Agno

import base64
from pathlib import Path
from typing import Optional

from agno.agent import Agent
from agno.media import Image
from agno.models.openai import OpenAIChat
from Zentry import MemoryClient


# Initialize the Zentry client
client = MemoryClient()

# Define the agent
agent = Agent(
    name="Personal Agent",
    model=OpenAIChat(id="gpt-4"),
    description="You are a helpful personal agent that helps me with day to day activities."
                "You can process both text and images.",
    markdown=True
)


def chat_user(
    user_input: Optional[str] = None,
    user_id: str = "user_123",
    image_path: Optional[str] = None
) -> str:
    """
    Handle user input with memory integration, supporting both text and images.

    Args:
        user_input: The user's text input
        user_id: Unique identifier for the user
        image_path: Path to an image file if provided

    Returns:
        The agent's response as a string
    """
    if image_path:
        # Convert image to base64
        with open(image_path, "rb") as image_file:
            base64_image = base64.b64encode(image_file.read()).decode("utf-8")

        # Create message objects for text and image
        messages = []

        if user_input:
            messages.append({
                "role": "user",
                "content": user_input
            })

        messages.append({
            "role": "user",
            "content": {
                "type": "image_url",
                "image_url": {
                    "url": f"data:image/jpeg;base64,{base64_image}"
                }
            }
        })

        # Store messages in memory
        client.add(messages, user_id=user_id)
        print("✅ Image and text stored in memory.")

    if user_input:
        # Search for relevant memories
        memories = client.search(user_input, user_id=user_id)
        memory_context = "\n".join(f"- {m['memory']}" for m in memories)

        # Construct the prompt
        prompt = f"""
You are a helpful personal assistant who helps users with their day-to-day activities and keeps track of everything.

Your task is to:
1. Analyze the given image (if present) and extract meaningful details to answer the user's question.
2. Use your past memory of the user to personalize your answer.
3. Combine the image content and memory to generate a helpful, context-aware response.

Here is what I remember about the user:
{memory_context}

User question:
{user_input}
"""
        # Get response from agent
        if image_path:
            response = agent.run(prompt, images=[Image(filepath=Path(image_path))])
        else:
            response = agent.run(prompt)

        # Store the interaction in memory
        client.add(f"User: {user_input}\nAssistant: {response.content}", user_id=user_id)
        return response.content

    return "No user input or image provided."


# Example Usage
if __name__ == "__main__":
    response = chat_user(
        "This is the picture of what I brought with me in the trip to Bahamas",
        image_path="travel_items.jpeg",
        user_id="user_123"
    )
    print(response)