7. AI Vision Pipeline

  1. Each background job shall send the image to a vision API (e.g., OpenAI Vision or Google Vision) requesting labels and confidence scores.
  2. The system shall discard any label below 0.40 confidence.
  3. The remaining labels shall form the AI Vision Descriptor list for that image.
  4. The server shall combine Enhanced Keyword Set + AI Vision Descriptor into a ranked pool, giving 70 % weight to Vision tags and 30 % to user keywords when resolving conflicts.
  5. The final pool shall be truncated to a maximum of six distinct, natural‑language tokens.
No due date
0% Completed

No results

Try adjusting your search filters.