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>
92 lines
3.2 KiB
Python
92 lines
3.2 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
"""
|
|
An example shows how to generate chat completions from reasoning models
|
|
like DeepSeekR1.
|
|
|
|
To run this example, you need to start the vLLM server with the reasoning
|
|
parser:
|
|
|
|
```bash
|
|
vllm serve deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B \
|
|
--enable-reasoning --reasoning-parser deepseek_r1
|
|
```
|
|
|
|
Unlike openai_chat_completion_with_reasoning.py, this example demonstrates the
|
|
streaming chat completions feature.
|
|
|
|
The streaming chat completions feature allows you to receive chat completions
|
|
in real-time as they are generated by the model. This is useful for scenarios
|
|
where you want to display chat completions to the user as they are generated
|
|
by the model.
|
|
|
|
Here we do not use the OpenAI Python client library, because it does not support
|
|
`reasoning_content` fields in the response.
|
|
"""
|
|
|
|
import json
|
|
|
|
import requests
|
|
|
|
# Modify OpenAI's API key and API base to use vLLM's API server.
|
|
openai_api_key = "EMPTY"
|
|
openai_api_base = "http://localhost:8000/v1"
|
|
|
|
models = requests.get(
|
|
f"{openai_api_base}/models",
|
|
headers={
|
|
"Authorization": f"Bearer {openai_api_key}"
|
|
},
|
|
).json()
|
|
model = models["data"][0]["id"]
|
|
|
|
# Streaming chat completions
|
|
messages = [{"role": "user", "content": "9.11 and 9.8, which is greater?"}]
|
|
|
|
response = requests.post(
|
|
f"{openai_api_base}/chat/completions",
|
|
headers={"Authorization": f"Bearer {openai_api_key}"},
|
|
json={
|
|
"model": model,
|
|
"messages": messages,
|
|
"stream": True
|
|
},
|
|
)
|
|
|
|
print("client: Start streaming chat completions...")
|
|
printed_reasoning_content = False
|
|
printed_content = False
|
|
# Make the streaming request
|
|
if response.status_code == 200:
|
|
# Process the streaming response
|
|
for line in response.iter_lines():
|
|
if line: # Filter out keep-alive new lines
|
|
# Decode the line and parse the JSON
|
|
decoded_line = line.decode("utf-8")
|
|
if decoded_line.startswith("data:"):
|
|
data = decoded_line[5:].strip() # Remove "data:" prefix
|
|
if data == "[DONE]": # End of stream
|
|
print("\nclient: Stream completed.")
|
|
break
|
|
try:
|
|
# Parse the JSON data
|
|
chunk = json.loads(data)
|
|
reasoning_content = chunk["choices"][0]["delta"].get(
|
|
"reasoning_content", "")
|
|
content = chunk["choices"][0]["delta"].get("content", "")
|
|
|
|
if reasoning_content:
|
|
if not printed_reasoning_content:
|
|
printed_reasoning_content = True
|
|
print("reasoning_content:", end="", flush=True)
|
|
print(reasoning_content, end="", flush=True)
|
|
elif content:
|
|
if not printed_content:
|
|
printed_content = True
|
|
print("\ncontent:", end="", flush=True)
|
|
# Extract and print the content
|
|
print(content, end="", flush=True)
|
|
except json.JSONDecodeError:
|
|
print("Error decoding JSON:", decoded_line)
|
|
else:
|
|
print(f"Error: {response.status_code} - {response.text}")
|