Agentic Code Fixing with GitHub Copilot SDK and Foundry Local
Introduction AI-powered coding assistants have transformed how developers write and review code. But most of these tools require sending your source code to cloud services, a non-starter for teams working with proprietary codebases, air-gapped environments, or strict compliance requirements. What if you could have an intelligent coding agent that finds bugs, fixes them, runs your tests, and produces PR-ready summaries, all without a single byte leaving your machine? The Local Repo Patch Agent demonstrates exactly this. By combining the GitHub Copilot SDK for agent orchestration with Foundry Local for on-device inference, this project creates a fully autonomous coding workflow that operates entirely on your hardware. The agent scans your repository, identifies bugs and code smells, applies fixes, verifies them through your test suite, and generates a comprehensive summary of all changes, completely offline and secure. This article explores the architecture behind this integration, walks through the key implementation patterns, and shows you how to run the agent yourself. Whether you're building internal developer tools, exploring agentic workflows, or simply curious about what's possible when you combine GitHub's SDK with local AI, this project provides a production-ready foundation to build upon. Why Local AI Matters for Code Analysis Cloud-based AI coding tools have proven their value—GitHub Copilot has fundamentally changed how millions of developers work. But certain scenarios demand local-first approaches where code never leaves the organisation's network. Consider these real-world constraints that teams face daily: Regulatory compliance: Financial services, healthcare, and government projects often prohibit sending source code to external services, even for analysis Intellectual property protection: Proprietary algorithms and trade secrets can't risk exposure through cloud API calls Air-gapped environments: Secure facilities and classified projects have no internet connectivity whatsoever Latency requirements: Real-time code analysis in IDEs benefits from zero network roundtrip Cost control: High-volume code analysis without per-token API charges The Local Repo Patch Agent addresses all these scenarios. By running the AI model on-device through Foundry Local and using the GitHub Copilot SDK for orchestration, you get the intelligence of agentic coding workflows with complete data sovereignty. The architecture proves that "local-first" doesn't mean "capability-limited." The Technology Stack Two core technologies make this architecture possible, working together through a clever integration called BYOK (Bring Your Own Key). Understanding how they complement each other reveals the elegance of the design. GitHub Copilot SDK The GitHub Copilot SDK provides the agent runtime, the scaffolding that handles planning, tool invocation, streaming responses, and the orchestration loop that makes agentic behaviour possible. Rather than managing raw LLM API calls, developers define tools (functions the agent can call) and system prompts, and the SDK handles everything else. Key capabilities the SDK brings to this project: Session management: Maintains conversation context across multiple agent interactions Tool orchestration: Automatically invokes defined tools when the model requests them Streaming support: Real-time response streaming for responsive user interfaces Provider abstraction: Works with any OpenAI-compatible API through the BYOK configuration Foundry Local Foundry Local brings Azure AI Foundry's model catalog to your local machine. It automatically selects the best available hardware acceleration—GPU, NPU, or CP, and exposes models through an OpenAI-compatible API on localhost. Models run entirely on-device with no telemetry or data transmission. For this project, Foundry Local provides: On-device inference: All AI processing happens locally, ensuring complete data privacy Dynamic port allocation: The SDK auto-detects the Foundry Local endpoint, eliminating configuration hassle Model flexibility: Swap between models like qwen2.5-coder-1.5b , phi-3-mini , or larger variants based on your hardware OpenAI API compatibility: Standard API format means the GitHub Copilot SDK works without modification The BYOK Integration The entire connection between the GitHub Copilot SDK and Foundry Local happens through a single configuration object. This BYOK (Bring Your Own Key) pattern tells the SDK to route all inference requests to your local model instead of cloud services: const session = await client.createSession({ model: modelId, provider: { type: "openai", // Foundry Local speaks OpenAI's API format baseUrl: proxyBaseUrl, // Streaming proxy → Foundry Local apiKey: manager.apiKey, wireApi: "completions", // Chat Completions API }, streaming: true, tools: [ /* your defined tools */ ], }); This configuration is the key insight: with one config object, you've redirected an entire agent framework to run on local hardware. No code changes to the SDK, no special adapters—just standard OpenAI-compatible API communication. Architecture Overview The Local Repo Patch Agent implements a layered architecture where each component has a clear responsibility. Understanding this flow helps when extending or debugging the system. ┌─────────────────────────────────────────────────────────┐ │ Your Terminal / Web UI │ │ npm run demo / npm run ui │ └──────────────┬──────────────────────────────────────────┘ │ ┌──────────────▼──────────────────────────────────────────┐ │ src/agent.ts (this project) │ │ │ │ ┌────────────────────────────┐ ┌──────────────────┐ │ │ │ GitHub Copilot SDK │ │ Agent Tools │ │ │ │ (CopilotClient) │ │ list_files │ │ │ │ BYOK → Foundry │ │ read_file │ │ │ └────────┬───────────────────┘ │ write_file │ │ │ │ │ run_command │ │ └────────────┼───────────────────────┴──────────────────┘ │ │ │ │ JSON-RPC │ ┌────────────▼─────────────────────────────────────────────┐ │ GitHub Copilot CLI (server mode) │ │ Agent orchestration layer │ └────────────┬─────────────────────────────────────────────┘ │ POST /v1/chat/completions (BYOK) ┌────────────▼─────────────────────────────────────────────┐ │ Foundry Local (on-device inference) │ │ Model: qwen2.5-coder-1.5b via ONNX Runtime │ │ Endpoint: auto-detected (dynamic port) │ └───────────────────────────────────────────────────────────┘ The data flow works as follows: your terminal or web browser sends a request to the agent application. The agent uses the GitHub Copilot SDK to manage the conversation, which communicates with the Copilot CLI running in server mode. The CLI, configured with BYOK, sends inference requests to Foundry Local running on localhost. Responses flow back up the same path, with tool invocations happening in the agent.ts layer. The Four-Phase Workflow The agent operates through a structured four-phase loop, each phase building on the previous one's output. This decomposition transforms what would be an overwhelming single prompt into manageable, verifiable steps. Phase 1: PLAN The planning phase scans the repository and produces a numbered fix plan. The agent reads every source and test file, identifies potential issues, and outputs specific tasks to address: // Phase 1 system prompt excerpt const planPrompt = ` You are a code analysis agent. Scan the repository and identify: 1. Bugs that cause test failures 2. Code smells and duplication 3. Style inconsistencies Output a numbered list of fixes, ordered by priority. Each item should specify: file path, line numbers, issue type, and proposed fix. `; The tools available during this phase are list_files and read_file —the agent explores the codebase without modifying anything. This read-only constraint prevents accidental changes before the plan is established. Phase 2: EDIT With a plan in hand, the edit phase applies each fix by rewriting affected files. The agent receives the plan from Phase 1 and systematically addresses each item: // Phase 2 adds the write_file tool const editTools = [ { name: "write_file", description: "Write content to a file, creating or overwriting it", parameters: { type: "object", properties: { path: { type: "string", description: "File path relative to repo root" }, content: { type: "string", description: "Complete file contents" } }, required: ["path", "content"] } } ]; The write_file tool is sandboxed to the demo-repo directory, path traversal attempts are blocked, preventing the agent from modifying files outside the designated workspace. Phase 3: VERIFY After making changes, the verification phase runs the project's test suite to confirm fixes work correctly. If tests fail, the agent attempts to diagnose and repair the issue: // Phase 3 adds run_command with an allowlist const allowedCommands = ["npm test", "npm run lint", "npm run build"]; const runCommandTool = { name: "run_command", description: "Execute a shell command (npm test, npm run lint, npm run build only)", execute: async (command: string) => { if (!allowedCommands.includes(command)) { throw new Error(`Command not allowed: ${command}`); } // Execute and return stdout/stderr } }; The command allowlist is a critical security measure. The agent can only run explicitly permitted commands—no arbitrary shell execution, no data exfiltration, no system modification. Phase 4: SUMMARY The final phase produces a PR-style Markdown report documenting all changes. This summary includes what was changed, why each change was necessary, test results, and recommended follow-up actions: ## Summary of Changes ### Bug Fix: calculateInterest() in account.js - **Issue**: Division instead of multiplication caused incorrect interest calculations - **Fix**: Changed `principal / annualRate` to `principal * (annualRate / 100)` - **Tests**: 3 previously failing tests now pass ### Refactor: Duplicate formatCurrency() removed - **Issue**: Identical function existed in account.js and transaction.js - **Fix**: Both files now import from utils.js - **Impact**: Reduced code duplication, single source of truth ### Test Results - **Before**: 6/9 passing - **After**: 9/9 passing This structured output makes code review straightforward, reviewers can quickly understand what changed and why without digging through diffs. The Demo Repository: Intentional Bugs The project includes a demo-repo directory containing a small banking utility library with intentional problems for the agent to find and fix. This provides a controlled environment to demonstrate the agent's capabilities. Bug 1: Calculation Error in calculateInterest() The account.js file contains a calculation bug that causes test failures: // BUG: should be principal * (annualRate / 100) function calculateInterest(principal, annualRate) { return principal / annualRate; // Division instead of multiplication! } This bug causes 3 of 9 tests to fail. The agent identifies it during the PLAN phase by correlating test failures with the implementation, then fixes it during EDIT. Bug 2: Code Duplication The formatCurrency() function is copy-pasted in both account.js and transaction.js, even though a canonical version exists in utils.js. This duplication creates maintenance burden and potential inconsistency: // In account.js (duplicated) function formatCurrency(amount) { return '$' + amount.toFixed(2); } // In transaction.js (also duplicated) function formatCurrency(amount) { return '$' + amount.toFixed(2); } // In utils.js (canonical, but unused) export function formatCurrency(amount) { return '$' + amount.toFixed(2); } The agent identifies this duplication during planning and refactors both files to import from utils.js, eliminating redundancy. Handling Foundry Local Streaming Quirks One technical challenge the project solves is Foundry Local's behaviour with streaming requests. As of version 0.5, Foundry Local can hang on stream: true requests. The project includes a streaming proxy that works around this limitation transparently. The Streaming Proxy The streaming-proxy.ts file implements a lightweight HTTP proxy that converts streaming requests to non-streaming, then re-encodes the single response as SSE (Server-Sent Events) chunks—the format the OpenAI SDK expects: // streaming-proxy.ts simplified logic async function handleRequest(req: Request): Promise { const body = await req.json(); // If it's a streaming chat completion, convert to non-streaming if (body.stream === true && req.url.includes('/chat/completions')) { body.stream = false; const response = await fetch(foundryEndpoint, { method: 'POST', body: JSON.stringify(body), headers: { 'Content-Type': 'application/json' } }); const data = await response.json(); // Re-encode as SSE stream for the SDK return createSSEResponse(data); } // Non-streaming and non-chat requests pass through unchanged return fetch(foundryEndpoint, req); } This proxy runs on port 8765 by default and sits between the GitHub Copilot SDK and Foundry Local. The SDK thinks it's talking to a streaming-capable endpoint, while the actual inference happens non-streaming. The conversion is transparent, no changes needed to SDK configuration. Text-Based Tool Call Detection Small on-device models like qwen2.5-coder-1.5b sometimes output tool calls as JSON text rather than using OpenAI-style function calling. The SDK won't fire tool.execution_start events for these text-based calls, so the agent includes a regex-based detector: // Pattern to detect tool calls in model output const toolCallPattern = /\{[\s\S]*"name":\s*"(list_files|read_file|write_file|run_command)"[\s\S]*\}/; function detectToolCall(text: string): ToolCall | null { const match = text.match(toolCallPattern); if (match) { try { return JSON.parse(match[0]); } catch { return null; } } return null; } This fallback ensures tool calls are captured regardless of whether the model uses native function calling or text output, keeping the dashboard's tool call counter and CLI log accurate. Security Considerations Running an AI agent that can read and write files and execute commands requires careful security design. The Local Repo Patch Agent implements multiple layers of protection: 100% local execution: No code, prompts, or responses leave your machine—complete data sovereignty Command allowlist: The agent can only run npm test , npm run lint , and npm run build —no arbitrary shell commands Path sandboxing: File tools are locked to the demo-repo/ directory; path traversal attempts like ../../../etc/passwd are rejected File size limits: The read_file tool rejects files over 256 KB, preventing memory exhaustion attacks Recursion limits: Directory listing caps at 20 levels deep, preventing infinite traversal These constraints demonstrate responsible AI agent design. The agent has enough capability to do useful work but not enough to cause harm. When extending this project for your own use cases, maintain similar principles, grant minimum necessary permissions, validate all inputs, and fail closed on unexpected conditions. Running the Agent Getting the Local Repo Patch Agent running on your machine takes about five minutes. The project includes setup scripts that handle prerequisites automatically. Prerequisites Before running the setup, ensure you have: Node.js 18 or higher: Download from nodejs.org (LTS version recommended) Foundry Local: Install via winget install Microsoft.FoundryLocal (Windows) or brew install foundrylocal (macOS) GitHub Copilot CLI: Follow the GitHub Copilot CLI install guide Verify your installations: node --version # Should print v18.x.x or higher foundry --version copilot --version One-Command Setup The easiest path uses the provided setup scripts that install dependencies, start Foundry Local, and download the AI model: # Clone the repository git clone https://github.com/leestott/copilotsdk_foundrylocal.git cd copilotsdk_foundrylocal # Windows (PowerShell) .\setup.ps1 # macOS / Linux chmod +x setup.sh ./setup.sh When setup completes, you'll see: ━━━ Setup complete! ━━━ You're ready to go. Run one of these commands: npm run demo CLI agent (terminal output) npm run ui Web dashboard (http://localhost:3000) Manual Setup If you prefer step-by-step control: # Install npm packages npm install cd demo-repo && npm install --ignore-scripts && cd .. # Start Foundry Local and download the model foundry service start foundry model run qwen2.5-coder-1.5b # Copy environment configuration cp .env.example .env # Run the agent npm run demo The first model download takes a few minutes depending on your connection. After that, the model runs from cache with no internet required. Using the Web Dashboard For a visual experience with real-time streaming, launch the web UI: npm run ui Open http://localhost:3000 in your browser. The dashboard provides: Phase progress sidebar: Visual indication of which phase is running, completed, or errored Live streaming output: Model responses appear in real-time via WebSocket Tool call log: Every tool invocation logged with phase context Phase timing table: Performance metrics showing how long each phase took Environment info: Current model, endpoint, and repository path at a glance Configuration Options The agent supports several environment variables for customisation. Edit the .env file or set them directly: Variable Default Description FOUNDRY_LOCAL_ENDPOINT auto-detected Override the Foundry Local API endpoint FOUNDRY_LOCAL_API_KEY auto-detected Override the API key FOUNDRY_MODEL qwen2.5-coder-1.5b Which model to use from the Foundry Local catalog FOUNDRY_TIMEOUT_MS 180000 (3 min) How long each agent phase can run before timing out FOUNDRY_NO_PROXY — Set to 1 to disable the streaming proxy PORT 3000 Port for the web dashboard Using Different Models To try a different model from the Foundry Local catalog: # Use phi-3-mini instead FOUNDRY_MODEL=phi-3-mini npm run demo # Use a larger model for higher quality (requires more RAM/VRAM) FOUNDRY_MODEL=qwen2.5-7b npm run demo Adjusting for Slower Hardware If you're running on CPU-only or limited hardware, increase the timeout to give the model more time per phase: # 5 minutes per phase instead of 3 FOUNDRY_TIMEOUT_MS=300000 npm run demo Troubleshooting Common Issues When things don't work as expected, these solutions address the most common problems: Problem Solution foundry: command not found Install Foundry Local—see Prerequisites section copilot: command not found Install GitHub Copilot CLI—see Prerequisites section Agent times out on every phase Increase FOUNDRY_TIMEOUT_MS (e.g., 300000 for 5 min). CPU-only machines are slower. Port 3000 already in use Set PORT=3001 npm run ui Model download is slow First download can take 5-10 min. Subsequent runs use the cache. Cannot find module errors Run npm install again, then cd demo-repo && npm install --ignore-scripts Tests still fail after agent runs The agent edits files in demo-repo/. Reset with git checkout demo-repo/ and run again. PowerShell blocks setup.ps1 Run Set-ExecutionPolicy -Scope Process Bypass first, then .\setup.ps1 Diagnostic Test Scripts The src/tests/ folder contains standalone scripts for debugging SDK and Foundry Local integration issues. These are invaluable when things go wrong: # Debug-level SDK event logging npx tsx src/tests/test-debug.ts # Test non-streaming inference (bypasses streaming proxy) npx tsx src/tests/test-nostream.ts # Raw fetch to Foundry Local (bypasses SDK entirely) npx tsx src/tests/test-stream-direct.ts # Start the traffic-inspection proxy npx tsx src/tests/test-proxy.ts These scripts isolate different layers of the stack, helping identify whether issues lie in Foundry Local, the streaming proxy, the SDK, or your application code. Key Takeaways BYOK enables local-first AI: A single configuration object redirects the entire GitHub Copilot SDK to use on-device inference through Foundry Local Phased workflows improve reliability: Breaking complex tasks into PLAN → EDIT → VERIFY → SUMMARY phases makes agent behaviour predictable and debuggable Security requires intentional design: Allowlists, sandboxing, and size limits constrain agent capabilities to safe operations Local models have quirks: The streaming proxy and text-based tool detection demonstrate how to work around on-device model limitations Real-time feedback matters: The web dashboard with WebSocket streaming makes agent progress visible and builds trust in the system The architecture is extensible: Add new tools, change models, or modify phases to adapt the agent to your specific needs Conclusion and Next Steps The Local Repo Patch Agent proves that sophisticated agentic coding workflows don't require cloud infrastructure. By combining the GitHub Copilot SDK's orchestration capabilities with Foundry Local's on-device inference, you get intelligent code analysis that respects data sovereignty completely. The patterns demonstrated here, BYOK integration, phased execution, security sandboxing, and streaming workarounds, transfer directly to production systems. Consider extending this foundation with: Custom tool sets: Add database queries, API calls to internal services, or integration with your CI/CD pipeline Multiple repository support: Scan and fix issues across an entire codebase or monorepo Different model sizes: Use smaller models for quick scans, larger ones for complex refactoring Human-in-the-loop approval: Add review steps before applying fixes to production code Integration with Git workflows: Automatically create branches and PRs from agent-generated fixes Clone the repository, run through the demo, and start building your own local-first AI coding tools. The future of developer AI isn't just cloud—it's intelligent systems that run wherever your code lives. Resources Local Repo Patch Agent Repository – Full source code with setup scripts and documentation Foundry Local – Official site for on-device AI inference Foundry Local GitHub Repository – Installation instructions and CLI reference Foundry Local Get Started Guide – Official Microsoft Learn documentation Foundry Local SDK Reference – Python and JavaScript SDK documentation GitHub Copilot SDK – Official SDK repository GitHub Copilot SDK BYOK Documentation – Bring Your Own Key integration guide GitHub Copilot SDK Getting Started – SDK setup and first agent tutorial Microsoft Sample: Copilot SDK + Foundry Local – Official integration sample from MicrosoftBuilding a Local Research Desk: Multi-Agent Orchestration
Introduction Multi-agent systems represent the next evolution of AI applications. Instead of a single model handling everything, specialised agents collaborate—each with defined responsibilities, passing context to one another, and producing results that no single agent could achieve alone. But building these systems typically requires cloud infrastructure, API keys, usage tracking, and the constant concern about what data leaves your machine. What if you could build sophisticated multi-agent workflows entirely on your local machine, with no cloud dependencies? The Local Research & Synthesis Desk demonstrates exactly this. Using Microsoft Agent Framework (MAF) for orchestration and Foundry Local for on-device inference, this demo shows how to create a four-agent research pipeline that runs entirely on your hardware—no API keys, no data leaving your network, and complete control over every step. This article walks through the architecture, implementation patterns, and practical code that makes multi-agent local AI possible. You'll learn how to bootstrap Foundry Local from Python, create specialised agents with distinct roles, wire them into sequential, concurrent, and feedback loop orchestration patterns, and implement tool calling for extended functionality. Whether you're building research tools, internal analysis systems, or simply exploring what's possible with local AI, this architecture provides a production-ready foundation. Why Multi-Agent Architecture Matters Single-agent AI systems hit limitations quickly. Ask one model to research a topic, analyse findings, identify gaps, and write a comprehensive report—and you'll get mediocre results. The model tries to do everything at once, with no opportunity for specialisation, review, or iterative refinement. Multi-agent systems solve this by decomposing complex tasks into specialised roles. Each agent focuses on what it does best: Planners break ambiguous questions into concrete sub-tasks Retrievers focus exclusively on finding and extracting relevant information Critics review work for gaps, contradictions, and quality issues Writers synthesise everything into coherent, well-structured output This separation of concerns mirrors how human teams work effectively. A research team doesn't have one person doing everything—they have researchers, fact-checkers, editors, and writers. Multi-agent AI systems apply the same principle to AI workflows, with each agent receiving the output of previous agents as context for their own specialised task. The Local Research & Synthesis Desk implements this pattern with four primary agents, plus an optional ToolAgent for utility functions. Here's how user questions flow through the system: This architecture demonstrates three essential orchestration patterns: sequential pipelines where each agent builds on the previous output, concurrent fan-out where independent tasks run in parallel to save time, and feedback loops where the Critic can send work back to the Retriever for iterative refinement. The Technology Stack: MAF + Foundry Local Before diving into implementation, let's understand the two core technologies that make this architecture possible and why they work so well together. Microsoft Agent Framework (MAF) The Microsoft Agent Framework provides building blocks for creating AI agents in Python and .NET. Unlike frameworks that require specific cloud providers, MAF works with any OpenAI-compatible API—which is exactly what Foundry Local provides. The key abstraction in MAF is the ChatAgent . Each agent has: Instructions: A system prompt that defines the agent's role and behaviour Chat client: An OpenAI-compatible client for making inference calls Tools: Optional functions the agent can invoke during execution Name: An identifier for logging and observability MAF handles message threading, tool execution, and response parsing automatically. You focus on designing agent behaviour rather than managing low-level API interactions. Foundry Local Foundry Local brings Azure AI Foundry's model catalog to your local machine. It automatically selects the best hardware acceleration available (GPU, NPU, or CPU) and exposes models through an OpenAI-compatible API. Models run entirely on-device with no data leaving your machine. The foundry-local-sdk Python package provides programmatic control over the Foundry Local service. You can start the service, download models, and retrieve connection information—all from your Python code. This is the "control plane" that manages the local AI infrastructure. The combination is powerful: MAF handles agent logic and orchestration, while Foundry Local provides the underlying inference. No cloud dependencies, no API keys, complete data privacy: Bootstrapping Foundry Local from Python The first practical challenge is starting Foundry Local programmatically. The FoundryLocalBootstrapper class handles this, encapsulating all the setup logic so the rest of the application can focus on agent behaviour. The bootstrap process follows three steps: start the Foundry Local service if it's not running, download the requested model if it's not cached, and return connection information that MAF agents can use. Here's the core implementation: from dataclasses import dataclass from foundry_local import FoundryLocalManager @dataclass class FoundryConnection: """Holds endpoint, API key, and model ID after bootstrap.""" endpoint: str api_key: str model_id: str model_alias: str This dataclass carries everything needed to connect MAF agents to Foundry Local. The endpoint is typically http://localhost:<port>/v1 (the port is assigned dynamically), and the API key is managed internally by Foundry Local. class FoundryLocalBootstrapper: def __init__(self, alias: str | None = None) -> None: self.alias = alias or os.getenv("MODEL_ALIAS", "qwen2.5-0.5b") def bootstrap(self) -> FoundryConnection: """Start service, download & load model, return connection info.""" from foundry_local import FoundryLocalManager manager = FoundryLocalManager() model_info = manager.download_and_load_model(self.alias) return FoundryConnection( endpoint=manager.endpoint, api_key=manager.api_key, model_id=model_info.id, model_alias=self.alias, ) Key design decisions in this implementation: Lazy import: The foundry_local import happens inside bootstrap() so the application can provide helpful error messages if the SDK isn't installed Environment configuration: Model alias comes from MODEL_ALIAS environment variable or defaults to qwen2.5-0.5b Automatic hardware selection: Foundry Local picks GPU, NPU, or CPU automatically—no configuration needed The qwen2.5 model family is recommended because it supports function/tool calling, which the ToolAgent requires. For higher quality outputs, larger variants like qwen2.5-7b or qwen2.5-14b are available via the --model flag. Creating Specialised Agents With Foundry Local bootstrapped, the next step is creating agents with distinct roles. Each agent is a ChatAgent instance with carefully crafted instructions that focus it on a specific task. The Planner Agent The Planner receives a user question and available documents, then breaks the research task into concrete sub-tasks. Its instructions emphasise structured output—a numbered list of specific tasks rather than prose: from agent_framework import ChatAgent from agent_framework.openai import OpenAIChatClient def _make_client(conn: FoundryConnection) -> OpenAIChatClient: """Create an MAF OpenAIChatClient pointing at Foundry Local.""" return OpenAIChatClient( api_key=conn.api_key, base_url=conn.endpoint, model_id=conn.model_id, ) def create_planner(conn: FoundryConnection) -> ChatAgent: return ChatAgent( chat_client=_make_client(conn), name="Planner", instructions=( "You are a planning agent. Given a user's research question and a list " "of document snippets (if any), break the question into 2-4 concrete " "sub-tasks. Output ONLY a numbered list of tasks. Each task should state:\n" " • What information is needed\n" " • Which source documents might help (if known)\n" "Keep it concise — no more than 6 lines total." ), ) Notice how the instructions are explicit about output format. Multi-agent systems work best when each agent produces structured, predictable output that downstream agents can parse reliably. The Retriever Agent The Retriever receives the Planner's task list plus raw document content, then extracts and cites relevant passages. Its instructions emphasise citation format—a specific pattern that the Writer can reference later: def create_retriever(conn: FoundryConnection) -> ChatAgent: return ChatAgent( chat_client=_make_client(conn), name="Retriever", instructions=( "You are a retrieval agent. You receive a research plan AND raw document " "text from local files. Your job:\n" " 1. Identify the most relevant passages for each task in the plan.\n" " 2. Output extracted snippets with citations in the format:\n" " [filename.ext, lines X-Y]: \"quoted text…\"\n" " 3. If no relevant content exists, say so explicitly.\n" "Be precise — quote only what is relevant, keep each snippet under 100 words." ), ) The citation format [filename.ext, lines X-Y] creates a consistent contract. The Writer knows exactly how to reference source material, and human reviewers can verify claims against original documents. The Critic Agent The Critic reviews the Retriever's work, identifying gaps and contradictions. This agent serves as a quality gate before the final report and can trigger feedback loops for iterative improvement: def create_critic(conn: FoundryConnection) -> ChatAgent: return ChatAgent( chat_client=_make_client(conn), name="Critic", instructions=( "You are a critical review agent. You receive a plan and extracted snippets. " "Your job:\n" " 1. Check for gaps — are any plan tasks unanswered?\n" " 2. Check for contradictions between snippets.\n" " 3. Suggest 1-2 specific improvements or missing details.\n" "Start your response with 'GAPS FOUND' if issues exist, or 'NO GAPS' if satisfied.\n" "Then output a short numbered list of issues (or say 'No issues found')." ), ) The Critic is instructed to output GAPS FOUND or NO GAPS at the start of its response. This structured output enables the orchestrator to detect when gaps exist and trigger the feedback loop—sending the gaps back to the Retriever for additional retrieval before re-running the Critic. This iterates up to 2 times before the Writer takes over, ensuring higher quality reports. Critics are essential for production systems. Without this review step, the Writer might produce confident-sounding reports with missing information or internal contradictions. The Writer Agent The Writer receives everything—original question, plan, extracted snippets, and critic review—then produces the final report: def create_writer(conn: FoundryConnection) -> ChatAgent: return ChatAgent( chat_client=_make_client(conn), name="Writer", instructions=( "You are the final report writer. You receive:\n" " • The original question\n" " • A plan, extracted snippets with citations, and a critic review\n\n" "Produce a clear, well-structured answer (3-5 paragraphs). " "Requirements:\n" " • Cite sources using [filename.ext, lines X-Y] notation\n" " • Address any gaps the critic raised (note if unresolvable)\n" " • End with a one-sentence summary\n" "Do NOT fabricate citations — only use citations provided by the Retriever." ), ) The final instruction—"Do NOT fabricate citations"—is crucial for responsible AI. The Writer has access only to citations the Retriever provided, preventing hallucinated references that plague single-agent research systems. Implementing Sequential Orchestration With agents defined, the orchestrator connects them into a workflow. Sequential orchestration is the simpler pattern: each agent runs after the previous one completes, passing its output as input to the next agent. The implementation uses Python's async/await for clean asynchronous execution: import asyncio import time from dataclasses import dataclass, field @dataclass class StepResult: """Captures one agent step for observability.""" agent_name: str input_text: str output_text: str elapsed_sec: float @dataclass class WorkflowResult: """Final result of the entire orchestration run.""" question: str steps: list[StepResult] = field(default_factory=list) final_report: str = "" async def _run_agent(agent: ChatAgent, prompt: str) -> tuple[str, float]: """Execute a single agent and measure elapsed time.""" start = time.perf_counter() response = await agent.run(prompt) elapsed = time.perf_counter() - start return response.content, elapsed The StepResult dataclass captures everything needed for observability: what went in, what came out, and how long it took. This information is invaluable for debugging and optimisation. The sequential pipeline chains agents together, building context progressively: async def run_sequential_workflow( question: str, docs: LoadedDocuments, conn: FoundryConnection, ) -> WorkflowResult: wf = WorkflowResult(question=question) doc_block = docs.combined_text if docs.chunks else "(no documents provided)" # Step 1 — Plan planner = create_planner(conn) planner_prompt = f"User question: {question}\n\nAvailable documents:\n{doc_block}" plan_text, elapsed = await _run_agent(planner, planner_prompt) wf.steps.append(StepResult("Planner", planner_prompt, plan_text, elapsed)) # Step 2 — Retrieve retriever = create_retriever(conn) retriever_prompt = f"Plan:\n{plan_text}\n\nDocuments:\n{doc_block}" snippets_text, elapsed = await _run_agent(retriever, retriever_prompt) wf.steps.append(StepResult("Retriever", retriever_prompt, snippets_text, elapsed)) # Step 3 — Critique critic = create_critic(conn) critic_prompt = f"Plan:\n{plan_text}\n\nExtracted snippets:\n{snippets_text}" critique_text, elapsed = await _run_agent(critic, critic_prompt) wf.steps.append(StepResult("Critic", critic_prompt, critique_text, elapsed)) # Step 4 — Write writer = create_writer(conn) writer_prompt = ( f"Original question: {question}\n\n" f"Plan:\n{plan_text}\n\n" f"Extracted snippets:\n{snippets_text}\n\n" f"Critic review:\n{critique_text}" ) report_text, elapsed = await _run_agent(writer, writer_prompt) wf.steps.append(StepResult("Writer", writer_prompt, report_text, elapsed)) wf.final_report = report_text return wf Each step receives all relevant context from previous steps. The Writer gets the most comprehensive prompt—original question, plan, snippets, and critique—enabling it to produce a well-informed final report. Adding Concurrent Fan-Out and Feedback Loops Sequential orchestration works well but can be slow. When tasks are independent—neither needs the other's output—running them in parallel saves time. The demo implements this with asyncio.gather . Consider the Retriever and ToolAgent: both need the Planner's output, but neither depends on the other. Running them concurrently cuts the wait time roughly in half: async def run_concurrent_retrieval( plan_text: str, docs: LoadedDocuments, conn: FoundryConnection, ) -> tuple[str, str]: """Run Retriever and ToolAgent in parallel.""" retriever = create_retriever(conn) tool_agent = create_tool_agent(conn) doc_block = docs.combined_text if docs.chunks else "(no documents)" retriever_prompt = f"Plan:\n{plan_text}\n\nDocuments:\n{doc_block}" tool_prompt = f"Analyse the following documents for word count and keywords:\n{doc_block}" # Execute both agents concurrently (snippets_text, r_elapsed), (tool_text, t_elapsed) = await asyncio.gather( _run_agent(retriever, retriever_prompt), _run_agent(tool_agent, tool_prompt), ) return snippets_text, tool_text The asyncio.gather function runs both coroutines concurrently and returns when both complete. If the Retriever takes 3 seconds and the ToolAgent takes 1.5 seconds, the total wait is approximately 3 seconds rather than 4.5 seconds. Implementing the Feedback Loop The most sophisticated orchestration pattern is the Critic–Retriever feedback loop. When the Critic identifies gaps in the retrieved information, the orchestrator sends them back to the Retriever for additional retrieval, then re-evaluates: async def run_critic_with_feedback( plan_text: str, snippets_text: str, docs: LoadedDocuments, conn: FoundryConnection, max_iterations: int = 2, ) -> tuple[str, str]: """ Run Critic with feedback loop to Retriever. Returns (final_snippets, final_critique). """ critic = create_critic(conn) retriever = create_retriever(conn) current_snippets = snippets_text for iteration in range(max_iterations): # Run Critic critic_prompt = f"Plan:\n{plan_text}\n\nExtracted snippets:\n{current_snippets}" critique_text, _ = await _run_agent(critic, critic_prompt) # Check if gaps were found if not critique_text.upper().startswith("GAPS FOUND"): return current_snippets, critique_text # Gaps found — send back to Retriever for more extraction gap_fill_prompt = ( f"Previous snippets:\n{current_snippets}\n\n" f"Gaps identified:\n{critique_text}\n\n" f"Documents:\n{docs.combined_text}\n\n" "Extract additional relevant passages to fill these gaps." ) additional_snippets, _ = await _run_agent(retriever, gap_fill_prompt) current_snippets = f"{current_snippets}\n\n--- Gap-fill iteration {iteration + 1} ---\n{additional_snippets}" # Max iterations reached — run final critique final_critique, _ = await _run_agent(critic, f"Plan:\n{plan_text}\n\nExtracted snippets:\n{current_snippets}") return current_snippets, final_critique This feedback loop pattern significantly improves output quality. The Critic acts as a quality gate, and when standards aren't met, the system iteratively improves rather than producing incomplete results. The full workflow combines all three patterns—sequential where dependencies require it, concurrent where independence allows it, and feedback loops for quality assurance: async def run_full_workflow( question: str, docs: LoadedDocuments, conn: FoundryConnection, ) -> WorkflowResult: """ End-to-end workflow showcasing THREE orchestration patterns: 1. Planner runs first (sequential — must happen before anything else). 2. Retriever + ToolAgent run concurrently (fan-out on independent tasks). 3. Critic reviews with feedback loop (iterates with Retriever if gaps found). 4. Writer produces final report (sequential — needs everything above). """ wf = WorkflowResult(question=question) # Step 1: Planner (sequential) plan_text, elapsed = await _run_agent(create_planner(conn), planner_prompt) wf.steps.append(StepResult("Planner", planner_prompt, plan_text, elapsed)) # Step 2: Concurrent fan-out (Retriever + ToolAgent) snippets_text, tool_text = await run_concurrent_retrieval(plan_text, docs, conn) # Step 3: Critic with feedback loop final_snippets, critique_text = await run_critic_with_feedback( plan_text, snippets_text, docs, conn ) # Step 4: Writer (sequential — needs everything) writer_prompt = ( f"Original question: {question}\n\n" f"Plan:\n{plan_text}\n\n" f"Snippets:\n{final_snippets}\n\n" f"Stats:\n{tool_text}\n\n" f"Critique:\n{critique_text}" ) report_text, elapsed = await _run_agent(create_writer(conn), writer_prompt) wf.final_report = report_text return wf This hybrid approach maximises both correctness and performance. Dependencies are respected, independent work happens in parallel, and quality is ensured through iterative feedback. Implementing Tool Calling Some agents benefit from deterministic tools rather than relying entirely on LLM generation. The ToolAgent demonstrates this pattern with two utility functions: word counting and keyword extraction. MAF supports tool calling through function declarations with Pydantic type annotations: from typing import Annotated from pydantic import Field def word_count( text: Annotated[str, Field(description="The text to count words in")] ) -> int: """Count words in a text string.""" return len(text.split()) def extract_keywords( text: Annotated[str, Field(description="The text to extract keywords from")], top_n: Annotated[int, Field(description="Number of keywords to return", default=5)] ) -> list[str]: """Extract most frequent words (simple implementation).""" words = text.lower().split() # Filter common words, count frequencies, return top N word_counts = {} for word in words: if len(word) > 3: # Skip short words word_counts[word] = word_counts.get(word, 0) + 1 sorted_words = sorted(word_counts.items(), key=lambda x: x[1], reverse=True) return [word for word, count in sorted_words[:top_n]] The Annotated type with Field descriptions provides metadata that MAF uses to generate function schemas for the LLM. When the model needs to count words, it invokes the word_count tool rather than attempting to count in its response (which LLMs notoriously struggle with). The ToolAgent receives these functions in its constructor: def create_tool_agent(conn: FoundryConnection) -> ChatAgent: return ChatAgent( chat_client=_make_client(conn), name="ToolHelper", instructions=( "You are a utility agent. Use the provided tools to compute " "word counts or extract keywords when asked. Return the tool " "output directly — do not embellish." ), tools=[word_count, extract_keywords], ) This pattern—combining LLM reasoning with deterministic tools—produces more reliable results. The LLM decides when to use tools and how to interpret results, but the actual computation happens in Python where precision is guaranteed. Running the Demo With the architecture explained, here's how to run the demo yourself. Setup takes about five minutes. Prerequisites You'll need Python 3.10 or higher and Foundry Local installed on your machine. Install Foundry Local by following the instructions at github.com/microsoft/Foundry-Local, then verify it works: foundry --help Installation Clone the repository and set up a virtual environment: git clone https://github.com/leestott/agentframework--foundrylocal.git cd agentframework--foundrylocal python -m venv .venv # Windows .venv\Scripts\activate # macOS / Linux source .venv/bin/activate pip install -r requirements.txt copy .env.example .env CLI Usage Run the research workflow from the command line: python -m src.app "What are the key features of Foundry Local and how does it compare to cloud inference?" --docs ./data You'll see agent-by-agent progress with timing information: Web Interface For a visual experience, launch the Flask-based web UI: python -m src.app.web Open http://localhost:5000 in your browser. The web UI provides real-time streaming of agent progress, a visual pipeline showing both orchestration patterns, and an interactive demos tab showcasing tool calling capabilities. CLI Options The CLI supports several options for customisation: --docs: Folder of local documents to search (default: ./data) --model: Foundry Local model alias (default: qwen2.5-0.5b) --mode: full for sequential + concurrent, or sequential for simpler pipeline --log-level: DEBUG, INFO, WARNING, or ERROR For higher quality output, try larger models: python -m src.app "Explain multi-agent benefits" --docs ./data --model qwen2.5-7b Validate Tool/Function Calling Run the dedicated tool calling demo to verify function calling works: python -m src.app.tool_demo This tests direct tool function calls ( word_count , extract_keywords ), LLM-driven tool calling via the ToolAgent, and multi-tool requests in a single prompt. Run Tests Run the smoke tests to verify your setup: pip install pytest pytest-asyncio pytest tests/ -v The smoke tests check document loading, tool functions, and configuration—they do not require a running Foundry Local service. Interactive Demos: Exploring MAF Capabilities Beyond the research workflow, the web UI includes five interactive demos showcasing different MAF capabilities. Each demonstrates a specific pattern with suggested prompts and real-time results. Weather Tools demonstrates multi-tool calling with an agent that provides weather information, forecasts, city comparisons, and activity recommendations. The agent uses four different tools to construct comprehensive responses. Math Calculator shows precise calculation through tool calling. The agent uses arithmetic, percentage, unit conversion, compound interest, and statistics tools instead of attempting mental math—eliminating the calculation errors that plague LLM-only approaches. Sentiment Analyser performs structured text analysis, detecting sentiment, emotions, key phrases, and word frequency through lexicon-based tools. The results are deterministic and verifiable. Code Reviewer analyses code for style issues, complexity problems, potential bugs, and improvement opportunities. This demonstrates how tool calling can extend AI capabilities into domain-specific analysis. Multi-Agent Debate showcases sequential orchestration with interdependent outputs. Three agents—one arguing for a position, one against, and a moderator—debate a topic. Each agent receives the previous agent's output, demonstrating how multi-agent systems can explore topics from multiple perspectives. Troubleshooting Common issues and their solutions: foundry: command not found : Install Foundry Local from github.com/microsoft/Foundry-Local foundry-local-sdk is not installed : Run pip install foundry-local-sdk Model download is slow: First download can be large. It's cached for future runs. No documents found warning: Add .txt or .md files to the --docs folder Agent output is low quality: Try a larger model alias, e.g. --model phi-3.5-mini Web UI won't start: Ensure Flask is installed: pip install flask Port 5000 in use: The web UI uses port 5000. Stop other services or set PORT=8080 environment variable Key Takeaways Multi-agent systems decompose complex tasks: Specialised agents (Planner, Retriever, Critic, Writer) produce better results than single-agent approaches by focusing each agent on what it does best Local AI eliminates cloud dependencies: Foundry Local provides on-device inference with automatic hardware acceleration, keeping all data on your machine MAF simplifies agent development: The ChatAgent abstraction handles message threading, tool execution, and response parsing, letting you focus on agent behaviour Three orchestration patterns serve different needs: Sequential pipelines maintain dependencies; concurrent fan-out parallelises independent work; feedback loops enable iterative quality improvement Feedback loops improve quality: The Critic–Retriever feedback loop catches gaps and contradictions, iterating until quality standards are met rather than producing incomplete results Tool calling adds precision: Deterministic functions for counting, calculation, and analysis complement LLM reasoning for more reliable results The same patterns scale to production: This demo architecture—bootstrapping, agent creation, orchestration—applies directly to real-world research and analysis systems Conclusion and Next Steps The Local Research & Synthesis Desk demonstrates that sophisticated multi-agent AI systems don't require cloud infrastructure. With Microsoft Agent Framework for orchestration and Foundry Local for inference, you can build production-quality workflows that run entirely on your hardware. The architecture patterns shown here—specialised agents with clear roles, sequential pipelines for dependent tasks, concurrent fan-out for independent work, feedback loops for quality assurance, and tool calling for precision—form a foundation for building more sophisticated systems. Consider extending this demo with: Additional agents for fact-checking, summarisation, or domain-specific analysis Richer tool integrations connecting to databases, APIs, or local services Human-in-the-loop approval gates before producing final reports Different model sizes for different agents based on task complexity Start with the demo, understand the patterns, then apply them to your own research and analysis challenges. The future of AI isn't just cloud models—it's intelligent systems that run wherever your data lives. Resources Local Research & Synthesis Desk Repository – Full source code with documentation and examples Foundry Local – Official site for on-device AI inference Foundry Local GitHub Repository – Installation instructions and CLI reference Foundry Local SDK Documentation – Python SDK reference on Microsoft Learn Microsoft Agent Framework Documentation – Official MAF tutorials and user guides MAF Orchestrations Overview – Deep dive into workflow patterns agent-framework-core on PyPI – Python package for MAF Agent Framework Samples – Additional MAF examples and patternsDeploying Custom Models with Microsoft Olive and Foundry Local
Over the past few weeks, we've been on quite a journey together. We started by exploring what makes Phi-4 and small language models so compelling, then got our hands dirty running models locally with Foundry Local. We leveled up with function calling, and most recently built a complete multi-agent quiz application with an orchestrator coordinating specialist agents. Our quiz app works great locally, but it relies on Foundry Local's catalog models — pre-optimized and ready to go. What happens when you want to deploy a model that isn't in the catalog? Maybe you've fine-tuned a model on domain-specific quiz data, or a new model just dropped on Hugging Face that you want to use. Today we'll take a model from Hugging Face, optimize it with Microsoft Olive, register it with Foundry Local, and run our quiz app against it. The same workflow applies to any model you might fine-tune for your specific use case. Understanding Deployment Options Before we dive in, let's understand the landscape of deployment options for SLM applications. There are several routes to deploying SLM applications depending on your target environment. The Three Main Paths vLLM is the industry standard for cloud deployments — containerized, scalable, handles many concurrent users. Great for Azure VMs or Kubernetes. Ollama offers a middle ground — simpler than vLLM but still provides Docker support for easy sharing and deployment. Foundry Local + Olive is Microsoft's edge-first approach. Optimize your model with Olive, serve with Foundry Local or a custom server. Perfect for on-premise, offline, or privacy-focused deployments. In keeping with the edge-first theme that's run through this series, we'll focus on the Foundry Local path. We'll use Qwen 2.5-0.5B-Instruct — small enough to optimize quickly and demonstrate the full workflow. Think of it as a stand-in for a model you've fine-tuned on your own quiz data. Prerequisites You'll need: Foundry Local version 0.8.117 or later Python 3.10+ for the quiz app (the foundry-local-sdk requires it) A separate Python 3.9 environment for Olive (Olive 0.9.x has this requirement) The quiz app from the previous article Having two Python versions might seem odd, but it mirrors a common real-world setup: you optimize models in one environment and serve them in another. The optimization is a one-time step. Installing Olive Dependencies In your Python 3.9 environment: pip install olive-ai onnxruntime onnxruntime-genai pip install transformers>=4.45.0,<5.0.0 Important: Olive is not compatible with Transformers 5.x. You must use version 4.x. Model Optimization with Olive Microsoft Olive is the bridge between a Hugging Face model and something Foundry Local can serve. It handles ONNX conversion, graph optimization, and quantization in a single command. Understanding Quantization Quantization reduces model size by converting weights from high-precision floating point to lower-precision integers: Precision Size Reduction Quality Best For FP32 Baseline Best Development, debugging FP16 50% smaller Excellent GPU inference with plenty of VRAM INT8 75% smaller Very Good Balanced production INT4 87.5% smaller Good Edge devices, resource-constrained We'll use INT4 to demonstrate the maximum compression. For production with better quality, consider INT8 — simply change --precision int4 to --precision int8 in the commands below. Running the Optimization The optimization script at scripts/optimize_model.py handles two things: downloading the model locally (to avoid authentication issues), then running Olive. The download step is important. The ONNX Runtime GenAI model builder internally requests HuggingFace authentication even for public models. Rather than configuring tokens, we download the model first with token=False, then point Olive at the local path: from huggingface_hub import snapshot_download local_path = snapshot_download("Qwen/Qwen2.5-0.5B-Instruct", token=False) Then the Olive command runs against the local copy: cmd = [ sys.executable, "-m", "olive", "auto-opt", "--model_name_or_path", local_path, "--trust_remote_code", "--output_path", "models/qwen2.5-0.5b-int4", "--device", "cpu", "--provider", "CPUExecutionProvider", "--precision", "int4", "--use_model_builder", "--use_ort_genai", "--log_level", "1", ] Key flags: --precision int4 quantizes weights to 4-bit integers, --use_model_builder reads each transformer layer and exports it to ONNX, and --use_ort_genai outputs in the format Foundry Local consumes. Run it: python scripts/optimize_model.py This process takes about a minute. When complete, you'll see the output directory structure. models/qwen2.5-0.5b-int4/model/ ├── model.onnx # ONNX graph (162 KB) ├── model.onnx.data # Quantized INT4 weights (823 MB) ├── genai_config.json # ONNX Runtime GenAI config ├── tokenizer.json # Tokenizer vocabulary (11 MB) ├── vocab.json # Token-to-ID map (2.7 MB) ├── merges.txt # BPE merges (1.6 MB) ├── tokenizer_config.json ├── config.json ├── generation_config.json ├── special_tokens_map.json └── added_tokens.json Total size: approximately 838MB — a significant reduction from the original, while maintaining usable quality for structured tasks like quiz generation. Registering with Foundry Local With the model optimized, we need to register it with Foundry Local. Unlike cloud model registries, there's no CLI command — you place files in the right directory and Foundry discovers them automatically. Foundry's Model Registry foundry cache cd # Windows: C:\Users\<username>\.foundry\cache\ # macOS/Linux: ~/.foundry/cache/ Foundry organizes models by publisher: .foundry/cache/models/ ├── foundry.modelinfo.json ← catalog of official models ├── Microsoft/ ← pre-optimized Microsoft models │ ├── qwen2.5-7b-instruct-cuda-gpu-4/ │ ├── Phi-4-cuda-gpu-1/ │ └── ... └── Custom/ ← your models go here The Registration Script The script at scripts/register_model.sh does two things: copies all model files into the Foundry cache, and creates the inference_model.json configuration file. The critical file is inference_model.json — without it, Foundry won't recognize your model: { "Name": "qwen-quiz-int4", "PromptTemplate": { "system": "<|im_start|>system\n{Content}<|im_end|>", "user": "<|im_start|>user\n{Content}<|im_end|>", "assistant": "<|im_start|>assistant\n{Content}<|im_end|>", "prompt": "<|im_start|>user\n{Content}<|im_end|>\n<|im_start|>assistant" } } The PromptTemplate defines the ChatML format that Qwen 2.5 expects. The {Content} placeholder is where Foundry injects the actual message content at runtime. If you were deploying a Llama or Phi model, you'd use their respective prompt templates. Run the registration: scripts/register_model.sh Verify Registration foundry cache ls Test the Model foundry model run qwen-quiz-int4 The model loads via ONNX Runtime on CPU. Try a simple prompt to verify it responds. Integrating with the Quiz App Here's where things get interesting. The application-level change is one line in utils/foundry_client.py: # Before: DEFAULT_MODEL_ALIAS = "qwen2.5-7b-instruct-cuda-gpu" # After: DEFAULT_MODEL_ALIAS = "qwen-quiz-int4" But that one line raised some issues worth understanding. Issue 1: The SDK Can't See Custom Models The Foundry Local Python SDK resolves models by looking them up in the official catalog — a JSON file of Microsoft-published models. Custom models in the Custom/ directory aren't in that catalog. So FoundryLocalManager("qwen-quiz-int4") throws a "model not found" error, despite foundry cache ls and foundry model run both working perfectly. The fix in foundry_client.py is a dual code path. It tries the SDK first (works for catalog models), and when that fails with a "not found in catalog" error, it falls back to discovering the running service endpoint directly: def _discover_endpoint(): """Discover running Foundry service endpoint via CLI.""" result = subprocess.run( ["foundry", "service", "status"], capture_output=True, text=True, timeout=10 ) match = re.search(r"(http://\S+?)(?:/openai)?/status", result.stdout) if not match: raise ConnectionError( "Foundry service is not running.\n" f"Start it with: foundry model run {DEFAULT_MODEL_ALIAS}" ) return match.group(1) The workflow becomes two terminals: Terminal 1: foundry model run qwen-quiz-int4 Terminal 2: python main.py The client auto-discovers the endpoint and connects. For catalog models, the existing FoundryLocalManager path works unchanged. Issue 2: Tool Calling Format For catalog models, Foundry's server-side middleware intercepts <tool_call> tags in the model's output and converts them into structured tool_calls objects in the API response. This is configured via metadata in foundry.modelinfo.json. For custom models, those metadata fields aren't recognized — Foundry ignores them in inference_model.json. The <tool_call> tags pass through as raw text in response.choices[0].message.content. Since our custom model outputs the exact same <tool_call> format, we added a small fallback parser in agents/base_agent.py — the same pattern we explored in our function calling article. After each model response, if tool_calls is None, we scan the content for tags: def _parse_text_tool_calls(content: str) -> list: """Parse <tool_call>...</tool_call> tags from model output.""" blocks = re.findall(r"<tool_call>\s*(\{.*?\})\s*</tool_call>", content, re.DOTALL) calls = [] for block in blocks: try: data = json.loads(block) calls.append(_TextToolCall(data["name"], json.dumps(data.get("arguments", {})))) except (json.JSONDecodeError, KeyError): continue return calls The model's behavior is identical; only the parsing location changes — from server-side (Foundry middleware) to client-side (our code). Part 7: Testing the Deployment With the model running in one terminal, start the quiz app in another: Terminal 1: foundry model run qwen-quiz-int4 Terminal 2: cd multi_agents_slm && python main.py Now test the full flow. Generate a quiz: Test the Full Flow Generate a quiz: Example output: The orchestrator successfully calls the generate_new_quiz tool, and the QuizGeneratorAgent produces well-structured quiz JSON. Model Limitations The 0.5B INT4 model occasionally struggles with complex reasoning or basic arithmetic. This is expected from such a small, heavily quantized model. For production use cases requiring higher accuracy, use Qwen 2.5-1.5B or Qwen 2.5-7B for better quality, or use INT8 quantization instead of INT4. The deployment workflow remains identical — just change the model name and precision in the optimization script. What You've Accomplished Take a moment to appreciate the complete journey across this series: Article What You Learned 1. Phi-4 Introduction Why SLMs matter, performance vs size tradeoffs 2. Running Locally Foundry Local setup, basic inference 3. Function Calling Tool use, external API integration 4. Multi-Agent Systems Orchestration, specialist agents 5. Deployment Olive optimization, Foundry Local registration, custom model deployment You now have end-to-end skills for building production SLM applications: understanding the landscape, local development with Foundry Local, agentic applications with function calling, multi-agent architectures, model optimization with Olive, and deploying custom models to the edge. Where to Go From Here The logical next step is fine-tuning for your domain. Medical quiz tutors trained on USMLE questions, legal assistants trained on case law, company onboarding bots trained on internal documentation — use the same Olive workflow to optimize and deploy your fine-tuned model. The same ONNX model we registered with Foundry Local could also run on mobile devices via ONNX Runtime Mobile, or be containerized for server-side edge deployment. The full source code, including the optimization and registration scripts, is available in the GitHub repository. Resources: Microsoft Olive — Model optimization toolkit Foundry Local Documentation — Setup and CLI reference Compiling Hugging Face models for Foundry Local — Official guide ONNX Runtime GenAI — Powers Foundry Local's inference Edge AI for Beginners — Microsoft's 8-module Edge AI curriculum Quiz App Source Code — Full repository with deployment scripts This series has been a joy to write. I'd love to see what you build — share your projects in the comments, and don't hesitate to open issues on the GitHub repo if you encounter challenges. Until next time — keep building, keep optimizing, and keep pushing what's possible with local AI.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!
