generated from pamelafox/python-project-template
-
Notifications
You must be signed in to change notification settings - Fork 154
/
Copy pathchat_async.py
69 lines (58 loc) · 2.13 KB
/
chat_async.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
import asyncio
import os
import azure.identity
import openai
from dotenv import load_dotenv
# Setup the OpenAI client to use either Azure, OpenAI.com, or Ollama API
load_dotenv(override=True)
API_HOST = os.getenv("API_HOST", "github")
if API_HOST == "azure":
token_provider = azure.identity.get_bearer_token_provider(
azure.identity.DefaultAzureCredential(), "https://cognitiveservices.azure.com/.default"
)
client = openai.AsyncAzureOpenAI(
api_version=os.environ["AZURE_OPENAI_VERSION"],
azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
azure_ad_token_provider=token_provider,
)
MODEL_NAME = os.environ["AZURE_OPENAI_DEPLOYMENT"]
elif API_HOST == "ollama":
client = openai.AsyncOpenAI(base_url=os.environ["OLLAMA_ENDPOINT"], api_key="nokeyneeded")
MODEL_NAME = os.environ["OLLAMA_MODEL"]
elif API_HOST == "github":
client = openai.AsyncOpenAI(base_url="https://models.inference.ai.azure.com", api_key=os.environ["GITHUB_TOKEN"])
MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
else:
client = openai.AsyncOpenAI(api_key=os.environ["OPENAI_KEY"])
MODEL_NAME = os.environ["OPENAI_MODEL"]
async def generate_response(location):
print("Generating response for", location)
response = await client.chat.completions.create(
model=MODEL_NAME,
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{
"role": "user",
"content": f"Name a single place I should visit on my trip to {location} and describe in one sentence",
},
],
temperature=1,
max_tokens=400,
top_p=0.95,
frequency_penalty=0,
presence_penalty=0,
stop=None,
)
print("Got response for ", location)
return response.choices[0].message.content
async def single():
print(await generate_response("Tokyo"))
async def multiple():
answers = await asyncio.gather(
generate_response("Tokyo"),
generate_response("Berkeley"),
generate_response("Singapore"),
)
for answer in answers:
print(answer, "\n")
asyncio.run(single())