t.sh

#!/bin/bash

# Check if the file path argument is provided
if [ $# -eq 0 ]; then
    echo "Usage: $0 <text_file> [language=eng]"
    exit 1
fi

# an "echo" that directly writes to STDERR
# so that the translated output can be piped
# from STDOUT
write_line() {
    local text=$1

    echo "$text" >&2
}

# reads text from a files
#
# $1 => path to the file to scan
# $2 => optional information of the language that is used in the file, like "eng" or "deu"
get_text_from_file() {
    local file_path=$1
    local language=$2

    filename=$(basename "$1")
    extension="${filename##*.}"

    case "$extension" in
        pdf)
            # PDF document
            text_from_pdf=$(pdftotext "$file_path" -)
            echo "$text_from_pdf"
            ;;
        gif|jpeg|jpg|png|tif|tiff)
            # image file
            text_from_image=$(tesseract "$file_path" stdout -l "$language" 2>/dev/null)
            echo "$text_from_image"
            ;;
        *)
            # handle anything else as text file
            echo $(<"$text_file")
            ;;
    esac
}

# calls Ollama API
#
# $1 => the prompt to send
chat_completion() {
    local prompt=$1

    # if you run the API on another address, you
    # can customize by using `TGF_API_URL` environment variable
    url="${TGF_API_URL:-http://localhost:11434/api/generate}"

    # if you prefer another model, you
    # can customize by using `TGF_LLM_MODEL` environment variable
    model="${TGF_LLM_MODEL:-phi3}"

    # if you prefer another temperature value, you
    # can customize by using `TGF_LLM_TEMPERATURE` environment variable
    temperature="${TGF_LLM_TEMPERATURE:-0}"

    # create a JSON for the Ollama API
    json_data=$(jq -n \
                    --arg model "$model" \
                    --arg prompt "$prompt" \
                    --argjson temperature "$temperature" \
                    '{model: $model, prompt: $prompt, options: {temperature: $temperature}, stream: false}')

    # execute Ollama API
    response=$(wget --header "Content-Type: application/json" \
                    --post-data "$json_data" \
                    "$url" \
                    -q \
                    -O - 2>&1) # Captures both the output and server response headers

    # if the execution was successful, there should
    # be a `response` property in the output
    extracted_response=$(echo "$response" | jq -r '.response')

    if [ -n "$extracted_response" ]; then
        echo "$extracted_response"
    else
        write_line "[ERROR] No valid JSON found!"
        exit 1
    fi
}

# collect parameters
file_with_text="$1"
language="${2:-deu}"

url="${TGF_API_URL:-http://localhost:11434/api/generate}"

# get text file
write_line "ℹ️ Get text from '$file_with_text' ..."
text_to_translate=$(get_text_from_file "$file_with_text" "$language")

# first let LLM fix typos in text
write_line "ℹ️ Fixing text of '$file_with_text' if needed ..."
fixed_text=$(chat_completion "Fix typos in the following text: $text_to_translate")

# now translate this text by LLM
write_line "ℹ️ Translating fixed version of '$file_with_text' ..."
translated_text=$(chat_completion "Translate the following text to english: $fixed_text")

write_line "✅ '$file_with_text' successfully translated"
echo "$translated_text" # output to STDOUT