microsoft--graphrag/packages/graphrag-llm/example_notebooks/basic_completion_example.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "45a56eb5",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Copyright (c) 2026 Microsoft Corporation.\n",
    "# Licensed under the MIT License."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7a49f267",
   "metadata": {},
   "source": [
    "##  Basic completion example\n",
    "\n",
    "This example demonstrates basic usage of the LLM library to interact with Azure OpenAI. It loads environment variables for API configuration, creates a ModelConfig for Azure OpenAI, and sends a simple question to the model. The code handles both streaming and non-streaming responses (streaming responses are printed chunk by chunk in real-time, while non-streaming responses are printed all at once). It also shows how to use the gather_completion_response utility function as a simpler alternative that automatically handles both response types and returns the complete text."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "88ca8061",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Not streaming response:\n",
      "The capital of France is **Paris**.\n",
      "The capital of France is **Paris**.\n"
     ]
    }
   ],
   "source": [
    "import os\n",
    "from collections.abc import Iterator\n",
    "\n",
    "from dotenv import load_dotenv\n",
    "from graphrag_llm.completion import LLMCompletion, create_completion\n",
    "from graphrag_llm.config import AuthMethod, ModelConfig\n",
    "from graphrag_llm.types import LLMCompletionChunk, LLMCompletionResponse\n",
    "from graphrag_llm.utils import (\n",
    "    gather_completion_response,\n",
    ")\n",
    "\n",
    "load_dotenv()\n",
    "\n",
    "api_key = os.getenv(\"GRAPHRAG_API_KEY\")\n",
    "api_base = os.getenv(\"GRAPHRAG_API_BASE\")\n",
    "\n",
    "model_config = ModelConfig(\n",
    "    model_provider=\"azure\",\n",
    "    model=os.getenv(\"GRAPHRAG_MODEL\", \"gpt-4o\"),\n",
    "    azure_deployment_name=os.getenv(\"GRAPHRAG_MODEL\", \"gpt-4o\"),\n",
    "    api_base=api_base,\n",
    "    api_version=os.getenv(\"GRAPHRAG_API_VERSION\", \"2025-04-01-preview\"),\n",
    "    api_key=api_key,\n",
    "    auth_method=AuthMethod.AzureManagedIdentity if not api_key else AuthMethod.ApiKey,\n",
    ")\n",
    "llm_completion: LLMCompletion = create_completion(model_config)\n",
    "\n",
    "response: LLMCompletionResponse | Iterator[LLMCompletionChunk] = (\n",
    "    llm_completion.completion(\n",
    "        messages=\"What is the capital of France?\",\n",
    "    )\n",
    ")\n",
    "\n",
    "if isinstance(response, Iterator):\n",
    "    print(\"Streaming response:\")\n",
    "    # Streaming response\n",
    "    for chunk in response:\n",
    "        print(chunk.choices[0].delta.content or \"\", end=\"\", flush=True)\n",
    "else:\n",
    "    # Non-streaming response\n",
    "    print(\"Not streaming response:\")\n",
    "    print(response.choices[0].message.content)\n",
    "\n",
    "# Alternatively, you can use the utility function to gather the full response\n",
    "# The following is equivalent to the above logic. If all you care about is\n",
    "# the first choice response then you can use the gather_completion_response\n",
    "# utility function.\n",
    "response_text = gather_completion_response(response)\n",
    "print(response_text)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.12.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}