* Improve title to better capture activity
* Improve efficiency of prompt
* Use json format for llama.cpp
* Cleanup prompt
* Add output format for other LLMs
* Support GenAI for embeddings
* Add embed API support
* Add support for embedding via genai
* Basic docs
* undo
* Fix sending images
* Don't require download check
* Set model
* Handle emb correctly
* Clarification
* Cleanup
* Cleanup
* fix ollama chat tool calling
handle dict arguments, streaming fallback, and message format
* pin setuptools<81 to ensure pkg_resources remains available
When ensure_torch_dependencies() installs torch/torchvision via pip, it can upgrade setuptools to >=81.0.0, which removed the pkg_resources module. rknn-toolkit2 depends on pkg_resources internally, so subsequent RKNN conversion fails with No module named 'pkg_resources'.
* GenAI client manager
* Add config migration
* Convert to roles list
* Support getting client via manager
* Cleanup
* Fix import issues
* Set model in llama.cpp config
* Clenaup
* Use config update
* Clenaup
* Add new title and desc
* 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>
* Adjust title prompt to have less rigidity
* Improve motion boxes handling for features that don't require motion
* Improve handling of classes starting with digits
* Improve vehicle nuance
* tweak lpr docs
* Improve grammar
* Don't allow # in face name
* add password requirements to new user dialog
* change password requirements
* Clenaup
---------
Co-authored-by: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com>
* Add 640x640 Intel NPU stats
* use css instead of js for reviewed button hover state in filmstrip
* update copilot instructions to copy HA's format
* Set json schema for genai
---------
Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
* use default stable api version for gemini genai client
* update gemini docs
* remove outdated genai.md and update correct file
* Classification fixes
* Mutate when a date is selected and marked as reviewed
---------
Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
* misc triggers tweaks
i18n fixes
fix toaster color
fix clicking on labels selecting incorrect checkbox
* update copilot instructions
* lpr docs tweaks
* add retry params to gemini
* i18n fix
* ensure users only see recognized plates from accessible cameras in explore
* ensure all zone filters are converted to pixels
zone-level filters were never converted from percentage area to pixels. RuntimeFilterConfig was only applied to filters at the camera level, not zone.filters.
Fixes https://github.com/blakeblackshear/frigate/discussions/21694
* add test for percentage based zone filters
* use export id for key instead of name
* update gemini docs
* Fix jetson stats reading
* Return result
* Avoid unknown class for cover image
* fix double encoding of passwords in camera wizard
* formatting
* empty homekit config fixes
* add locks to jina v1 embeddings
protect tokenizer and feature extractor in jina_v1_embedding with per-instance thread lock to avoid the "Already borrowed" RuntimeError during concurrent tokenization
* Capitalize correctly
* replace deprecated google-generativeai with google-genai
update gemini genai provider with new calls from SDK
provider_options specifies any http options
suppress unneeded info logging
* fix attribute area on detail stream hover
---------
Co-authored-by: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com>
* Strip model name before training
* Handle options file for go2rtc option
* Make reviewed optional and add null to API call
* Send reviewed for dashboard
* Allow setting context size for openai compatible endpoints
* push empty go2rtc config to avoid homekit error in log
* Add option to set runtime options for LLM providers
* Docs
---------
Co-authored-by: Josh Hawkins <32435876+hawkeye217@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>
* use fallback timeout for opening media source
covers the case where there is no active connection to the go2rtc stream and the camera takes a long time to start
* Add review thumbnail URL to integration docs
* fix weekday starting point on explore when set to monday in UI settings
* only show allowed cameras and groups in camera filter button
* Reset the wizard state after closing with model
* remove footnote about 0.17
* 0.17
* add triggers to note
* add slovak
* Ensure genai client exists
* Correctly catch JSONDecodeError
* clarify docs for none class
* version bump on updating page
* fix ExportRecordingsBody to allow optional name field
fixes https://github.com/blakeblackshear/frigate/discussions/21413 because of https://github.com/blakeblackshear/frigate-hass-integration/pull/1021
* Catch remote protocol error from ollama
---------
Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
* Send preferred language for report service
* make object lifecycle scrollable in tracking details
* fix info popovers in live camera drawer
* ensure metrics are initialized if genai is enabled
* docs
* ollama cloud model docs
* Ensure object descriptions get claened up
---------
Co-authored-by: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com>
* conditionally display actions for admin role only
* only allow admins to save annotation offset
* Fix classification reset filter
* fix explore context menu from blocking pointer events on the body element after dialog close
applying modal=false to the menu (not to the dialog) to fix this in the same way as elsewhere in the codebase
* add select all link to face library, classification, and explore
* Disable iOS image dragging for classification card
* add proxmox ballooning comment
* lpr docs tweaks
* yaml list
* clarify tls_insecure
* Improve security summary format and usefulness
---------
Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
* Remove source_type from API
* Don't require state classification models to select all classes
* Specifically validate provided end_time for manual events
* Remove yolov9 specification for warning
* Remove warning for coral
* clarify zone name tip
* clarify replace rules in lpr docs
* remove periods
* Add explanation for review report
* adjust HLS gap controller params
defaults to false, should help to recover from hangs and stalling in tracking details videos on chrome
* only redirect to login page once on 401
attempt to fix ios pwa safari redirect storm
* Use contextual information from other cameras to inform report summary
* Formatting and prompt improvements for review summary report
* More improvements to prompt
* Remove examples
* Don't show admin action buttons on export card
* fix redirect race condition
Coordinate 401 redirect logic between ApiProvider and ProtectedRoute using a shared flag to prevent multiple simultaneous redirects that caused UI flashing. Ensure both auth error paths check and set the redirect flag before navigating to login, eliminating race conditions where both mechanisms could trigger at once
---------
Co-authored-by: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com>
* Fix history management failing when updating URL
* Handle case where user doesn't have images that represent all states
If a user selects all imags and can't proceed we show a warning that they can still proceed but the model won't be trained until they get at least one image for every state.
* Still create all classes
We stil need to create all classes even if the user didn't assign images to them.
* fix camera group access for non admin users
changes from previous PR wrongly included users from the standard viewer role (but excluded custom viewer roles)
* Adjust threat level interaction to be less strict
* use base path when fetching go2rtc data
* show config error message when starting in safe mode
* fix genai migration
* fix genai
* Fix genai migration
---------
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>
* Fix filtering for classification
* Adjust prompt to account for response tokens
* Correctly return response for reprocess
* Use API response to update data instead of trying to re-parse all of the values
* Implement rename class api
* Fix model deletion / rename dialog
* Remove camera spatial context
* Catch error
* 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>
* Pull context size from openai models
* Adjust wording based on type of model
* Instruct to not use parenthesis
* Simplify genai config
* Don't use GPU for training
* Update docs for review descriptions
* Add logging for context tokens used
* Incrase number of images due to lower than expected context usage
* Re-balance the suspicious activity checks
* Adjustments to context sizing
* optimize context usage
* Adjust context usage
* Make title more direct
* Update docs
* 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
* Make prompt more fair and reduce time extension
* Adjust naming of unrecognized objects
* Improve object naming behavior
* Add more context image levels
* Map verified objects to their sub label directly
* Simplify access
* Cleanup
* Add protection for mismatched object and index
* Keep track of verified objects separately
* Improve prompt to have better discernment and logic based on detected objects
* Be more specific about the time of day
* Add re-inforcers for LLM to be accurate and not complete a narrative
