microsoft--graphrag/packages/graphrag-llm/notebooks/07_rate_limiting.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "0a68b531",
   "metadata": {},
   "source": [
    "# Rate Limiting\n",
    "\n",
    "Rate limiting is disabled by default. Requests can be limited by either requests per period or tokens per period or both.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "df4fa775",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Time taken for two requests: 20.87 seconds\n",
      "Metrics for: azure/gpt-4o\n",
      "{\n",
      "  \"attempted_request_count\": 2,\n",
      "  \"successful_response_count\": 2,\n",
      "  \"failed_response_count\": 0,\n",
      "  \"failure_rate\": 0.0,\n",
      "  \"requests_with_retries\": 0,\n",
      "  \"retries\": 0,\n",
      "  \"retry_rate\": 0.0,\n",
      "  \"compute_duration_seconds\": 3.534508228302002,\n",
      "  \"compute_duration_per_response_seconds\": 1.767254114151001,\n",
      "  \"cache_hit_rate\": 0.0,\n",
      "  \"streaming_responses\": 0,\n",
      "  \"responses_with_tokens\": 2,\n",
      "  \"prompt_tokens\": 28,\n",
      "  \"completion_tokens\": 16,\n",
      "  \"total_tokens\": 44,\n",
      "  \"tokens_per_response\": 22.0,\n",
      "  \"responses_with_cost\": 2,\n",
      "  \"input_cost\": 7.000000000000001e-05,\n",
      "  \"output_cost\": 0.00016,\n",
      "  \"total_cost\": 0.00023,\n",
      "  \"cost_per_response\": 0.000115\n",
      "}\n"
     ]
    }
   ],
   "source": [
    "# Copyright (c) 2024 Microsoft Corporation.\n",
    "# Licensed under the MIT License\n",
    "\n",
    "import json\n",
    "import os\n",
    "import time\n",
    "\n",
    "from dotenv import load_dotenv\n",
    "from graphrag_llm.completion import LLMCompletion, create_completion\n",
    "from graphrag_llm.config import AuthMethod, ModelConfig, RateLimitConfig, RateLimitType\n",
    "\n",
    "load_dotenv()\n",
    "\n",
    "api_key = os.getenv(\"GRAPHRAG_API_KEY\")\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=os.getenv(\"GRAPHRAG_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",
    "    rate_limit=RateLimitConfig(\n",
    "        type=RateLimitType.SlidingWindow,\n",
    "        period_in_seconds=60,  # limit requests per minute\n",
    "        requests_per_period=3,  # max 3 requests per minute. Fire one off every 20 seconds\n",
    "    ),\n",
    ")\n",
    "\n",
    "llm_completion: LLMCompletion = create_completion(model_config)\n",
    "\n",
    "start_time = time.time()\n",
    "response = llm_completion.completion(\n",
    "    messages=\"What is the capital of France?\",\n",
    ")\n",
    "response = llm_completion.completion(\n",
    "    messages=\"What is the capital of France?\",\n",
    ")\n",
    "end_time = time.time()\n",
    "total_time = end_time - start_time\n",
    "assert total_time >= 20, \"Rate limiting did not work as expected.\"\n",
    "\n",
    "print(f\"Time taken for two requests: {total_time:.2f} seconds\")\n",
    "print(f\"Metrics for: {llm_completion.metrics_store.id}\")\n",
    "print(json.dumps(llm_completion.metrics_store.get_metrics(), indent=2))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "59f92d3f",
   "metadata": {},
   "source": [
    "Notice that the `compute_duration_seconds` in the metrics only tracks how long a network request actually takes and does track paused periods that occur due to rate limits.\n"
   ]
  }
 ],
 "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": "3.11.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}