knight/TLC-Search
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Revert "Fix secondary transcript timestamps by indexing parts"

Browse Source 
This reverts commit 2efe5e0c799d2a177a520506a22b7fcb037ffe47.
This commit is contained in:
knight 2025-11-05 00:57:29 -05:00
parent 2efe5e0c79
commit e998eadd79
1 changed files with 1 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
ingest.py
View File

@ -74,16 +74,6 @@ def build_bulk_actions(
segment.get("text", "") if isinstance(segment, dict) else str(segment)
for segment in parts
).strip()
# Handle secondary transcript parts
secondary_parts = doc.get("transcript_secondary_parts") or []
transcript_secondary_full = doc.get("transcript_secondary_full")
if not transcript_secondary_full and isinstance(secondary_parts, list):
transcript_secondary_full = " ".join(
segment.get("text", "") if isinstance(segment, dict) else str(segment)
for segment in secondary_parts
).strip()
yield {
"_id": video_id,
"_index": index or CONFIG.elastic.index,
@ -98,9 +88,8 @@ def build_bulk_actions(
"url": doc.get("url"),
"duration": doc.get("duration"),
"transcript_full": transcript_full,
"transcript_secondary_full": transcript_secondary_full,
"transcript_secondary_full": doc.get("transcript_secondary_full"),
"transcript_parts": parts,
"transcript_secondary_parts": secondary_parts,
},
}
@ -132,14 +121,6 @@ def ensure_index(client: "Elasticsearch", index: str) -> None:
"text": {"type": "text"},
},
},
"transcript_secondary_parts": {
"type": "nested",
"properties": {
"start": {"type": "float"},
"duration": {"type": "float"},
"text": {"type": "text"},
},
},
}
},
)