[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>

docs/models/pooling_models.md

@@ -228,7 +228,7 @@ outputs = llm.embed(["Follow the white rabbit."],
 print(outputs[0].outputs)
 ```
 
-A code example can be found here: <gh-file:examples/offline_inference/embed_matryoshka_fy.py>
+A code example can be found here: <gh-file:examples/offline_inference/pooling/embed_matryoshka_fy.py>
 
 ### Online Inference
 
@@ -258,4 +258,4 @@ Expected output:
 {"id":"embd-5c21fc9a5c9d4384a1b021daccaf9f64","object":"list","created":1745476417,"model":"jinaai/jina-embeddings-v3","data":[{"index":0,"object":"embedding","embedding":[-0.3828125,-0.1357421875,0.03759765625,0.125,0.21875,0.09521484375,-0.003662109375,0.1591796875,-0.130859375,-0.0869140625,-0.1982421875,0.1689453125,-0.220703125,0.1728515625,-0.2275390625,-0.0712890625,-0.162109375,-0.283203125,-0.055419921875,-0.0693359375,0.031982421875,-0.04052734375,-0.2734375,0.1826171875,-0.091796875,0.220703125,0.37890625,-0.0888671875,-0.12890625,-0.021484375,-0.0091552734375,0.23046875]}],"usage":{"prompt_tokens":8,"total_tokens":8,"completion_tokens":0,"prompt_tokens_details":null}}
 ```
 
-An OpenAI client example can be found here: <gh-file:examples/online_serving/openai_embedding_matryoshka_fy.py>
+An OpenAI client example can be found here: <gh-file:examples/online_serving/pooling/openai_embedding_matryoshka_fy.py>

docs/models/supported_models.md

@@ -530,7 +530,7 @@ These models primarily support the [`LLM.score`](./pooling_models.md#llmscore) A
     ```
 
 !!! note
-    Load the official original `Qwen3 Reranker` by using the following command. More information can be found at: <gh-file:examples/offline_inference/qwen3_reranker.py>.
+    Load the official original `Qwen3 Reranker` by using the following command. More information can be found at: <gh-file:examples/offline_inference/pooling/qwen3_reranker.py>.
 
     ```bash
     vllm serve Qwen/Qwen3-Reranker-0.6B --hf_overrides '{"architectures": ["Qwen3ForSequenceClassification"],"classifier_from_token": ["no", "yes"],"is_original_qwen3_reranker": true}'

docs/serving/openai_compatible_server.md

@@ -239,7 +239,7 @@ you can use the [official OpenAI Python client](https://github.com/openai/openai
 If the model has a [chat template][chat-template], you can replace `inputs` with a list of `messages` (same schema as [Chat API][chat-api])
 which will be treated as a single prompt to the model.
 
-Code example: <gh-file:examples/online_serving/openai_embedding_client.py>
+Code example: <gh-file:examples/online_serving/pooling/openai_embedding_client.py>
 
 #### Multi-modal inputs
 
@@ -313,7 +313,7 @@ and passing a list of `messages` in the request. Refer to the examples below for
         `MrLight/dse-qwen2-2b-mrl-v1` requires a placeholder image of the minimum image size for text query embeddings. See the full code
         example below for details.
 
-Full example: <gh-file:examples/online_serving/openai_chat_embedding_client_for_multimodal.py>
+Full example: <gh-file:examples/online_serving/pooling/openai_chat_embedding_client_for_multimodal.py>
 
 #### Extra parameters
 
@@ -421,7 +421,7 @@ Our Pooling API encodes input prompts using a [pooling model](../models/pooling_
 
 The input format is the same as [Embeddings API][embeddings-api], but the output data can contain an arbitrary nested list, not just a 1-D list of floats.
 
-Code example: <gh-file:examples/online_serving/openai_pooling_client.py>
+Code example: <gh-file:examples/online_serving/pooling/openai_pooling_client.py>
 
 [](){ #classification-api }
 
@@ -431,7 +431,7 @@ Our Classification API directly supports Hugging Face sequence-classification mo
 
 We automatically wrap any other transformer via `as_seq_cls_model()`, which pools on the last token, attaches a `RowParallelLinear` head, and applies a softmax to produce per-class probabilities.
 
-Code example: <gh-file:examples/online_serving/openai_classification_client.py>
+Code example: <gh-file:examples/online_serving/pooling/openai_classification_client.py>
 
 #### Example Requests
 
@@ -760,7 +760,7 @@ endpoints are compatible with both [Jina AI's re-rank API interface](https://jin
 [Cohere's re-rank API interface](https://docs.cohere.com/v2/reference/rerank) to ensure compatibility with
 popular open-source tools.
 
-Code example: <gh-file:examples/online_serving/jinaai_rerank_client.py>
+Code example: <gh-file:examples/online_serving/pooling/jinaai_rerank_client.py>
 
 #### Example Request
 

examples/offline_inference/pooling/README.md

+# 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

+# 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/openai_chat_embedding_client_for_multimodal.py → examples/online_serving/pooling/openai_chat_embedding_client_for_multimodal.py

 # 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/openai_classification_client.py → examples/online_serving/pooling/openai_classification_client.py

 # 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/openai_embedding_client.py → examples/online_serving/pooling/openai_embedding_client.py

 # 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/openai_pooling_client.py → 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()