wehub-resource-sync
a0c8464e58
Build Package / build (ubuntu-latest) (push) Failing after 1s
CodeQL / Analyze (python) (push) Failing after 1s
Core Typecheck / core-typecheck (push) Failing after 1s
Linting / lint (push) Failing after 1s
llama-dev tests / test-llama-dev (push) Failing after 1s
Publish Sub-Package to PyPI if Needed / publish_subpackage_if_needed (push) Has been skipped
Sync Docs to Developer Hub / sync-docs (push) Failing after 0s
Build Package / build (windows-latest) (push) Has been cancelled
444 lines
17 KiB
Plaintext
444 lines
17 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Setup and Installation"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"<a href=\"https://colab.research.google.com/drive/1vysj4eGqYt4sBdMp1BDI5Kxp4jtQbBxZ?usp=sharing\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
|
|
"\n",
|
|
"# Cookbook LlamaIndex Integration by Maxim AI (Instrumentation Module)\n",
|
|
"\n",
|
|
"This is a simple cookbook that demonstrates how to use the [LlamaIndex Maxim integration](https://www.getmaxim.ai/docs/sdk/python/integrations/llamaindex/llamaindex) using the [instrumentation module](https://docs.llamaindex.ai/en/stable/module_guides/observability/instrumentation/) by LlamaIndex (available in llama-index v0.10.20 and later)."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"<img \n",
|
|
" src=\"https://cdn.getmaxim.ai/public/images/llamaindex.gif\" \n",
|
|
" alt=\"LlamaIndex demo gif\"\n",
|
|
" style=\"max-width: 100%; height: auto; border-radius: 10px;\"\n",
|
|
"/>\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Install required packages\n",
|
|
"\n",
|
|
"# pip install llama-index\n",
|
|
"# pip install llama-index-llms-openai\n",
|
|
"# pip install llama-index-embeddings-openai\n",
|
|
"# pip install llama-index-tools-wikipedia\n",
|
|
"# pip install llama-index-tools-requests\n",
|
|
"# pip install maxim-py\n",
|
|
"# pip install python-dotenv"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import os\n",
|
|
"from dotenv import load_dotenv\n",
|
|
"\n",
|
|
"# Load environment variables from .env file\n",
|
|
"load_dotenv()\n",
|
|
"\n",
|
|
"# Get environment variables\n",
|
|
"MAXIM_API_KEY = os.getenv(\"MAXIM_API_KEY\")\n",
|
|
"MAXIM_LOG_REPO_ID = os.getenv(\"MAXIM_LOG_REPO_ID\")\n",
|
|
"OPENAI_API_KEY = os.getenv(\"OPENAI_API_KEY\")\n",
|
|
"\n",
|
|
"# Verify required environment variables are set\n",
|
|
"if not MAXIM_API_KEY:\n",
|
|
" raise ValueError(\"MAXIM_API_KEY environment variable is required\")\n",
|
|
"if not MAXIM_LOG_REPO_ID:\n",
|
|
" raise ValueError(\"MAXIM_LOG_REPO_ID environment variable is required\")\n",
|
|
"if not OPENAI_API_KEY:\n",
|
|
" raise ValueError(\"OPENAI_API_KEY environment variable is required\")\n",
|
|
"\n",
|
|
"print(\"✅ Environment variables loaded successfully\")\n",
|
|
"print(\n",
|
|
" f\"MAXIM_API_KEY: {'*' * (len(MAXIM_API_KEY) - 4) + MAXIM_API_KEY[-4:] if MAXIM_API_KEY else 'Not set'}\"\n",
|
|
")\n",
|
|
"print(f\"MAXIM_LOG_REPO_ID: {MAXIM_LOG_REPO_ID}\")\n",
|
|
"print(\n",
|
|
" f\"OPENAI_API_KEY: {'*' * (len(OPENAI_API_KEY) - 4) + OPENAI_API_KEY[-4:] if OPENAI_API_KEY else 'Not set'}\"\n",
|
|
")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Maxim Configuration"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import asyncio\n",
|
|
"from maxim import Config, Maxim\n",
|
|
"from maxim.logger import LoggerConfig\n",
|
|
"from maxim.logger.llamaindex import instrument_llamaindex\n",
|
|
"\n",
|
|
"# Initialize Maxim logger\n",
|
|
"maxim = Maxim(Config(api_key=os.getenv(\"MAXIM_API_KEY\")))\n",
|
|
"logger = maxim.logger(LoggerConfig(id=os.getenv(\"MAXIM_LOG_REPO_ID\")))\n",
|
|
"\n",
|
|
"# Instrument LlamaIndex with Maxim observability\n",
|
|
"# Set debug=True to see detailed logs during development\n",
|
|
"instrument_llamaindex(logger)\n",
|
|
"\n",
|
|
"print(\"✅ Maxim instrumentation enabled for LlamaIndex\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Simple FunctionAgent with Observability"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from llama_index.core.agent import FunctionAgent\n",
|
|
"from llama_index.core.tools import FunctionTool\n",
|
|
"from llama_index.llms.openai import OpenAI\n",
|
|
"\n",
|
|
"\n",
|
|
"# Define simple calculator tools\n",
|
|
"def add_numbers(a: float, b: float) -> float:\n",
|
|
" \"\"\"Add two numbers together.\"\"\"\n",
|
|
" return a + b\n",
|
|
"\n",
|
|
"\n",
|
|
"def multiply_numbers(a: float, b: float) -> float:\n",
|
|
" \"\"\"Multiply two numbers together.\"\"\"\n",
|
|
" return a * b\n",
|
|
"\n",
|
|
"\n",
|
|
"def divide_numbers(a: float, b: float) -> float:\n",
|
|
" \"\"\"Divide first number by second number.\"\"\"\n",
|
|
" if b == 0:\n",
|
|
" raise ValueError(\"Cannot divide by zero\")\n",
|
|
" return a / b\n",
|
|
"\n",
|
|
"\n",
|
|
"# Create function tools\n",
|
|
"add_tool = FunctionTool.from_defaults(fn=add_numbers)\n",
|
|
"multiply_tool = FunctionTool.from_defaults(fn=multiply_numbers)\n",
|
|
"divide_tool = FunctionTool.from_defaults(fn=divide_numbers)\n",
|
|
"\n",
|
|
"# Initialize LLM\n",
|
|
"llm = OpenAI(model=\"gpt-4o-mini\", temperature=0)\n",
|
|
"\n",
|
|
"# Create FunctionAgent\n",
|
|
"agent = FunctionAgent(\n",
|
|
" tools=[add_tool, multiply_tool, divide_tool],\n",
|
|
" llm=llm,\n",
|
|
" verbose=True,\n",
|
|
" system_prompt=\"\"\"You are a helpful calculator assistant.\n",
|
|
" Use the provided tools to perform mathematical calculations.\n",
|
|
" Always explain your reasoning step by step.\"\"\",\n",
|
|
")\n",
|
|
"\n",
|
|
"# Test the agent with a complex calculation\n",
|
|
"import asyncio\n",
|
|
"\n",
|
|
"\n",
|
|
"async def test_function_agent():\n",
|
|
" print(\"🔍 Testing FunctionAgent with Maxim observability...\")\n",
|
|
"\n",
|
|
" query = \"What is (15 + 25) multiplied by 2, then divided by 8?\"\n",
|
|
"\n",
|
|
" print(f\"\\n📝 Query: {query}\")\n",
|
|
"\n",
|
|
" # This will be automatically logged by Maxim instrumentation\n",
|
|
" # FunctionAgent.run() is async, so we need to await it\n",
|
|
" response = await agent.run(query)\n",
|
|
"\n",
|
|
" print(f\"\\n🤖 Response: {response}\")\n",
|
|
" print(\"\\n✅ Check your Maxim dashboard for detailed trace information!\")\n",
|
|
"\n",
|
|
"\n",
|
|
"# Run the async function\n",
|
|
"await test_function_agent()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Multi Modal Requests"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from llama_index.core.agent.workflow import FunctionAgent\n",
|
|
"from llama_index.core.llms import ChatMessage, ImageBlock, TextBlock\n",
|
|
"from llama_index.llms.openai import OpenAI\n",
|
|
"import requests\n",
|
|
"from PIL import Image\n",
|
|
"import io\n",
|
|
"import base64\n",
|
|
"\n",
|
|
"\n",
|
|
"# Tool for image analysis\n",
|
|
"def describe_image_content(description: str) -> str:\n",
|
|
" \"\"\"Analyze and describe what's in an image based on the model's vision.\"\"\"\n",
|
|
" return f\"Image analysis complete: {description}\"\n",
|
|
"\n",
|
|
"\n",
|
|
"# Math tools for the agent\n",
|
|
"def add(a: int, b: int) -> int:\n",
|
|
" \"\"\"Add two numbers together.\"\"\"\n",
|
|
" return a + b\n",
|
|
"\n",
|
|
"\n",
|
|
"def multiply(a: int, b: int) -> int:\n",
|
|
" \"\"\"Multiply two numbers together.\"\"\"\n",
|
|
" return a * b\n",
|
|
"\n",
|
|
"\n",
|
|
"# Create multi-modal agent with vision-capable model\n",
|
|
"multimodal_llm = OpenAI(model=\"gpt-4o-mini\") # Vision-capable model\n",
|
|
"\n",
|
|
"multimodal_agent = FunctionAgent(\n",
|
|
" tools=[add, multiply, describe_image_content],\n",
|
|
" llm=multimodal_llm,\n",
|
|
" system_prompt=\"You are a helpful assistant that can analyze images and perform calculations.\",\n",
|
|
")\n",
|
|
"\n",
|
|
"\n",
|
|
"async def test_multimodal_agent():\n",
|
|
" print(\"🔍 Testing Multi-Modal Agent with Maxim observability...\")\n",
|
|
"\n",
|
|
" # Create a simple test image (you can replace this with an actual image path)\n",
|
|
" # For demo purposes, we'll create a simple mathematical equation image\n",
|
|
" try:\n",
|
|
" # You can replace this with a real image path if available\n",
|
|
" # For now, we'll use text-based interaction\n",
|
|
" # text_query = \"Calculate 15 + 25 and then multiply the result by 3\"\n",
|
|
"\n",
|
|
" # response = await multimodal_agent.run(text_query)\n",
|
|
" # print(f\"\\n🤖 Text Response: {response}\")\n",
|
|
"\n",
|
|
" # If you have an image, you can use this pattern:\n",
|
|
" msg = ChatMessage(\n",
|
|
" role=\"user\",\n",
|
|
" blocks=[\n",
|
|
" TextBlock(\n",
|
|
" text=\"What do you see in this image? If there are numbers, perform calculations.\"\n",
|
|
" ),\n",
|
|
" ImageBlock(\n",
|
|
" url=\"https://www.shutterstock.com/image-photo/simple-mathematical-equation-260nw-350386472.jpg\"\n",
|
|
" ), # Replace with actual image path\n",
|
|
" ],\n",
|
|
" )\n",
|
|
" response = await multimodal_agent.run(msg)\n",
|
|
"\n",
|
|
" except Exception as e:\n",
|
|
" print(\n",
|
|
" f\"Note: Multi-modal features require actual image files. Error: {e}\"\n",
|
|
" )\n",
|
|
" print(\n",
|
|
" \"The agent structure is set up correctly for when you have images to process!\"\n",
|
|
" )\n",
|
|
"\n",
|
|
" print(\"\\n✅ Check Maxim dashboard for multi-modal agent traces!\")\n",
|
|
"\n",
|
|
"\n",
|
|
"# Run the test\n",
|
|
"await test_multimodal_agent()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Multiple Agents"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from llama_index.core.agent.workflow import AgentWorkflow, FunctionAgent\n",
|
|
"from llama_index.llms.openai import OpenAI\n",
|
|
"from llama_index.core.tools import FunctionTool # Import FunctionTool\n",
|
|
"\n",
|
|
"\n",
|
|
"# Research agent tools\n",
|
|
"def research_topic(topic: str) -> str:\n",
|
|
" \"\"\"Research a given topic and return key findings.\"\"\"\n",
|
|
" # Mock research results - in production, this would call real APIs\n",
|
|
" research_data = {\n",
|
|
" \"climate change\": \"Climate change refers to long-term shifts in global temperatures and weather patterns, primarily caused by human activities since the 1800s.\",\n",
|
|
" \"renewable energy\": \"Renewable energy comes from sources that are naturally replenishing like solar, wind, hydro, and geothermal power.\",\n",
|
|
" \"artificial intelligence\": \"AI involves creating computer systems that can perform tasks typically requiring human intelligence.\",\n",
|
|
" \"sustainability\": \"Sustainability involves meeting present needs without compromising the ability of future generations to meet their needs.\",\n",
|
|
" }\n",
|
|
"\n",
|
|
" topic_lower = topic.lower()\n",
|
|
" for key, info in research_data.items():\n",
|
|
" if key in topic_lower:\n",
|
|
" return f\"Research findings on {topic}: {info} Additional context includes recent developments and policy implications.\"\n",
|
|
"\n",
|
|
" return f\"Research completed on {topic}. This is an emerging area requiring further investigation and analysis.\"\n",
|
|
"\n",
|
|
"\n",
|
|
"# Analysis agent tools\n",
|
|
"def analyze_data(research_data: str) -> str:\n",
|
|
" \"\"\"Analyze research data and provide insights.\"\"\"\n",
|
|
" if \"climate change\" in research_data.lower():\n",
|
|
" return \"Analysis indicates climate change requires immediate action through carbon reduction, renewable energy adoption, and international cooperation.\"\n",
|
|
" elif \"renewable energy\" in research_data.lower():\n",
|
|
" return \"Analysis shows renewable energy is becoming cost-competitive with fossil fuels and offers long-term economic and environmental benefits.\"\n",
|
|
" elif \"artificial intelligence\" in research_data.lower():\n",
|
|
" return \"Analysis reveals AI has transformative potential across industries but requires careful consideration of ethical implications and regulation.\"\n",
|
|
" else:\n",
|
|
" return \"Analysis suggests this topic has significant implications requiring strategic planning and stakeholder engagement.\"\n",
|
|
"\n",
|
|
"\n",
|
|
"# Report writing agent tools\n",
|
|
"def write_report(analysis: str, topic: str) -> str:\n",
|
|
" \"\"\"Write a comprehensive report based on analysis.\"\"\"\n",
|
|
" return f\"\"\"\n",
|
|
"═══════════════════════════════════════\n",
|
|
"COMPREHENSIVE RESEARCH REPORT: {topic.upper()}\n",
|
|
"═══════════════════════════════════════\n",
|
|
"\n",
|
|
"EXECUTIVE SUMMARY:\n",
|
|
"{analysis}\n",
|
|
"\n",
|
|
"KEY FINDINGS:\n",
|
|
"- Evidence-based analysis indicates significant implications\n",
|
|
"- Multiple stakeholder perspectives must be considered\n",
|
|
"- Implementation requires coordinated approach\n",
|
|
"- Long-term monitoring and evaluation necessary\n",
|
|
"\n",
|
|
"RECOMMENDATIONS:\n",
|
|
"1. Develop comprehensive strategy framework\n",
|
|
"2. Engage key stakeholders early in process\n",
|
|
"3. Establish clear metrics and milestones\n",
|
|
"4. Create feedback mechanisms for continuous improvement\n",
|
|
"5. Allocate appropriate resources and timeline\n",
|
|
"\n",
|
|
"NEXT STEPS:\n",
|
|
"- Schedule stakeholder consultations\n",
|
|
"- Develop detailed implementation plan\n",
|
|
"- Establish monitoring and evaluation framework\n",
|
|
"- Begin pilot program if applicable\n",
|
|
"\n",
|
|
"This report provides a foundation for informed decision-decision making and strategic planning.\n",
|
|
"\"\"\"\n",
|
|
"\n",
|
|
"\n",
|
|
"# Initialize LLM\n",
|
|
"llm = OpenAI(model=\"gpt-4o-mini\", temperature=0)\n",
|
|
"\n",
|
|
"# Create individual agents using the modern API\n",
|
|
"research_agent = FunctionAgent(\n",
|
|
" name=\"research_agent\",\n",
|
|
" description=\"This agent researches a given topic and returns key findings.\",\n",
|
|
" tools=[FunctionTool.from_defaults(fn=research_topic)],\n",
|
|
" llm=llm,\n",
|
|
" system_prompt=\"You are a research specialist. Use the research tool to gather comprehensive information on requested topics.\",\n",
|
|
")\n",
|
|
"\n",
|
|
"analysis_agent = FunctionAgent(\n",
|
|
" name=\"analysis_agent\",\n",
|
|
" description=\"This agent analyzes research data and provides actionable insights.\",\n",
|
|
" tools=[FunctionTool.from_defaults(fn=analyze_data)],\n",
|
|
" llm=llm,\n",
|
|
" system_prompt=\"You are a data analyst. Analyze research findings and provide actionable insights.\",\n",
|
|
")\n",
|
|
"\n",
|
|
"report_agent = FunctionAgent(\n",
|
|
" name=\"report_agent\",\n",
|
|
" description=\"This agent creates comprehensive, well-structured reports based on analysis.\",\n",
|
|
" tools=[FunctionTool.from_defaults(fn=write_report)],\n",
|
|
" llm=llm,\n",
|
|
" system_prompt=\"You are a report writer. Create comprehensive, well-structured reports based on analysis.\",\n",
|
|
")\n",
|
|
"\n",
|
|
"# Create AgentWorkflow\n",
|
|
"multi_agent_workflow = AgentWorkflow(\n",
|
|
" agents=[research_agent, analysis_agent, report_agent],\n",
|
|
" root_agent=\"research_agent\",\n",
|
|
")\n",
|
|
"\n",
|
|
"\n",
|
|
"async def test_agent_workflow():\n",
|
|
" print(\"🔍 Testing AgentWorkflow with Maxim observability...\")\n",
|
|
"\n",
|
|
" query = \"\"\"I need a comprehensive report on renewable energy.\n",
|
|
" Please research the current state of renewable energy,\n",
|
|
" analyze the key findings, and create a structured report\n",
|
|
" with recommendations for implementation.\"\"\"\n",
|
|
"\n",
|
|
" print(f\"\\n📝 Query: {query}\")\n",
|
|
" print(\"🔄 This will coordinate multiple agents...\")\n",
|
|
"\n",
|
|
" # This will create a complex trace showing:\n",
|
|
" # - Multi-agent coordination\n",
|
|
" # - Agent handoffs and communication\n",
|
|
" # - Sequential tool execution\n",
|
|
" # - Individual agent performances\n",
|
|
" response = await multi_agent_workflow.run(query)\n",
|
|
"\n",
|
|
" print(f\"\\n🤖 Multi-Agent Response:\\n{response}\")\n",
|
|
" print(\n",
|
|
" \"\\n✅ Check Maxim dashboard for comprehensive multi-agent workflow traces!\"\n",
|
|
" )\n",
|
|
"\n",
|
|
"\n",
|
|
"# Run the async function\n",
|
|
"await test_agent_workflow()"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"colab": {
|
|
"provenance": []
|
|
},
|
|
"kernelspec": {
|
|
"display_name": "Python 3",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"name": "python"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 0
|
|
}
|