collection.upsert([
    {
        "id": "doc_001",
        "values": [0.1, 0.2, ...],
        "metadata": {"text": "Hello world"}
    }
])

embeddings = batch_embed([d["text"] for d in documents])

collection.upsert([
    {
        "id": doc["id"],
        "values": embeddings[i],
        "metadata": {"text": doc["text"]}
    }
    for i, doc in enumerate(documents)
])

BATCH_SIZE = 200
for i in range(0, len(items), BATCH_SIZE):
    batch = items[i:i + BATCH_SIZE]
    embeddings = batch_embed([item["text"] for item in batch])
    collection.upsert([
        {"id": item["id"], "values": embeddings[j], "metadata": {"text": item["text"]}}
        for j, item in enumerate(batch)
    ])
    print(f"Indexed {min(i + BATCH_SIZE, len(items))} / {len(items)}")