jobdata

Optimized Vector Embeddings & Search

jobdataapi.com v4.14 / API version 1.16

0 min read · March 28, 2025

We’ve significantly optimized our vector embeddings and search capabilities to improve performance and efficiency while maintaining high-quality semantic matching.

Key improvements:

  • All job post embeddings now use 768-dimensional half-precision (16-bit) vectors (embed_3sh), cutting bandwidth and compute costs without sacrificing accuracy.

  • Embedding data in CSV downloads is now much smaller, reducing storage and processing needs.

  • The previous embed_3s parameter has been replaced with embed_3sh for consistency.

These refinements make semantic search and matching lighter, faster, and just as effective, ensuring you get the best balance of performance and relevance. Based on our tests, we found that smaller, leaner embeddings deliver nearly identical results - just faster and with far less overhead. For full details, see the updated Vector Embeddings and Search API Documentation.

Related Docs

Introducing Vector Embeddings and Vector Search in the jobdata API
Removal of clearance_required field from job result structure
Enhanced multi-value parameters for Job and Company queries
GeoNames upgrade, new population field and filters, expired field now in job results
Change of length for job title and location fields
Added application URL query filter + (multi) country code parameter enhancements
jobdataapi.com now has Changelog section 🎉
Maximum value for "page_size" parameter increased to 5000
Added company open/total job counts + filters
Full job data downloads now available!
New location, ID fields and filters
Added plain-text field for cleaned job description
Added new Job States (geo) endpoint, query filters, and more
Added company website/domain filter to jobs endpoint
Added company flag for recruiting/staffing firms + enhanced filtering options
Improved Job States (geo) search, Markdown job descriptions, and lean data retrieval