export LINKUP_API_KEY="your-api-key"

# /extract is async: POST returns immediately with an id. Poll until completed,
# then download the NDJSON result from output.resultUrl (valid 24h).

# 1. Submit
curl -X POST "https://api.linkup.so/v1/extract" \
  -H "Authorization: Bearer $LINKUP_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "q": "All engineering team members with their name, role, and profile page",
    "url": "https://example.com/team",
    "schema": {
      "type": "object",
      "properties": {
        "name": { "type": "string" },
        "role": { "type": "string" },
        "profileUrl": { "type": "string", "format": "uri" }
      },
      "required": ["name", "profileUrl"]
    },
    "verifyUrls": true
  }'

# 2. Poll (initial 2s, back off to 10s, max 1 request/second)
curl "https://api.linkup.so/v1/extract/<id>" \
  -H "Authorization: Bearer $LINKUP_API_KEY"

# 3. Download rows once status == "completed"
curl "<output.resultUrl>"

{
  "type": "function",
  "function": {
    "name": "linkup_extract",
    "description": "Extracts structured rows of data from a web page. Provide a seed URL and a natural-language description of the rows to collect; returns the rows as an NDJSON file. Use for repeated records on a known page (team members, products, jobs, directory entries). Async: the handler should poll until completion and download the result.",
    "parameters": {
      "type": "object",
      "properties": {
        "q": {
          "type": "string",
          "description": "Natural-language query describing which rows to extract and what each row should contain. Name the unit of repetition (one person, one product, one job) and the fields each row must include."
        },
        "url": {
          "type": "string",
          "description": "The seed URL the extract task starts from. Point it at the page that already lists the records, not the site homepage."
        },
        "schema": {
          "type": "object",
          "description": "Optional JSON schema describing a single extracted row. When provided, every returned row must match it. Keep it flat; use format 'uri' for link fields. Omit to let the agent infer the shape from q and the data structure on the website."
        },
        "verifyUrls": {
          "type": "boolean",
          "description": "Whether URLs found in extracted rows are checked for reachability after extraction. Adds latency. Defaults to false.",
          "default": false
        }
      },
      "required": ["q", "url"]
    }
  }
}