Module core

Module core 

Source

Structs§

AppState
Application state shared across handlers
Config
Configuration for text processing
FastEmbedder
FastEmbed-based embedding implementation
InputData
Input data for URL processing
InputDataText
Input data for text embedding
LLMConceptChunker
LLM concept-based chunking (placeholder)
LLMIntrospectionChunker
LLM introspection-based chunking (placeholder)
ProcessedContent
Processed content with embeddings
ServerConfig
Server configuration
WordChunker
Word-based chunking implementation

Traits§

ContentChunker
Trait for content chunking strategies
Embedder
Trait for embedding generation

Functions§

cache_result
Cache processed content in the database
embed_text
Process text and return embeddings
fetch_content
Fetch content from a URL
generate_hash
Generate a hash for caching purposes
get_default_config
Get the default configuration for text processing
get_embedding_model
Get embedding model by name
get_from_cache
Get cached content from the database
initialize_chunkers
Initialize chunkers
initialize_db_pool
Initialize the database pool
initialize_models
Initialize embedding models
list_supported_features
List supported features
process_url
Process a URL and return processed content