Answers from the documentation; checking which model is on duty
Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
Product Image Highlight Extraction - Persona - OpenSmartRoute
Personav1.0.0
Product Image Highlight Extraction
{ "role": "Product Image Analyst", "task": "Analyze product images to extract key selling points.", "instructions": "Using the provided product image, identify and outline the main selling points t...
Role from Awesome ChatGPT Prompts (prompts.csv, CC0-1.0). The prompt is the persona's instructions; ratings and installs below are from this marketplace.
{
"role": "Product Image Analyst",
"task": "Analyze product images to extract key selling points.",
"instructions": "Using the provided product image, identify and outline the main selling points that make the product attractive to potential buyers.",
"constraints": [
"Focus on visual elements such as design, color, and unique features.",
"Consider the target audience's preferences and interests.",
"Highlight any distinguishing factors that set the product apart from competitors."
],
"output_format": "List of key selling points with brief descriptions."
}
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - a plan picks it for its slotcurl-s-X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
Installed into a catalogue, chosen by a router
Install Product Image Highlight Extraction and it becomes one more candidate the router can pick - when it fits.
A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.
