[Model] Improve multimodal pooling examples (#32085)

Signed-off-by: wang.yuqi <noooop@126.com>
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
This commit is contained in:
wang.yuqi
2026-01-12 07:54:09 +00:00
committed by GitHub
parent 9101dc756c
commit 60446cd684
10 changed files with 381 additions and 69 deletions
@@ -1,60 +0,0 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
"""
Example online usage of Score API.
Run `vllm serve <model> --runner pooling` to start up the server in vLLM.
"""
import argparse
import pprint
import requests
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="jinaai/jina-reranker-m0")
return parser.parse_args()
def main(args):
api_url = f"http://{args.host}:{args.port}/score"
model_name = args.model
text_1 = "slm markdown"
text_2 = {
"content": [
{
"type": "image_url",
"image_url": {
"url": "https://raw.githubusercontent.com/jina-ai/multimodal-reranker-test/main/handelsblatt-preview.png"
},
},
{
"type": "image_url",
"image_url": {
"url": "https://raw.githubusercontent.com/jina-ai/multimodal-reranker-test/main/paper-11.png"
},
},
]
}
prompt = {"model": model_name, "text_1": text_1, "text_2": text_2}
score_response = post_http_request(prompt=prompt, api_url=api_url)
print("\nPrompt when text_1 is string and text_2 is a image list:")
pprint.pprint(prompt)
print("\nScore Response:")
pprint.pprint(score_response.json())
if __name__ == "__main__":
args = parse_args()
main(args)
@@ -0,0 +1,80 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
# ruff: noqa: E501
"""
Example Python client for multimodal rerank API which is compatible with
Jina and Cohere https://jina.ai/reranker
Run `vllm serve <model> --runner pooling` to start up the server in vLLM.
e.g.
vllm serve jinaai/jina-reranker-m0 --runner pooling
vllm serve Qwen/Qwen3-VL-Reranker-2B \
--runner pooling \
--max-model-len 4096 \
--hf_overrides '{"architectures": ["Qwen3VLForSequenceClassification"],"classifier_from_token": ["no", "yes"],"is_original_qwen3_reranker": true}' \
--chat-template examples/pooling/score/template/qwen3_vl_reranker.jinja
"""
import argparse
import json
import requests
headers = {"accept": "application/json", "Content-Type": "application/json"}
query = "A woman playing with her dog on a beach at sunset."
documents = {
"content": [
{
"type": "text",
"text": (
"A woman shares a joyful moment with her golden retriever on a sun-drenched beach at sunset, " # noqa: E501
"as the dog offers its paw in a heartwarming display of companionship and trust." # noqa: E501
),
},
{
"type": "image_url",
"image_url": {
"url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"
},
},
]
}
def parse_args():
parser = argparse.ArgumentParser()
parser.add_argument("--host", type=str, default="localhost")
parser.add_argument("--port", type=int, default=8000)
return parser.parse_args()
def main(args):
base_url = f"http://{args.host}:{args.port}"
models_url = base_url + "/v1/models"
rerank_url = base_url + "/rerank"
response = requests.get(models_url, headers=headers)
model = response.json()["data"][0]["id"]
data = {
"model": model,
"query": query,
"documents": documents,
}
response = requests.post(rerank_url, headers=headers, json=data)
# Check the response
if response.status_code == 200:
print("Request successful!")
print(json.dumps(response.json(), indent=2))
else:
print(f"Request failed with status code: {response.status_code}")
print(response.text)
if __name__ == "__main__":
args = parse_args()
main(args)
@@ -0,0 +1,71 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
# ruff: noqa: E501
"""
Example online usage of Score API.
Run `vllm serve <model> --runner pooling` to start up the server in vLLM.
e.g.
vllm serve jinaai/jina-reranker-m0 --runner pooling
vllm serve Qwen/Qwen3-VL-Reranker-2B \
--runner pooling \
--max-model-len 4096 \
--hf_overrides '{"architectures": ["Qwen3VLForSequenceClassification"],"classifier_from_token": ["no", "yes"],"is_original_qwen3_reranker": true}' \
--chat-template examples/pooling/score/template/qwen3_vl_reranker.jinja
"""
import argparse
import json
import pprint
import requests
headers = {"accept": "application/json", "Content-Type": "application/json"}
text_1 = "slm markdown"
text_2 = {
"content": [
{
"type": "image_url",
"image_url": {
"url": "https://raw.githubusercontent.com/jina-ai/multimodal-reranker-test/main/handelsblatt-preview.png"
},
},
{
"type": "image_url",
"image_url": {
"url": "https://raw.githubusercontent.com/jina-ai/multimodal-reranker-test/main/paper-11.png"
},
},
]
}
def parse_args():
parser = argparse.ArgumentParser()
parser.add_argument("--host", type=str, default="localhost")
parser.add_argument("--port", type=int, default=8000)
return parser.parse_args()
def main(args):
base_url = f"http://{args.host}:{args.port}"
models_url = base_url + "/v1/models"
score_url = base_url + "/score"
response = requests.get(models_url, headers=headers)
model = response.json()["data"][0]["id"]
prompt = {"model": model, "text_1": text_1, "text_2": text_2}
response = requests.post(score_url, headers=headers, json=prompt)
print("\nPrompt when text_1 is string and text_2 is a image list:")
pprint.pprint(prompt)
print("\nScore Response:")
print(json.dumps(response.json(), indent=2))
if __name__ == "__main__":
args = parse_args()
main(args)