[Frontend][Doc][5/N] Improve all pooling task | Polish encode (pooling) api & Document. (#25524)

Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
This commit is contained in:
wang.yuqi
2025-10-30 12:13:05 +00:00
committed by GitHub
co-authored by gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> Cyrus Leung
parent 74374386e2
commit 4464723f22
27 changed files with 499 additions and 131 deletions
+35 -5
View File
@@ -3,65 +3,95 @@
## Cohere rerank usage
```bash
# vllm serve BAAI/bge-reranker-base
python examples/online_serving/pooling/cohere_rerank_client.py
```
## Embedding requests base64 encoding_format usage
```bash
# vllm serve intfloat/e5-small
python examples/online_serving/pooling/embedding_requests_base64_client.py
```
## Embedding requests bytes encoding_format usage
```bash
# vllm serve intfloat/e5-small
python examples/online_serving/pooling/embedding_requests_bytes_client.py
```
## Jinaai rerank usage
```bash
# vllm serve BAAI/bge-reranker-base
python examples/online_serving/pooling/jinaai_rerank_client.py
```
## Multi vector retrieval usage
```bash
# vllm serve BAAI/bge-m3
python examples/online_serving/pooling/multi_vector_retrieval_client.py
```
## Named Entity Recognition (NER) usage
```bash
# vllm serve boltuix/NeuroBERT-NER
python examples/online_serving/pooling/ner_client.py
```
## Openai chat embedding for multimodal usage
## OpenAI chat embedding for multimodal usage
```bash
python examples/online_serving/pooling/openai_chat_embedding_client_for_multimodal.py
```
## Openai classification usage
## OpenAI classification usage
```bash
# vllm serve jason9693/Qwen2.5-1.5B-apeach
python examples/online_serving/pooling/openai_classification_client.py
```
## Openai embedding usage
## OpenAI cross_encoder score usage
```bash
# vllm serve BAAI/bge-reranker-v2-m3
python examples/online_serving/pooling/openai_cross_encoder_score.py
```
## OpenAI cross_encoder score for multimodal usage
```bash
# vllm serve jinaai/jina-reranker-m0
python examples/online_serving/pooling/openai_cross_encoder_score_for_multimodal.py
```
## OpenAI embedding usage
```bash
# vllm serve intfloat/e5-small
python examples/online_serving/pooling/openai_embedding_client.py
```
## Openai embedding matryoshka dimensions usage
## OpenAI embedding matryoshka dimensions usage
```bash
# vllm serve jinaai/jina-embeddings-v3 --trust-remote-code
python examples/online_serving/pooling/openai_embedding_matryoshka_fy.py
```
## Openai pooling usage
## OpenAI pooling usage
```bash
# vllm serve internlm/internlm2-1_8b-reward --trust-remote-code
python examples/online_serving/pooling/openai_pooling_client.py
```
## Online Prithvi Geospatial MAE usage
```bash
python examples/online_serving/pooling/prithvi_geospatial_mae.py
```
@@ -0,0 +1,63 @@
# 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="BAAI/bge-reranker-v2-m3")
return parser.parse_args()
def main(args):
api_url = f"http://{args.host}:{args.port}/score"
model_name = args.model
text_1 = "What is the capital of Brazil?"
text_2 = "The capital of Brazil is Brasilia."
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 and text_2 are both strings:")
pprint.pprint(prompt)
print("\nScore Response:")
pprint.pprint(score_response.json())
text_1 = "What is the capital of France?"
text_2 = ["The capital of Brazil is Brasilia.", "The capital of France is Paris."]
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 list:")
pprint.pprint(prompt)
print("\nScore Response:")
pprint.pprint(score_response.json())
text_1 = ["What is the capital of Brazil?", "What is the capital of France?"]
text_2 = ["The capital of Brazil is Brasilia.", "The capital of France is Paris."]
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 and text_2 are both lists:")
pprint.pprint(prompt)
print("\nScore Response:")
pprint.pprint(score_response.json())
if __name__ == "__main__":
args = parse_args()
main(args)
@@ -0,0 +1,60 @@
# 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 +1,56 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
import base64
import os
import requests
# This example shows how to perform an online inference that generates
# multimodal data. In this specific case this example will take a geotiff
# image as input, process it using the multimodal data processor, and
# perform inference.
# Requirements :
# - install TerraTorch v1.1 (or later):
# pip install terratorch>=v1.1
# - start vllm in serving mode with the below args
# --model='christian-pinto/Prithvi-EO-2.0-300M-TL-VLLM'
# --model-impl terratorch
# --task embed --trust-remote-code
# --skip-tokenizer-init --enforce-eager
# --io-processor-plugin terratorch_segmentation
# --enable-mm-embeds
def main():
image_url = "https://huggingface.co/christian-pinto/Prithvi-EO-2.0-300M-TL-VLLM/resolve/main/valencia_example_2024-10-26.tiff" # noqa: E501
server_endpoint = "http://localhost:8000/pooling"
request_payload_url = {
"data": {
"data": image_url,
"data_format": "url",
"image_format": "tiff",
"out_data_format": "b64_json",
},
"priority": 0,
"model": "christian-pinto/Prithvi-EO-2.0-300M-TL-VLLM",
}
ret = requests.post(server_endpoint, json=request_payload_url)
print(f"response.status_code: {ret.status_code}")
print(f"response.reason:{ret.reason}")
response = ret.json()
decoded_image = base64.b64decode(response["data"]["data"])
out_path = os.path.join(os.getcwd(), "online_prediction.tiff")
with open(out_path, "wb") as f:
f.write(decoded_image)
if __name__ == "__main__":
main()