GitHub Support Me

🍱 Semantic Chunking UI

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

Document Name:

Text to Chunk:

Basic Settings

Max Token Size (50-2500):

Similarity Threshold (0.1-1.0):

Similarity Sentences Lookahead (1-10):

Dynamic Threshold Settings

Dynamic Threshold Lower Bound (0.1-1.0):

Dynamic Threshold Upper Bound (0.1-1.0):

Combine Chunks Settings

Combine Chunks:

Combine Chunks Similarity Threshold (0.1-1.0):

Model Settings

Embedding Model: ⓘ

Model Precision:

Output Settings

Return Token Length:

Return Embedding:

Chunk Prefix: For embedding models that support task prefixes

Exclude Chunk Prefix in Results:

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.

×