Skip to main content

Configuring Generative AI

Configuration​

A Generative AI provider can be configured in the global config, which will make the Generative AI features available for use. There are currently 5 native providers available to integrate with Nabik. Other providers that support the OpenAI standard API can also be used. See the OpenAI-Compatible section below.

genai is a map of named providers. Each key under genai is a name you choose, and its value is that provider's settings:

  1. Navigate to Settings→Enrichments→Generative AI.
    • Click Add and enter a Provider name. Any name of letters, numbers, hyphens, and underscores is accepted, but it cannot be changed from the UI after the provider is created.
    • Set Provider to the service you are using (e.g., ollama)
    • Set Base URL, API key, and Model as required by that provider
    • Set Roles to the roles this provider should handle.

The examples on this page all use my_provider, but the name is arbitrary and is only used to reference the provider elsewhere in the config (for example, semantic_search.model).

Each provider handles one or more roles: chat, descriptions, embeddings, and transcribe. A provider handles the first three by default; transcribe must always be listed explicitly, and is not available on Ollama, which has no audio input. Each role may be assigned to exactly one provider. Define a single provider if you want it to do everything, or split the roles across several providers using the roles option.

If the provider you choose requires an API key, you may either directly paste it in your configuration, or store it in an environment variable prefixed with FRIGATE_.

Local Providers​

Local providers run on your own hardware and keep all data processing private. These require a GPU or dedicated hardware for best performance.

warning

Running Generative AI models on CPU is not recommended, as high inference times make using Generative AI impractical.

Vision models​

You must use a vision-capable model with Nabik. The following models are recommended for local deployment of the descriptions and chat roles:

ModelReview frame modeNotes
qwen3-vlframesStrong visual and situational understanding, enhanced ability to identify smaller objects and interactions with object. Follows a sequence of frames on its own.
qwen3.6/qwen3.8framesStrong situational understanding, but missing DeepStack from qwen3-vl leading to worse performance for identifying objects in people's hand and other small details.
gemma4annotated_framesStrong situational understanding, sometimes resorts to more vague terms like 'interacts' instead of assigning a specific action. Loses track of activity that repeats or reverses, so it benefits from annotated frames.

Embedding models​

The embeddings role needs a different kind of model. Text queries are matched against the stored image embeddings, so the model must be trained to place images and text into the same vector space. A chat or description model will still return vectors when asked, but those vectors are not trained for retrieval and text searches will return poor matches with no error to indicate why.

ModelNotes
qwen3-vl-embeddingMultimodal embeddings for Semantic Search. Must be served by llama.cpp started with --embeddings and --mmproj.

Transcription models​

The transcribe role needs a model that accepts audio input. A text-only or vision-only model cannot serve this role. The following are recommended for local deployment of the transcribe role:

ModelNotes
qwen3-asrDedicated speech recognition model covering 30 languages, and the better choice for transcription quality. It only transcribes, so it cannot be shared with the descriptions or chat roles.
gemma4General multimodal model that accepts audio as well as images, so one served model can cover transcribe alongside the other roles. Transcript quality is below qwen3-asr, particularly on noisy audio.

Both must be served by llama.cpp started with the matching audio --mmproj. llama.cpp only reports audio support when an audio projector is loaded. Without it Nabik sees the model as text-only and the transcribe role is unavailable in the UI. Nabik transcribes through the server's /v1/audio/transcriptions route, which llama.cpp serves for any audio-capable model.

info

Each model is available in multiple parameter sizes (3b, 4b, 8b, etc.). Larger sizes are more capable of complex tasks and understanding of situations, but requires more memory and computational resources. It is recommended to try multiple models and experiment to see which performs best.

note

You should have at least 8 GB of RAM available (or VRAM if running on GPU) to run the 7B models, 16 GB to run the 13B models, and 24 GB to run the 33B models.

Model Types: Instruct vs Thinking​

Vision-language models come in instruct variants (fine-tuned to follow instructions and respond concisely), thinking variants (fine-tuned for free-form, speculative reasoning), and hybrid variants that support both modes per request. Most modern vision-language models are hybrid.

Nabik manages reasoning per task automatically:

  • Description tasks (object descriptions, review descriptions, review summaries) are synthesis-only and benefit from concise, direct output, so Nabik disables thinking for these calls when the model exposes a per-request toggle.
  • Chat lets you toggle thinking on or off from the composer when the configured model supports it.

You can use a pure instruct, hybrid, or thinking-capable model with Nabik. No extra configuration is required to disable thinking for descriptions.

llama.cpp​

llama.cpp is a C++ implementation of LLaMA that provides a high-performance inference server.

It is highly recommended to host the llama.cpp server on a machine with a discrete graphics card, or on an Apple silicon Mac for best performance.

Supported Models​

You must use a vision capable model with Nabik. The llama.cpp server supports various vision models in GGUF format.

Configuration​

All llama.cpp native options can be passed through provider_options, including temperature, top_k, top_p, min_p, repeat_penalty, repeat_last_n, seed, grammar, and more. See the llama.cpp server documentation for a complete list of available parameters.

  1. Navigate to Settings→Enrichments→Generative AI.
    • Set Provider to llamacpp
    • Set Base URL to your llama.cpp server address (e.g., http://localhost:8080)
    • Set Model to the name of your model
    • Optionally, under Provider Options, set context_size to override the context size Nabik detects from the server

Nabik queries the llama.cpp server for the model's context size at startup and logs it along with the other detected capabilities. If context_size is set in provider_options, that value is always used instead, even when the server reports its own.

Ollama​

Ollama allows you to self-host large language models and keep everything running locally. It is highly recommended to host this server on a machine with an Nvidia graphics card, or on a Apple silicon Mac for best performance.

Most of the 7b parameter 4-bit vision models will fit inside 8GB of VRAM. There is also a Docker container available.

Parallel requests also come with some caveats. You will need to set OLLAMA_NUM_PARALLEL=1 and choose a OLLAMA_MAX_QUEUE and OLLAMA_MAX_LOADED_MODELS values that are appropriate for your hardware and preferences. See the Ollama documentation.

tip

If you are trying to use a single model for Nabik and HomeAssistant, it will need to support vision and tools calling. qwen3-VL supports vision and tools simultaneously in Ollama.

Note that Nabik will not automatically download the model you specify in your config. Ollama will try to download the model but it may take longer than the timeout, so it is recommended to pull the model beforehand by running ollama pull your_model on your Ollama server/Docker container. The model specified in Nabik's config must match the downloaded model tag.

Configuration​

  1. Navigate to Settings→Enrichments→Generative AI.
    • Set Provider to ollama
    • Set Base URL to your Ollama server address (e.g., http://localhost:11434)
    • Set Model to the model tag (e.g., qwen3-vl:4b)
    • Under Provider Options, set keep_alive (e.g., -1) and options.num_ctx to match your desired context size

OpenAI-Compatible​

Nabik supports any provider that implements the OpenAI API standard. This includes self-hosted solutions like vLLM, LocalAI, and other OpenAI-compatible servers.

tip

For OpenAI-compatible servers (such as llama.cpp) that don't expose the configured context size in the API response, you can manually specify the context size in provider_options:

genai:
  my_provider:
    provider: openai
    base_url: http://your-llama-server
    model: your-model-name
    provider_options:
      context_size: 8192 # Specify the configured context size

This ensures Nabik uses the correct context window size when generating prompts.

Configuration​

  1. Navigate to Settings→Enrichments→Generative AI.
    • Set Provider to openai
    • Set Base URL to your server address (e.g., http://your-server:port)
    • Set API key if required by your server
    • Set Model to the model name

To use a different OpenAI-compatible API endpoint, set the OPENAI_BASE_URL environment variable to your provider's API URL.

Cloud Providers​

Cloud providers run on remote infrastructure and require an API key for authentication. These services handle all model inference on their servers.

info

Cloud Generative AI providers require an active internet connection to send images and prompts for processing. Local providers like llama.cpp and Ollama (with local models) do not require internet. See Network Requirements for details.

Ollama Cloud​

Ollama also supports cloud models, where model inference is performed in the cloud. You can connect directly to Ollama Cloud by setting base_url to https://ollama.com and providing an API key. Alternatively, you can run Ollama locally and use a cloud model name so your local instance forwards requests to the cloud. For more details, see the Ollama cloud model docs.

Configuration​

  1. Navigate to Settings→Enrichments→Generative AI.
    • Set Provider to ollama
    • Set Base URL to your local Ollama address (e.g., http://localhost:11434) or https://ollama.com for direct cloud inference
    • Set API key if required by your endpoint (e.g., when using https://ollama.com)
    • Set Model to the cloud model name

Google Gemini​

Google Gemini has a free tier for the API, however the limits may not be sufficient for standard Nabik usage. Choose a plan appropriate for your installation.

Supported Models​

You must use a vision capable model with Nabik. Current model variants can be found in their documentation.

Get API Key​

To start using Gemini, you must first get an API key from Google AI Studio.

  1. Accept the Terms of Service
  2. Click "Get API Key" from the right hand navigation
  3. Click "Create API key in new project"
  4. Copy the API key for use in your config

Configuration​

  1. Navigate to Settings→Enrichments→Generative AI.
    • Set Provider to gemini
    • Set API key to your Gemini API key (or use an environment variable such as {FRIGATE_GEMINI_API_KEY})
    • Set Model to the desired model (e.g., gemini-2.5-flash)
note

To use a different Gemini-compatible API endpoint, set the provider_options with the base_url key to your provider's API URL. For example:

genai:
  my_provider:
    provider: gemini
    ...
    provider_options:
      base_url: https://...

Other HTTP options are available, see the python-genai documentation.

OpenAI​

OpenAI does not have a free tier for their API.

Supported Models​

You must use a vision capable model with Nabik. Current model variants can be found in their documentation.

Get API Key​

To start using OpenAI, you must first create an API key and configure billing.

Configuration​

  1. Navigate to Settings→Enrichments→Generative AI.
    • Set Provider to openai
    • Set API key to your OpenAI API key (or use an environment variable such as {FRIGATE_OPENAI_API_KEY})
    • Set Model to the desired model (e.g., gpt-4o)
note

To use a different OpenAI-compatible API endpoint, set the OPENAI_BASE_URL environment variable to your provider's API URL.

tip

For OpenAI-compatible servers (such as llama.cpp) that don't expose the configured context size in the API response, you can manually specify the context size in provider_options:

genai:
  my_provider:
    provider: openai
    base_url: http://your-llama-server
    model: your-model-name
    provider_options:
      context_size: 8192 # Specify the configured context size

This ensures Nabik uses the correct context window size when generating prompts.

Azure OpenAI​

Microsoft offers several vision models through Azure OpenAI. A subscription is required.

Supported Models​

You must use a vision capable model with Nabik. Current model variants can be found in their documentation.

Create Resource and Get API Key​

To start using Azure OpenAI, you must first create a resource. You'll need your API key, model name, and resource URL, which must include the api-version parameter (see the example below).

Configuration​

  1. Navigate to Settings→Enrichments→Generative AI.
    • Set Provider to azure_openai
    • Set Base URL to your Azure resource URL including the api-version parameter (e.g., https://instance.cognitiveservices.azure.com/openai/responses?api-version=2025-04-01-preview)
    • Set Model to your deployed model name (e.g., gpt-5-mini)
    • Set API key to your Azure OpenAI API key (or use an environment variable such as {FRIGATE_OPENAI_API_KEY})

FAQ​

​

Nabik's Generative AI features are configured and enabled separately. Review descriptions and summaries live under review.genai, and object descriptions live under objects.genai. Configuring a provider on this page does not enable either feature, and enabling one does not enable the other. Decide which of the two is not working, then work through the steps below.

  1. Confirm a provider is available and holds the descriptions role.

    • Review descriptions, review summaries, and object descriptions all use the provider that has the descriptions role assigned in Settings→Enrichments→Generative AI→Roles (genai.<provider>.roles).
    • A provider is contacted the first time one of its roles is actually used. A provider holding the embeddings role for semantic search is initialized during startup, while a descriptions provider is not initialized until the first description is requested, which may be well after boot.
    • In Settings→Enrichments→Generative AI, use Refresh models next to the model field. It queries the provider for its model list and is a quick way to verify that the base URL, API key, and network path between Nabik and your provider are correct.

  2. Confirm the feature you expect is actually enabled.

    • Object descriptions are disabled by default. Turn on Settings→Global configuration→Objects→GenAI object config→Enable GenAI (objects.genai.enabled), either globally or per camera. This is the most common reason custom prompts appear to be ignored while review summaries are still being generated.
    • Review descriptions are disabled by default. Turn on Settings→Global configuration→Review→GenAI config→Enable GenAI descriptions (review.genai.enabled). Once enabled, alerts are described by default but detections are not, so a detection-only review item will never get a summary unless Enable GenAI for detections (review.genai.detections) is also on.

  3. If object descriptions are never requested, check the filters that skip generation.

    • Settings→Global configuration→Objects→GenAI object config→GenAI objects (objects.genai.objects) limits generation to specific labels, and Required zones (objects.genai.required_zones) requires the object to have entered one of those zones. If either is set and does not match, Nabik skips the request silently.
    • Thumbnails are only collected while an object is moving. Objects that go stationary early contribute fewer frames.
    • Use snapshots (objects.genai.use_snapshot) requires snapshots to be enabled for the camera. If the snapshot cannot be read, Nabik logs Cannot load snapshot for <id>, file not found and no description is generated.
    • Send on end (objects.genai.send_triggers.tracked_object_end) is on by default. If you have turned it off in favor of Early GenAI trigger (objects.genai.send_triggers.after_significant_updates), descriptions are only requested once that number of updates is reached.

  4. Enable debug logs to see exactly what Nabik is doing. Restart Nabik after this change. The next step also requires a restart, so turn both on at the same time to avoid restarting twice.

    logger:
      default: info
      logs:
        frigate.genai: debug
        frigate.data_processing.post.object_descriptions: debug
        frigate.data_processing.post.review_descriptions: debug

  5. Save the exact images and prompts that were sent to your provider.

    • Turn on Save thumbnails for the feature you are debugging (review.genai.debug_save_thumbnails or objects.genai.debug_save_thumbnails). Both features write to /media/nabik/clips/genai-requests/, and these files are admin-only.
    • Review descriptions write genai-requests/<review_id>/ containing the numbered frames that were sent, plus prompt.txt and response.txt with the exact prompt and the raw, unparsed model response.
    • Review summary reports write genai-requests/<start_ts>-<end_ts>/prompt.txt and response.txt. No images are involved, since a report summarizes existing review descriptions.
    • Object descriptions write genai-requests/<event_id>/ containing the numbered thumbnails. The prompt for object descriptions is not written to a file, it is only visible in the debug logs from step 4.
    • Look at the saved images before blaming the model. If the object is small, blurry, or out of frame, no prompt will fix the result. For object descriptions, consider turning on Use snapshots (objects.genai.use_snapshot) to send a higher quality image. For review items, consider setting Review image source (review.genai.image_source) to recordings for 480p frames instead of the lower resolution preview frames.

For review descriptions, navigate to Settings→Global configuration→Review and set GenAI config > Save thumbnails to on.

For object descriptions, navigate to Settings→Global configuration→Objects, expand GenAI object config, and set Save thumbnails to on.

  1. Verify the prompt is what you think it is.

    • Object description prompts are the ones you control directly. A camera-level Settings→Camera configuration→Objects→GenAI object config→Caption prompt (objects.genai.prompt) overrides the global one, and an entry in Object prompts (objects.genai.object_prompts) for a label overrides both for that label. Only {label}, {sub_label}, and {camera} are substituted.
    • Review description prompts are built by Nabik and request a structured JSON response, so they are not fully replaceable. The parts you control are Settings→Global configuration→Review→GenAI config→Activity context prompt (review.genai.activity_context_prompt) and Additional concerns (review.genai.additional_concerns). Keep the activity context prompt general, since overly specific rules will sway the model's threat level scoring.

  2. If descriptions are generated but the results are poor or inconsistent, look at the model and the context window.

    • Empty fields, missing shortSummary values, or Failed to parse review description errors usually mean the model is not following the requested JSON schema. Smaller models struggle with structured output. Try a larger parameter size or one of the recommended models.
    • Nabik calculates how many frames to send from the context size the provider reports. If your server reports a different value than it is actually running with, frames will be truncated or the request will fail. Pin the value by adding context_size under Settings→Enrichments→Generative AI→Provider options (genai.<provider>.provider_options), and for Ollama also confirm options.num_ctx there matches the context you have configured.
    • Check Review Description Speed and Object Description Speed in Health and Metrics→Enrichments. If inference takes tens of seconds, requests will queue behind each other and descriptions will appear to stop. For Ollama, review OLLAMA_NUM_PARALLEL, OLLAMA_MAX_QUEUE, and OLLAMA_MAX_LOADED_MODELS so that concurrent requests from Nabik are handled the way you expect.