š New Blog Post Alert! š
After building the transcription process in the
first part of my series, I'm excited to share the next step in "
Semantic Search to Glean Valuable Insights from Podcasts: Part 2."
In this post, I walk you through the embedding of my
podcast transcripts and efficiently storing them in ApertureDB. This step is crucial for enhancing search capabilities and ensuring our data is well-organized and ready for semantic querying.
Dataset: Podcast transcripts (.txt)
Embedding model:
Cohereās embed-english-v3.0
Metadata, embeddings, text storage: ApertureDB from
ApertureData