Schema | smart-search

smart-search

Describes the environment variables required to run the server.

Name	Required	Description	Default
`SMART_SEARCH_DATA_DIR`	No	Override the default data directory path where LanceDB and SQLite data are stored.
`SMART_SEARCH_EMBEDDING_MODEL`	No	Embedding model to use for vector search.	Snowflake/snowflake-arctic-embed-m-v2.0
`SMART_SEARCH_CHUNK_MAX_TOKENS`	No	Maximum tokens per chunk.	512
`SMART_SEARCH_EXCLUDE_PATTERNS`	No	JSON array of directory patterns to exclude from indexing.	[".git", ".obsidian", "node_modules"]
`SMART_SEARCH_WATCH_DIRECTORIES`	No	JSON array of directories to watch for indexing.	[]
`SMART_SEARCH_RELEVANCE_THRESHOLD`	No	Minimum similarity score for semantic mode.	0.30
`SMART_SEARCH_SEARCH_DEFAULT_MODE`	No	Default search mode (hybrid, semantic, or keyword).	hybrid
`SMART_SEARCH_EMBEDDING_DIMENSIONS`	No	Vector dimensions (Matryoshka truncation).	256
`SMART_SEARCH_SEARCH_DEFAULT_LIMIT`	No	Default number of search results to return.	10
`SMART_SEARCH_SUPPORTED_EXTENSIONS`	No	JSON array of file extensions to index.	[".md", ".txt", ".pdf", ".docx", ".epub", ".xlsx", ".xls", ".csv", ".pptx", ".html", ".htm", ".json", ".jsonl", ".msg", ".ipynb"]
`SMART_SEARCH_WATCHER_DEBOUNCE_SECONDS`	No	File watcher debounce time in seconds.	2.0

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

This server cannot be deployed

ActivityInactive

ResponsivenessResponsive