Agents and coding · Posted 5 days ago
Search over 5,000 support tickets with Postgres and pgvector
- Fixed price
- $1,200
- Level
- Expert
- Length
- 1 month
The work
We want our support team to search past tickets by meaning, not keywords: "customer can't log in after password reset" should find every similar ticket even when the words differ.
Our stack is Postgres and TypeScript. Add pgvector, embed the 5,000 tickets, keep new ones embedded, and build a small search page with filters for date and product. Show us how good it is on 30 test searches we provide.
What to hand in
- Embeddings stored and kept current
- A search page with filters
- Results on 30 test searches
Skills
PostgrespgvectorEmbeddingsTypeScript
The buyer asks
Which embedding model would you start with, and how would you know it is good enough?
Activity
Proposals: Less than 5