Advanced Function Calling and Multi-Agent Systems with Small Language Models in Foundry Local
Advanced Function Calling and Multi-Agent Systems with Small Language Models in Foundry Local In our previous exploration of function calling with Small Language Models, we demonstrated how to enable local SLMs to interact with external tools using a text-parsing approach with regex patterns. While that method worked, it required manual extraction of function calls from the model's output; functional but fragile. Today, I'm excited to show you something far more powerful: Foundry Local now supports native OpenAI-compatible function calling with select models. This update transforms how we build agentic AI systems locally, making it remarkably straightforward to create sophisticated multi-agent architectures that rival cloud-based solutions. What once required careful prompt engineering and brittle parsing now works seamlessly through standardized API calls. We'll build a complete multi-agent quiz application that demonstrates both the elegance of modern function calling and the power of coordinated agent systems. The full source code is available in this GitHub repository, but rather than walking through every line of code, we'll focus on how the pieces work together and what you'll see when you run it. What's New: Native Function Calling in Foundry Local As we explored in our guide to running Phi-4 locally with Foundry Local, we ran powerful language models on our local machine. The latest version now support native function calling for models specifically trained with this capability. The key difference is architectural. In our weather assistant example, we manually parsed JSON strings from the model's text output using regex patterns and frankly speaking, meticulously testing and tweaking the system prompt for the umpteenth time 🙄. Now, when you provide tool definitions to supported models, they return structured tool_calls objects that you can directly execute. Currently, this native function calling capability is available for the Qwen 2.5 family of models in Foundry Local. For this tutorial, we're using the 7B variant, which strikes a great balance between capability and resource requirements. Quick Setup Getting started requires just a few steps. First, ensure you have Foundry Local installed. On Windows, use winget install Microsoft.FoundryLocal , and on macOS, use bash brew install microsoft/foundrylocal/foundrylocal You'll need version 0.8.117 or later. Install the Python dependencies in the requirements file, then start your model. The first run will download approximately 4GB: foundry model run qwen2.5-7b-instruct-cuda-gpu If you don't have a compatible GPU, use the CPU version instead, or you can specify any other Qwen 2.5 variant that suits your hardware. I have set a DEFAULT_MODEL_ALIAS variable you can modify to use different models in utils/foundry_client.py file. Keep this terminal window open. The model needs to stay running while you develop and test your application. Understanding the Architecture Before we dive into running the application, let's understand what we're building. Our quiz system follows a multi-agent architecture where specialized agents handle distinct responsibilities, coordinated by a central orchestrator. The flow works like this: when you ask the system to generate a quiz about photosynthesis, the orchestrator agent receives your message, understands your intent, and decides which tool to invoke. It doesn't try to generate the quiz itself, instead, it calls a tool that creates a specialist QuizGeneratorAgent focused solely on producing well-structured quiz questions. Then there's another agent, reviewAgent, that reviews the quiz with you. The project structure reflects this architecture: quiz_app/ ├── agents/ # Base agent + specialist agents ├── tools/ # Tool functions the orchestrator can call ├── utils/ # Foundry client connection ├── data/ ├── quizzes/ # Generated quiz JSON files │── responses/ # User response JSON files └── main.py # Application entry point The orchestrator coordinates three main tools: generate_new_quiz, launch_quiz_interface, and review_quiz_interface. Each tool either creates a specialist agent or launches an interactive interface (Gradio), handling the complexity so the orchestrator can focus on routing and coordination. How Native Function Calling Works When you initialize the orchestrator agent in main.py, you provide two things: tool schemas that describe your functions to the model, and a mapping of function names to actual Python functions. The schemas follow the OpenAI function calling specification, describing each tool's purpose, parameters, and when it should be used. Here's what happens when you send a message to the orchestrator: The agent calls the model with your message and the tool schemas. If the model determines a tool is needed, it returns a structured tool_calls attribute containing the function name and arguments as a proper object—not as text to be parsed. Your code executes the tool, creates a message with "role": "tool" containing the result, and sends everything back to the model. The model can then either call another tool or provide its final response. The critical insight is that the model itself controls this flow through a while loop in the base agent. Each iteration represents the model examining the current state, deciding whether it needs more information, and either proceeding with another tool call or providing its final answer. You're not manually orchestrating when tools get called; the model makes those decisions based on the conversation context. Seeing It In Action Let's walk through a complete session to see how these pieces work together. When you run python main.py, you'll see the application connect to Foundry Local and display a welcome banner: Now type a request like "Generate a 5 question quiz about photosynthesis." Watch what happens in your console: The orchestrator recognized your intent, selected the generate_new_quiz tool, and extracted the topic and number of questions from your natural language request. Behind the scenes, this tool instantiated a QuizGeneratorAgent with a focused system prompt designed specifically for creating quiz JSON. The agent used a low temperature setting to ensure consistent formatting and generated questions that were saved to the data/quizzes folder. This demonstrates the first layer of the multi-agent architecture: the orchestrator doesn't generate quizzes itself. It recognizes that this task requires specialized knowledge about quiz structure and delegates to an agent built specifically for that purpose. Now request to take the quiz by typing "Take the quiz." The orchestrator calls a different tool and Gradio server is launched. Click the link to open in a browser window displaying your quiz questions. This tool demonstrates how function calling can trigger complex interactions—it reads the quiz JSON, dynamically builds a user interface with radio buttons for each question, and handles the submission flow. After you answer the questions and click submit, the interface saves your responses to the data/responses folder and closes the Gradio server. The orchestrator reports completion: The system now has two JSON files: one containing the quiz questions with correct answers, and another containing your responses. This separation of concerns is important—the quiz generation phase doesn't need to know about response collection, and the response collection doesn't need to know how quizzes are created. Each component has a single, well-defined responsibility. Now request a review. The orchestrator calls the third tool: A new chat interface opens, and here's where the multi-agent architecture really shines. The ReviewAgent is instantiated with full context about both the quiz questions and your answers. Its system prompt includes a formatted view of each question, the correct answer, your answer, and whether you got it right. This means when the interface opens, you immediately see personalized feedback: The Multi-Agent Pattern Multi-agent architectures solve complex problems by coordinating specialized agents rather than building monolithic systems. This pattern is particularly powerful for local SLMs. A coordinator agent routes tasks to specialists, each optimized for narrow domains with focused system prompts and specific temperature settings. You can use a 1.7B model for structured data generation, a 7B model for conversations, and a 4B model for reasoning, all orchestrated by a lightweight coordinator. This is more efficient than requiring one massive model for everything. Foundry Local's native function calling makes this straightforward. The coordinator reliably invokes tools that instantiate specialists, with structured responses flowing back through proper tool messages. The model manages the coordination loop—deciding when it needs another specialist, when it has enough information, and when to provide a final answer. In our quiz application, the orchestrator routes user requests but never tries to be an expert in quiz generation, interface design, or tutoring. The QuizGeneratorAgent focuses solely on creating well-structured quiz JSON using constrained prompts and low temperature. The ReviewAgent handles open-ended educational dialogue with embedded quiz context and higher temperature for natural conversation. The tools abstract away file management, interface launching, and agent instantiation, the orchestrator just knows "this tool launches quizzes" without needing implementation details. This pattern scales effortlessly. If you wanted to add a new capability like study guides or flashcards, you could just easily create a new tool or specialists. The orchestrator gains these capabilities automatically by having the tool schemas you have defined without modifying core logic. This same pattern powers production systems with dozens of specialists handling retrieval, reasoning, execution, and monitoring, each excelling in its domain while the coordinator ensures seamless collaboration. Why This Matters The transition from text-parsing to native function calling enables a fundamentally different approach to building AI applications. With text parsing, you're constantly fighting against the unpredictability of natural language output. A model might decide to explain why it's calling a function before outputting the JSON, or it might format the JSON slightly differently than your regex expects, or it might wrap it in markdown code fences. Native function calling eliminates this entire class of problems. The model is trained to output tool calls as structured data, separate from its conversational responses. The multi-agent aspect builds on this foundation. Because function calling is reliable, you can confidently delegate to specialist agents knowing they'll integrate smoothly with the orchestrator. You can chain tool calls—the orchestrator might generate a quiz, then immediately launch the interface to take it, based on a single user request like "Create and give me a quiz about machine learning." The model handles this orchestration intelligently because the tool results flow back as structured data it can reason about. Running everything locally through Foundry Local adds another dimension of value and I am genuinely excited about this (hopefully, the phi models get this functionality soon). You can experiment freely, iterate quickly, and deploy solutions that run entirely on your infrastructure. For educational applications like our quiz system, this means students can interact with the AI tutor as much as they need without cost concerns. Getting Started With Your Own Multi-Agent System The complete code for this quiz application is available in the GitHub repository, and I encourage you to clone it and experiment. Try modifying the tool schemas to see how the orchestrator's behavior changes. Add a new specialist agent for a different task. Adjust the system prompts to see how agent personalities and capabilities shift. Think about the problems you're trying to solve. Could they benefit from having different specialists handling different aspects? A customer service system might have agents for order lookup, refund processing, and product recommendations. A research assistant might have agents for web search, document summarization, and citation formatting. A coding assistant might have agents for code generation, testing, and documentation. Start small, perhaps with two or three specialist agents for a specific domain. Watch how the orchestrator learns to route between them based on the tool descriptions you provide. You'll quickly see opportunities to add more specialists, refine the existing ones, and build increasingly sophisticated systems that leverage the unique strengths of each agent while presenting a unified, intelligent interface to your users. In the next entry, we will be deploying our quizz app which will mark the end of our journey in Foundry and SLMs these past few weeks. I hope you are as excited as I am! Thanks for reading.Function Calling with Small Language Models
In our previous article on running Phi-4 locally, we built a web-enhanced assistant that could search the internet and provide informed answers. Here's what that implementation looked like: def web_enhanced_query(question): # 1. ALWAYS search (hardcoded decision) search_results = search_web(question) # 2. Inject results into prompt prompt = f"""Here are recent search results: {search_results} Question: {question} Using only the information above, give a clear answer.""" # 3. Model just summarizes what it reads return ask_phi4(endpoint, model_id, prompt) Today, we're upgrading to true function calling. With this, we have ability to transform small language models from passive text generators into intelligent agents that can: Decide when to use external tools Reason which tool bests fit each task Execute real-world actions thrugh apis Function calling represents a significant evolution in AI capabilities. Let's understand where this positions our small language models: Agent Classification Framework Simple Reflex Agents (Basic) React to immediate input with predefined rules Example: Thermostat, basic chatbot Without function calling, models operate here Model-Based Agents (Intermediate) Maintain internal state and context Example: Robot vacuum with room mapping Function calling enables this level Goal-Based Agents (Advanced) Plan multi-step sequences to achieve objectives Example: Route planner, task scheduler Function calling + reasoning enables this Learning Agents (Expert) Adapt and improve over time Example: Recommendation systems Future: Function calling + fine-tuning As usual with these articles, let's get ready to get our hands dirty! Project Setup Let's set up our environment for building function-calling assistants. Prerequisites First, ensure you have Foundry Local installed and a model running. We'll use Qwen 2.5-7B for this tutorial as it has excellent function calling support. Important: Not all small language models support function calling equally. Qwen 2.5 was specifically trained for this capability and provides a reliable experience through Foundry Local. # 1. Check Foundry Local is installed foundry --version # 2. Start the Foundry Local service foundry service start # 3. Download and run Qwen 2.5-7B foundry model run qwen2.5-7b Python Environment Setup # 1. Create Python virtual environment python -m venv venv source venv/bin/activate # Windows: venv\Scripts\activate # 2. Install dependencies pip install openai requests python-dotenv # 3. Get a free OpenWeatherMap API key # Sign up at: https://openweathermap.org/api ``` Create `.env` file: ``` OPENWEATHER_API_KEY=your_api_key_here ``` Building a Weather-Aware Assistant So in this scenario, a user wants to plan outdoor activities but needs weather context. Without function calling, You will get something like this: User: "Should I schedule my team lunch outside at 2pm in Birmingham?" Model: "That depends on weather conditions. Please check the forecast for rain and temperature." However, with fucntion-calling you get an answer that is able to look up the weather and reply with the needed context. We will do that now. Understanding Foundry Local's Function Calling Implementation Before we start coding, there's an important implementation detail to understand. Foundry Local uses a non-standard function calling format. Instead of returning function calls in the standard OpenAI tool_calls field, Qwen models return the function call as JSON text in the response content. For example, when you ask about weather, instead of: # Standard OpenAI format message.tool_calls = [ {"name": "get_weather", "arguments": {"location": "Birmingham"}} ] You get: # Foundry Local format message.content = '{"name": "get_weather", "arguments": {"location": "Birmingham"}}' This means we need to parse the JSON from the content ourselves. Don't worry—this is straightforward, and I'll show you exactly how to handle it! Step 1: Define the Weather Tool Create weather_assistant.py: import os from openai import OpenAI import requests import json import re from dotenv import load_dotenv load_dotenv() # Initialize Foundry Local client client = OpenAI( base_url="http://127.0.0.1:59752/v1/", api_key="not-needed" ) # Define weather tool tools = [ { "type": "function", "function": { "name": "get_weather", "description": "Get current weather information for a location", "parameters": { "type": "object", "properties": { "location": { "type": "string", "description": "The city or location name" }, "units": { "type": "string", "description": "Temperature units", "enum": ["celsius", "fahrenheit"], "default": "celsius" } }, "required": ["location"] } } } ] A tool is necessary because it provides the model with a structured specification of what external functions are available and how to use them. The tool definition contains the function name, description, parameters schema, and information returned. Step 2: Implement the Weather Function def get_weather(location: str, units: str = "celsius") -> dict: """Fetch weather data from OpenWeatherMap API""" api_key = os.getenv("OPENWEATHER_API_KEY") url = "http://api.openweathermap.org/data/2.5/weather" params = { "q": location, "appid": api_key, "units": "metric" if units == "celsius" else "imperial" } response = requests.get(url, params=params, timeout=5) response.raise_for_status() data = response.json() temp_unit = "°C" if units == "celsius" else "°F" return { "location": data["name"], "temperature": f"{round(data['main']['temp'])}{temp_unit}", "feels_like": f"{round(data['main']['feels_like'])}{temp_unit}", "conditions": data["weather"][0]["description"], "humidity": f"{data['main']['humidity']}%", "wind_speed": f"{round(data['wind']['speed'] * 3.6)} km/h" } The model calls this function to get the weather data. it contacts OpenWeatherMap API, gets real weather data and returns it as a python dictionary Step 3: Parse Function Calls from Content This is the crucial step where we handle Foundry Local's non-standard format: def parse_function_call(content: str): """Extract function call JSON from model response""" if not content: return None json_pattern = r'\{"name":\s*"get_weather",\s*"arguments":\s*\{[^}]+\}\}' match = re.search(json_pattern, content) if match: try: return json.loads(match.group()) except json.JSONDecodeError: pass try: parsed = json.loads(content.strip()) if isinstance(parsed, dict) and "name" in parsed: return parsed except json.JSONDecodeError: pass return None Step 4: Main Chat Function with Function Calling and lastly, calling the model. Notice the tools and tool_choice parameter. Tools tells the model it is allowed to output a tool_call requesting that the function be executed. While tool_choice instructs the model how to decide whether to call a tool. def chat(user_message: str) -> str: """Process user message with function calling support""" messages = [ {"role": "user", "content": user_message} ] response = client.chat.completions.create( model="qwen2.5-7b-instruct-generic-cpu:4", messages=messages, tools=tools, tool_choice="auto", temperature=0.3, max_tokens=500 ) message = response.choices[0].message if message.content: function_call = parse_function_call(message.content) if function_call and function_call.get("name") == "get_weather": print(f"\n[Function Call] {function_call.get('name')}({function_call.get('arguments')})") args = function_call.get("arguments", {}) weather_data = get_weather(**args) print(f"[Result] {weather_data}\n") final_prompt = f"""User asked: "{user_message}" Weather data: {json.dumps(weather_data, indent=2)} Provide a natural response based on this weather information.""" final_response = client.chat.completions.create( model="qwen2.5-7b-instruct-generic-cpu:4", messages=[{"role": "user", "content": final_prompt}], max_tokens=200, temperature=0.7 ) return final_response.choices[0].message.content return message.content Step 5: Run the script Now put all the above together and run the script def main(): """Interactive weather assistant""" print("\nWeather Assistant") print("=" * 50) print("Ask about weather or general questions.") print("Type 'exit' to quit\n") while True: user_input = input("You: ").strip() if user_input.lower() in ['exit', 'quit']: print("\nGoodbye!") break if user_input: response = chat(user_input) print(f"Assistant: {response}\n") if __name__ == "__main__": if not os.getenv("OPENWEATHER_API_KEY"): print("Error: OPENWEATHER_API_KEY not set") print("Set it with: export OPENWEATHER_API_KEY='your_key_here'") exit(1) main() Note: Make sure Qwen 2.5 is running in Foundry Local in a new terminal Now let's talk about Model Context Protocol! Our weather assistant works beautifully with a single function, but what happens when you need dozens of tools? Database queries, file operations, calendar integration, email—each would require similar setup code. This is where Model Context Protocol (MCP) comes in. MCP is an open standard that provides pre-built, standardized servers for common tools. Instead of writing custom integration code for every capability, you can connect to MCP servers that handle the complexity for you. With MCP, You only need one command to enable weather, database, and file access npx @modelcontextprotocol/server-weather npx @modelcontextprotocol/server-sqlite npx @modelcontextprotocol/server-filesystem Your model automatically discovers and uses these tools without custom integration code. Learn more: Model Context Protocol Documentation EdgeAI Course - Module 03: MCP Integration Key Takeaways Function calling transforms models into agents - From passive text generators to active problem-solvers Qwen 2.5 has excellent function calling support - Specifically trained for reliable tool use Foundry Local uses non-standard format - Parse JSON from content instead of tool_calls field Start simple, then scale with MCP - Build one tool to understand the pattern, then leverage standards Documentation Running Phi-4 Locally with Foundry Local Phi-4: Small Language Models That Pack a Punch Microsoft Foundry Local GitHub EdgeAI for Beginners Course OpenWeatherMap API Documentation Model Context Protocol Qwen 2.5 Documentation Thank you for reading! I hope this article helps you build more capable AI agents with small language models. Function calling opens up incredible possibilities—from simple weather assistants to complex multi-tool workflows. Start with one tool, understand the pattern, and scale from there.Running Phi-4 Locally with Microsoft Foundry Local: A Step-by-Step Guide
In our previous post, we explored how Phi-4 represents a new frontier in AI efficiency that delivers performance comparable to models 5x its size while being small enough to run on your laptop. Today, we're taking the next step: getting Phi-4 up and running locally on your machine using Microsoft Foundry Local. Whether you're a developer building AI-powered applications, an educator exploring AI capabilities, or simply curious about running state-of-the-art models without relying on cloud APIs, this guide will walk you through the entire process. Microsoft Foundry Local brings the power of Azure AI Foundry to your local device without requiring an Azure subscription, making local AI development more accessible than ever. So why do you want to run Phi-4 Locally? Before we dive into the setup, let's quickly recap why running models locally matters: Privacy and Control: Your data never leaves your machine. This is crucial for sensitive applications in healthcare, finance, or education where data privacy is paramount. Cost Efficiency: No API costs, no rate limits. Once you have the model downloaded, inference is completely free. Speed and Reliability: No network latency or dependency on external services. Your AI applications work even when you're offline. Learning and Experimentation: Full control over model parameters, prompts, and fine-tuning opportunities without restrictions. With Phi-4's compact size, these benefits are now accessible to anyone with a modern laptop—no expensive GPU required. What You'll Need Before we begin, make sure you have: Operating System: Windows 10/11, macOS (Intel or Apple Silicon), or Linux RAM: Minimum 16GB (32GB recommended for optimal performance) Storage: At least 5 - 10GB of free disk space Processor: Any modern CPU (GPU optional but provides faster inference) Note: Phi-4 works remarkably well even on consumer hardware 😀. Step 1: Installing Microsoft Foundry Local Microsoft Foundry Local is designed to make running AI models locally as simple as possible. It handles model downloads, manages memory efficiently, provides OpenAI-compatible APIs, and automatically optimizes for your hardware. For Windows Users: Open PowerShell or Command Prompt and run: winget install Microsoft.FoundryLocal For macOS Users (Apple Silicon): Open Terminal and run: brew install microsoft/foundrylocal/foundrylocal Verify Installation: Open your terminal and type. This should return the Microsoft Foundry Local version, confirming installation: foundry --version Step 2: Downloading Phi-4-Mini For this tutorial, we'll use Phi-4-mini, the lightweight 3.8 billion parameter version that's perfect for learning and experimentation. Open your terminal and run: foundry model run phi-4-mini You should see your download begin and something similar to the image below Available Phi Models on Foundry Local While we're using phi-4-mini for this guide, Foundry Local offers several Phi model variants and other open-source models optimized for different hardware and use cases: Model Hardware Type Size Best For phi-4-mini GPU chat-completion 3.72 GB Learning, fast responses, resource-constrained environments with GPU phi-4-mini CPU chat-completion 4.80 GB Learning, fast responses, CPU-only systems phi-4-mini-reasoning GPU chat-completion 3.15 GB Reasoning tasks with GPU acceleration phi-4-mini-reasoning CPU chat-completion 4.52 GB Mathematical proofs, logic puzzles with lower resource requirements phi-4 GPU chat-completion 8.37 GB Maximum reasoning performance, complex tasks with GPU phi-4 CPU chat-completion 10.16 GB Maximum reasoning performance, CPU-only systems phi-3.5-mini GPU chat-completion 2.16 GB Most lightweight option with GPU support phi-3.5-mini CPU chat-completion 2.53 GB Most lightweight option, CPU-optimized phi-3-mini-128k GPU chat-completion 2.13 GB Extended context (128k tokens), GPU-optimized phi-3-mini-128k CPU chat-completion 2.54 GB Extended context (128k tokens), CPU-optimized phi-3-mini-4k GPU chat-completion 2.13 GB Standard context (4k tokens), GPU-optimized phi-3-mini-4k CPU chat-completion 2.53 GB Standard context (4k tokens), CPU-optimized Note: Foundry Local automatically selects the best variant for your hardware. If you have an NVIDIA GPU, it will use the GPU-optimized version. Otherwise, it will use the CPU-optimized version. run the command below to see full list of models foundry model list Step 3: Test It Out Once the download completes, an interactive session will begin. Let's test Phi-4-mini's capabilities with a few different prompts: Example 1: Explanation Phi-4-mini provides a thorough, well-structured explanation! It starts with the basic definition, explains the process in biological systems, gives real-world examples (plant cells, human blood cells). The response is detailed yet accessible. Example 2: Mathematical Problem Solving Excellent step-by-step solution! Phi-4-mini breaks down the problem methodically: 1. Distributes on the left side 2. Isolates the variable terms 3. Simplifies progressively 4. Arrives at the final answer: x = 11 The model shows its work clearly, making it easy to follow the logic and ideal for educational purposes Example 3: Code Generation The model provides a concise Python function using string slicing ([::-1]) - the most Pythonic approach to reversing a string. It includes clear documentation with a docstring explaining the function's purpose, provides example usage demonstrating the output, and even explains how the slicing notation works under the hood. The response shows that the model understands not just how to write the code, but why this approach is preferred - noting that the [::-1] slice notation means "start at the end of the string and end at position 0, move with the step -1, negative one, which means one step backwards." This showcases the model's ability to generate production-ready code with proper documentation while being educational about Python idioms. To exit the interactive session, type `/bye` Step 4: Extending Phi-4 with Real-Time Tools Understanding Phi-4's Knowledge Cutoff Like all language models, Phi-4 has a knowledge cutoff date from its training data (typically several months old). This means it won't know about very recent events, current prices, or breaking news. For example, if you ask "Who won the 2024 NBA championship?" it might not have the answer. The good thing is, there's a powerful work-around. While Phi-4 is incredibly capable, connecting it to external tools like web search, databases, or APIs transforms it from a static knowledge base into a dynamic reasoning engine. This is where Microsoft Foundry's REST API comes in. Microsoft Foundry provides a simple API that lets you integrate Phi-4 into Python applications and connect it to real-time data sources. Here's a practical example: building a web-enhanced AI assistant. Web-Enhanced AI Assistant This simple application combines Phi-4's reasoning with real-time web search, allowing it to answer current questions accurately. Prerequisites: pip install foundry-local-sdk requests ddgs Create phi4_web_assistant.py: import requests from foundry_local import FoundryLocalManager from ddgs import DDGS import json def search_web(query): """Search the web and return top results""" try: results = list(DDGS().text(query, max_results=3)) if not results: return "No search results found." search_summary = "\n\n".join([ f"[Source {i+1}] {r['title']}\n{r['body'][:500]}" for i, r in enumerate(results) ]) return search_summary except Exception as e: return f"Search failed: {e}" def ask_phi4(endpoint, model_id, prompt): """Send a prompt to Phi-4 and stream response""" response = requests.post( f"{endpoint}/chat/completions", json={ "model": model_id, "messages": [{"role": "user", "content": prompt}], "stream": True }, stream=True, timeout=180 ) full_response = "" for line in response.iter_lines(): if line: line_text = line.decode('utf-8') if line_text.startswith('data: '): line_text = line_text[6:] # Remove 'data: ' prefix if line_text.strip() == '[DONE]': break try: data = json.loads(line_text) if 'choices' in data and len(data['choices']) > 0: delta = data['choices'][0].get('delta', {}) if 'content' in delta: chunk = delta['content'] print(chunk, end="", flush=True) full_response += chunk except json.JSONDecodeError: continue print() return full_response def web_enhanced_query(question): """Combine web search with Phi-4 reasoning""" # By using an alias, the most suitable model will be downloaded # to your device automatically alias = "phi-4-mini" # Create a FoundryLocalManager instance. This will start the Foundry # Local service if it is not already running and load the specified model. manager = FoundryLocalManager(alias) model_info = manager.get_model_info(alias) print("🔍 Searching the web...\n") search_results = search_web(question) prompt = f"""Here are recent search results: {search_results} Question: {question} Using only the information above, give a clear answer with specific details.""" print("🤖 Phi-4 Answer:\n") return ask_phi4(manager.endpoint, model_info.id, prompt) if __name__ == "__main__": # Try different questions question = "Who won the 2024 NBA championship?" # question = "What is the latest iPhone model released in 2024?" # question = "What is the current price of Bitcoin?" print(f"Question: {question}\n") print("=" * 60 + "\n") web_enhanced_query(question) print("\n" + "=" * 60) Run It: python phi4_web_assistant.py What Makes This Powerful By connecting Phi-4 to external tools, you create an intelligent system that: Accesses Real-Time Information: Get news, weather, sports scores, and breaking developments Verifies Facts: Cross-reference information with multiple sources Extends Capabilities: Connect to databases, APIs, file systems, or any other tool Enables Complex Applications: Build research assistants, customer support bots, educational tutors, and personal assistants This same pattern can be applied to connect Phi-4 to: Databases: Query your company's internal data APIs: Weather services, stock prices, translation services File Systems: Analyze documents and spreadsheets IoT Devices: Control smart home systems The possibilities are endless when you combine local AI reasoning with real-world data access. Troubleshooting Common Issues Service not running: Make sure Foundry Local is properly installed and the service is running. Try restarting with foundry --version to verify installation. Model downloads slowly: Check your internet connection and ensure you have enough disk space (5-10GB per model). Out of memory: Close other applications or try using a smaller model variant like phi-3.5-mini instead of the full phi-4. Connection issues: Verify that no other services are using the same ports. Foundry Local typically runs on http://localhost:5272. Model not found: Run foundry model list to see available models, then use foundry model run <model-name> to download and run a specific model. Your Next Steps with Foundry Local Congratulations! You now have Phi-4 running locally through Microsoft Foundry Local and understand how to extend it with external tools like web search. This combination of local AI reasoning with real-time data access opens up countless possibilities for building intelligent applications. Coming in Future Posts In the coming weeks, we'll explore advanced topics using Hugging Face: Fine-tuning Phi models on your own data for domain-specific applications Phi-4-multimodal: Analyze images, process audio, and combine multiple data types Advanced deployment patterns: RAG systems and multi-agent orchestration Resources to Explore EdgeAI for Beginners Course: Comprehensive 36-45 hour course covering Edge AI fundamentals, optimization, and production deployment Phi-4 Technical Report: Deep dive into architecture and benchmarks Phi Cookbook on GitHub: Practical examples and recipes Foundry Local Documentation: Complete technical documentation and API reference Module 08: Foundry Local Toolkit: 10 comprehensive samples including RAG applications and multi-agent systems Keep experimenting with Foundry Local, and stay tuned as we unlock the full potential of Edge AI! What will you build with Phi-4? Share your ideas and projects in the comments below!Phi-4: Small Language Models That Pack a Punch
What Are Small Language Models, and Why Should You Care? If you've been following AI development, you can probably recall "bigger is better" being the mantra for years. GPT-3.5 was 175 billion parameters, GPT-4 is even larger, and everyone seemed to be in an arms race to build the biggest model possible. But here's the thing: bigger models are expensive to run, slow to respond, and often overkill for what you actually need. Small Language Models (SLMs) flip this script. These are models with fewer parameters (typically 1-15 billion) that are trained really thoughtfully on high-quality data. The outcome of this is models that can run on your laptop, respond instantly, and still handle complex reasoning tasks. You can extrapolate from this, increased speed, privacy, and cost-effectiveness. Microsoft's been exploring this space for a while. It started with Phi-1, which showed that small models trained on carefully curated "textbook-like" data could punch way above their weight class. Then came Phi-2 and Phi-3, each iteration getting better at reasoning and problem-solving. Now we have Phi-4, and it's honestly impressive. At 14 billion parameters, it outperforms models that are 5 times its size on math and reasoning tasks. Microsoft trained it on 9.8 trillion tokens over three weeks, using a mix of synthetic data (generated by larger models like GPT-4o) and high-quality web content. The key innovation isn't just throwing more data at it but they were incredibly selective about what to include, focusing on teaching reasoning patterns rather than memorizing facts. The Phi family has also expanded recently. There's Phi-4-mini at 3.8 billion parameters for even lighter deployments, and Phi-4-multimodal at 5.6 billion parameters that can handle text, images, and audio all at once. Pretty cool if you're building something that needs to understand screenshots or transcribe audio. How Well Does It Actually Perform? Let's talk numbers, because that's where Phi-4 really shines. On MMLU (a broad test of knowledge across 57 subjects), Phi-4 scores 84.8%. That's better than Phi-3's 77.9% and competitive with models like GPT-4o-mini. On MATH (competition-level math problems), it hits 56.1%, which is significantly higher than Phi-3's 42.5%. For code generation on HumanEval, it achieves 82.6%. Model Parameters MMLU MATH HumanEval Phi-3-medium 14B 77.9% 42.5% 62.5% Phi-4 14B 84.8% 56.1% 82.6% Llama 3.3 70B 86.0% ~51% ~73% GPT-4o-mini Unknown ~82% 52.2% 87.2% Microsoft tested Phi-4 on the November 2024 AMC-10 and AMC-12 math competitions. These are tests that over 150,000 high school students take each year, and the questions appeared after all of Phi-4's training data was collected. Phi-4 beat not just similar-sized models, but also much larger ones. That suggests it's actually learned to reason, not just memorize benchmark answers. The model also does well on GPQA (graduate-level science questions) and even outperforms its teacher model GPT-4o on certain reasoning tasks. That's pretty remarkable for a 14 billion parameter model. If you're wondering about practical performance, Phi-4 runs about 2-4x faster than comparable larger models and uses significantly less memory. You can run it on a single GPU or even on newer AI-capable laptops with NPUs. That makes it practical for real-time applications where latency matters. Try Phi-4 Yourself You can start experimenting with Phi-4 right now without any complicated setup. Azure AI Foundry Microsoft's Azure AI Foundry is probably the quickest way to get started. Once you're logged in: Go to the Model Catalog and search for "Phi-4" Click "Use this Model" Select an active subscription in the subsequent pop-up and confirm Deploy and start chatting or testing prompts The playground lets you adjust parameters like temperature and see how the model responds. You can test it on math problems, coding questions, or reasoning tasks without writing any code. There's also a code view that shows you how to integrate it into your own applications. Hugging Face (for open-source enthusiasts) If you prefer to work with open-source tools, the model weights are available on Hugging Face. You can run it locally or use their hosted inference API: # Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="microsoft/phi-4") messages = [ {"role": "user", "content": "What's the derivative of x²?"}, ] pipe(messages) Other Options The Phi Cookbook on GitHub has tons of examples for different use cases like RAG (retrieval-augmented generation), function calling, and multimodal inputs. If you want to run it locally with minimal setup, you can use Ollama (ollama pull phi-4) or LM Studio, which provides a nice GUI. The Azure AI Foundry Labs also has experimental features where you can test Phi-4-multimodal with audio and image inputs. What's Next? Phi-4 is surprisingly capable for its size, and it's practical enough to run almost anywhere. Whether you're building a chatbot, working on educational software, or just experimenting with AI, it's worth checking out. We might explore local deployment in more detail later, including how to build multi-agent systems where several SLMs work together, and maybe even look at fine-tuning Phi-4 for specific tasks. But for now, give it a try and see what you can build with it. The model weights are MIT licensed, so you're free to use them commercially. Microsoft's made it pretty easy to get started, so there's really no reason not to experiment. Resources: Azure AI Foundry Phi-4 on Hugging Face Phi Cookbook Phi-4 Technical ReportBringing AI to the edge: Hackathon Windows ML
AI Developer Hackathon Windows ML Hosted by Qualcomm on SnapDragonX We’re excited to announce our support and participation for the upcoming global series of Edge AI hackathons, hosted by Qualcomm Technologies. The first is on June 14-15 in Bangalore. We see a world of hybrid AI, developing rapidly as new generation of intelligent applications get built for diverse scenarios. These range from mobile, desktop, spatial computing and extending all the way to industrial and automotive. Mission critical workloads oscillate between decision-making in the moment, on device, to fine tuning models on the cloud. We believe we are in the early stages of development of agentic applications that efficiently run on the edge for scenarios needing local deployment and on-device inferencing. Microsoft Windows ML Windows ML – a cutting-edge runtime optimized for performant on-device model inference and simplified deployment, and the foundation of Windows AI Foundry. Windows ML is designed to support developers creating AI-infused applications with ease, harnessing the incredible strength of Windows’ diverse hardware ecosystem whether it’s for entry-level laptops, Copilot+ PCs or top-of-the-line AI workstations. It’s built to help developers leverage the client silicon best suited for their specific workload on any given device whether it’s an NPU for low-power and sustained inference, a GPU for raw horsepower or CPU for the broadest footprint and flexibility. Introducing Windows ML: The future of machine learning development on Windows - Windows Developer Blog Getting Started To get started, install AI Toolkit, leverage one of our conversion and optimization templates, or start building your own. Explore documentation and code samples available on Microsoft Learn, check out AI Dev Gallery (install, documentation) for demos and more samples to help you get started with Windows ML. Microsoft and Qualcomm Technologies: A strong collaboration Microsoft and Qualcomm Technologies’ collaboration bring new advanced AI features into Copilot+ PCs, leveraging the Snapdragon X Elite. Microsoft Research has played a pivotal role by optimizing new lightweight LLMs, such as Phi Silica, specifically for on-device execution with the Hexagon NPU. These models are designed to run efficiently on Hexagon NPUs, enabling multimodal AI experiences like vision-language tasks directly on Copilot+ PCs without relying on the cloud. Additionally, Microsoft has made DeepSeek R1 7B and 14B distilled models available via Azure AI Foundry, further expanding the AI ecosystem on the edge. This collaboration marks a significant step in democratizing AI by making powerful, efficient models accessible on everyday devices Windows AI Foundry expands AI capabilities by providing high-performance built-in models and supports developers' custom models with silicon performance. This developer platform plays a key role in this collaboration. Windows ML enables Windows 11 and Copilot+ PCs to use the Hexagon NPU for power efficient inference. Scaling optimization through Olive toolchain The Windows ML foundation of the Windows AI Foundry provides a unified platform for AI development across various hardware architectures and brings silicon performance using QNN Execution provider. This stack includes Windows ML and toolchains like Olive, easily accessible in AI Toolkit for VS Code, which streamlines model optimization and deployment. Qualcomm Technologies has contributed to Microsoft’s Olive, an open-source model optimization tool that enhances AI performance by optimizing models for efficient inference on client systems. This tool is particularly beneficial for running LLMs and GenAI workloads on Qualcomm Technologies’ platforms. Real-World Applications Through Qualcomm Technologies and Microsoft’s collaboration we have partnered with top developers to adopt Windows ML and have demonstrated impressive performance for their AI features. Independent Solution Vendors (ISVs) such as Powder, Topaz Labs, Camo and McAfee, Join us at the Hackathon With the recent launch of Qualcomm Snapdragon® X Elite-powered Windows laptops, developers can now take advantage of powerful NPUs (Neural Processing Units) to deploy AI applications that are both responsive and energy-efficient. These new devices open up a world of opportunities for developers to rethink how applications are built from productivity tools to creative assistants and intelligent agents all running directly on the device. Our mission has always been to enable high-quality AI experiences using compact, optimized models. These models are tailor-made for edge computing, offering faster inference, lower memory usage, and enhanced privacy without compromising performance. We encourage all application developers whether you’re building with open-source SLMs (small language models), working on smart assistants, or exploring new on-device AI use cases to join us at the event. You can register here: https://www.qualcomm.com/support/contact/forms/edge-ai-developer-hackathon-bengaluru-proposal-submission Dive deeper into these innovative developer solutions: Windows AI Foundry & Windows ML on Qualcomm NPU Microsoft and Qualcomm Technologies collaborate on Windows 11, Copilot+ PCs and Windows AI Foundry | Qualcomm Unlocking the power of Qualcomm QNN Execution Provider GPU backen Introducing Windows ML: The future of machine learning development on Windows - Windows Developer BlogShowcasing Phi-4-Reasoning: A Game-Changer for AI Developers
Showcasing Phi-4-Reasoning: A Game-Changer for AI Developers Introduction Phi-4-Reasoning is a state-of-the-art AI model developed by Microsoft Research, designed to excel in complex reasoning tasks. With its advanced capabilities, Phi-4-Reasoning is a powerful tool for AI developers, enabling them to tackle intricate problems with ease and precision. What is Phi-4-Reasoning? Phi-4-Reasoning is a 14-billion parameter open-weight reasoning model that has been fine-tuned from the Phi-4 model using supervised fine-tuning on a dataset of chain-of-thought traces.. We are also releasing Phi-4-reasoning-plus, a variant enhanced through a short phase of outcome-based reinforcement learning that offers higher performance by generating longer reasoning traces. This model is designed to handle complex reasoning tasks, including mathematical problems, scientific queries, and coding challenges Why Phi-4-reasoning and Phi-4-reasoning-plus Excels Advanced Reasoning Capabilities: Phi-4-Reasoning is trained to generate detailed reasoning chains, making it highly effective in solving complex problems. It leverages additional inference-time compute to enhance its reasoning abilities High-Quality Data Curation: The model's training involved meticulous data curation and the use of high-quality synthetic datasets, allowing it to compete with much larger models Performance: Despite its smaller size, Phi-4-Reasoning outperforms larger models like OpenAI's o1-mini and DeepSeek-R1-Distill-Llama-70B on various benchmarks, including mathematical reasoning and PhD-level science questions Industry Applications: Phi-4-Reasoning is versatile and can be deployed in various industry scenarios, including medicine, where it can be used for reasoning tasks on edge devices Real-World Examples Wordplay Riddle: Phi-4-Reasoning can solve wordplay riddles by recognizing patterns and applying logical reasoning. For example, it deduced that collecting three strawberries would yield 9 r's because the word "strawberry" contains three r's Example 1: How many strawberries for 9 r’s? User: How many strawberries do I need to collect 9 r’s? Phi-4-Reasoning: <think> TRUNCATED </think> It’s a wordplay riddle! Notice that the word “strawberry” has three r’s in it. So if you “collect” three strawberries, you get 3 Å~ 3 = 9 r’s. Thus, you need 3 strawberries. Solving a Riddle: The model can decrypt complex riddles by identifying patterns and performing arithmetic operations. It demonstrated this capability by solving a riddle involving foreign language number-words and reversed number-words. What This Problem Proves: Pattern Recognition: Phi-4-Reasoning demonstrates its ability to identify patterns in words and apply logical reasoning to solve the riddle. Wordplay Understanding: The model showcases its proficiency in understanding and solving wordplay riddles, which require a combination of linguistic knowledge and logical deduction. Efficiency: Phi-4-Reasoning quickly arrives at the correct solution by applying a straightforward multiplication operation, highlighting its efficiency in solving such problems. Example 2: Solving a Riddle User: I will give you a riddle to solve with a few examples, and something to complete at the end What is a likely completion for X that is consistent the with examples above? Phi-4-Reasoning: <think> TRUNCATED </think> We can “decrypt” the riddle by noticing that each line has five parts. In every example the parts are: A “number-word” in a foreign language (or with an extra minus sign), A “first name” (of any nationality), A “reversed number-word” (or two, joined by a hyphen), A “second name”, and A final number. When you “reverse” the third word you get a familiar numberin English: In line 1 “evif” is “five” (5) and the first number is “uno” = 1, and 5 – 1 = 4. In line 2 “neves” is “seven” (7) and “tres” = 3, and 7 – 3 = 4. In line 3 “evlewt” is “twelve” (12) and “drei” = 3, and 12 – 3 = 9. In lines 4 and 5 with two reversed “number-words”: – Line 4: “xis” →“six” (6) and “ytnewt” →“twelve” (12); 6 + 12 = 18, plus 3 = 21. – Line 5: “eerht” → “three” (3) and “ytnewt” → “twelve” (12); 3 + 12 = 15, plus 3 = 18. Now look at the final line: “minus one-point-two Satya eno Bill X” It follows the same five–part format. Notice that “eno” reversed is “one” (1). And the “first number” is “minus onepoint-two” (–1.2). Since for a one–number–word line the rule is: final number = (number from reversed word)−(first number) we compute: final = 1 − (−1.2) = 1 + 1.2 = 2.2 Thus, a likely completion for X is 2.2. Phi-4-Reasoning: Phi-4-Reasoning decrypts the riddle by identifying a pattern in the examples provided. Each line consists of five parts: a number-word in a foreign language, a first name, a reversed number-word, a second name, and a final number. By reversing the third word and performing arithmetic operations, Phi-4-Reasoning determines that the likely completion for X is 2.2 What This Problem Proves: Complex Pattern Recognition: Phi-4-Reasoning excels in recognizing complex patterns involving multiple elements, such as foreign language number-words and reversed number-words. Logical Deduction: The model demonstrates its ability to apply logical deduction to solve the riddle by performing arithmetic operations based on the identified patterns. Versatility: Phi-4-Reasoning showcases its versatility in handling diverse types of riddles and problems, making it a valuable tool for AI developers. Example 3. solve complex graph traversal tasks, such as finding a path through a maze. The maze is represented as an adjacency list, which is a common way to describe graphs in computer science. Each node in the graph (or maze) is connected to other nodes, and the task is to find a valid path from the starting node (node 0) to the destination node Example 3: Solving a maze User: Please solve the maze provided in adjacency list form below, by outputting a valid path from node 0 to node {destination}, in a space-separated list of integers. Adjacency list: {depicted as an image below} Phi-4-Reasoning: <think> TRUNCATED </think> {path depicted as an image below} What This Problem Proves: Graph Traversal Capability: Phi-4-Reasoning can effectively navigate through graphs using algorithms like Depth-First Search (DFS) or Breadth-First Search (BFS). This capability is crucial for solving problems that involve finding paths, cycles, or connectivity in graphs. Logical Reasoning: The model demonstrates its ability to apply logical reasoning to determine the correct sequence of nodes to traverse from the start to the destination. This involves understanding the structure of the graph and making decisions based on the connections between nodes. Pattern Recognition: Phi-4-Reasoning can recognize patterns in the adjacency list and use them to find a solution. This is important for tasks that require identifying and following specific paths or routes. Versatility: The ability to solve a maze using an adjacency list showcases the model's versatility in handling different types of data structures and problem-solving scenarios. This is beneficial for AI developers who need to work with various data representations and algorithms. Efficiency: The model's ability to quickly and accurately find a valid path through the maze highlights its efficiency in solving complex problems. This is valuable for applications that require fast and reliable solutions. Conclusion: Phi-4-Reasoning's ability to solve a maze using an adjacency list demonstrates its advanced reasoning capabilities, making it a powerful tool for AI developers. Its proficiency in graph traversal, logical reasoning, pattern recognition, versatility, and efficiency makes it well-suited for tackling a wide range of complex problems. Deployment and Integration Phi-4-Reasoning can be deployed on various platforms, including Azure AI Foundry and Hugging Face. It supports quantization using tools like Microsoft Olive, making it suitable for deployment on edge devices such as IoT, laptops, and mobile devices. Phi-4-Reasoning is a groundbreaking AI model that offers advanced reasoning capabilities, high performance, and versatility. Its ability to handle complex reasoning tasks makes it an invaluable tool for AI developers, enabling them to create innovative solutions across various industries. References Make Phi-4-mini-reasoning more powerful with industry reasoning on edge devices | Microsoft Community Hub Phi-4 Reasoning Technical Paper Phi-4-Mini-Reasoning Technical Paper One year of Phi: Small language models making big leaps in AI | Microsoft Azure Blog PhiCookBook Access Phi-4-reasoning models Phi Models at Azure AI Foundry Models Phi Models on Hugging Face Phi Models on GitHub Marketplace ModelsAI Sparks: Unleashing Agents with the AI Toolkit
The final episode of our "AI Sparks" series delved deep into the exciting world of AI Agents and their practical implementation. We also covered a fair part of MCP with Microsoft AI Toolkit extension for VS Code. We kicked off by charting the evolutionary path of intelligent conversational systems. Starting with the rudimentary rule-based Basic Chatbots, we then explored the advancements brought by Basic Generative AI Chatbots, which offered contextually aware interactions. Then we explored the Retrieval-Augmented Generation (RAG), highlighting its ability to ground generative models in specific knowledge bases, significantly enhancing accuracy and relevance. The limitations were also discussed for the above mentioned techniques. The session was then centralized to the theme – Agents and Agentic Frameworks. We uncovered the fundamental shift from basic chatbots to autonomous agents capable of planning, decision-making, and executing tasks. We moved forward with detailed discussion on the distinction between Single Agentic systems, where one core agent orchestrates the process, and Multi-Agent Architectures, where multiple specialized agents collaborate to achieve complex goals. A key part of building robust and reliable AI Agents, as we discussed, revolves around carefully considering four critical factors. Firstly, Knowledge-Providing agents with the right context is paramount for them to operate effectively and make informed decisions. Secondly, equipping agents with the necessary Actions by granting them access to the appropriate tools allows them to execute tasks and achieve desired outcomes. Thirdly, Security is non-negotiable; ensuring agents have access only to the data and services they genuinely need is crucial for maintaining privacy and preventing unintended actions. Finally, establishing robust Evaluations mechanisms is essential to verify that agents are completing tasks correctly and meeting the required standards. These four pillars – Knowledge, Actions, Security, and Evaluation – form the bedrock of any successful agentic implementation. To illustrate the transformative power of AI Agents, we explored several interesting use cases and applications. These ranged from intelligent personal assistants capable of managing schedules and automating workflows to sophisticated problem-solving systems in domains like customer service. A significant portion of the session was dedicated to practical implementation through demonstrations. We highlighted key frameworks that are empowering developers to build agentic systems.: Semantic Kernel: We highlighted its modularity and rich set of features for integrating various AI services and tools. Autogen Studio: The focus here was on its capabilities for facilitating the creation and management of multi-agent conversations and workflows. Agent Service: We discussed its role in providing a more streamlined and managed environment for deploying and scaling AI agents. The major point of attraction was that these were demonstrated using the local LLMs which were hosted using AI Toolkit. This showcased the ease with which developers can utilize VS Code AI toolkit to build and experiment with agentic workflows directly within their familiar development environment. Finally, we demystified the concept of Model Context Protocol (MCP) and demonstrated how seamlessly it can be implemented using the Agent Builder within the VS Code AI Toolkit. We demonstrated this with a basic Website development using MCP. This practical demonstration underscored the toolkit's power in simplifying the development of complex solutions that can maintain context and engage in more natural, multi-step interactions. The "AI Sparks" series concluded with a discussion, where attendees had a clearer understanding of the evolution, potential and practicalities of AI Agents. The session underscored that we are on the cusp of a new era of intelligent systems that are not just reactive but actively work alongside us to achieve goals. The tools and frameworks are maturing, and the possibilities for agentic applications are sparking innovation across various industries. It was an exciting journey, and engagement during the final session on AI Sparks around Agents truly highlighted the transformative potential of this field. "AI Sparks" Series Roadmap: The "AI Sparks" series delved deeper into specific topics using AI Toolkit for Visual Studio Code, including: Introduction to AI toolkit and feature walkthrough: Introduction to the AI Toolkit extension for VS Code a powerful way to explore and integrate the latest AI models from OpenAI, Meta, Deepseek, Mistral, and more. Introduction to SLMs and local model with use cases: Explore Small Language Models (SLMs) and how they compare to larger models. Building RAG Applications: Create powerful applications that combine the strengths of LLMs with external knowledge sources. Multimodal Support and Image Analysis: Working with vision models and building multimodal applications. Evaluation and Model Selection: Evaluate model performance and choose the best model for your needs. Agents and Agentic Frameworks: Exploring the cutting edge of AI agents and how they can be used to build more complex and autonomous systems. The full playlist of the series with all the episodes of "AI Sparks" is available at AI Sparks Playlist. Continue the discussion and questions in Microsoft AI Discord Community where we have a dedicated AI-sparks channel. All the code samples can be found on AI_Toolkit_Samples .We look forward to continuing these insightful discussions in future series!Building AI Agents on edge devices using Ollama + Phi-4-mini Function Calling
The new Phi-4-mini and Phi-4-multimodal now support Function Calling. This feature enables the models to connect with external tools and APIs. By deploying Phi-4-mini and Phi-4-multimodal with Function Calling capabilities on edge devices, we can achieve local expansion of knowledge capabilities and enhance their task execution efficiency. This blog will focus on how to use Phi-4-mini's Function Calling capabilities to build efficient AI Agents on edge devices. What‘s Function Calling How it works First we need to learn how Function Calling works Tool Integration: Function Calling allows LLM/SLM to interact with external tools and APIs, such as weather APIs, databases, or other services. Function Definition: Defines a function (tool) that LLM/SLM can call, specifying its name, parameters, and expected output. LLM Detection: LLM/SLM analyzes the user's input and determines if a function call is required and which function to use. JSON Output: LLM/SLM outputs a JSON object containing the name of the function to call and the parameters required by the function. External Execution: The application executes the function call using the parameters provided by LLM/SLM. Response to LLM: Returns the output of Function Calling to LLM/SLM, and LLM/SLM can use this information to generate a response to the user. Application scenarios Data retrieval: convert natural language queries into API calls to fetch data (e.g., "show my recent orders" triggers a database query) Operation execution: convert user requests into specific function calls (e.g., "schedule a meeting" becomes a calendar API call) Computational tasks: handle mathematical or logical operations through dedicated functions (e.g., calculate compound interest or statistical analysis) Data processing: chain multiple function calls together (e.g., get data → parse → transform → store) UI/UX integration: trigger interface updates based on user interactions (e.g., update map markers or display charts) Phi-4-mini / Phi-4-multimodal's Function Calling Phi-4-mini / Phi-4-multimodal supports single and parallel Function Calling. Things to note when calling You need to define Tools in System to start single or parallel Function Calling If you want to start parallel Function Calling, you also need to add 'some tools' to the System prompt The following is an example Single Function Calling tools = [ { "name": "get_match_result", "description": "get match result", "parameters": { "match": { "description": "The name of the match", "type": "str", "default": "Arsenal vs ManCity" } } }, ] messages = [ { "role": "system", "content": "You are a helpful assistant", "tools": json.dumps(tools), # pass the tools into system message using tools argument }, { "role": "user", "content": "What is the result of Arsenal vs ManCity today?" } ] Full Sample : Click Parallel Function Calling AGENT_TOOLS = { "booking_fight": { "name": "booking_fight", "description": "booking fight", "parameters": { "departure": { "description": "The name of Departure airport code", "type": "str", }, "destination": { "description": "The name of Destination airport code", "type": "str", }, "outbound_date": { "description": "The date of outbound flight", "type": "str", }, "return_date": { "description": "The date of return flight", "type": "str", } } }, "booking_hotel": { "name": "booking_hotel", "description": "booking hotel", "parameters": { "query": { "description": "The name of the city", "type": "str", }, "check_in_date": { "description": "The date of check in", "type": "str", }, "check_out_date": { "description": "The date of check out", "type": "str", } } }, } SYSTEM_PROMPT = """ You are my travel agent with some tools available. """ messages = [ { "role": "system", "content": SYSTEM_PROMPT, "tools": json.dumps(AGENT_TOOLS), # pass the tools into system message using tools argument }, { "role": "user", "content": """I have a business trip from London to New York in March 21 2025 to March 27 2025, can you help me to book a hotel and flight tickets""" } ] Full sample : click Using Ollama and Phi-4-mini Function Calling to Create AI Agents on Edge Devices Ollama is a popular free tool for deploying LLM/SLM locally and can be used in combination with AI Toolkit for VS Code. In addition to being deployed on your PC/Laptop, it can also be deployed on IoT, mobile phones, containers, etc. To use Phi-4-mini on Ollama, you need to use Ollama 0.5.13+. Different quantitative versions are supported on Ollama, as shown in the figure below: Using Ollama, we can deploy Phi-4-mini on the edge, and implement AI Agent with Function Calling under limited computing power, so that Generative AI can be applied more effectively on the edge. Current Issues A sad experience - If you directly use the interface to try to call Ollama in the above way, you will find that Function Calling will not be triggered. There are discussions on Ollama's GitHub Issue. You can enter the Issue https://github.com/ollama/ollama/issues/9437. By modifying the Phi-4-mini Template on the ModelFile to implement a single Function Calling, but the call to Parallel Function Calling still failed. Resolution We have implemented a fix by making a adjustments to the template. We have improved it according to Phi-4-mini's Chat Template and re-modified the Modelfile. Of course, the quantitative model has a huge impact on the results. The adjustments are as follows: TEMPLATE """ {{- if .Messages }} {{- if or .System .Tools }}<|system|> {{ if .System }}{{ .System }} {{- end }} In addition to plain text responses, you can chose to call one or more of the provided functions. Use the following rule to decide when to call a function: * if the response can be generated from your internal knowledge (e.g., as in the case of queries like "What is the capital of Poland?"), do so * if you need external information that can be obtained by calling one or more of the provided functions, generate a function calls If you decide to call functions: * prefix function calls with functools marker (no closing marker required) * all function calls should be generated in a single JSON list formatted as functools[{"name": [function name], "arguments": [function arguments as JSON]}, ...] * follow the provided JSON schema. Do not hallucinate arguments or values. Do to blindly copy values from the provided samples * respect the argument type formatting. E.g., if the type if number and format is float, write value 7 as 7.0 * make sure you pick the right functions that match the user intent Available functions as JSON spec: {{- if .Tools }} {{ .Tools }} {{- end }}<|end|> {{- end }} {{- range .Messages }} {{- if ne .Role "system" }}<|{{ .Role }}|> {{- if and .Content (eq .Role "tools") }} {"result": {{ .Content }}} {{- else if .Content }} {{ .Content }} {{- else if .ToolCalls }} functools[ {{- range .ToolCalls }}{{ "{" }}"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}{{ "}" }} {{- end }}] {{- end }}<|end|> {{- end }} {{- end }}<|assistant|> {{ else }} {{- if .System }}<|system|> {{ .System }}<|end|>{{ end }}{{ if .Prompt }}<|user|> {{ .Prompt }}<|end|>{{ end }}<|assistant|> {{ end }}{{ .Response }}{{ if .Response }}<|user|>{{ end }} """ We have tested the solution using different quantitative models. In the laptop environment, we recommend that you use the following model to enable single/parallel Function Calling: phi4-mini:3.8b-fp16. Note: you need to bind the defined Modelfile and phi4-mini:3.8b-fp16 together to enable this to work. Please execute the following command in the command line: #If you haven't downloaded it yet, please execute this command firstr ollama run phi4-mini:3.8b-fp16 #Binding with the adjusted Modelfile ollama create phi4-mini:3.8b-fp16 -f {Your Modelfile Path} To test the single Function Calling and Parallel Function Calling of Phi-4-mini. Single Function Calling Parallel Function Calling Full Sample in notebook The above example is just a simple introduction. As we move forward with the development we hope to find simpler ways to apply it on the edge, use Function Calling to expand the scenarios of Phi-4-mini / Phi-4-multimodal, and also develop more usecases in vertical industries. Resources Phi-4 model on Hugging face https://huggingface.co/collections/microsoft/phi-4-677e9380e514feb5577a40e4 Phi-4-mini on Ollama https://ollama.com/library/phi4-mini Learn Function Calling https://huggingface.co/docs/hugs/en/guides/function-calling Phi Cookbook - Samples and Resources for Phi Models https://aka.ms/phicookbookUsing Advanced Reasoning Model on EdgeAI Part 2 - Evaluate local models using AITK for VSCode
Quantizing a generative AI model assists in ease of deployment of edge devices. For development purposes we would like to have 1) quantization 2) optimization and 3) evaluation of models all in one tool. We recommend AI Toolkit for Visual Studio Code (AITK) for as an all-in-one tool for developers experimenting with GenAI models. This is a lightweight open-source tool that covers model selection, fine-tuning, deployment, application development, batch data for testing, and evaluation. In Using Advanced Reasoning Model on EdgeAI Part 1 - Quantization, Conversion, Performance, we performed quantization and format conversion for Phi-4 and DeepSeek-R1-Distill-Qwen-1.5B. In This blog will evaluate Phi-4-14B-ONNX-INT4-GPU and DeepSeek-R1-Distill-Qwen-14B-ONNX-INT4-GPU using AITK. About model quantization Quantization refers to the process of approximating the continuous value of a signal to a finite number of discrete values. It can be understood as a method of information compression. When considering this concept on a computer system, it is generally represented by "low bits". Some people also call quantization "fixed-point", but strictly speaking, the range represented is reduced. Fixed-point refers specifically to linear quantization with a scale of 2, which is a more practical quantization method. Our trained models generally have the characteristics of large number of parameters, large amount of calculation, high memory usage, and high precision. However, after model quantization, we can compress parameters, increase the calculation speed of the model, and reduce memory usage, but there is a problem that the quantization approximation algorithm reduces the precision. In the use of generative AI, we will face some errors and omissions in the results. We therefore need to evaluate the quantization model. Use AITK to evaluate quantitative models Model deployment AITK is an open-source tool with GenAIOps, based on Visual Studio Code. If you want to evaluate the model, you first need to deploy the model, which can be deployed locally or remotely. Currently AITK only supports the deployment of ONNX models in the Model Catalog (Phi-3/Phi-3.5 Family/Mistral 7B) To test models that are not currently supported within model catalog we propose API that is compatible with AITK. This uses the remote deployment method of the Open AI Chat completion. We use Python + Flask to create the Open AI Chat completion service, the code is as follows: from flask import Flask, request, jsonify, stream_with_context, Response import json import onnxruntime_genai as og import numpy as np import requests import uuid, time app = Flask(__name__) model_path = "Your Phi-4-14B-ONNX-INT4-GPU or DeepSeek-R1-Distill-Qwen-14B-ONNX-INT4-GPU path" model = og.Model(model_path) tokenizer = og.Tokenizer(model) tokenizer_stream = tokenizer.create_stream() # Your Phi-4 chat template chat_template = "<|user|>{input}<|assistant|>" # Your DeepSeek-R1-Distill-Qwen chat template # chat_template = "<|im_start|> user {input}<|im_end|><|im_start|> assistant" @app.route('/v1/chat/completions', methods=['POST']) def ort_chat(): data = request.get_json() messages = data.get("messages") if not messages or not isinstance(messages, list): return jsonify({ "error": { "message": "Invalid request. 'messages' is required and must be a list of strings.", "type": "invalid_request_error", "param": "messages", "code": None } }), 400 prompt = '' if messages: last_message = messages[-1] if last_message.get("role") == "user" and last_message.get("content"): prompt = last_message['content'] search_options = {} search_options['max_length'] = data.get("max_tokens") search_options['temperature'] = data.get("temperature") search_options['top_p'] = data.get("top_p") search_options['past_present_share_buffer'] = False prompt = f'{chat_template.format(input=messages)}' input_tokens = tokenizer.encode(prompt) params = og.GeneratorParams(model) params.set_search_options(**search_options) params.input_ids = input_tokens generator = og.Generator(model, params) reply = "" while not generator.is_done(): generator.compute_logits() generator.generate_next_token() new_token = generator.get_next_tokens()[0] reply += tokenizer.decode(new_token) if data.get("stream"): def generate(): tokens = reply.split() for token in tokens: chunk = { "id": "chatcmpl-"+ str(uuid.uuid4()), "object": "chat.completion.chunk", "created": int(time.time()), "model": data.get("model"), "choices": [ { "delta": {"content": token + " "}, "index": 0, "finish_reason": None } ] } yield "data: " + json.dumps(chunk) + "\n\n" time.sleep(0.5) yield "data: [DONE]\n\n" return Response(stream_with_context(generate()), mimetype="text/event-stream") response_data = { "id": "chatcmpl-"+ str(uuid.uuid4()), "object": "chat.completion", "created": int(time.time()), "model": data.get("model"), "choices": [ { "index": 0, "message": { "role": "assistant", "content": reply }, "finish_reason": "stop" } ], "usage": { "prompt_tokens": len(messages), "completion_tokens": len(reply.split()), "total_tokens": len(reply.split()) } } return jsonify(response_data) if __name__ == '__main__': app.run(debug=True, port=5000) After create service, through AITK's My MODELS Remote models select "Add a custom model" select the API (http://127.0.0.1:5000/v1/chat/completions) set the name such as DeepSeek-R1-Distill-Qwen-14B-ONNX-INT4-GPU or Phi-4-14B-ONNX-INT4-GPU. We can test it in playground DeepSeek-R1-Distill-Qwen-14B-ONNX-INT4-GPU Playground Phi-4-14B-ONNX-INT4-GPU Playground Batch Data We can use AITK's Bulk Data to set up the execution environment for batch data. I simulate the execution of 10 data here. We can execute in batches to see the relevant results. This is an important step in the evaluation because we need to know the results based on a specific problem before the evaluation. After the run, we can export the run results Evaluation You can evaluate the exported batch data results. AITK supports different evaluation methods. Create an evaluation by selecting Evaluation from Tools and importing the data exported from Bulk Data. You can choose different evaluation methods. We select F1 to complete the evaluation selection, Let's take a look at the evaluation results of DeepSeek-R1-Distill-Qwen-14B-ONNX-INT4-GPU Summary The AI Toolkit (AITK) enables us to assess various models, which is instrumental for our edge deployments. As Responsible AI gains importance, continuous testing and evaluation post-deployment become essential. In this context, AITK serves as a crucial tool for our daily operations. Resource Learn about AI Toolkit for Visual Studio Code https://marketplace.visualstudio.com/items?itemName=ms-windows-ai-studio.windows-ai-studio DeepSeek-R1 in GitHub Models https://github.com/marketplace/models/azureml-deepseek/DeepSeek-R1 DeepSeek-R1 in Azure AI Foundry https://ai.azure.com/explore/models/DeepSeek-R1/version/1/registry/azureml-deepseek Phi-4-14B in Hugging face https://huggingface.co/microsoft/phi-4 Learn about Microsoft Olive https://github.com/microsoft/olive Learn about ONNX Runtime GenAI https://github.com/microsoft/onnxruntime-genaiFine-Tuning Language Models with Azure AI Foundry: A Detailed Guide
What is Azure AI Foundry? Azure AI Foundry is a comprehensive platform designed to simplify the development, deployment, and management of AI models. It provides a user-friendly interface and powerful tools that enable developers to create custom AI solutions without needing extensive machine learning expertise. Key Features of Azure AI Foundry One-Button Fine-Tuning: A streamlined process that allows users to fine-tune models with minimal configuration. Integration with Development Tools: Seamless integration with popular development environments, particularly Visual Studio Code. Support for Multiple Models: Access to a variety of pre-trained models, including the Phi family of models. Understanding Fine-Tuning Fine-tuning is the process of taking a pre-trained model and adapting it to a specific dataset or task. This is particularly useful when the base model has been trained on a large corpus of general data but needs to perform well on a narrower domain. Why Fine-Tune? Improved Performance: Fine-tuning can significantly enhance the model's accuracy and relevance for specific tasks. Reduced Training Time: Starting with a pre-trained model reduces the amount of data and time required for training. Customization: Tailor the model to meet the unique needs of your application or business. One-Button Fine-Tuning in Azure AI Foundry Step-by-Step Process Select the Model: Log in to Azure AI Foundry and navigate to the model selection interface. Choose Phi-3 or another small language model from the available options. Prepare Your Data: Ensure your dataset is formatted correctly. Typically, this involves having a set of input-output pairs that the model can learn from. Upload your dataset to Azure AI Foundry. The platform supports various data formats, making it easy to integrate your existing data. Initiate Fine-Tuning: Locate the one-button fine-tuning feature within the Azure AI Foundry interface. Click the button to start the fine-tuning process. The platform will handle the configuration and setup automatically. Monitor Progress: After initiating fine-tuning, you can monitor the process through the Azure portal. The portal provides real-time updates on training metrics, allowing you to track the model's performance as it learns. Evaluate the Model: Once fine-tuning is complete, evaluate the model's performance using a validation dataset. Azure AI Foundry provides tools for assessing accuracy, precision, recall, and other relevant metrics. Deploy the Model: After successful evaluation, you can deploy the fine-tuned model directly from Azure AI Foundry. The platform supports various deployment options, including REST APIs and integration with other Azure services. Using the AI Toolkit in Visual Studio Code Overview of the AI Toolkit The AI Toolkit for Visual Studio Code enhances the development experience by providing tools specifically designed for AI model management and fine-tuning. This integration allows developers to work within a familiar environment while leveraging powerful AI capabilities. Key Features of the AI Toolkit 1) Model Management: Easily manage and switch between different models, including Phi-3 and Ollama models. 2) Data Handling: Simplified data upload and preprocessing tools to prepare datasets for training. 3) Real-Time Collaboration: Collaborate with team members in real-time, sharing insights and progress on AI projects. How to Use the AI Toolkit 1) Install the AI Toolkit: Open Visual Studio Code and navigate to the Extensions Marketplace. Search for "AI Toolkit" and install the extension. 2) Connect to Azure AI Foundry: Once installed, configure the toolkit to connect to your Azure AI Foundry account. This will allow you to access your models and datasets directly from Visual Studio Code. 3) Fine-Tune Models: Use the toolkit to initiate fine-tuning processes directly from your development environment. Monitor training progress and view logs without leaving Visual Studio Code. 4) Consume Ollama Models: The AI Toolkit supports the consumption of Ollama models, providing additional flexibility in your AI projects. This feature allows you to integrate various models seamlessly, enhancing your application's capabilities. Microsoft ONNX Live for Fine-Tuning What is Microsoft ONNX Live? Microsoft ONNX Live is a platform that allows developers to deploy and optimize AI models using the Open Neural Network Exchange (ONNX) format. ONNX is an open-source format that enables interoperability between different AI frameworks, making it easier to deploy models across various environments. Key Features of Microsoft ONNX Live Model Optimization: ONNX Live provides tools to optimize models for performance, ensuring they run efficiently in production environments. Cross-Framework Compatibility: Models trained in different frameworks (like PyTorch or TensorFlow) can be converted to ONNX format, allowing for greater flexibility in deployment. Real-Time Inference: ONNX Live supports real-time inference, enabling applications to utilize AI models for immediate predictions. Fine-Tuning with ONNX Live Model Conversion: If you have a model trained in a different framework, you can convert it to ONNX format using tools provided by Microsoft. This conversion allows you to leverage the benefits of ONNX Live for deployment and optimization. Integration with Azure AI Foundry: Once your model is in ONNX format, you can integrate it with Azure AI Foundry for fine-tuning. The one-button fine-tuning feature can be used to adapt the ONNX model to your specific dataset. Optimization Techniques: After fine-tuning, you can apply various optimization techniques available in ONNX Live to enhance the model's performance. Techniques such as quantization and pruning can significantly reduce the model size and improve inference speed. Deployment: Once optimized, the model can be deployed directly from Azure AI Foundry or ONNX Live. This deployment can be done as a REST API, allowing easy integration with web applications and services. Additional Resources To further enhance your understanding and capabilities in fine-tuning language models, consider exploring the following resources: Phi-3 Cookbook: This comprehensive guide provides insights into getting started with Phi models, including best practices for fine-tuning and deployment. Explore the Phi-3 Cookbook. Ignite Fine-Tuning Workshop: This workshop offers a hands-on approach to learning about fine-tuning techniques and tools. It includes real-world scenarios to help you understand the practical applications of fine-tuning. Visit the GitHub Repository. Conclusion Fine-tuning language models like Phi-3 using Azure AI Foundry, combined with the AI Toolkit in Visual Studio Code and Microsoft ONNX Live, provides a powerful and efficient workflow for developers. The one-button fine-tuning feature simplifies the process, while the integration with ONNX Live allows for optimization and deployment flexibility. By leveraging these tools, you can enhance your AI applications, ensuring they are tailored to meet specific needs and perform optimally in production environments. Whether you are a seasoned AI developer or just starting, Azure AI Foundry and its associated tools offer a robust ecosystem for building and deploying advanced AI solutions. References Microsoft Docs Links Fine-Tuning Models in Azure OpenAI Azure AI Services Documentation Azure Machine Learning Documentation Microsoft Learn Links Develop Generative AI Apps in Azure Fine-Tune a Language Model Azure AI Foundry Overview Get started with AI Toolkit for Visual Studio Code
