chat_history.py

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")

if API_HOST == "azure":
    token_provider = azure.identity.get_bearer_token_provider(
        azure.identity.DefaultAzureCredential(), "https://cognitiveservices.azure.com/.default"
    )
    client = openai.AzureOpenAI(
        api_version=os.getenv("AZURE_OPENAI_VERSION"),
        azure_endpoint=os.getenv("AZURE_OPENAI_ENDPOINT"),
        azure_ad_token_provider=token_provider,
    )
    MODEL_NAME = os.getenv("AZURE_OPENAI_DEPLOYMENT")
elif API_HOST == "ollama":
    client = openai.OpenAI(
        base_url=os.getenv("OLLAMA_ENDPOINT"),
        api_key="nokeyneeded",
    )
    MODEL_NAME = os.getenv("OLLAMA_MODEL")
elif API_HOST == "github":
    client = openai.OpenAI(base_url="https://models.inference.ai.azure.com", api_key=os.getenv("GITHUB_TOKEN"))
    MODEL_NAME = os.getenv("GITHUB_MODEL")
else:
    client = openai.OpenAI(api_key=os.environ["OPENAI_KEY"])
    MODEL_NAME = os.environ["OPENAI_MODEL"]


messages = [
    {"role": "system", "content": "I am a teaching assistant helping with Python questions for Berkeley CS 61A."},
]

while True:
    question = input("\nYour question: ")
    print("Sending question...")

    messages.append({"role": "user", "content": question})
    response = client.chat.completions.create(
        model=MODEL_NAME,
        messages=messages,
        temperature=1,
        max_tokens=400,
        top_p=0.95,
        frequency_penalty=0,
        presence_penalty=0,
        stop=None,
    )
    bot_response = response.choices[0].message.content
    messages.append({"role": "assistant", "content": bot_response})

    print("Answer: ")
    print(bot_response)