mirror of
https://git.datalinker.icu/vllm-project/vllm.git
synced 2025-12-10 18:54:57 +08:00
e489ad7a21
- **Add SPDX license headers to python source files**
- **Check for SPDX headers using pre-commit**
commit 9d7ef44c3cfb72ca4c32e1c677d99259d10d4745
Author: Russell Bryant <rbryant@redhat.com>
Date: Fri Jan 31 14:18:24 2025 -0500
Add SPDX license headers to python source files
This commit adds SPDX license headers to python source files as
recommended to
the project by the Linux Foundation. These headers provide a concise way
that is
both human and machine readable for communicating license information
for each
source file. It helps avoid any ambiguity about the license of the code
and can
also be easily used by tools to help manage license compliance.
The Linux Foundation runs license scans against the codebase to help
ensure
we are in compliance with the licenses of the code we use, including
dependencies. Having these headers in place helps that tool do its job.
More information can be found on the SPDX site:
- https://spdx.dev/learn/handling-license-info/
Signed-off-by: Russell Bryant <rbryant@redhat.com>
commit 5a1cf1cb3b80759131c73f6a9dddebccac039dea
Author: Russell Bryant <rbryant@redhat.com>
Date: Fri Jan 31 14:36:32 2025 -0500
Check for SPDX headers using pre-commit
Signed-off-by: Russell Bryant <rbryant@redhat.com>
---------
Signed-off-by: Russell Bryant <rbryant@redhat.com>
85 lines
2.7 KiB
Python
85 lines
2.7 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
import argparse
|
|
|
|
import gradio as gr
|
|
from openai import OpenAI
|
|
|
|
# Argument parser setup
|
|
parser = argparse.ArgumentParser(
|
|
description='Chatbot Interface with Customizable Parameters')
|
|
parser.add_argument('--model-url',
|
|
type=str,
|
|
default='http://localhost:8000/v1',
|
|
help='Model URL')
|
|
parser.add_argument('-m',
|
|
'--model',
|
|
type=str,
|
|
required=True,
|
|
help='Model name for the chatbot')
|
|
parser.add_argument('--temp',
|
|
type=float,
|
|
default=0.8,
|
|
help='Temperature for text generation')
|
|
parser.add_argument('--stop-token-ids',
|
|
type=str,
|
|
default='',
|
|
help='Comma-separated stop token IDs')
|
|
parser.add_argument("--host", type=str, default=None)
|
|
parser.add_argument("--port", type=int, default=8001)
|
|
|
|
# Parse the arguments
|
|
args = parser.parse_args()
|
|
|
|
# Set OpenAI's API key and API base to use vLLM's API server.
|
|
openai_api_key = "EMPTY"
|
|
openai_api_base = args.model_url
|
|
|
|
# Create an OpenAI client to interact with the API server
|
|
client = OpenAI(
|
|
api_key=openai_api_key,
|
|
base_url=openai_api_base,
|
|
)
|
|
|
|
|
|
def predict(message, history):
|
|
# Convert chat history to OpenAI format
|
|
history_openai_format = [{
|
|
"role": "system",
|
|
"content": "You are a great ai assistant."
|
|
}]
|
|
for human, assistant in history:
|
|
history_openai_format.append({"role": "user", "content": human})
|
|
history_openai_format.append({
|
|
"role": "assistant",
|
|
"content": assistant
|
|
})
|
|
history_openai_format.append({"role": "user", "content": message})
|
|
|
|
# Create a chat completion request and send it to the API server
|
|
stream = client.chat.completions.create(
|
|
model=args.model, # Model name to use
|
|
messages=history_openai_format, # Chat history
|
|
temperature=args.temp, # Temperature for text generation
|
|
stream=True, # Stream response
|
|
extra_body={
|
|
'repetition_penalty':
|
|
1,
|
|
'stop_token_ids': [
|
|
int(id.strip()) for id in args.stop_token_ids.split(',')
|
|
if id.strip()
|
|
] if args.stop_token_ids else []
|
|
})
|
|
|
|
# Read and return generated text from response stream
|
|
partial_message = ""
|
|
for chunk in stream:
|
|
partial_message += (chunk.choices[0].delta.content or "")
|
|
yield partial_message
|
|
|
|
|
|
# Create and launch a chat interface with Gradio
|
|
gr.ChatInterface(predict).queue().launch(server_name=args.host,
|
|
server_port=args.port,
|
|
share=True)
|