feat: complete catalog-driven preprocessing
Publish documentation / publish (push) Successful in 2m12s

This commit is contained in:
Codex
2026-09-06 17:49:35 +02:00
parent 8707ae1d46
commit cffa60772e
141 changed files with 5898 additions and 3015 deletions
+8 -14
View File
@@ -9,7 +9,7 @@ from tht.config import workspace_id_for_config
KIND_MAP = {
"evidence": ["evidence"],
"schema": ["schema_table", "schema_column"],
"schema": ["schema_table", "schema_column", "schema_relationship"],
"values": [], # solo LSH
"formula": ["evidence"],
}
@@ -235,15 +235,8 @@ def search_cmd(
from tht.mschema.render import to_mschema_text
from tht.search import schema_tables
phys_file = dwh_snapshot.physical
if not phys_file.exists():
typer.secho(
f"ERRORE: {phys_file} non trovato. Esegui prima `tht schema introspect`.",
fg=typer.colors.RED, err=True,
)
raise typer.Exit(code=1)
try:
schema_context = load_schema_context(cfg, physical_file=phys_file)
schema_context = load_schema_context(cfg)
except SchemaContextError as exc:
typer.secho(f"ERRORE: {exc}", fg=typer.colors.RED, err=True)
raise typer.Exit(code=1) from None
@@ -390,7 +383,7 @@ def pack_cmd(
workspace_id = workspace_id_for_config(cfg, config)
validate_corpus_workspace(cfg, workspace_id)
dwh_snapshot = _leased_dwh_snapshot(cfg, ctx)
_leased_dwh_snapshot(cfg, ctx)
require_vector_cfg(cfg)
tables: list[dict] = []
@@ -414,12 +407,13 @@ def pack_cmd(
if vec is not None:
descriptions: dict[str, str] = {}
phys_file = dwh_snapshot.physical
if phys_file.exists():
from tht.mschema.models import PhysicalSchema
from tht.mschema.context import SchemaContextError, load_schema_context
phys = PhysicalSchema.from_yaml(phys_file)
try:
phys = load_schema_context(cfg).physical
descriptions = {t: tab.comment for t, tab in phys.tables.items()}
except SchemaContextError:
pass
try:
cand = combined_search(
keyword=question, lsh_hits=None, store=searcher, embedder=embedder,