Social Department builds QuickSearch video discovery on AWS Bedrock
Start here
Social Department, an AI operating system for entertainment marketing, built QuickSearch, a set of single-action queries that returns video clips marketers cannot easily describe in a search box: Shareable Scenes, Quotable Quotes, Memeable Moments and Trend Align. AWS published a technical walkthrough of the system's AWS components: the ingest and indexing pipeline, the retrieval path and the services that run them. The pipeline runs TwelveLabs' Marengo 3.0 and Pegasus 1.2 models on Amazon Bedrock, uses Amazon OpenSearch Serverless for retrieval, and has Claude models available through Bedrock. According to AWS, customer data stays within the AWS data boundary, is not shared with model providers and is not used to train the underlying models. Completed results are stored in Amazon DynamoDB and reused for 30 days.
Generated from reports · updated 23 h ago
Report timeline
Follow the reports to see the event from different sides.
- AWS Machine Learning BlogHow Social Department Built Culture-Aware Video Discovery with QuickSearch on Amazon Bedrock
Social Department built QuickSearch, a set of single-action queries for entertainment marketing that returns clips marketers cannot describe in a search box: Shareable Scenes, Quotable Quotes, Memeable Moments, and Trend Align. The pipeline runs TwelveLabs' Marengo 3.0 and Pegasus 1.2 models on Amazon Bedrock, with Amazon OpenSearch Serverless for retrieval and Claude models available through Bedrock.
Heat for this event
- Current, comparable range
- 5
- Peak, comparable range
- 10November 19 05:00
- Change in 24 hours
- –
The trend compares the same participants over hours observed continuously, so its range can be narrower than the current heat count. Hover or tap the chart for hourly heat; the arrow keys move through it.