[examples] Resettle pooling examples. (#29365)

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

examples/pooling/token_embed/multi_vector_retrieval.py

@@ -0,0 +1,56 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
+from argparse import Namespace
+
+from vllm import LLM, EngineArgs
+from vllm.utils.argparse_utils import FlexibleArgumentParser
+
+
+def parse_args():
+    parser = FlexibleArgumentParser()
+    parser = EngineArgs.add_cli_args(parser)
+    # Set example specific arguments
+    parser.set_defaults(
+        model="BAAI/bge-m3",
+        runner="pooling",
+        enforce_eager=True,
+    )
+    return parser.parse_args()
+
+
+def main(args: Namespace):
+    # Sample prompts.
+    prompts = [
+        "Hello, my name is",
+        "The president of the United States is",
+        "The capital of France is",
+        "The future of AI is",
+    ]
+
+    # Create an LLM.
+    # You should pass runner="pooling" for embedding models
+    llm = LLM(**vars(args))
+
+    # Generate embedding. The output is a list of EmbeddingRequestOutputs.
+    outputs = llm.embed(prompts)
+
+    # Print the outputs.
+    print("\nGenerated Outputs:\n" + "-" * 60)
+    for prompt, output in zip(prompts, outputs):
+        embeds = output.outputs.embedding
+        print(len(embeds))
+
+    # Generate embedding for each token. The output is a list of PoolingRequestOutput.
+    outputs = llm.encode(prompts, pooling_task="token_embed")
+
+    # Print the outputs.
+    print("\nGenerated Outputs:\n" + "-" * 60)
+    for prompt, output in zip(prompts, outputs):
+        multi_vector = output.outputs.data
+        print(multi_vector.shape)
+
+
+if __name__ == "__main__":
+    args = parse_args()
+    main(args)

examples/pooling/token_embed/multi_vector_retrieval_client.py

@@ -0,0 +1,54 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
+"""
+Example online usage of Pooling API for multi vector retrieval.
+
+Run `vllm serve <model> --runner pooling`
+to start up the server in vLLM. e.g.
+
+vllm serve BAAI/bge-m3
+"""
+
+import argparse
+
+import requests
+import torch
+
+
+def post_http_request(prompt: dict, api_url: str) -> requests.Response:
+    headers = {"User-Agent": "Test Client"}
+    response = requests.post(api_url, headers=headers, json=prompt)
+    return response
+
+
+def parse_args():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--host", type=str, default="localhost")
+    parser.add_argument("--port", type=int, default=8000)
+    parser.add_argument("--model", type=str, default="BAAI/bge-m3")
+
+    return parser.parse_args()
+
+
+def main(args):
+    api_url = f"http://{args.host}:{args.port}/pooling"
+    model_name = args.model
+
+    prompts = [
+        "Hello, my name is",
+        "The president of the United States is",
+        "The capital of France is",
+        "The future of AI is",
+    ]
+    prompt = {"model": model_name, "input": prompts}
+
+    pooling_response = post_http_request(prompt=prompt, api_url=api_url)
+    for output in pooling_response.json()["data"]:
+        multi_vector = torch.tensor(output["data"])
+        print(multi_vector.shape)
+
+
+if __name__ == "__main__":
+    args = parse_args()
+    main(args)