dapr-agents/cookbook/llm/azure_openai_chat_basic.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# LLM: Azure OpenAI Chat Endpoint Basic Examples\n",
    "\n",
    "This notebook demonstrates how to use the `OpenAIChatClient` in `dapr-agents` for basic tasks with the Azure OpenAI Chat API. We will explore:\n",
    "\n",
    "* Initializing the OpenAI Chat client.\n",
    "* Generating responses to simple prompts.\n",
    "* Using a `.prompty` file to provide context/history for enhanced generation."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Install Required Libraries\n",
    "Before starting, ensure the required libraries are installed:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install dapr-agents python-dotenv"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Load Environment Variables\n",
    "\n",
    "Load API keys or other configuration values from your `.env` file using `dotenv`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from dotenv import load_dotenv\n",
    "load_dotenv()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Import OpenAIChatClient"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "from dapr_agents import OpenAIChatClient"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Basic Chat Completion\n",
    "\n",
    "Initialize the `OpenAIChatClient` and generate a response to a simple prompt."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Initialize the client\n",
    "import os\n",
    "\n",
    "llm = OpenAIChatClient(\n",
    "    #api_key=os.getenv(\"AZURE_OPENAI_API_KEY\") # or add AZURE_OPENAI_API_KEY environment variable to .env file\n",
    "    azure_endpoint=os.getenv(\"AZURE_OPENAI_ENDPOINT\"), # or add AZURE_OPENAI_ENDPOINT environment variable to .env file\n",
    "    azure_deployment=\"gpt-4o\"\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "ChatCompletion(choices=[Choice(finish_reason='stop', index=0, message=MessageContent(content='One famous dog is Lassie, the fictional Rough Collie from the \"Lassie\" television series and movies. Lassie is known for her intelligence, loyalty, and the ability to help her human companions out of tricky situations.', role='assistant'), logprobs=None)], created=1743846818, id='chatcmpl-BIuVWArM8Lzqug16s43O9M8BLaFkZ', model='gpt-4o-2024-08-06', object='chat.completion', usage={'completion_tokens': 48, 'prompt_tokens': 12, 'total_tokens': 60, 'completion_tokens_details': {'accepted_prediction_tokens': 0, 'audio_tokens': 0, 'reasoning_tokens': 0, 'rejected_prediction_tokens': 0}, 'prompt_tokens_details': {'audio_tokens': 0, 'cached_tokens': 0}})"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "# Generate a response\n",
    "response = llm.generate('Name a famous dog!')\n",
    "\n",
    "# Display the response\n",
    "response"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'content': 'One famous dog is Lassie, the fictional Rough Collie from the \"Lassie\" television series and movies. Lassie is known for her intelligence, loyalty, and the ability to help her human companions out of tricky situations.', 'role': 'assistant'}\n"
     ]
    }
   ],
   "source": [
    "print(response.get_message())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Using a Prompty File for Context\n",
    "\n",
    "Use a `.prompty` file to provide context for chat history or additional instructions."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "llm = OpenAIChatClient.from_prompty('basic-azopenai-chat.prompty')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "ChatPromptTemplate(input_variables=['question'], pre_filled_variables={}, messages=[SystemMessage(content='You are an AI assistant who helps people find information.\\nAs the assistant, you answer questions briefly, succinctly.', role='system'), UserMessage(content='{{question}}', role='user')], template_format='jinja2')"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "llm.prompt_template"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "ChatCompletion(choices=[Choice(finish_reason='stop', index=0, message=MessageContent(content=\"I am an AI assistant and don't have a personal name, but you can call me Assistant.\", role='assistant'), logprobs=None)], created=1743846828, id='chatcmpl-BIuVgBC6I3w1TFn15pmuCBGu6VZQM', model='gpt-4o-2024-08-06', object='chat.completion', usage={'completion_tokens': 20, 'prompt_tokens': 39, 'total_tokens': 59, 'completion_tokens_details': {'accepted_prediction_tokens': 0, 'audio_tokens': 0, 'reasoning_tokens': 0, 'rejected_prediction_tokens': 0}, 'prompt_tokens_details': {'audio_tokens': 0, 'cached_tokens': 0}})"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "llm.generate(input_data={\"question\":\"What is your name?\"})"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Chat Completion with Messages"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Initialize the client\n",
    "llm = OpenAIChatClient(\n",
    "    api_key=os.getenv(\"AZURE_OPENAI_API_KEY\"), # or add AZURE_OPENAI_API_KEY environment variable to .env file\n",
    "    #azure_endpoint=os.getenv(\"AZURE_OPENAI_ENDPOINT\"), # or add AZURE_OPENAI_ENDPOINT environment variable to .env file\n",
    "    azure_deployment=\"gpt-4o\"\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'content': 'Hello! How can I assist you today?', 'role': 'assistant'}\n"
     ]
    }
   ],
   "source": [
    "from dapr_agents.types import UserMessage\n",
    "\n",
    "# Generate a response using structured messages\n",
    "response = llm.generate(messages=[UserMessage(\"hello\")])\n",
    "\n",
    "# Display the structured response\n",
    "print(response.get_message())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "llm.prompt_template"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.13.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}