668)
* refactor time lapse creation to be a separate API call with ability to pass arbitrary ffmpeg args
* Add CPU fallback
* Optimize empty directory cleanup for recordings (#21695)
The previous empty directory cleanup did a full recursive directory
walk, which can be extremely slow. This new implementation only removes
directories which have a chance of being empty due to a recent file
deletion.
* Implement llama.cpp GenAI Provider (#21690)
* Implement llama.cpp GenAI Provider
* Add docs
* Update links
* Fix broken mqtt links
* Fix more broken anchors
* Remove parents in remove_empty_directories (#21726)
The original implementation did a full directory tree walk to find and remove
empty directories, so this implementation should remove the parents as well,
like the original did.
* Implement LLM Chat API with tool calling support (#21731)
* Implement initial tools definiton APIs
* Add initial chat completion API with tool support
* Implement other providers
* Cleanup
* Offline preview image (#21752)
* use latest preview frame for latest image when camera is offline
* remove frame extraction logic
* tests
* frontend
* add description to api endpoint
* Update to ROCm 7.2.0 (#21753)
* Update to ROCm 7.2.0
* ROCm now works properly with JinaV1
* Arcface has compilation error
* Add live context tool to LLM (#21754)
* Add live context tool
* Improve handling of images in request
* Improve prompt caching
* Add networking options for configuring listening ports (#21779)
* feat: add X-Frame-Time when returning snapshot (#21932)
Co-authored-by: Florent MORICONI <170678386+fmcloudconsulting@users.noreply.github.com>
* Improve jsmpeg player websocket handling (#21943)
* improve jsmpeg player websocket handling
prevent websocket console messages from appearing when player is destroyed
* reformat files after ruff upgrade
* Allow API Events to be Detections or Alerts, depending on the Event Label (#21923)
* - API created events will be alerts OR detections, depending on the event label, defaulting to alerts
- Indefinite API events will extend the recording segment until those events are ended
- API event start time is the actual start time, instead of having a pre-buffer of record.event_pre_capture
* Instead of checking for indefinite events on a camera before deciding if we should end the segment, only update last_detection_time and last_alert_time if frame_time is greater, which should have the same effect
* Add the ability to set a pre_capture number of seconds when creating a manual event via the API. Default behavior unchanged
* Remove unnecessary _publish_segment_start() call
* Formatting
* handle last_alert_time or last_detection_time being None when checking them against the frame_time
* comment manual_info["label"].split(": ")[0] for clarity
* ffmpeg Preview Segment Optimization for "high" and "very_high" (#21996)
* Introduce qmax parameter for ffmpeg preview encoding
Added PREVIEW_QMAX_PARAM to control ffmpeg encoding quality.
* formatting
* Fix spacing in qmax parameters for preview quality
* Adapt to new Gemini format
* Fix frame time access
* Remove exceptions
* Cleanup
---------
Co-authored-by: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com>
Co-authored-by: tigattack <10629864+tigattack@users.noreply.github.com>
Co-authored-by: Andrew Roberts <adroberts@gmail.com>
Co-authored-by: Eugeny Tulupov <zhekka3@gmail.com>
Co-authored-by: Eugeny Tulupov <eugeny.tulupov@spirent.com>
Co-authored-by: John Shaw <1753078+johnshaw@users.noreply.github.com>
Co-authored-by: Eric Work <work.eric@gmail.com>
Co-authored-by: FL42 <46161216+fl42@users.noreply.github.com>
Co-authored-by: Florent MORICONI <170678386+fmcloudconsulting@users.noreply.github.com>
Co-authored-by: nulledy <254504350+nulledy@users.noreply.github.com>
* Add shortSummary field to review summary to be used for notifications
* pull in current config version into default config
* fix crash when dynamically adding cameras
depending on where we are in the update loop, camera configs might not be updated yet and we are receiving detections already
* add no tracked objects and icon to explore summary view
* reset add camera wizard when closing and saving
* don't flash no exports icon while loading
* Improve handling of homekit config
* Increase prompt tokens reservation
* Adjust
* Catch event not found object detection
* Use thread lock for JinaV2 in onnxruntime
* remove incorrect embeddings process from memray docs
* only show transcribe button if audio event has video
* apply aspect ratio and margin constraints to path overlay in detail stream on mobile
improves a specific case where the overlay was not aligned with 4:3 cameras on mobile phones
* show metadata title as tooltip on icon hover in detail stream
---------
Co-authored-by: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com>
* Don't warn when event ids have expired for trigger sync
* Import faster_whisper conditinally to avoid illegal instruction
* Catch OpenVINO runtime error
* fix race condition in detail stream context
navigating between tracked objects in Explore would sometimes prevent the object track from appearing
* Handle case where classification images are deleted
* Adjust default rounded corners on larger screens
* Improve flow handling for classification state
* Remove images when wizard is cancelled
* Improve deletion handling for classes
* Set constraints on review buffers
* Update to support correct data format
* Set minimum duration for recording based review items
* Use friendly name in review genai prompt
---------
Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
* show id field when editing zone
* improve zone capitalization
* Update NPU models and docs
* fix mobilepage in tracked object details
* Use thread lock for openvino to avoid concurrent requests with JinaV2
* fix hashing function to avoid collisions
* remove extra flex div causing overflow
* ensure header stays on top of video controls
* don't smart capitalize friendly names
* Fix incorrect object classification crop
* don't display submit to plus if object doesn't have a snapshot
* check for snapshot and clip in actions menu
* frigate plus submission fix
still show frigate+ section if snapshot has already been submitted and run optimistic update, local state was being overridden
* Don't fail to show 0% when showing classification
* Don't fail on file system error
* Improve title and description for review genai
* fix overflowing truncated review item description in detail stream
* catch events with review items that start after the first timeline entry
review items may start later than events within them, so subtract a padding from the start time in the filter so the start of events are not incorrectly filtered out of the list in the detail stream
* also pad on review end_time
* fix
* change order of timeline zoom buttons on mobile
* use grid to ensure genai title does not cause overflow
* small tweaks
* Cleanup
---------
Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
* Correctly sort summary responses
* Consider JinaV2 as a complex model
* Subscribe to record updates in camera watchdog
* Cleanup score showing
* No need to sort review summary
* Add tests for recording summary
* Don't break existing format
* Sort event summary by day
* Adjust for commutes
* Tweaks
* Don't show no models view in grid
* Add text-md to inputs
* Adjust train title for mobile
* Cleanup prompt more
* Use i18n functions for tooltip
* Fix model complexity causing crash
* Cleanup
* Update ROCm to 7.0.1
* Update ONNXRuntime
* Add back in
* Get basic detection working
* Use env vars
* Handle complex migraphx models
* Enable model caching
* Remove unused
* Add tip to docs
* Cleanup onnx detector
* Fix
* Fix classification cropping
* Deprioritize openvino
* Send model type
* Use model type to decide if model can use full optimization
* Clenanup
* Cleanup
* Use OpenVINO directly to detect if devices are available
* Cleanup
* Update OpenVINO
* Cleanup
* Don't try to use OpenVINO when CPU is set as device
* Catch case where input tensor can't be pre-defined
* Cleanup
* Use re-usable inference request to reduce CPU usage
* Share tensor
* Don't count performance
* Create openvino runner class
* Break apart onnx runner
* Add specific note about inability to use CUDA graphs for some models
* Adjust rknn to use RKNNRunner
* Use optimized runner
* Add support for non-complex models for CudaExecutionProvider
* Use core mask for rknn
* Correctly handle cuda input
* Cleanup
* Sort imports
