๐—•๐˜‚๐—ถ๐—น๐—ฑ๐—ถ๐—ป๐—ด ๐—ฆ๐—ฒ๐—บ๐—ฎ๐—ป๐˜๐—ถ๐—ฐ ๐—ฆ๐—ฒ๐—ฎ๐—ฟ๐—ฐ๐—ต ๐˜„๐—ถ๐˜๐—ต ๐—ฝ๐—ด๐˜ƒ๐—ฒ๐—ฐ๐˜๐—ผ๐—ฟ ๐—ฎ๐—ป๐—ฑ ๐—ข๐—ฝ๐—ฒ๐—ป๐—”๐—œ

Keyword search failed 31% of users. People searched for funny cats. Titles used different words. The results were empty.

Semantic search fixes this. It looks at meaning.

The setup:

Three ways to make it work:

  1. Use content hashes. Do not embed the same text twice. You save 94% on costs.

  2. Create a structured document. Combine the title, channel, and tags. This gives the vector more context.

  3. Add an extra score for exact matches. Semantic search is fuzzy. Give a bonus to titles with the exact words. This keeps precision high.

Privacy matters. Send only video metadata to the US API. Keep all personal data in the EU.

The result:

Stop relying on keyword matching. Use vectors to find what your users mean.

Source: https://dev.to/ahmet_gedik778845/building-video-metadata-semantic-search-with-pgvector-and-openai-embeddings-34c Optional learning community: https://t.me/GyaanSetuAi