Mahal Systems Overview › 8Retrieval › b.Querying precisely
Querying precisely
2 optimizations.
- i.
Tune the search tool: snippets, enough results, retries, reformulation, filters, source quality
Make the search tool return what the model needs to choose what to open (a snippet per result, not just titles; five or more results; a full-document reader beside truncated search), retry failed searches, and reformulate when a query returns little (start broad, then narrow; use the corpus's own terms) rather than retrying it verbatim.
- ii.
Link large schemas by exploration: start broad, grow the linked set with probing queries, favor recall
When a schema is too large to load whole, link the tables and columns a question needs by exploration rather than by one up-front retrieval or by loading everything: start from all table names plus the top retrieved columns, give the agent a column-level vector index, metadata probes and trial queries to grow the linked set, favor recall over minimizing noise, and cap the exploration turns low.
See also
- 5.b.i
Give the model the schema it queries, in context: descriptions, keys, codes, sample values
When the model writes SQL or structured filters, put the schema it is querying in its context: table and column descriptions, key relationships, what enum codes and nulls mean, sample values.
- 7.a.i
Route metric questions through a deterministic semantic layer; fall back to text-to-SQL
Where a semantic layer exists, have the agent answer metric questions by choosing metrics and dimensions that the layer compiles to SQL, and write SQL only when the layer cannot answer.
- 8.a.i
Choose the retriever by corpus size and question type
On a bounded corpus (up to about 100K documents), grep and file reads over the raw text beat an embedding retriever: the agent narrows into documents it has found.