Product Overview

Cody is an AI assistant designed to let you interactively query your codebase using natural language. It utilizes vector embeddings, chunking, and OpenAI's language models to help you navigate through your code efficiently and intuitively.

Key Features

• File Monitoring: Real-time monitoring of all files in your project's directory and subdirectories.
• Embedding-based Knowledge Base: Create a knowledge base using OpenAI Embeddings. Cody collects the contents of all text and JSON files and adds them to this knowledge base.
• Interactive Q&A: Listen to user inputs, ask questions, and generate responses using the knowledge base.
• Customizable: Easily specify files or directories to ignore during monitoring.

How It Works

Cody continuously updates its knowledge base every time you save a file, ensuring you have the most up-to-date information. It utilizes vector embeddings, chunking, and OpenAI's language models to understand natural language queries and provide relevant responses based on the knowledge base.

Use Cases

• Querying codebase for specific functions or variables
• Navigating through large codebases efficiently
• Getting explanations or examples for code snippets

Technical Requirements

• Dependencies: dotenv, langchain-community, langchain_openai, litellm, watchdog, openai, speech_recognition, gtts, pygame
• Memory: Sufficient memory available for storing vectors
• OpenAI API Key: Replace YOUR_API_KEY_HERE in the .env file with your OpenAI API Key

Benefits

• Efficient and intuitive codebase navigation
• Real-time monitoring of code changes
• Customizable ignore list for excluding irrelevant files or directories

Conclusion

Cody is a powerful AI assistant that helps developers navigate and query their codebase using natural language. With its real-time monitoring, embedding-based knowledge base, and interactive Q&A capabilities, Cody provides an efficient and customizable solution for code exploration and understanding.