🔍 RAG Pipeline For LLMs

📖 Wikipedia Topic

Enter any topic available on Wikipedia

📏 Chunk Size (tokens)

Larger chunks = more context, smaller chunks = more precision

128 512

🔗 Chunk Overlap (tokens)

Overlap helps maintain context between chunks

10 50

📊 Processing Status

Process an article to see statistics

📊 Chunk Analysis Visualization

❓ Your Question

Ask any question about the processed article

🔍 Number of Chunks to Retrieve

More chunks = broader context, fewer chunks = more focused

1 10

🎯 Similarity Scores

📊 Confidence Meter

Ask a question to see retrieved context chunks

🔍 RAG Pipeline For LLMs 🚀