"""Embed chunks on the local endpoint, checkpointing as we go."""
import json, pathlib, ssl, time, urllib.request

URL = 'https://inference.lan:8443/v1/embeddings'   # placeholder: the real host is never committed
MODEL = 'nomic-embed-text'
BATCH = 24
ctx = ssl.create_default_context(); ctx.check_hostname = False; ctx.verify_mode = ssl.CERT_NONE

chunks = json.loads(pathlib.Path('chunks.json').read_text(encoding='utf-8'))
out = pathlib.Path('embeddings.json')
done = json.loads(out.read_text()) if out.exists() else []

start = len(done)
print(f'{len(chunks)} chunks, resuming at {start}', flush=True)
t0 = time.time()
for i in range(start, len(chunks), BATCH):
    batch = [c['text'] for c in chunks[i:i + BATCH]]
    body = json.dumps({'model': MODEL, 'input': batch}).encode()
    req = urllib.request.Request(URL, data=body, headers={'Content-Type': 'application/json'})
    for attempt in range(4):
        try:
            with urllib.request.urlopen(req, timeout=180, context=ctx) as r:
                d = json.load(r)
            done.extend(e['embedding'] for e in d['data'])
            break
        except Exception as e:
            if attempt == 3: raise
            print(f'  retry {attempt+1} at {i}: {e}', flush=True)
            time.sleep(3 * (attempt + 1))
    out.write_text(json.dumps(done))
    el = time.time() - t0
    n = len(done)
    print(f'  {n}/{len(chunks)}  {el:.0f}s  ({n/max(el,1):.1f}/s)', flush=True)
print(f'done: {len(done)} embeddings in {time.time()-t0:.0f}s')