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.
* widen the logger name field in the per-process log level settings
* add details to timestamp error faq
* tweak genai docs
* tweak vector language
* Combine Qwen3.5 and Qwen3.6 listings
* fix openvino yolox detector crashing on every detection
The intermediate (N, 7) array in the yolox branch shadowed the pre-allocated (20, 6) detections buffer, so writing a detection into it raised "could not broadcast input array from shape (6,) into shape (7,)" on the first frame with anything above the confidence threshold. An empty frame also returned a (0, 7) array instead of the (20, 6) buffer.
Regressed in #13794, which renamed the intermediate from dets to detections as part of a cspell cleanup. Broken since 0.15.0.
---------
Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
* 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
* openvino log message and preview directory checks
* restrict config vars for viewer users
* recording timestamp fix
when startTime is exactly on an hour boundary, findIndex returns the first matching chunk, which is the previous hour's chunk (where before == startTime), instead of the correct chunk (where after == startTime)
the bug shows up when using the share timestamp feature and sharing a specific timestamp on the exact hour mark. when accessing the shared link, the timeline would jump to the incorrect hour
* use helper for chunked time range
* Adjustments to contributing docs
* tweak
* Improve wording
* tweak
---------
Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
* tweak language
* show validation errors in json response
* fix export hwaccel args field in UI
* increase annotation offset consts
* fix save button race conditions, add reset spinner, and fix enrichments profile leak
- Disable both Save and SaveAll buttons while either operation is in progress so users cannot trigger concurrent saves
- Show activity indicator on Reset to Default/Global button during the API call
- Enrichments panes (semantic search, genai, face recognition) now always show base config fields regardless of profile selection in the header dropdown
* fix genai additional_concerns validation error with textarea array widget
The additional_concerns field is list[str] in the backend but was using the textarea widget which produces a string value, causing validation errors.
Created a TextareaArrayWidget that converts between array (one item per line) and textarea display, and switched additional_concerns to use it
* populate and sort global audio filters for all audio labels
* add column labels in profiles view
* enforce a minimum value of 2 for min_initialized
* reuse widget and refactor for multiline
* fix
* change record copy preset to transcode audio to aac
* fix genai settings ui
- add roles widget to select roles for genai providers
- add dropdown in semantic search to allow selection of embeddings genai provider
* tweak grouping to prioritize fieldOrder before groups
previously, groups were always rendered first. now fieldOrder is respected, and any fields in a group will cause the group and all the fields in that group to be rendered in order. this allows moving the enabled switches to the top of the section
* mobile tweaks
stack buttons, add more space on profiles pane, and move the overridden badge beneath the description
* language consistency
* prevent camera config sections from being regenerated for profiles
* conditionally import axengine module
to match other detectors
* i18n
* update vscode launch.json for new integrated browser
* formatting
* use react-jsonschema-form for UI config
* don't use properties wrapper when generating config i18n json
* configure for full i18n support
* section fields
* add descriptions to all fields for i18n
* motion i18n
* fix nullable fields
* sanitize internal fields
* add switches widgets and use friendly names
* fix nullable schema entries
* ensure update_topic is added to api calls
this needs further backend implementation to work correctly
* add global sections, camera config overrides, and reset button
* i18n
* add reset logic to global config view
* tweaks
* fix sections and live validation
* fix validation for schema objects that can be null
* generic and custom per-field validation
* improve generic error validation messages
* remove show advanced fields switch
* tweaks
* use shadcn theme
* fix array field template
* i18n tweaks
* remove collapsible around root section
* deep merge schema for advanced fields
* add array field item template and fix ffmpeg section
* add missing i18n keys
* tweaks
* comment out api call for testing
* add config groups as a separate i18n namespace
* add descriptions to all pydantic fields
* make titles more concise
* new titles as i18n
* update i18n config generation script to use json schema
* tweaks
* tweaks
* rebase
* clean up
* form tweaks
* add wildcards and fix object filter fields
* add field template for additionalproperties schema objects
* improve typing
* add section description from schema and clarify global vs camera level descriptions
* separate and consolidate global and camera i18n namespaces
* clean up now obsolete namespaces
* tweaks
* refactor sections and overrides
* add ability to render components before and after fields
* fix titles
* chore(sections): remove legacy single-section components replaced by template
* refactor configs to use individual files with a template
* fix review description
* apply hidden fields after ui schema
* move util
* remove unused i18n
* clean up error messages
* fix fast refresh
* add custom validation and use it for ffmpeg input roles
* update nav tree
* remove unused
* re-add override and modified indicators
* mark pending changes and add confirmation dialog for resets
* fix red unsaved dot
* tweaks
* add docs links, readonly keys, and restart required per field
* add special case and comments for global motion section
* add section form special cases
* combine review sections
* tweaks
* add audio labels endpoint
* add audio label switches and input to filter list
* fix type
* remove key from config when resetting to default/global
* don't show description for new key/val fields
* tweaks
* spacing tweaks
* add activity indicator and scrollbar tweaks
* add docs to filter fields
* wording changes
* fix global ffmpeg section
* add review classification zones to review form
* add backend endpoint and frontend widget for ffmpeg presets and manual args
* improve wording
* hide descriptions for additional properties arrays
* add warning log about incorrectly nested model config
* spacing and language tweaks
* fix i18n keys
* networking section docs and description
* small wording tweaks
* add layout grid field
* refactor with shared utilities
* field order
* add individual detectors to schema
add detector titles and descriptions (docstrings in pydantic are used for descriptions) and add i18n keys to globals
* clean up detectors section and i18n
* don't save model config back to yaml when saving detectors
* add full detectors config to api model dump
works around the way we use detector plugins so we can have the full detector config for the frontend
* add restart button to toast when restart is required
* add ui option to remove inner cards
* fix buttons
* section tweaks
* don't zoom into text on mobile
* make buttons sticky at bottom of sections
* small tweaks
* highlight label of changed fields
* add null to enum list when unwrapping
* refactor to shared utils and add save all button
* add undo all button
* add RJSF to dictionary
* consolidate utils
* preserve form data when changing cameras
* add mono fonts
* add popover to show what fields will be saved
* fix mobile menu not re-rendering with unsaved dots
* tweaks
* fix logger and env vars config section saving
use escaped periods in keys to retain them in the config file (eg "frigate.embeddings")
* add timezone widget
* role map field with validation
* fix validation for model section
* add another hidden field
* add footer message for required restart
* use rjsf for notifications view
* fix config saving
* add replace rules field
* default column layout and add field sizing
* clean up field template
* refactor profile settings to match rjsf forms
* tweaks
* refactor frigate+ view and make tweaks to sections
* show frigate+ model info in detection model settings when using a frigate+ model
* update restartRequired for all fields
* fix restart fields
* tweaks and add ability enable disabled cameras
more backend changes required
* require restart when enabling camera that is disabled in config
* disable save when form is invalid
* refactor ffmpeg section for readability
* change label
* clean up camera inputs fields
* misc tweaks to ffmpeg section
- add raw paths endpoint to ensure credentials get saved
- restart required tooltip
* maintenance settings tweaks
* don't mutate with lodash
* fix description re-rendering for nullable object fields
* hide reindex field
* update rjsf
* add frigate+ description to settings pane
* disable save all when any section is invalid
* show translated field name in validation error pane
* clean up
* remove unused
* fix genai merge
* fix genai
The fallback to tensorflow was established back in 2023, because we could
not provide tflite-runtime downstream in nixpkgs.
By now we have ai-edge-litert available, which is the successor to the
tflite-runtime. It still provides the same entrypoints as tflite-runtime
and functionality has been verified in multiple deployments for the last
two weeks.
* 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>
* Fix genai callbacks in MQTT
* Cleanup cursor pointer for classification cards
* Cleanup
* Handle unknown SOCs for RKNN converter by only using known SOCs
* don't allow "none" as a classification class name
* change internal port user to admin and default unspecified username to viewer
* keep 5000 as anonymous user
* suppress tensorflow logging during classification training
* Always apply base log level suppressions for noisy third-party libraries even if no specific logConfig is provided
* remove decorator and specifically suppress TFLite delegate creation messages
---------
Co-authored-by: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com>
* Adds support for YOLO v9 models running on Google Coral
* fix format by using ruff instead of black
* Remove comment
Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
* Remove log message
Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
* revert to hard-coded settings. use ModelTypeEnum directly
* remove log messages. detect invalid output tensor count
* remove 1-tensor processing. add pre_process() function
* check for valid model type
* fix formatting
* remove unused import and variable
* remove tip that indicates other YOLO models may be supported.
---------
Co-authored-by: Nicolas Mowen <nickmowen213@gmail.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
* [Init] Initial commit for Synaptics SL1680 NPU
* add a rough detector which is testing with yolov8 tflite model.
* [Feat] Add dependencies installation in docker build
- Add runtime library and wheels installation in main/Dockerfile
- Add model.synap(default model, transfer from mobilenet_224full80) in docker/synap1680
* [Update] Remove dependencies installation from main Dockerfile
- remove deps installation from Dockerfile
- add dependencies installation and split wheels, deps stage in synap1680 Dockerfile
* Refactor synap detector to more closely match other implementations
* [Update] Add model path configuration check
* [Update] update ModelType to ssd
* [Update] Remove unuse script
- install_deps.sh has already been executing in deps download stage
- Dockerfile.toolchain is for testing to extract runtime libraries from Synaptics toolchain
* [Update] update Synaptics SL1680 setup description
* [Update] remove install_synap1680
- The deps download and installation is existed in synap1680
* [Fix] update document content
* [Update] Update detector from synap1680 to synaptics
This update is in order to make the synaptics SL-series NPU detector more general.
- Fix detector `os` module not import bug
- Update detector type `synap1680` to `synaptics`
- Update document description `SL1680` to `Synaptics` only
- Update docker build content `synap1680` to `synaptics`
* [Fix] Update configuration document
* Update docs/docs/configuration/object_detectors.md
Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
* [Update] Update document content and detector default layout
- Update object_detectors document
- Update detector's default layout
- Update default model name
* [Update] Update object detector document content
* [Fix] Fix InputTensorEnum not defined error
- import InputTensorEnum from detector_config
* [Update] Update detector script coding format
* [Update] Update synaptics detector coding format
* [Update] Add synaptics ci workflow
* [Update] update synaptics runtime libs download path
- Fork Synaptics astra sdk repo and put the runtime lib package on it
- Frigate team can update this download path later
---------
Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
