from pocketgroq import GroqProvider

groq = GroqProvider()

# Analyze an image from URL
image_url = "https://example.com/image.jpg"
response = groq.process_image(
    prompt="What do you see in this image?",
    image_source=image_url
)

print(f"Analysis: {response}")

# Analyze your screen
screen_analysis = groq.process_image_desktop(
    prompt="What applications are open on my screen?"
)

print(f"Screen analysis: {screen_analysis}")

# Analyze specific screen region
region_analysis = groq.process_image_desktop_region(
    prompt="What's in this part of the screen?",
    x1=0,    # Top-left corner
    y1=0,    # Top-left corner
    x2=400,  # Width
    y2=300   # Height
)

print(f"Region analysis: {region_analysis}")

# Start a conversation about an image
messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": "What do you see in this image?"
            },
            {
                "type": "image_url",
                "image_url": {"url": "https://example.com/image.jpg"}
            }
        ]
    }
]

response1 = groq.process_image_conversation(messages=messages)
print(f"First response: {response1}")

# Add follow-up question
messages.append({
    "role": "assistant",
    "content": response1
})
messages.append({
    "role": "user",
    "content": "What colors are most prominent?"
})

response2 = groq.process_image_conversation(messages=messages)
print(f"Second response: {response2}")

from pocketgroq import GroqProvider

groq = GroqProvider()

# Transcribe audio
response = groq.transcribe_audio(
    audio_file="recording.wav",
    language="en",
    model="distil-whisper-large-v3-en"  # Fastest for English
)

print(f"Transcription: {response}")

# Translate audio to English
translation = groq.translate_audio(
    audio_file="french_speech.wav",
    model="whisper-large-v3",  # Required for translation
    prompt="This is a French conversation about cooking."
)

print(f"Translation: {translation}")