🍱 Semantic Chunking UI

Sandbox to tune your semantic chunking settings to get the best results for your use case

Basic Settings

500
0.500moderately similar
3

Dynamic Threshold Settings

0.400low similarity
0.800very similar

Combine Chunks Settings

0.500moderately similar

Model Settings

2q8 - 8-bit Quantized

Output Settings

Results

Update the "Text to Chunk" value, modify the settings, and click "Process Text" to view the chunking results here. Feel free to experiment with different settings to see how they affect the results. Once you're satisfied, use the "Get Code" button to view/copy your Chunkit settings Object for use in your own project.