Case study · Summer 2025
Source-Linked YouTube RAG
A transcript-ingestion and retrieval service where every generated answer points back to its source and timestamp.
- Discipline
- Retrieval systems · Data engineering
- Technology
- Python · FastAPI · OpenAI · Milvus · REST API
Overview
I built a FastAPI pipeline that ingests YouTube transcripts, embeds them in Milvus, and returns source-linked answers through a REST API.
System map
How the pieces connect
The challenge
What made the problem worth solving
Retrieval makes generated answers more grounded, but users still need a direct path back to the evidence—especially when a long video makes manual verification expensive.
The approach
Turning the problem into an engineering plan
- 01
Built an ingestion pipeline for transcript segments and their source metadata.
- 02
Stored embeddings in Milvus and exposed retrieval through a FastAPI service.
- 03
Preserved transcript and timestamp lineage through the entire response path.
Result
The system made auditability a first-class product behavior: the answer was useful, but the path back to the original moment in the video was equally important.