[Frontend][1/n] Make pooling entrypoints request schema consensus | CompletionRequest (#32395)

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>

examples/pooling/classify/classification_online.py

@@ -0,0 +1,67 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+"""Example Python client for classification API using vLLM API server
+NOTE:
+    start a supported classification model server with `vllm serve`, e.g.
+    vllm serve jason9693/Qwen2.5-1.5B-apeach
+"""
+
+import argparse
+import pprint
+
+import requests
+
+headers = {"accept": "application/json", "Content-Type": "application/json"}
+
+
+def parse_args():
+    parse = argparse.ArgumentParser()
+    parse.add_argument("--host", type=str, default="localhost")
+    parse.add_argument("--port", type=int, default=8000)
+    return parse.parse_args()
+
+
+def main(args):
+    base_url = f"http://{args.host}:{args.port}"
+    models_url = base_url + "/v1/models"
+    classify_url = base_url + "/classify"
+    tokenize_url = base_url + "/tokenize"
+
+    response = requests.get(models_url, headers=headers)
+    model = response.json()["data"][0]["id"]
+
+    # /classify can accept str as input
+    prompts = [
+        "Hello, my name is",
+        "The president of the United States is",
+        "The capital of France is",
+        "The future of AI is",
+    ]
+
+    payload = {
+        "model": model,
+        "input": prompts,
+    }
+    response = requests.post(classify_url, headers=headers, json=payload)
+    pprint.pprint(response.json())
+
+    # /classify can accept token ids as input
+    token_ids = []
+    for prompt in prompts:
+        response = requests.post(
+            tokenize_url,
+            json={"model": model, "prompt": prompt},
+        )
+        token_ids.append(response.json()["tokens"])
+
+    payload = {
+        "model": model,
+        "input": token_ids,
+    }
+    response = requests.post(classify_url, headers=headers, json=payload)
+    pprint.pprint(response.json())
+
+
+if __name__ == "__main__":
+    args = parse_args()
+    main(args)

examples/pooling/classify/openai_classification_client.py

@@ -1,53 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
-"""Example Python client for classification API using vLLM API server
-NOTE:
-    start a supported classification model server with `vllm serve`, e.g.
-    vllm serve jason9693/Qwen2.5-1.5B-apeach
-"""
-
-import argparse
-import pprint
-
-import requests
-
-
-def post_http_request(payload: dict, api_url: str) -> requests.Response:
-    headers = {"User-Agent": "Test Client"}
-    response = requests.post(api_url, headers=headers, json=payload)
-    return response
-
-
-def parse_args():
-    parse = argparse.ArgumentParser()
-    parse.add_argument("--host", type=str, default="localhost")
-    parse.add_argument("--port", type=int, default=8000)
-    parse.add_argument("--model", type=str, default="jason9693/Qwen2.5-1.5B-apeach")
-    return parse.parse_args()
-
-
-def main(args):
-    host = args.host
-    port = args.port
-    model_name = args.model
-
-    api_url = f"http://{host}:{port}/classify"
-    prompts = [
-        "Hello, my name is",
-        "The president of the United States is",
-        "The capital of France is",
-        "The future of AI is",
-    ]
-
-    payload = {
-        "model": model_name,
-        "input": prompts,
-    }
-
-    classify_response = post_http_request(payload=payload, api_url=api_url)
-    pprint.pprint(classify_response.json())
-
-
-if __name__ == "__main__":
-    args = parse_args()
-    main(args)

examples/pooling/pooling/vision_language_pooling.py

@@ -16,7 +16,7 @@ from typing import Literal, NamedTuple, TypeAlias, TypedDict, get_args
 from PIL.Image import Image
 
 from vllm import LLM, EngineArgs
-from vllm.entrypoints.score_utils import ScoreMultiModalParam
+from vllm.entrypoints.pooling.score.utils import ScoreMultiModalParam
 from vllm.multimodal.utils import fetch_image
 from vllm.utils.argparse_utils import FlexibleArgumentParser
 

examples/pooling/score/vision_reranker_offline.py

@@ -15,7 +15,7 @@ from pathlib import Path
 from typing import NamedTuple
 
 from vllm import LLM, EngineArgs
-from vllm.entrypoints.score_utils import ScoreMultiModalParam
+from vllm.entrypoints.pooling.score.utils import ScoreMultiModalParam
 from vllm.utils.argparse_utils import FlexibleArgumentParser
 
 TEMPLATE_HOME = Path(__file__).parent / "template"