Generative AI can be used to automatically generate structured summaries of review items. These summaries will show up in Frigate's native notifications as well as in the UI. Generative AI can also be used to take a collection of summaries over a period of time and provide a report, which may be useful to get a quick report of everything that happened while out for some amount of time.
Requests for a summary are requested automatically to your AI provider for alert review items when the activity has ended, they can also be optionally enabled for detections as well.
- `title` (string): A concise, direct title that describes the purpose or overall action (e.g., "Person taking out trash", "Joe walking dog").
- `scene` (string): A narrative description of what happens across the sequence from start to finish, including setting, detected objects, and their observable actions.
This will show in multiple places in the UI to give additional context about each activity, and allow viewing more details when extra attention is required. Frigate's built in notifications will automatically show the title and `shortSummary` when the data is available, while the full `scene` description is available in the UI for detailed review.
Each installation and even camera can have different parameters for what is considered suspicious activity. Frigate allows the `activity_context_prompt` to be defined globally and at the camera level, which allows you to define more specifically what should be considered normal activity. It is important that this is not overly specific as it can sway the output of the response.
- **Testing or attempting to open doors/windows/handles on vehicles or buildings** — ALWAYS Level 1 regardless of time or duration
- **Unidentified person in private areas (driveways, near vehicles/buildings) during late night/early morning (11 PM - 5 AM)** — ALWAYS Level 1 regardless of activity or duration
- Taking items that don't belong to them (packages, objects from porches/driveways)
- Climbing or jumping fences/barriers to access property
- Attempting to conceal actions or items from view
- Prolonged loitering: remaining in same area without visible purpose throughout most of the sequence
- Otherwise, if daytime/evening (6 AM - 10 PM) with clear legitimate purpose (delivery, service worker) → Level 0
3. **Escalate to Level 2 if:** Weapons, break-in tools, forced entry in progress, violence, or active property damage visible (escalates from Level 0 or 1)
The mere presence of an unidentified person in private areas during late night hours is inherently suspicious and warrants human review, regardless of what activity they appear to be doing or how brief the sequence is.
By default, review summaries use preview images (cached preview frames) which have a lower resolution but use fewer tokens per image. For better image quality and more detailed analysis, configure Frigate to extract frames directly from recordings at a higher resolution.
<ConfigTabs>
<TabItem value="ui">
Navigate to <NavPath path="Settings > Global configuration > Review" />.
- Set **GenAI config > Enable GenAI descriptions** to on
- Set **GenAI config > Review image source** to `recordings` (default is `preview`)
When using `recordings`, frames are extracted at 480px height while maintaining the camera's original aspect ratio, providing better detail for the LLM while being mindful of context window size. This is particularly useful for scenarios where fine details matter, such as identifying license plates, reading text, or analyzing distant objects.
The number of frames sent to the LLM is dynamically calculated based on:
- Your LLM provider's context window size
- The camera's resolution and aspect ratio (ultrawide cameras like 32:9 use more tokens per image)
- The image source (recordings use more tokens than preview images)
Frame counts are automatically optimized to use ~98% of the available context window while capping at 20 frames maximum to ensure reasonable inference times. Note that using recordings will:
Along with the concern of suspicious activity or immediate threat, you may have concerns such as animals in your garden or a gate being left open. Configure these concerns so that review summaries will make note of them if the activity requires additional review.
<ConfigTabs>
<TabItem value="ui">
Navigate to <NavPath path="Settings > Global configuration > Review" />.
- Set **GenAI config > Additional concerns** to a list of your concerns (e.g., `animals in the garden`)
By default, review summaries are generated in English. Configure Frigate to generate summaries in your preferred language by setting the `preferred_language` option.
<ConfigTabs>
<TabItem value="ui">
Navigate to <NavPath path="Settings > Global configuration > Review" />.
- Set **GenAI config > Preferred language** to the desired language (e.g., `Spanish`)
Review items are sent to the model as a sequence of still frames. Some models follow that sequence well on their own; others lose track of activity that repeats or reverses, and describe a single trip when the subject actually made several. The `frame_mode` option controls how those frames are presented.
- `frames` (default): the prompt followed by the frames, exactly as earlier versions of Frigate sent them.
- `annotated_frames`: each frame is preceded by its frame number and elapsed time, along with notes describing what the object tracker recorded at that moment, such as an object being first detected, starting to move, turning around, stopping, or no longer being detected.
The notes come from tracking data rather than from the images, so they describe activity the model may not have picked up on its own. In testing with a person carrying three waste bins to the curb one at a time, `gemma4` described a single trip on every attempt with `frames`, and consistently described multiple trips with `annotated_frames`. Models that already handle these sequences well, such as the `qwen3-vl` family, gain little and should stay on `frames`.
Changes reported by [state classification](/configuration/custom_classification/state_classification#review-items) models during the review item are listed in the prompt in both modes. `annotated_frames` also notes each change before the frame where it happened.
Annotated mode also caps the number of frames, since the notes already establish the order of events and extra near-duplicate frames tend to crowd out the middle of a clip. Longer review items are sampled more sparsely as a result, and typically use fewer tokens than `frames` mode for the same item.
:::note
Annotated mode needs tracking data for the review item. If none is available, Frigate falls back to sending plain frames for that item.
:::
<ConfigTabs>
<TabItem value="ui">
Navigate to <NavPath path="Settings > Global configuration > Review" />.
- Set **GenAI config > Frame mode** to the desired mode (e.g., `annotated_frames`)
Different models respond to the built-in prompt with very different writing styles: some produce natural narration while others sound short and mechanical. The `response_style` option selects a writing style preset that rewords the prompt's instructions for the user-facing fields (the title, short summary, and scene description). Presets replace those instructions rather than adding extra ones, so the model never receives competing style directions.
Available presets:
- `default`: The built-in prompt, unchanged. This already reads like a neutral security report.
- `natural`: Plain, everyday narration with flowing sentences and sentence-style headline titles. Useful when a model's output sounds robotic.
- `concise`: As brief as possible while still covering each significant action, with terse two-to-four word titles.
- `detailed`: Thorough descriptions and titles that include the most identifying specifics, like colors, clothing, and carried items.
Style presets only adjust how the user-facing text reads; the model's step-by-step observations and threat level scoring guidance are unaffected. Results vary by model, so it is worth comparing presets against saved debug output using `testing-scripts/genai_review_tester.py` in the Frigate repository.
<ConfigTabs>
<TabItem value="ui">
Navigate to <NavPath path="Settings > Global configuration > Review" />.
- Set **GenAI config > Response style** to the desired preset (e.g., `natural`)
Along with individual review item summaries, Generative AI can also produce a single report of review items from all cameras marked "suspicious" over a specified time period (for example, a daily summary of suspicious activity while you're on vacation).
Review reports can be requested via the [API](/integrations/api/generate-review-summary-review-summarize-start-start-ts-end-end-ts-post) by sending a POST request to `/api/review/summarize/start/{start_ts}/end/{end_ts}` with Unix timestamps.
For Home Assistant users, there is a built-in service (`frigate.review_summarize`) that makes it easy to request review reports as part of automations or scripts. This allows you to automatically generate daily summaries, vacation reports, or custom time period reports based on your specific needs.
If summaries are not being generated, or the generated summaries are not what you expect, see [How do I debug GenAI issues?](/configuration/genai/genai_config#how-do-i-debug-genai-issues).
