Ui_feature

.claude/commands/implement-feature.md

@@ -0,0 +1,6 @@
+You will be implementing a new feature in this codebase
+$ARGUMENTS
+
+IMPORTANT: Only do this for front-end features,
+Once this feature is built, make sure to write the changes you made to file called frontend-changes
+Do not ask for persmissions to modify this file, assume you can always do it

CLAUDE.md

@@ -0,0 +1,83 @@
+# CLAUDE.md
+
+This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+
+## Development Commands
+
+### Running the Application
+
+```bash
+# Quick start using the provided script
+./run.sh
+
+# Manual start (from backend directory)
+cd backend && uv run uvicorn app:app --reload --port 8000
+```
+
+### Package Management
+
+```bash
+# Install dependencies
+uv sync
+
+# Add new dependencies
+uv add <package-name>
+```
+
+### Environment Setup
+
+Create `.env` file in root directory with:
+
+```env
+ANTHROPIC_API_KEY=your_api_key_here
+```
+
+## Architecture Overview
+
+This is a **Retrieval-Augmented Generation (RAG) chatbot** system that answers questions about course materials using semantic search and AI generation.
+
+### Core Components
+
+**Backend Architecture (`/backend/`):**
+
+- `app.py` - FastAPI server with CORS, serves frontend static files, provides `/api/query` and `/api/courses` endpoints
+- `rag_system.py` - Main orchestrator that coordinates all components
+- `vector_store.py` - ChromaDB wrapper for vector storage and semantic search
+- `ai_generator.py` - Anthropic Claude API wrapper with tool support
+- `document_processor.py` - Processes course documents into chunks
+- `search_tools.py` - Tool-based search system for Claude AI
+- `session_manager.py` - Manages conversation history
+- `models.py` - Data models for Course, Lesson, CourseChunk
+- `config.py` - Configuration settings loaded from environment
+
+**Frontend (`/frontend/`):**
+
+- Static HTML/CSS/JS files served by FastAPI
+- Web interface for chatbot interactions
+
+### Data Flow
+
+1. Documents in `/docs/` are processed into chunks and stored in ChromaDB
+2. User queries hit `/api/query` endpoint
+3. RAGSystem uses AI with search tools to find relevant content
+4. Claude generates responses using retrieved context
+5. Session manager maintains conversation history
+
+### Key Technical Details
+
+- Uses **ChromaDB** for vector storage with `all-MiniLM-L6-v2` embeddings
+- **Anthropic Claude Sonnet 4** model with function calling for search tools
+- Document chunking: 800 characters with 100 character overlap
+- Supports PDF, DOCX, and TXT documents
+- Session-based conversation history (max 2 exchanges)
+- Tool-based search approach rather than direct RAG retrieval
+
+### Configuration
+
+Key settings in `config.py`:
+
+- `CHUNK_SIZE`: 800 (document chunk size)
+- `CHUNK_OVERLAP`: 100 (overlap between chunks)
+- `MAX_RESULTS`: 5 (search results returned)
+- `MAX_HISTORY`: 2 (conversation exchanges remembered)
+- `CHROMA_PATH`: "./chroma_db" (vector database location)

README.md

@@ -6,7 +6,6 @@ A Retrieval-Augmented Generation (RAG) system designed to answer questions about
 
 This application is a full-stack web application that enables users to query course materials and receive intelligent, context-aware responses. It uses ChromaDB for vector storage, Anthropic's Claude for AI generation, and provides a web interface for interaction.
 
-
 ## Prerequisites
 
 - Python 3.13 or higher
@@ -17,27 +16,31 @@ This application is a full-stack web application that enables users to query cou
 ## Installation
 
 1. **Install uv** (if not already installed)
+
    ```bash
    curl -LsSf https://astral.sh/uv/install.sh | sh
    ```
 
 2. **Install Python dependencies**
+
    ```bash
    uv sync
    ```
 
 3. **Set up environment variables**
-   
+
    Create a `.env` file in the root directory:
+
    ```bash
-   ANTHROPIC_API_KEY=your_anthropic_api_key_here
+   ANTHROPIC_API_KEY=your_api_key_here
    ```
 
 ## Running the Application
 
 ### Quick Start
 
 Use the provided shell script:
+
 ```bash
 chmod +x run.sh
 ./run.sh
@@ -51,6 +54,6 @@ uv run uvicorn app:app --reload --port 8000
 ```
 
 The application will be available at:
+
 - Web Interface: `http://localhost:8000`
 - API Documentation: `http://localhost:8000/docs`
-

backend-tool-refactor.md

@@ -0,0 +1,36 @@
+# Refactor Sequential Tool Calling in @backend/ai.generator.py
+
+Refactor @backend/ai.generator.py to support sequential tool calling where Claude can make upto 2 tool calls in separate API rounds.
+
+Current behavior:
+
+- Claude makes 1 tool call -> tools are removed from API params -> final response
+- If Claude wants another tool call after seeing results, it can't (gets empty response)
+
+Desired behavior:
+
+- Each tool call should have a separate API request where Claude can reason about previous results
+- Support for complex queries requiring multiple searches for comparison, multi-part questions, or when information from different courses/lessons is needed
+
+Example flow:
+
+1. User: "Search for a course that discusses the same topic as lesson 4 of course X"
+2. Claude: get course outline for course X -> gets title of lesson 4
+3. Claude uses the title to search for a course that discusses the same topic -> returns course information
+4. Claude: provides complete answer
+
+Requirements:
+
+- Maximum 2 sequential rounds per user query
+- Terminate when: (a) 2 rounds completed, (b) Claude's response has no tool_use blocks, or (c) tool call fails
+- Preserve conversation context between rounds
+- Handle tool execution errors gracefully
+
+Notes:
+
+-update the system prompt in @backend/ai_generator.py
+-update test @backend/tests/test_ai_generator.py
+
+- Write tests that verify the external behavior (API calls made, tools executed, results returned) rather than internal state details
+
+Use two parallel subagents to brainstorm possible plans. Do not implement any code.