Skip to content

experimental: return the expanded transcriptions directly on the search endpoint #14

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
gabrielmouallem wants to merge 1 commit into
base: dev
Choose a base branch
from
Open

experimental: return the expanded transcriptions directly on the search endpoint #14

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
108 changes: 63 additions & 45 deletions app/api/v1/search/controller.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,8 +36,71 @@ def search_transcriptions_by_video(self, search: SearchDTO):
}
},
]

# Aggregation for expanded transcription within each transcription
expanded_transcription_stage = {
"$lookup": {
"from": "videoTranscriptions", # Assuming collection name is videoTranscriptions
"let": {"videoId": "$video.videoId", "startTime": "$start"},
"pipeline": [
{
"$match": {
"$expr": {
"$and": [
{"$eq": ["$video.videoId", "$$videoId"]},
{
"$gt": [
"$start",
{"$subtract": ["$$startTime", 10]},
]
},
{
"$lt": [
"$start",
{"$add": ["$$startTime", 10]},
]
},
]
}
}
},
{"$sort": {"start": 1}},
{
"$group": {
"_id": "$video.videoId",
"merged_start": {"$first": "$start"},
"merged_end": {
"$last": {"$add": ["$start", "$duration"]}
},
"merged_text": {"$push": "$text"},
"merged_duration": {"$sum": "$duration"},
}
},
{
"$project": {
"_id": 0,
"start": "$merged_start",
"end": "$merged_end",
"text": {
"$reduce": {
"input": "$merged_text",
"initialValue": "",
"in": {"$concat": ["$$value", " ", "$$this"]},
}
},
"duration": "$merged_duration",
}
},
],
"as": "expanded_transcription",
}
}

# Create the text search query
results_pipeline = common_pipeline + [
{"$unwind": "$transcriptions"},
{"$addFields": {"start": "$transcriptions.start"}},
expanded_transcription_stage,
{"$sort": search.order_by},
{"$skip": skip_count},
{"$limit": search.per_page},
Expand Down Expand Up @@ -79,48 +142,3 @@ def search_transcriptions_by_video(self, search: SearchDTO):
status=500,
mimetype="application/json",
)

def expanded_transcription(self, video_id, start_time):

# Aggregation pipeline to find 2 before and 2 after the target transcription
pipeline = [
{
"$match": {
"video._id": video_id,
"start": {"$gt": start_time - 10, "$lt": start_time + 10},
}
},
{"$sort": {"start": 1}}, # Ensure documents are sorted by start time
{
"$group": {
"_id": "$video._id", # Grouping by videoId, adjust if you need different granularity
"merged_start": {"$first": "$start"},
"merged_end": {"$last": {"$add": ["$start", "$duration"]}},
"merged_text": {"$push": "$text"},
"merged_duration": {"$sum": "$duration"},
}
},
{
"$project": {
"_id": 0,
"start": "$merged_start",
"end": "$merged_end",
"text": {
"$reduce": {
"input": "$merged_text",
"initialValue": "",
"in": {"$concat": ["$$value", " ", "$$this"]},
}
},
"duration": "$merged_duration",
}
},
]

transcriptions = self.search_service.aggregate_transcriptions(pipeline=pipeline)
if len(transcriptions) > 0:
return jsonify(transcriptions)
return (
jsonify({"error": "No transcriptions found or error in aggregation"}),
404,
)