Web data infrastructure for AI agents and research

# 1. Search the web
curl -sS https://api.cormorant.ch/v1/search \
  -H "Authorization: Bearer $CORMORANT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "Holcim annual report 2025", "max_results": 5}'

# 2. Fetch the page you picked
curl -sS https://api.cormorant.ch/v1/fetch \
  -H "Authorization: Bearer $CORMORANT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://www.holcim.com/investors"}'

import os

import httpx

client = httpx.Client(
    base_url="https://api.cormorant.ch",
    headers={"Authorization": f"Bearer {os.environ['CORMORANT_API_KEY']}"},
    timeout=180,
)

# 1. Search the web
hits = client.post(
    "/v1/search", json={"query": "Holcim annual report 2025", "max_results": 5}
).json()["results"]

# 2. Fetch the first result
page = client.post("/v1/fetch", json={"url": hits[0]["url"]}).json()
if page["error"] is None:
    print(page["title"], page["tier"], page["billing_category"])
    print(page["text"][:500])

{
  "status": 200,
  "tier": "direct",
  "attempts": [
    {"tier": "direct", "status": 200, "reason": "ok", "ms": 412}
  ],
  "title": "Annual Report 2025",
  "sha256": "a3f1...",
  "bytes": 2483112,
  "cached": false,
  "cost_usd": 0.0,
  "billing_category": "fetch_own"
}