[Frontend][3/n] Make pooling entrypoints request schema consensus | EmbedRequest & ClassifyRequest (#32905)

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

tests/entrypoints/pooling/classify/test_online_vision.py

@@ -1,27 +1,30 @@
 # SPDX-License-Identifier: Apache-2.0
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
-
 import json
 
 import pytest
 import requests
 
+from tests.entrypoints.test_utils import encode_base64_content_from_url
 from tests.utils import RemoteOpenAIServer
 from vllm.entrypoints.pooling.classify.protocol import ClassificationResponse
 
-VLM_MODEL_NAME = "muziyongshixin/Qwen2.5-VL-7B-for-VideoCls"
+MODEL_NAME = "muziyongshixin/Qwen2.5-VL-7B-for-VideoCls"
 MAXIMUM_VIDEOS = 1
-TEST_VIDEO_URL = "https://www.bogotobogo.com/python/OpenCV_Python/images/mean_shift_tracking/slow_traffic_small.mp4"
 
 HF_OVERRIDES = {
     "text_config": {
         "architectures": ["Qwen2_5_VLForSequenceClassification"],
     },
 }
+input_text = "This product was excellent and exceeded my expectations"
+image_url = "https://vllm-public-assets.s3.us-west-2.amazonaws.com/multimodal_asset/cat_snow.jpg"
+image_base64 = encode_base64_content_from_url(image_url)
+video_url = "https://www.bogotobogo.com/python/OpenCV_Python/images/mean_shift_tracking/slow_traffic_small.mp4"
 
 
 @pytest.fixture(scope="module")
-def server_vlm_classify():
+def server():
     args = [
         "--runner",
         "pooling",
@@ -33,26 +36,26 @@ def server_vlm_classify():
     ]
 
     with RemoteOpenAIServer(
-        VLM_MODEL_NAME, args, override_hf_configs=HF_OVERRIDES
+        MODEL_NAME, args, override_hf_configs=HF_OVERRIDES
     ) as remote_server:
         yield remote_server
 
 
-@pytest.mark.parametrize("model_name", [VLM_MODEL_NAME])
-def test_classify_accepts_chat_text_only(
-    server_vlm_classify: RemoteOpenAIServer, model_name: str
-) -> None:
+@pytest.mark.parametrize("model_name", [MODEL_NAME])
+def test_chat_text_request(server: RemoteOpenAIServer, model_name: str):
     messages = [
+        {
+            "role": "assistant",
+            "content": "Please classify this text request.",
+        },
         {
             "role": "user",
-            "content": [
-                {"type": "text", "text": "Please classify this text request."},
-            ],
-        }
+            "content": input_text,
+        },
     ]
 
     response = requests.post(
-        server_vlm_classify.url_for("classify"),
+        server.url_for("classify"),
         json={"model": model_name, "messages": messages},
     )
     response.raise_for_status()
@@ -63,25 +66,77 @@ def test_classify_accepts_chat_text_only(
     assert output.model == model_name
     assert len(output.data) == 1
     assert len(output.data[0].probs) == 2
-    assert output.usage.prompt_tokens == 22
+    assert output.usage.prompt_tokens == 35
 
 
-@pytest.mark.parametrize("model_name", [VLM_MODEL_NAME])
-def test_classify_accepts_chat_video_url(
-    server_vlm_classify: RemoteOpenAIServer, model_name: str
-) -> None:
+@pytest.mark.parametrize("model_name", [MODEL_NAME])
+def test_chat_image_url_request(server: RemoteOpenAIServer, model_name: str):
     messages = [
         {
             "role": "user",
             "content": [
-                {"type": "text", "text": "Please classify this video."},
-                {"type": "video_url", "video_url": {"url": TEST_VIDEO_URL}},
+                {"type": "text", "text": "Please classify this image."},
+                {"type": "image_url", "image_url": {"url": image_url}},
             ],
         }
     ]
 
     response = requests.post(
-        server_vlm_classify.url_for("classify"),
+        server.url_for("classify"),
+        json={"model": model_name, "messages": messages},
+    )
+    response.raise_for_status()
+
+    output = ClassificationResponse.model_validate(response.json())
+
+    assert output.object == "list"
+    assert output.model == model_name
+    assert len(output.data) == 1
+    assert len(output.data[0].probs) == 2
+    assert output.usage.prompt_tokens == 47
+
+
+@pytest.mark.parametrize("model_name", [MODEL_NAME])
+def test_chat_image_base64_request(server: RemoteOpenAIServer, model_name: str):
+    messages = [
+        {
+            "role": "user",
+            "content": [
+                {"type": "text", "text": "Please classify this image."},
+                {"type": "image_url", "image_url": image_base64},
+            ],
+        }
+    ]
+
+    response = requests.post(
+        server.url_for("classify"),
+        json={"model": model_name, "messages": messages},
+    )
+    response.raise_for_status()
+
+    output = ClassificationResponse.model_validate(response.json())
+
+    assert output.object == "list"
+    assert output.model == model_name
+    assert len(output.data) == 1
+    assert len(output.data[0].probs) == 2
+    assert output.usage.prompt_tokens == 47
+
+
+@pytest.mark.parametrize("model_name", [MODEL_NAME])
+def test_chat_video_url_request(server: RemoteOpenAIServer, model_name: str):
+    messages = [
+        {
+            "role": "user",
+            "content": [
+                {"type": "text", "text": "Please classify this video."},
+                {"type": "video_url", "video_url": {"url": video_url}},
+            ],
+        }
+    ]
+
+    response = requests.post(
+        server.url_for("classify"),
         json={"model": model_name, "messages": messages},
     )
     response.raise_for_status()