Structs§
- AppState
- Application state shared across handlers
- Config
- Configuration for text processing
- Fast
Embedder - FastEmbed-based embedding implementation
- Input
Data - Input data for URL processing
- Input
Data Text - Input data for text embedding
- LLMConcept
Chunker - LLM concept-based chunking (placeholder)
- LLMIntrospection
Chunker - LLM introspection-based chunking (placeholder)
- Processed
Content - Processed content with embeddings
- Server
Config - Server configuration
- Word
Chunker - Word-based chunking implementation
Traits§
- Content
Chunker - 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