admin/momentry_core
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: OCR independent chunks + TMDb seed with file_uuid

Browse Source 
- Rule 1 now creates OCR-only chunks instead of merging into ASRX
- generate_seed_embeddings.py supports --file-uuid parameter
- get_seeds() filters by file_uuid
- identity_matcher.py uses file_uuid for seed matching
- Push QDRANT_API_KEY to Python subprocesses
- Face clustering uses frame+bbox matching instead of face_id
- Portal uses JWT authentication
- FilesView filter logic fixed
This commit is contained in:
Accusys
2026-07-06 08:56:56 +08:00
parent cb604b74ec
commit 799ede5a0e
10 changed files with 147 additions and 38 deletions
Download Patch File Download Diff File Expand all files Collapse all files

49
scripts/generate_seed_embeddings.py
View File

@@ -46,11 +46,12 @@ SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
FACENET_PATH = os.path.join(SCRIPT_DIR, "..", "models", "facenet512.mlpackage")
def get_tmdb_identities(limit: int = None) -> List[Dict]:
def get_tmdb_identities(limit: int = None, file_uuid: str = None) -> List[Dict]:
"""Query PG for TMDb identities with profile photos
Args:
limit: Max identities to process
file_uuid: Filter by file_uuid via file_identities table
Returns:
List of {id, uuid, name, tmdb_id, tmdb_profile}
@@ -63,20 +64,34 @@ def get_tmdb_identities(limit: int = None) -> List[Dict]:
if SCHEMA == "public":
table = "identities"
file_table = "file_identities"
else:
table = f"{SCHEMA}.identities"
file_table = f"{SCHEMA}.file_identities"
query = f"""
SELECT id, uuid, name, tmdb_id, tmdb_profile
FROM {table}
WHERE source = 'tmdb' AND tmdb_profile IS NOT NULL
ORDER BY id
"""
if file_uuid:
query = f"""
SELECT DISTINCT i.id, i.uuid, i.name, i.tmdb_id, i.tmdb_profile
FROM {table} i
JOIN {file_table} fi ON fi.identity_id = i.id
WHERE i.source = 'tmdb' AND i.tmdb_profile IS NOT NULL
AND fi.file_uuid = %s
ORDER BY i.id
"""
if limit:
query += f" LIMIT {limit}"
cur.execute(query, (file_uuid,))
else:
query = f"""
SELECT id, uuid, name, tmdb_id, tmdb_profile
FROM {table}
WHERE source = 'tmdb' AND tmdb_profile IS NOT NULL
ORDER BY id
"""
if limit:
query += f" LIMIT {limit}"
cur.execute(query)
if limit:
query += f" LIMIT {limit}"
cur.execute(query)
rows = cur.fetchall()
cur.close()
conn.close()
@@ -180,7 +195,7 @@ def extract_face_embedding(image_path: str) -> Optional[List[float]]:
return None
def generate_seed_embeddings(limit: int = None, dry_run: bool = False) -> Dict:
def generate_seed_embeddings(limit: int = None, dry_run: bool = False, file_uuid: str = None) -> Dict:
"""Generate embeddings for all TMDb identities
Args:
@@ -198,14 +213,14 @@ def generate_seed_embeddings(limit: int = None, dry_run: bool = False) -> Dict:
"errors": [],
}
identities = get_tmdb_identities(limit)
identities = get_tmdb_identities(limit, file_uuid)
result["total"] = len(identities)
if not identities:
print("[SEED] No TMDb identities with profile photos")
print(f"[SEED] No TMDb identities with profile photos{' for ' + file_uuid if file_uuid else ''}")
return result
print(f"[SEED] Found {len(identities)} TMDb identities")
print(f"[SEED] Found {len(identities)} TMDb identities{' for ' + file_uuid if file_uuid else ''}")
if not dry_run:
ensure_seeds_collection()
@@ -259,6 +274,7 @@ def generate_seed_embeddings(limit: int = None, dry_run: bool = False) -> Dict:
name=name,
embedding=embedding,
source="tmdb",
file_uuid=file_uuid,
tmdb_id=tmdb_id,
)
result["success"] += 1
@@ -280,12 +296,13 @@ def main():
parser.add_argument("--dry-run", action="store_true", help="Don't push to Qdrant")
parser.add_argument("--tmdb-api-key", help="TMDb API key (optional, for rate limiting)")
parser.add_argument("--output", help="Output JSON file path")
parser.add_argument("--file-uuid", help="File UUID to generate seeds for")
args = parser.parse_args()
if args.tmdb_api_key:
TMDB_API_KEY = args.tmdb_api_key
result = generate_seed_embeddings(args.limit, args.dry_run)
result = generate_seed_embeddings(args.limit, args.dry_run, args.file_uuid)
output_json = json.dumps(result, indent=2, ensure_ascii=False)