RAG Visualizer
Interactive Retrieval-Augmented Generation Simulator
Input
→
Chunk
→
Embed
→
Search
→
Filter
→
Generate
Knowledge Base
Parameters
Chunk Size
300
Overlap
50
Top-K Results
3
Similarity Threshold
0.30
-
Chunks
-
Retrieved
-
Tokens
-
ms
Embedding Space
Waiting...
Similarity Ranking
Similarity scores will appear here
Generated Answer
The AI-generated answer will appear here...
Chunks
0
Processed chunks will appear here
rag_pipeline.py
# Python code will be generated here from langchain.text_splitter import RecursiveCharacterTextSplitter from langchain.embeddings import OpenAIEmbeddings from langchain.vectorstores import FAISS