A one-stop hub, like a sample library. This repository is organized by topic to help reduce the time spent searching for and reviewing sample code. It offers a curated collection of minimal implementations and sample code from various sources.

💡How to switch between OpenAI and Azure OpenAI endpoints with Python

• Programming Languages
  • Python:🐍
  • Jupyter Notebook:📔
  • JavaScript/TypeScript:🟦
  • Extra:🔴
• Status & Action
  • Created:✨ (A unique example found only in this repository)
  • Modified:🎡 (An example that has been modified from a referenced source)
  • Copied:🧲 (When created or modified emojis are not following)
  • See the details at the URL:🔗
• Microsoft libraries or products:🪟

⭐ If you find this repository useful, please consider giving it a star!

• a2a_semantic_kernel🐍✨🔗🪟: Agent2Agent (A2A) Protocol Implementation with Semantic Kernel
• a2a_server_client🐍: Agent2Agent (A2A) Protocol - official implementation of Server/Client
• agent_multi-agent_pattern📔🪟: Agent multi-agent pattern
• agent_planning_pattern📔🪟: Agent planning pattern
• agent_react_pattern📔: Agent react pattern
• agent_reflection_pattern📔: Agent reflection pattern with LangGraph
• agent_reflection_pattern📔: Agent reflection pattern
• agent_tool_use_pattern📔🪟: Agent tool use pattern
• arxiv_agent🐍✨🎡: ArXiv agent
• chess_agent🐍: Chess agent
• multi_agentic_system_simulator🐍✨🔗: A Multi-Agentic System Simulator. Visualize Agent interactions.
• role_playing📔: Role-playing
• web_scrap_agent🐍✨🎡: Web scraping agent
• x-ref: 📁industry

• azure_ai_foundry_sft_finetuning📔🪟: Supervised Fine-tuning
• azure_ai_foundry_workshop📔🪟: Azure AI Foundry Workshop
• azure_ai_search📔🪟: Chunking, Document Processing, Evaluation
• azure_bot📔🪟: Bot Service API
• azure_cosmos_db📔🪟: Cosmos DB as a Vector Database
• azure_cosmos_db_enn🐍✨🪟: Cosmos DB Exact Nearest Neighbor (ENN) Vector Search for Precise Retrieval
• azure_devops_(project_status_report)🐍✨🪟: Azure DevOps – Project Status Report
• azure_document_intelligence🐍🪟: Azure Document Intelligence
• azure_evaluation_sdk🐍🪟: Azure Evaluation SDK
• azure_machine_learning📔🪟: Azure Machine Learning
• azure_postgres_db📔🪟: pgvector for Vector Database
• azure_sql_db📔🪟: Azure SQL as a Vector Database
• copilot_studio🔗🪟: A low-code platform for bots and agents (formerly Power Virtual Agents)
• m365_agents_sdk🟦🪟: Rebranding of Azure Bot Framework
• sentinel_openai🔗🪟: Sentinel – Security Information and Event Management (SIEM)
• sharepoint_azure_function📔🪟: SharePoint Integration with Azure Functions
• teams_ai_sdk🔗🪟: Teams AI SDK

• anthropic: Anthropic Cookbook
• gemini: Gemini API Cookbook
• openai: OpenAI Cookbook

• azure_oai_usage_stats_(power_bi)🔴🪟: Azure OpenAI usage stats using Power BI
• azure_ocr_scan_doc_to_table🐍✨🪟: Azure Document Intelligence – Extract tables from document images and convert them to Excel
• chain-of-thought🐍🔴: Chain-of-thought reasoning prompt
• fabric_cosmosdb_chat_analytics📔🔴✨(visual)🪟: Fabric: Data processing, ingestion, transformation, and reporting on a single platform
• firecrawl_(crawling)🐍: Firecrawl – Web crawling and scraping
• ms_graph_api📔🪟: Microsoft Graph API
• presidio_(redaction)📔🪟: Presidio – Data redaction and anonymization
• prompt_buddy_(power_app)🔴🪟: Prompt sharing application built on Power App
• prompt_leaked🔴: Prompt leakage detection and analysis
• sammo_(prompt_opt)📔🪟: A Structure-Aware Approach to Efficient Compile-Time Prompt Optimization
• semantic_chunking_(rag)📔: Semantic chunking for Retrieval-Augmented Generation (RAG)

• code_editor_(vscode)🐍✨🔗🪟: Visual Studio Code extension development
• diagram_to_infra_template_(bicep)🐍✨🪟: Bicep – Infrastructure as Code (IaC) language
• e2e_testing_agent📔🪟: End-to-end testing with Playwright automation framework
• git_repo_with_chat🐍✨: Chat with Github repository
• gui_automation🔗🪟: Omni Parser – Screen parsing tool / Windows Agent Arena (WAA)
• llm_router🐍✨🎡: LLM request routing and orchestration
• mcp_(model_context_protocol)🐍✨🔗: Model Context Protocol
• mcp_(sse)🐍✨🔗: Remote MCP (Model Context Protocol) calls
• mcp_to_openai_func_call🐍✨: MCP Tool Spec to OpenAI Function Call Converter
• memory_for_llm🐍🔗: Memory management techniques for LLMs – K-LaMP🪟
• memory_graphiti🐍✨: Graph and neo4j based Memory
• mini-copilot🐍✨🔗: DSL approach to calling the M365 API
• mixture_of_agents🐍✨🎡: Multi-agent system for collecting responses from multiple LLMs
• open_telemetry🐍✨: OpenTelemetry – Tracing LLM requests and logging

• evaluation_llm_as_judge📔: Using LLMs for automated evaluation and scoring
• guardrails📔: Guardrails for AI safety and compliance
• pyrit_(safety_eval)📔🪟: Python Risk Identification Tool

• agno_(framework)🐍: Agno – A simple, intuitive agent framework
• autogen_(framework)🐍🪟: AutoGen – A Framework for LLM Agent
• crewai_(framework)🐍: CrewAI – Agent collaboration framework
• dspy_(framework)🐍📔: DSPy – Declarative Language Model Calls into Self-Improving Pipelines
• guidance_(framework)📔🪟: Guidance – Prompt programming framework
• haystack_(framework)🐍📔: Haystack – NLP framework for RAG and search
• langchain_(framework)📔: LangChain – Framework for LLM applications
• llamaindex_(framework)📔: LlamaIndex – Data framework for LLM retrieval/agent
• magentic-one_(agent)🐍🪟: Magentic-One – Multi-agent system for solving open-ended web and file-based tasks
• mem0_(framework)🐍📔: Mem0 – LLM Memory
• omniparser_(gui)📔🪟: OmniParser – GUI automation and parsing tool
• prompt_flow_(framework)📔🪟: Prompt Flow – LLM Workflow
• prompty_(framework)🔗🔴🪟: Prompty – Prompt management
• pydantic_ai_(framework)🐍: Pydantic AI – Pydantic agent framework
• semantic_kernel_(framework)🐍🪟: Semantic Kernel – Microsoft LLM orchestration framework
• smolagent_(framework)🐍: SmolAgent – Hugging Face Lightweight AI agent framework
• tiny_troupe_(framework)📔🪟: Tiny Troupe – Multi agent persona simulation
• x-ref: 📁microsoft-frameworks-and-libraries:

• auto_insurance_claims📔: Automation for auto insurance claims processing
• career_assistant_agent📔: Career guidance and job recommendation agent
• contract_review📔: Legal contract analysis and review
• customer_support_agent📔: Customer support automation
• damage_insurance_claims📔: Automated claims processing for damage insurance
• invoice_sku_product_catalog_matching📔: Invoice and SKU reconciliation for accounting
• invoice_payments📔: Automation for invoice payments
• invoice_standardization📔: Standardizing invoice units for consistency
• music_compositor_agent📔: Music composition assistant
• news_summarization_agent📔: Automated summarization of news articles
• nyc_taxi_pickup_(ui)🐍: NYC taxi pickup analysis and UI visualization
• patient_case_summary📔: Summaries for patient medical cases
• project_management📔: a tools for project tracking and task management
• stock_analysis🐍✨🔗: AutoGen demo for analyzing stock investments
• travel_planning_agent📔: Travel itinerary planner
• youtube_summarize🐍✨: Summarizing YouTube videos using AI

• finetuning_grpo📔: Group Relative Policy Optimization (GRPO) for LLM fine-tuning
• knowledge_distillation📔: Compressing LLM knowledge into smaller models
• llama_finetuning_with_lora📔: LoRA – Low-Rank Adaptation of Large Language Models
• nanoGPT🐍: Lightweight GPT implementation
• nanoMoE🐍: Lightweight Mixture of Experts (MoE) implementation

• azure_prompt_flow🔗🪟: Azure AI Foundry - Prompt flow: E2E development tools for creating LLM flows and evaluation
• mlflow📔: OSS platform managing ML workflows

• image_gen📔: Image creation
• image_gen_dalle📔: Image creation with segmentaion
• openai-agents-sdk-voice-pipeline📔✨: OpenAI Agents SDK for voice processing
• openai-chat-vision📔: Multimodal chat with vision capabilities
• phi-series-cookbook_(slm)🔗🪟: Phi series models cookbook (small language models)
• video_understanding📔: Video content analysis and understanding
• vision_rag📔: Combining visual data with retrieval-augmented generation (RAG)
• visualize_embedding📔: Tools for embedding visualization and analysis
• voice_audio🟦: RTClient sample for using the Realtime API in voice applications

• multilingual_translation_(co-op-translator)🐍🪟: a library for multilingual translation
• search_the_internet_and_summarize📔: Internet search and summarization
• sentiment_analysis_for_customer_feedback📔: Sentiment analysis for customer feedback
• translate_manga_into_english🐍✨: Manga translation into English
• txt2sql🐍: Converting natural language queries into SQL

• adaptive-rag📔: Adaptive retrieval-augmented generation (RAG)
• agentic_rag📔: Agent-based RAG system
• contextual_retrieval_(rag)📔: Context-aware retrieval for RAG
• corrective_rag📔: Improving retrieval results with corrective techniques
• fusion_retrieval_reranking_(rag)📔: Fusion-based retrieval and reranking for RAG
• graphrag📔🪟: Graph-based retrieval-augmented generation
• hyde_(rag)📔: Hypothetical Document Embeddings for better retrieval
• query_rewriting_(rag)📔: Enhancing RAG by rewriting queries for better retrieval
• raptor_(rag)📔: Recursive Abstractive Processing for Tree-Organized Retrieval
• self_rag📔: Self-improving retrieval-augmented generation

• analysis_of_twitter_the-algorithm_source_code📔: Analyzing Twitter’s open-source ranking algorithm
• deep_research_langchain🐍📔: AI-driven deep research and analysis tools using LangChain
• deep_research_smolagents🐍📔: AI-driven deep research and analysis tools using smolagents
• openai_code_interpreter🐍📔: OpenAI’s code interpreter for data analysis
• r&d-agent🐍🪟: Research and development AI agent

You can use the git_cmp.py script (and related files) to compare your local project directories with their corresponding remote GitHub repositories.

1. Index all projects and their GitHub URLs:

   python git_cmp.py --index --root <root_dir> --csv git_cmp_index.csv

   This creates a CSV file listing all projects and their remote URLs.

2. Compare local and remote repositories:

   python git_cmp.py --compare --root <root_dir> --csv git_cmp_index.csv --report git_cmp_report.txt --update_csv git_cmp_needs_update.csv

   This generates a report and a CSV of projects needing updates. It also copies changed files into .cache/ for review.

3. Update local files from cache (optional, use with care):

   python git_cmp.py --manipulate --root <root_dir> --update_csv git_cmp_needs_update.csv

   This copies files from .cache/ back into your project directories, optionally deleting files if flagged.

• --delay_sec <seconds>: Add a delay between GitHub API calls to avoid rate limits.
• --index: Index projects and write a CSV.
• --compare: Compare projects and write a report.
• --manipulate: Update local files from the cache based on the update CSV.

python git_cmp.py --index --root . --csv git_cmp_index.csv
python git_cmp.py --compare --root . --csv git_cmp_index.csv --report git_cmp_report.txt --update_csv git_cmp_needs_update.csv
python git_cmp.py --manipulate --root . --update_csv git_cmp_needs_update.csv

Note:

• Create .env file. Set the GITHUB_TOKEN. e.g.,GITHUB_TOKEN=<your_key>
• Review .cache/ and the generated report before running --manipulate.
• See comments and docstrings in git_cmp.py for more details.

• OpenAI Cookbook
• LangChain Cookbook
• LlamaCloud Demo
• Chainlit Cookbook
• Microsoft AI Agents for Beginners
• GenAI Agents by NirDiamant
• RAG Techniques by NirDiamant
• Gemini API Cookbook
• Anthropic Cookbook
• Awesome LLM Apps
• AI Engineering Hub

1. Semantic Kernel (Feb 2023): An open-source SDK for integrating AI services like OpenAI, Azure OpenAI, and Hugging Face with conventional programming languages such as C# and Python. It's an LLM orchestrator, similar to LangChain. / git
2. Azure ML Prompt Flow (Jun 2023): A visual designer for prompt crafting using Jinja as a prompt template language. / ref / git
3. SAMMO (Apr 2024): A general-purpose framework for prompt optimization. / ref
4. guidance (Nov 2022): A domain-specific language (DSL) for controlling large language models, focusing on model interaction and implementing the "Chain of Thought" technique.
5. Autogen (Mar 2023): A customizable and conversable agent framework. / ref / Autogen Studio (June 2024)
6. UFO (Mar 2024): A UI-focused agent for Windows OS interaction.
7. Prompty (Apr 2024): A template language for integrating prompts with LLMs and frameworks, enhancing prompt management and evaluation.
8. OmniParser (Sep 2024): A simple screen parsing tool towards pure vision based GUI agent.
9. TinyTroupe: LLM-powered multiagent persona simulation for imagination enhancement and business insights. [Mar 2024]
10. RD-Agent: open source R&D automation tool ref [Apr 2024]
11. Magentic-One: Built on AutoGen. A Generalist Multi-Agent System for Solving Complex Tasks [Nov 2024]
12. PyRIT (Dec 2023): Python Risk Identification Tool for generative AI, focusing on LLM robustness against issues like hallucination, bias, and harassment.
13. Presidio: Presidio (Origin from Latin praesidium ‘protection, garrison’). Context aware, pluggable and customizable data protection and de-identification SDK for text and images. [Oct 2019]
14. Microsoft Fabric: Fabric integrates technologies like Azure Data Factory, Azure Synapse Analytics, and Power BI into a single unified product [May 2023]

• To convert a Jupyter notebook (.ipynb) into a runnable Python scrip

pip install nbformat nbconvert

import nbformat
from nbconvert import PythonExporter

# Load the notebook
notebook_filename = 'your_notebook.ipynb'
with open(notebook_filename, 'r', encoding='utf-8') as notebook_file:
notebook_content = nbformat.read(notebook_file, as_version=4)

# Convert the notebook to a Python script
python_exporter = PythonExporter()
python_code, _ = python_exporter.from_notebook_node(notebook_content)

# Save the converted Python code to a .py file
python_filename = notebook_filename.replace('.ipynb', '.py')
with open(python_filename, 'w', encoding='utf-8') as python_file:
python_file.write(python_code)

print(f"Notebook converted to Python script: {python_filename}")

ⓒ https://github.com/kimtth all rights reserved.