Function getChunkStats

Calculates statistics for a chunked directory structure.

Recursively traverses the chunked directory tree and computes:

• Number of files and directories
• Total number of chunks across all files
• Total characters in all chunks
• Estimated token count (based on chars/token ratio)
• Estimated embedding cost (based on cost per token)

Example

const chunked = recursively_chunk_directory('/path/to/project');
const stats = getChunkStats(chunked);
console.log(`Files: ${stats.numFiles}, Chunks: ${stats.numChunks}`);
console.log(`Estimated cost: $${stats.estimatedCost.toFixed(4)}`);
Copy

Example

// Custom pricing for OpenAI text-embedding-3-small ($0.00002 per 1K tokens)
const stats = getChunkStats(chunked, {
  charsPerToken: 4,
  costPerToken: 0.00002 / 1000
});
Copy