Format the final response. Returns: Formatted context response

Format the context data into a readable string for the prompt. Args: context_data: Context data from ContextBuilder Returns:

Generate a minimal 0.5s silence WAV file in memory (16kHz, 16-bit mono).

Get chunk overlap from environment variable or calculate default (15% of chunk size).

Get chunk size from environment variable or use default.

Find the appropriate subclass based on table_name.

Read the embedding batch size from the environment. This is intentionally configurable because provider limits vary widely, and CPU-only

Get the encryption key, initializing lazily on first call.

Get HTML header splitter configured for h1, h2, h3.

Get Markdown header splitter configured for #, ##, ###.

Get minimum chunk size from environment variable or use default. Chunks below this token count are dropped. Some splitters (notably the HTML

Get encryption key from environment, requires explicit configuration. Priority: 1. OPEN_NOTEBOOK_ENCRYPTION_KEY_FILE (Docker secrets)

Select the best model from a list based on provider priority and model preferences. Args: models: List of model dictionaries with 'p

Return a short speech clip for STT testing, or silence as a fallback.

Load data from database if not already loaded

Normalize common error patterns into user-friendly messages.

Parse CORS_ORIGINS env value into a list of origins.

Prepare data for database storage. SecretStr values are extracted, encrypted, and stored as strings. Encryption is performed

Override to ensure command field is always RecordID format for database

Process any additional custom parameters.

Set environment variables for Azure OpenAI from DB config. Returns: True if any keys were set from database

Set environment variables for OpenAI-Compatible providers from DB config. Returns: True if any keys were set from database

Set environment variable for a simple provider from DB config. Returns: True if key was set from database, False otherwise

Set environment variables for Google Vertex AI from DB config. Returns: True if any keys were set from database

Test Azure OpenAI connectivity by listing models. Azure requires deployment names which vary per user, so instead of invoking a model, w

Test Ollama server connectivity.

Test OpenAI-compatible server connectivity.

Ask the knowledge base a question (simple, non-streaming).

Build context in a new event loop

Bump the version by adding a new entry to migrations table.

Cancel a running command job

Check if database is reachable using a lightweight query. Returns: dict with 'status' ("online" | "offline") and optional 'error'

Collect items to rebuild based on mode and include flags. Returns: Dict with keys: 'sources', 'notes', 'insights' containing lists o

Consolidate all markdown files from a folder into a single file with a TOC.

Create a Credential from environment variables for a given provider.

Create a new source with support for both JSON and multipart form data.

Create a new source with support for async processing. Args: notebook_id: Single notebook ID (deprecated, use notebooks

Discover models using explicit config instead of env vars. Returns model names only — no type classification. The user chooses the model

Generate and store embedding for a single source insight. Uses the unified embedding pipeline with automatic chunking and mean pooling f

Generate and store embedding for a single note. Uses the unified embedding pipeline with automatic chunking and mean pooling for notes t

Generate unique filename like Streamlit app (append counter if file exists).

Get all versions from the migrations table.

Get status of any command job

Get password with backward compatibility

Get database URL with backward compatibility

Get counts of items that would be affected by deleting this notebook. Returns a dict with: - note_count: Number of notes tha

Get all episode profiles.

Always fetch fresh defaults from database (override parent caching behavior)

Get status of a podcast generation job

Check for the latest version from GitHub with caching. Returns: tuple: (latest_version, has_update) - latest_version: str or

Get all markdown files in a folder, excluding index.md files.

Get all models with optional type filtering.

Get all notebooks.

Get count of registered models for a provider, grouped by type. Args: provider: Provider name (case-insensitive) Returns:

Get configuration status: encryption key status, and per-provider configured/source information.

Get a specific source.

Get processing status for a source.

Get all transformations.

Read version from pyproject.toml

Fetch and parse the version from pyproject.toml in a public GitHub repository (async).