Quick Example
Visual Indexing
Convert video frames into structured descriptions using prompts.batch_config Options
| Field | Type | Description |
|---|---|---|
type | str | Only "time" is supported |
value | int | Window size in seconds |
frame_count | int | Frames to extract per window |
Managing Indexes
Audio Indexing
Extract insights from audio tracks:Audio batch_config
| Type | Value | Description |
|---|---|---|
"word" | count | Segment every N words |
"sentence" | count | Segment every N sentences |
"time" | seconds | Segment every N seconds |
Transcription
Real-time speech-to-text:Search
Query indexed content with natural language:Search Results
Each shot contains:| Attribute | Description |
|---|---|
start | Start timestamp |
end | End timestamp |
text | Content description |
search_score | Relevance score (0-1) |
stream_url | Playback URL |
Events and Alerts
Events are reusable detection rules. Alerts wire events to indexes for notifications.Create Event
Create Alert
Alert Delivery
| Method | Latency | Use Case |
|---|---|---|
| Webhook | Under 1s | Server-to-server POST |
| WebSocket | Real-time | Frontend dashboards |
Manage Alerts
WebSocket Events
Receive real-time events by passingws_connection_id:
Event Channels
| Channel | Source | Content |
|---|---|---|
transcript | start_transcript() | Real-time speech-to-text |
scene_index | index_visuals() | Visual analysis |
audio_index | index_audio() | Audio analysis |
alert | create_alert() | Alert notifications |