sqliteai/SQLite AI - AI search for documents

Out-of-the-box database for AI search for documents powered by SQLite AI.

Trust Signals

name	description	required	default
connection_string	The SQLite Cloud project connection string.	yes	—
base_url	Your website's documentation base url.	yes	—
database_name	The name of the database to use on SQLite Cloud	yes	—
source_files	The path of the files, by default it will parse every file recursively starting from the working directory.	no	./
only_extensions	Comma-separated list of file extensions to include (e.g., "md,txt,html"). If not set, all supported file types are included.	no	""
exclude_extensions	Comma-separated list of file extensions to exclude (e.g., "js,jsx"). If not set, no file types are excluded.	no	""
hf_model_id	The Hugging Face model ID to use for generating embeddings.	no	unsloth/embeddinggemma-300m-GGUF
hf_gguf_file	The GGUF file name for the Hugging Face model.	no	embeddinggemma-300M-Q8_0.gguf
hf_gguf_update_date	The date to force update the GGUF model cache, format YYYYMMDD.	no	20250904
hf_model_local_path	The local path to store the downloaded Hugging Face model.	no	./models

no outputs