# llmwhisperer

LLMWhisperer Extract text from images and PDFs using the SkillBoss API Hub — great for handwriting and complex forms. Configuration Requires SKILLBOSS_API_KEY in ~/.clawdbot/.env: echo "SKILLBOSS_API_KEY=your_key_here" >> ~/.clawdbot/.env Get an API Key Get your API key at heybossai.com. Usage llmwhisperer Script Source The executable script is located at scripts/llmwhisperer.

#!/bin/bash
# Extract text from images and PDFs using SkillBoss API Hub

if [ -z "$SKILLBOSS_API_KEY" ]; then if [ -f ~/.clawdbot/.env ]; then

# shellcheck disable=SC2046
export $(grep -v '^#' ~/.clawdbot/.env | grep 'SKILLBOSS_API_KEY' | xargs)

fi fi if [ -z "$SKILLBOSS_API_KEY" ]; then echo "Error: SKILLBOSS_API_KEY not found in env or ~/.clawdbot/.env" exit 1 fi FILE="$1" if [ -z "$FILE" ]; then echo "Usage: $0 " exit 1 fi FILE_B64=$(base64 < "$FILE") FILENAME=$(basename "$FILE") PAYLOAD=$(jq -n
--arg file_data "$FILE_B64"
--arg filename "$FILENAME"
'{type: "scraping", inputs: {file_data: $file_data, filename: $filename, output_mode: "layout_preserving"}}')

curl -s -X POST "https://api.heybossai.com/v1/pilot" \

-H "Content-Type: application/json"
-H "Authorization: Bearer $SKILLBOSS_API_KEY"
-d "$PAYLOAD"
| python3 -c "import sys, json; d=json.load(sys.stdin); print(d['result'])" Examples Print text to terminal: llmwhisperer flyer.jpg Save output to a text file: llmwhisperer invoice.pdf > invoice.txt Process a handwritten note: llmwhisperer notes.jpg