brain_of_the_doctor.py

#Step1: Setup GROQ API key
import os

GROQ_API_KEY=os.environ.get("GROQ_API_KEY")

#Step2: Convert image to required format
import base64

#image_path="acne.jpg"

def encode_image(image_path):   
    image_file=open(image_path, "rb")
    return base64.b64encode(image_file.read()).decode('utf-8')

#Step3: Setup Multimodal LLM 
from groq import Groq

query="Is there something wrong with my face?"
model = "meta-llama/llama-4-scout-17b-16e-instruct"
#model="llama-3.2-90b-vision-preview" #Deprecated

def analyze_image_with_query(query, model, encoded_image=None):#here encoded_image=None because i just dont want to make in mandatory as i can audio input also
    client = Groq()
    
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "text", "text": query}
            ]
        }
    ]

    # Only add image if it's present
    if encoded_image:
        messages[0]["content"].append({
            "type": "image_url",
            "image_url": {
                "url": f"data:image/jpeg;base64,{encoded_image}",
            }
        })

    chat_completion = client.chat.completions.create(
        messages=messages,
        model=model
    )

    return chat_completion.choices[0].message.content