Turn a folder of documents, a table you already have, or documents fetched out of a service (wiki, cloud docs, mail) into governed, searchable context an agent can query — hybrid search (vector + full-text) served by skardi-server over SQLite, Postgres+pgvector, MongoDB, or Lance. Three raw-material entries, one flow.
Answer questions from live data through a running skardi-server using the skardi CLI. Discovers sources, pipelines, and the table schemas the deployment exposes, searches any semantic surface first, then writes read-only SQL against exact qualified table names, checks truncation before trusting counts, and reports…
Connect a property graph (knowledge graph, GraphRAG corpus, Apache AGE / openCypher data) to Skardi and query it through SQL, end to end: provision the AGE backend with a least-privilege role, declare the type: graph source and its views in context YAML, verify registration health, write correct queries (cypherquery.