danvics/haiku.rag
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

rename document_items repository's _LIGHT_COLUMNS to _METADATA_COLUMNS

Browse source
This commit is contained in:
Yiorgis Gozadinos 2026-04-30 15:43:03 +03:00
parent 35e6568f59
commit b290bbe82d
No known key found for this signature in database
1 changed files with 7 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

15
haiku_rag_slim/haiku/rag/store/repositories/document_item.py
View file

@ -4,11 +4,10 @@ from haiku.rag.store.engine import DocumentItemRecord, Store
from haiku.rag.store.models.document_item import DocumentItem from haiku.rag.store.models.document_item import DocumentItem
from haiku.rag.utils import escape_sql_string from haiku.rag.utils import escape_sql_string
# Columns returned by the lightweight read path. `picture_data` is intentionally # Per-item metadata columns. The payload column ``picture_data`` is fetched
# excluded so context expansion and the analysis-sandbox items.jsonl build don't # explicitly via ``get_picture_bytes`` / ``get_pictures_for_chunk`` /
# pull MB-scale image bytes into memory. Use get_picture_bytes / # ``get_all_picture_data`` so bulk scans don't pull MB-scale image bytes.
# get_pictures_for_chunk to fetch picture_data explicitly. _METADATA_COLUMNS = [
_LIGHT_COLUMNS = [
"document_id", "document_id",
"position", "position",
"self_ref", "self_ref",
@ -59,7 +58,7 @@ class DocumentItemRepository:
safe_id = escape_sql_string(document_id) safe_id = escape_sql_string(document_id)
rows = await ( rows = await (
self.store.document_items_table.query() self.store.document_items_table.query()
.select(_LIGHT_COLUMNS) .select(_METADATA_COLUMNS)
.where(f"document_id = '{safe_id}'") .where(f"document_id = '{safe_id}'")
.to_list() .to_list()
) )
@ -79,7 +78,7 @@ class DocumentItemRepository:
Returns: Returns:
Dict mapping document_id to sorted list of DocumentItem. Dict mapping document_id to sorted list of DocumentItem.
""" """
query = self.store.document_items_table.query().select(_LIGHT_COLUMNS) query = self.store.document_items_table.query().select(_METADATA_COLUMNS)
if document_ids is not None: if document_ids is not None:
safe_ids = ", ".join(f"'{escape_sql_string(did)}'" for did in document_ids) safe_ids = ", ".join(f"'{escape_sql_string(did)}'" for did in document_ids)
query = query.where(f"document_id IN ({safe_ids})") query = query.where(f"document_id IN ({safe_ids})")
@ -100,7 +99,7 @@ class DocumentItemRepository:
safe_id = escape_sql_string(document_id) safe_id = escape_sql_string(document_id)
rows = await ( rows = await (
self.store.document_items_table.query() self.store.document_items_table.query()
.select(_LIGHT_COLUMNS) .select(_METADATA_COLUMNS)
.where( .where(
f"document_id = '{safe_id}' " f"document_id = '{safe_id}' "
f"AND position >= {start} AND position <= {end}" f"AND position >= {start} AND position <= {end}"