48854aef5c
### What this PR does / why we need it?
This PR adds the method for sending chat and non-chat request, we need
it to test much folloing cases.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
by running the test
- vLLM version: release/v0.13.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: jiangyunfan1 <jiangyunfan1@h-partners.com>
38 lines
1.2 KiB
Python
38 lines
1.2 KiB
Python
from typing import Any
|
|
|
|
import requests
|
|
|
|
|
|
def send_v1_completions(prompt, model, server, request_args=None):
|
|
data: dict[str, Any] = {"model": model, "prompt": prompt}
|
|
if request_args:
|
|
data.update(request_args)
|
|
url = server.url_for("v1", "completions")
|
|
response = requests.post(url, json=data)
|
|
print(f"Status Code: {response.status_code}")
|
|
response_json = response.json()
|
|
print(f"Response json: {response_json}")
|
|
response_text = response_json["choices"][0]["text"]
|
|
print(f"Response: {response_text}")
|
|
assert response_text, "empty response"
|
|
|
|
|
|
def send_v1_chat_completions(prompt, model, server, request_args=None):
|
|
data: dict[str, Any] = {
|
|
"model": model,
|
|
"messages": [{
|
|
"role": "user",
|
|
"content": prompt,
|
|
}],
|
|
}
|
|
if request_args:
|
|
data.update(request_args)
|
|
url = server.url_for("v1", "chat", "completions")
|
|
response = requests.post(url, json=data)
|
|
print(f"Status Code: {response.status_code}")
|
|
response_json = response.json()
|
|
print(f"Response json: {response_json}")
|
|
response_text = response_json["choices"][0]["message"]["content"]
|
|
print(f"Response: {response_text}")
|
|
assert response_text, "empty response"
|