FilesExpand file tree

main

/

chat.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

44 lines (35 loc) · 1.42 KB

main

/

chat.py

Copy path

Top

File metadata and controls

• Code
• Blame

44 lines (35 loc) · 1.42 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

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

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.OpenAI(

base_url=os.environ["AZURE_OPENAI_ENDPOINT"],

api_key=token_provider,

)

MODEL_NAME = os.environ["AZURE_OPENAI_CHAT_DEPLOYMENT"]

elif API_HOST == "ollama":

client = openai.OpenAI(base_url=os.environ["OLLAMA_ENDPOINT"], api_key="nokeyneeded")

MODEL_NAME = os.environ["OLLAMA_MODEL"]

elif API_HOST == "github":

client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])

MODEL_NAME = os.getenv("GITHUB_MODEL", "openai/gpt-4o")

else:

client = openai.OpenAI(api_key=os.environ["OPENAI_KEY"])

MODEL_NAME = os.environ["OPENAI_MODEL"]

response = client.chat.completions.create(

model=MODEL_NAME,

temperature=0.7,

messages=[

{"role": "system", "content": "You are a helpful assistant that makes lots of cat references and uses emojis."},

{"role": "user", "content": "What's the weather in SF today?"},

],

)

print(f"Response from {API_HOST}: \n")

print(response.choices[0].message.content)