Azure OpenAI Samples

📌 Quick Reference: Code Cookbook / Sample Code Collection

Note

To explore relevant demo codes across various repositories, you'll need to click through serveral pages and review them back and forth.

This repository's topic-based reclassification reduces the time spent reviewing code and contains demo code copied from various sources to showcase minimal implementations.

Important

🔹For more details and the latest code updates, please refer to the original link provided in the README.md file within each directory.
🔹Disclaimer: This repository is created to collect sample code. Configuration for execution is not included, and it contains code that does not utilize LLMs. The focus is on collecting samples relevant to Azure OpenAI and OpenAI as much as possible.

📖 Repository structure

📁 agent

• agent_debates_with_tools
• agent_multi-agent_pattern
• agent_planning_pattern
• agent_react_pattern
• agent_reflection_pattern
• agent_tool_use_pattern
• role_playing

📁 azure

• azure_ai_foundry_sft_finetuning
• azure_ai_search
• azure_bot
• azure_cosmos_db
• azure_postgres_db
• azure_sql_db
• sharepoint_azure_function

📁 data

• azure_oai_usage_stats_(power_bi)
• chain-of-thought
• fabric_cosmosdb_chat_analytics
• presidio_(redaction)
• prompt_buddy_(power_app)
• sammo_(prompt_opt)
• semantic_chunking_(rag)

📁 eval_safety

• evaluation_llm_as_judge
• guardrails
• pyrit_(safety_eval)

📁 framework_dev

• autogen_(framework)
• code_editor_(vscode)
• diagram_to_infra_template
• e2e_testing_agent
• gui_automation
• guidance_(framework)
• magentic-one_(agent)
• mcp_(model_context_protocol)
• memory_for_llm
• mini-copilot
• omniparser_(gui)
• prompt_flow_(framework)
• semantic_kernel_(framework)
• tiny_troupe_(framework)

📁 industry

• auto_insurance_claims
• career_assistant_agent
• contract_review
• customer_support_agent
• damage_insurance_claims
• invoice_+_sku_matching
• invoice_payments
• invoice_unit_standardization
• music_compositor_agent
• news_summarization_agent
• nyc_taxi_pickup_(ui)
• patient_case_summary
• project_management
• stock_analysis
• travel_planning_agent

📁 multi_modal

• image_gen
• video_understanding
• vision_rag
• visualize_embedding
• voice_audio

📁 nlp

• multilingual_translation_(co-op-translator)
• search_the_internet_and_summarize
• sentiment_analysis_for_customer_feedback
• translate_manga_into_english
• txt2sql

📁 rag

• adaptive-rag
• agentic_rag
• contextual_retrieval_(rag)
• corrective_rag
• fusion_retrieval_reranking_(rag)
• graphrag
• hyde_(rag)
• query_rewriting_(rag)
• raptor_(rag)
• self_rag

📁 research_analysis

• analysis_of_twitter_the-algorithm_source_code
• deep_research
• openai_code_interpreter
• r&d-agent

📚 References

• OpenAI Cookbook
• LangChain Cookbook
• LlamaCloud Demo
• Chainlit Cookbook
• Microsoft AI Agents for Beginners
• GenAI Agents by NirDiamant
• RAG Techniques by NirDiamant

💻 Microsoft Frameworks and Libraries

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 / x-ref
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. OmniParser (Sep 2024): A simple screen parsing tool towards pure vision based GUI agent.
8. TinyTroupe: LLM-powered multiagent persona simulation for imagination enhancement and business insights. [Mar 2024]
9. RD-Agent: open source R&D automation tool ref [Apr 2024]
10. Magentic-One: Built on AutoGen. A Generalist Multi-Agent System for Solving Complex Tasks [Nov 2024]
11. PyRIT (Dec 2023): Python Risk Identification Tool for generative AI, focusing on LLM robustness against issues like hallucination, bias, and harassment.
12. 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]
13. Microsoft Fabric: Fabric integrates technologies like Azure Data Factory, Azure Synapse Analytics, and Power BI into a single unified product [May 2023]

➡️ Convert ipynb to Python

• 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}")

Contributor 👀

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