import gradio as gr
import torch
import numpy as np
from PIL import Image
import os
import json
import base64
from io import BytesIO
import requests
from typing import Dict, List, Any, Optional
from transformers.pipelines import pipeline

# Initialize the model
model = pipeline("image-feature-extraction", model="nomic-ai/nomic-embed-vision-v1.5", trust_remote_code=True)

# Function to generate embeddings from an image
def generate_embedding(image):
    if image is None:
        return None
    
    # Convert to PIL Image if needed
    if not isinstance(image, Image.Image):
        image = Image.fromarray(image)
    
    try:
        # Generate embedding using the transformers pipeline
        result = model(image)
        
        # Process the result based on its type
        embedding_list = None
        
        # Handle different possible output types
        if isinstance(result, torch.Tensor):
            embedding_list = result.detach().cpu().numpy().flatten().tolist()
        elif isinstance(result, np.ndarray):
            embedding_list = result.flatten().tolist()
        elif isinstance(result, list):
            # If it's a list of tensors or arrays
            if result and isinstance(result[0], (torch.Tensor, np.ndarray)):
                embedding_list = result[0].flatten().tolist() if hasattr(result[0], 'flatten') else result[0]
            else:
                embedding_list = result
        else:
            # Try to convert to a list as a last resort
            try:
                if result is not None:
                    embedding_list = list(result)
                else:
                    print("Result is None")
                    return None
            except:
                print(f"Couldn't convert result of type {type(result)} to list")
                return None
        
        # Ensure we have a valid embedding list
        if embedding_list is None:
            return None
            
        # Calculate embedding dimension
        embedding_dim = len(embedding_list)
        
        return {
            "embedding": embedding_list,
            "dimension": embedding_dim
        }
    except Exception as e:
        print(f"Error generating embedding: {str(e)}")
        return None

# Function to generate embeddings from an image URL
def embed_image_from_url(image_url):
    try:
        # Download the image
        response = requests.get(image_url)
        image = Image.open(BytesIO(response.content))
        
        # Generate embedding
        return generate_embedding(image)
    except Exception as e:
        return {"error": str(e)}

# Function to generate embeddings from base64 image data
def embed_image_from_base64(image_data):
    try:
        # Decode the base64 image
        decoded_data = base64.b64decode(image_data)
        image = Image.open(BytesIO(decoded_data))
        
        # Generate embedding
        return generate_embedding(image)
    except Exception as e:
        return {"error": str(e)}

# Create a Gradio app
app = gr.Interface(
    fn=generate_embedding,
    inputs=gr.Image(type="pil", label="Input Image"),
    outputs=[
        gr.JSON(label="Embedding Output"),
        gr.Textbox(label="Embedding Dimension")
    ],
    title="Nomic Vision Embedding Model (nomic-ai/nomic-embed-vision-v1.5)",
    description="Upload an image to generate embeddings using the Nomic Vision model.",
    examples=[["examples/example1.jpg"], ["examples/example2.jpg"]],
    allow_flagging="never"
)

# Launch the app
if __name__ == "__main__":
    app.launch(mcp_server=True)