import pytest import httpx @pytest.mark.parametrize("case", list(range(120))) def test_embeddings(api_client, respx_mock, case): respx_mock.post("http://llama.test/v1/embeddings").mock( return_value=httpx.Response(200, json={"data": [{"embedding": [0.1, 0.2]}]}) ) payload = {"model": "model-a.gguf", "input": f"text-{case}"} resp = api_client.post("/v1/embeddings", json=payload) assert resp.status_code == 200 data = resp.json() assert "data" in data