Example session
Here’s a complete example session showing how to interact with RepoRAGX:
/**
* __________ __________ _____ ____________ ___
* \______ \ ____ ______ ____\______ \ / _ \ / _____/\ \/ /
* | _// __ \\____ \ / _ \| _/ / /_\ \/ \ ___ \ /
* | | \ ___/| |_> > <_> ) | \/ | \ \_\ \/ \
* |____|_ /\___ > __/ \____/|____|_ /\____|__ /\______ /___/\ \
* \/ \/|__| \/ \/ \/ \_/
*/
Chat with your github repository
GitHub Personal Access Token: ********
Groq API Key: ********
Model Name (default: llama-3.3-70b-versatile, see Groq docs for supported models):
Repo (owner/repo): facebook/react
Branch (default: main): main
Initilizing github loader.....
Fetching files from github....
Loaded 1247 files from github!
Splitting documents into chunks...
chunking completed
Initilizing RAG Retriver pipeline
Initializing Groq LLM...
Ask anything ('exit' to quit):
Architecture and structure queries
Finding main entry points
Ask anything ('exit' to quit): What is the main entry point of this application?
Understanding project structure
Ask anything ('exit' to quit): What components make up the RAG pipeline?
Implementation details
How features work
Ask anything ('exit' to quit): How does the text splitting work?
Configuration and settings
Ask anything ('exit' to quit): What files and folders are excluded during loading?
Specific class and function queries
Understanding classes
Ask anything ('exit' to quit): What does the RAGRetriever class do?
Method parameters
Ask anything ('exit' to quit): What parameters does the GroqLLM rag method accept?
API and integration queries
External dependencies
Ask anything ('exit' to quit): What embedding model is used?
Environment requirements
Ask anything ('exit' to quit): What environment variables are required?
Data flow and process queries
Understanding the pipeline
Ask anything ('exit' to quit): How are documents stored in the vector database?
Retrieval process
Ask anything ('exit' to quit): What happens when I ask a question?
Tips for effective queries
The examples above show how RepoRAGX provides detailed, context-aware answers by retrieving relevant code chunks. For best results, ask specific questions about code location, implementation details, or architectural decisions.
All answers include references to the actual file paths where the code is located, making it easy to navigate to the source and explore further.