[Frontend] Score entrypoint support data_1 & data_2 and queries & documents as inputs (#32577)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
This commit is contained in:
@@ -21,8 +21,8 @@ def parse_args():
|
||||
|
||||
def main(args: Namespace):
|
||||
# Sample prompts.
|
||||
text_1 = "What is the capital of France?"
|
||||
texts_2 = [
|
||||
query = "What is the capital of France?"
|
||||
documents = [
|
||||
"The capital of Brazil is Brasilia.",
|
||||
"The capital of France is Paris.",
|
||||
]
|
||||
@@ -32,13 +32,13 @@ def main(args: Namespace):
|
||||
llm = LLM(**vars(args))
|
||||
|
||||
# Generate scores. The output is a list of ScoringRequestOutputs.
|
||||
outputs = llm.score(text_1, texts_2)
|
||||
outputs = llm.score(query, documents)
|
||||
|
||||
# Print the outputs.
|
||||
print("\nGenerated Outputs:\n" + "-" * 60)
|
||||
for text_2, output in zip(texts_2, outputs):
|
||||
for document, output in zip(documents, outputs):
|
||||
score = output.outputs.score
|
||||
print(f"Pair: {[text_1, text_2]!r} \nScore: {score}")
|
||||
print(f"Pair: {[query, document]!r} \nScore: {score}")
|
||||
print("-" * 60)
|
||||
|
||||
|
||||
|
||||
@@ -255,8 +255,8 @@ cat results.jsonl
|
||||
Add score requests to your batch file. The following is an example:
|
||||
|
||||
```text
|
||||
{"custom_id": "request-1", "method": "POST", "url": "/v1/score", "body": {"model": "BAAI/bge-reranker-v2-m3", "text_1": "What is the capital of France?", "text_2": ["The capital of Brazil is Brasilia.", "The capital of France is Paris."]}}
|
||||
{"custom_id": "request-2", "method": "POST", "url": "/v1/score", "body": {"model": "BAAI/bge-reranker-v2-m3", "text_1": "What is the capital of France?", "text_2": ["The capital of Brazil is Brasilia.", "The capital of France is Paris."]}}
|
||||
{"custom_id": "request-1", "method": "POST", "url": "/v1/score", "body": {"model": "BAAI/bge-reranker-v2-m3", "queries": "What is the capital of France?", "documents": ["The capital of Brazil is Brasilia.", "The capital of France is Paris."]}}
|
||||
{"custom_id": "request-2", "method": "POST", "url": "/v1/score", "body": {"model": "BAAI/bge-reranker-v2-m3", "queries": "What is the capital of France?", "documents": ["The capital of Brazil is Brasilia.", "The capital of France is Paris."]}}
|
||||
```
|
||||
|
||||
You can mix chat completion, embedding, and score requests in the batch file, as long as the model you are using supports them all (note that all requests must use the same model).
|
||||
|
||||
@@ -50,8 +50,8 @@ documents = [
|
||||
# Request payload for the score API
|
||||
data = {
|
||||
"model": "Qwen/Qwen3-Reranker-0.6B",
|
||||
"text_1": queries,
|
||||
"text_2": documents,
|
||||
"queries": queries,
|
||||
"documents": documents,
|
||||
}
|
||||
|
||||
|
||||
|
||||
@@ -30,29 +30,35 @@ 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}
|
||||
queries = "What is the capital of Brazil?"
|
||||
documents = "The capital of Brazil is Brasilia."
|
||||
prompt = {"model": model_name, "queries": queries, "documents": documents}
|
||||
score_response = post_http_request(prompt=prompt, api_url=api_url)
|
||||
print("\nPrompt when text_1 and text_2 are both strings:")
|
||||
print("\nPrompt when queries and documents 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}
|
||||
queries = "What is the capital of France?"
|
||||
documents = [
|
||||
"The capital of Brazil is Brasilia.",
|
||||
"The capital of France is Paris.",
|
||||
]
|
||||
prompt = {"model": model_name, "queries": queries, "documents": documents}
|
||||
score_response = post_http_request(prompt=prompt, api_url=api_url)
|
||||
print("\nPrompt when text_1 is string and text_2 is a list:")
|
||||
print("\nPrompt when queries is string and documents 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}
|
||||
queries = ["What is the capital of Brazil?", "What is the capital of France?"]
|
||||
documents = [
|
||||
"The capital of Brazil is Brasilia.",
|
||||
"The capital of France is Paris.",
|
||||
]
|
||||
prompt = {"model": model_name, "queries": queries, "documents": documents}
|
||||
score_response = post_http_request(prompt=prompt, api_url=api_url)
|
||||
print("\nPrompt when text_1 and text_2 are both lists:")
|
||||
print("\nPrompt when queries and documents are both lists:")
|
||||
pprint.pprint(prompt)
|
||||
print("\nScore Response:")
|
||||
pprint.pprint(score_response.json())
|
||||
|
||||
@@ -18,10 +18,22 @@ e.g.
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import base64
|
||||
import json
|
||||
|
||||
import requests
|
||||
|
||||
|
||||
def encode_base64_content_from_url(content_url: str) -> dict[str, str]:
|
||||
"""Encode a content retrieved from a remote url to base64 format."""
|
||||
|
||||
with requests.get(content_url, headers=headers) as response:
|
||||
response.raise_for_status()
|
||||
result = base64.b64encode(response.content).decode("utf-8")
|
||||
|
||||
return {"url": f"data:image/jpeg;base64,{result}"}
|
||||
|
||||
|
||||
headers = {"accept": "application/json", "Content-Type": "application/json"}
|
||||
|
||||
query = "A woman playing with her dog on a beach at sunset."
|
||||
@@ -30,8 +42,8 @@ documents = {
|
||||
{
|
||||
"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
|
||||
"A woman shares a joyful moment with her golden retriever on a sun-drenched beach at sunset, "
|
||||
"as the dog offers its paw in a heartwarming display of companionship and trust."
|
||||
),
|
||||
},
|
||||
{
|
||||
@@ -40,6 +52,12 @@ documents = {
|
||||
"url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"
|
||||
},
|
||||
},
|
||||
{
|
||||
"type": "image_url",
|
||||
"image_url": encode_base64_content_from_url(
|
||||
"https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"
|
||||
),
|
||||
},
|
||||
]
|
||||
}
|
||||
|
||||
|
||||
@@ -17,15 +17,27 @@ e.g.
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import base64
|
||||
import json
|
||||
import pprint
|
||||
|
||||
import requests
|
||||
|
||||
|
||||
def encode_base64_content_from_url(content_url: str) -> dict[str, str]:
|
||||
"""Encode a content retrieved from a remote url to base64 format."""
|
||||
|
||||
with requests.get(content_url, headers=headers) as response:
|
||||
response.raise_for_status()
|
||||
result = base64.b64encode(response.content).decode("utf-8")
|
||||
|
||||
return {"url": f"data:image/jpeg;base64,{result}"}
|
||||
|
||||
|
||||
headers = {"accept": "application/json", "Content-Type": "application/json"}
|
||||
|
||||
text_1 = "slm markdown"
|
||||
text_2 = {
|
||||
queries = "slm markdown"
|
||||
documents = {
|
||||
"content": [
|
||||
{
|
||||
"type": "image_url",
|
||||
@@ -39,6 +51,12 @@ text_2 = {
|
||||
"url": "https://raw.githubusercontent.com/jina-ai/multimodal-reranker-test/main/paper-11.png"
|
||||
},
|
||||
},
|
||||
{
|
||||
"type": "image_url",
|
||||
"image_url": encode_base64_content_from_url(
|
||||
"https://raw.githubusercontent.com/jina-ai/multimodal-reranker-test/main/paper-11.png"
|
||||
),
|
||||
},
|
||||
]
|
||||
}
|
||||
|
||||
@@ -58,9 +76,9 @@ def main(args):
|
||||
response = requests.get(models_url, headers=headers)
|
||||
model = response.json()["data"][0]["id"]
|
||||
|
||||
prompt = {"model": model, "text_1": text_1, "text_2": text_2}
|
||||
prompt = {"model": model, "queries": queries, "documents": documents}
|
||||
response = requests.post(score_url, headers=headers, json=prompt)
|
||||
print("\nPrompt when text_1 is string and text_2 is a image list:")
|
||||
print("\nPrompt when queries is string and documents is a image list:")
|
||||
pprint.pprint(prompt)
|
||||
print("\nScore Response:")
|
||||
print(json.dumps(response.json(), indent=2))
|
||||
|
||||
Reference in New Issue
Block a user