Find aerial detection/segmentation datasets on HF via CLI
Session from hf-find-traces on Hugging Face by merve · Apache-2.0 · condensed by Coders Talk
Click a segment to jump to that moment
3msession
1interventions
GOAL
Search Hugging Face Hub for aerial object detection and segmentation datasets using the hf CLI, and ensure future sessions use the better semantic search tool.
- +0Prompt · +0Find aerial object detection segmentation datasets on HF
- +0mAgent did · +0mTried several hf CLI subcommands (dataset-search, datasets search, datasets list --search) with various queries like xview, dota, visdrone, hrsc - most returned no results or errors
- +0mAgent did · +0mContinued keyword search with hf datasets list --search 'aerial', got some results and summarized a table of aerial detection datasets
- +0mPrompt · +0mAsked if hf-find is installed with pi
- +1mPrompt · +1mPointed out hf-find is an hf extension and asked to run hf find --help
- +1mAgent did · +1mRan hf find --help, discovered hf-find extension exists, used hf find datasets semantic search, got much better matching results (isaid, dota-v1.5, SkyScenes, etc.)
- +2mIntervention · +2mAsked why the agent didn't use hf-find from the start since it's already installedWhy: It was already installed - the agent should have checked for better tools before defaulting to weak keyword search.
- +2mPrompt · +2mAsked what to do so pi sees hf-find next time
- +2mAgent did · +2mRead the hf-cli SKILL.md, found it lacked hf-find extension docs, and edited the skill file to document hf find commands for future sessions
- +3mOutcome · +3mUpdated SKILL.md with hf find semantic search commands (+22 −6 lines) so future sessions default to the better search tool
VERDICT
Next time I'd just ask upfront whether there's a better search tool installed instead of letting the agent grind through keyword search failures. Pointing out that hf-find was already installed was what actually fixed things - once I nudged it to check, the semantic search immediately gave better results. Updating the skill doc afterward should prevent this same detour from happening again.