[Misc] Fix examples openai_pooling_client.py (#24853)

Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

examples/offline_inference/pooling/README.md

@@ -0,0 +1,33 @@
+# Pooling models
+
+## Convert llm model to seq cls
+
+```bash
+# for BAAI/bge-reranker-v2-gemma
+# Caution: "Yes" and "yes" are two different tokens
+python examples/offline_inference/pooling/convert_model_to_seq_cls.py --model_name BAAI/bge-reranker-v2-gemma --classifier_from_tokens '["Yes"]' --method no_post_processing --path ./bge-reranker-v2-gemma-seq-cls
+# for mxbai-rerank-v2
+python examples/offline_inference/pooling/convert_model_to_seq_cls.py --model_name mixedbread-ai/mxbai-rerank-base-v2 --classifier_from_tokens '["0", "1"]' --method from_2_way_softmax --path ./mxbai-rerank-base-v2-seq-cls
+# for Qwen3-Reranker
+python examples/offline_inference/pooling/convert_model_to_seq_cls.py --model_name Qwen/Qwen3-Reranker-0.6B --classifier_from_tokens '["no", "yes"]' --method from_2_way_softmax --path ./Qwen3-Reranker-0.6B-seq-cls
+```
+
+## Embed jina_embeddings_v3 usage
+
+Only text matching task is supported for now. See <gh-pr:16120>
+
+```bash
+python examples/offline_inference/pooling/embed_jina_embeddings_v3.py
+```
+
+## Embed matryoshka dimensions usage
+
+```bash
+python examples/offline_inference/pooling/embed_matryoshka_fy.py
+```
+
+## Qwen3 reranker usage
+
+```bash
+python qwen3_reranker.py
+```

examples/online_serving/openai_embedding_long_text/service.sh

@@ -120,7 +120,7 @@ echo "   - API Key: $API_KEY"
 echo "   - Native Pooling: $POOLING_TYPE | Cross-chunk: MEAN"
 echo ""
 echo "🧪 Test the server with:"
-echo "   python examples/online_serving/openai_embedding_long_text_client.py"
+echo "   python examples/online_serving/openai_embedding_long_text/client.py"
 echo ""
 echo "📚 Enhanced features enabled:"
 echo "   ✅ Intelligent native pooling type detection"

examples/online_serving/pooling/README.md

@@ -0,0 +1,43 @@
+# Pooling models
+
+## Cohere rerank usage
+
+```bash
+python examples/online_serving/pooling/cohere_rerank_client.py
+```
+
+## Jinaai rerank usage
+
+```bash
+python examples/online_serving/pooling/jinaai_rerank_client.py
+```
+
+## Openai chat embedding for multimodal usage
+
+```bash
+python examples/online_serving/pooling/openai_chat_embedding_client_for_multimodal.py
+```
+
+## Openai classification usage
+
+```bash
+python examples/online_serving/pooling/openai_classification_client.py
+```
+
+## Openai embedding usage
+
+```bash
+python examples/online_serving/pooling/openai_embedding_client.py
+```
+
+## Openai embedding matryoshka dimensions usage
+
+```bash
+python examples/online_serving/pooling/openai_embedding_matryoshka_fy.py
+```
+
+## Openai pooling usage
+
+```bash
+python examples/online_serving/pooling/openai_pooling_client.py
+```

examples/online_serving/pooling/openai_chat_embedding_client_for_multimodal.py

@@ -1,5 +1,11 @@
 # SPDX-License-Identifier: Apache-2.0
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+# ruff: noqa: E501
+"""Example Python client for multimodal embedding API using vLLM API server
+NOTE:
+    start a supported multimodal embeddings model server with `vllm serve`, e.g.
+    vllm serve TIGER-Lab/VLM2Vec-Full --runner pooling --trust_remote_code --max_model_len=1024
+"""
 
 import argparse
 import base64

examples/online_serving/pooling/openai_classification_client.py

@@ -1,5 +1,10 @@
 # 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

examples/online_serving/pooling/openai_embedding_client.py

@@ -1,5 +1,10 @@
 # SPDX-License-Identifier: Apache-2.0
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+"""Example Python client for embedding API using vLLM API server
+NOTE:
+    start a supported embeddings model server with `vllm serve`, e.g.
+    vllm serve intfloat/e5-small
+"""
 
 from openai import OpenAI
 

examples/online_serving/pooling/openai_pooling_client.py

@@ -4,7 +4,9 @@
 Example online usage of Pooling API.
 
 Run `vllm serve <model> --runner pooling`
-to start up the server in vLLM.
+to start up the server in vLLM. e.g.
+
+vllm serve internlm/internlm2-1_8b-reward --trust-remote-code
 """
 
 import argparse
@@ -23,7 +25,7 @@ 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="jason9693/Qwen2.5-1.5B-apeach")
+    parser.add_argument("--model", type=str, default="internlm/internlm2-1_8b-reward")
 
     return parser.parse_args()