AI SummaryCopilot instructions for the Agentic RAG Demo project that provides context about an Azure-based RAG system with SharePoint integration, helping developers understand the codebase architecture and key components. Developers working on or extending this enterprise document processing system benefit from having immediate project context available.
Install
Copy this and paste it into Claude Code, Cursor, or any AI assistant:
I want to add the "agentic-rag-demo — Copilot Instructions" prompt rules to my project. Repository: https://github.com/roie9876/agentic-rag-demo Please read the repo to find the rules/prompt file, then: 1. Download it to the correct location (.cursorrules, .windsurfrules, .github/prompts/, or project root — based on the file type) 2. If there's an existing rules file, merge the new rules in rather than overwriting 3. Confirm what was added
Description
Copilot Instructions for agentic-rag-demo
Agentic RAG Demo - Project Context Instructions
You are working with the Agentic RAG Demo project - a comprehensive Azure-based RAG system with SharePoint integration and multimodal document processing. Use this context to understand the codebase when helping with development tasks.
🎯 **Quick Project Summary**
Tech Stack: Streamlit UI + Azure Functions + Azure OpenAI + Azure AI Search + SharePoint integration Main File: agentic-rag-demo.py (2400+ lines) - Primary Streamlit app with tabbed interface Key Purpose: Enterprise document ingestion, processing, and intelligent retrieval from SharePoint and uploads
📁 **Key Directory Structure**
` agentic-rag-demo/ ├── agentic-rag-demo.py # Main Streamlit app (PRIMARY FILE) ├── agent_foundry.py # AI Foundry agent management ├── azure_function_helper.py # Azure Function deployment ├── sharepoint_index_manager.py # SharePoint indexing with dynamic index selection ├── sharepoint_scheduler.py # SharePoint parallel processing & reporting ├── sharepoint_reports.py # SharePoint processing reports ├── chunking/ # Document processing modules │ ├── document_chunking.py # Main DocumentChunker class │ ├── chunker_factory.py # Chunker selection logic │ └── chunkers/ # Format-specific processors ├── connectors/sharepoint/ # SharePoint integration │ ├── sharepoint_data_reader.py # Main SharePoint client & file access │ └── sharepoint_files_indexer.py # Document processor (legacy) ├── tools/ # Azure service clients ├── health_check/ # Health monitoring ├── function/ # Azure Function code └── app/ # Modular components `
Main Application (`agentic-rag-demo.py`)
7 Tabs: • 🩺 Health Check - Service monitoring • 1️⃣ Create Index - New search index • 2️⃣ Manage Index - Index management + agent config • 3️⃣ Test Retrieval - Query testing • 📁 SharePoint Index - Dynamic SharePoint folder indexing with index selection • ⚙️ Function Config - Azure Function deployment • 🤖 AI Foundry Agent - Agent creation Key Functions: • run_streamlit_ui() - Main UI orchestrator • _chunk_to_docs() - Document processing pipeline (shared by all tabs) • init_openai() - OpenAI client setup • init_search_client() - Azure AI Search setup • Dynamic index selection available across all tabs
Discussion
Health Signals
My Fox Den
Community Rating
Sign in to rate this booster
Works With
Any AI assistant that accepts custom rules or system prompts