Platform configuration and data overview
Videos per channel limit
Cap the number of videos imported per channel. Useful for testing. Set to 0 for no limit.
Used to split video transcripts into topic chunks during import. Cheapest model recommended — quality difference is minimal for this task.
Language Model
Used for all chat responses via OpenRouter
—
Current model
Embedding Model
Used for semantic search via OpenAI
Chunking Model
Used for splitting transcripts into topic chunks
Retrieval Strategy
70% semantic, 30% keyword — top 12 chunks
Default Mode
Can be changed per session in the chat interface
Max History
Prior messages included for conversation context
Streaming
Responses stream token by token
Export all personas, sources, and knowledge chunks as a JSON file. Import on another instance to sync data.
Rebuild All Knowledge
Deletes all knowledge chunks and re-processes every persona from their existing transcripts.