import gradio as gr
from transformers import CLIPProcessor, CLIPModel, CLIPTokenizer
import sentence_transformers
from sentence_transformers import SentenceTransformer, util
import pickle
from PIL import Image
import os


## Define model
model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
tokenizer = CLIPTokenizer.from_pretrained("openai/clip-vit-base-patch32")



#Open the precomputed embeddings
emb_filename = 'unsplash-25k-photos-embeddings.pkl'
with open(emb_filename, 'rb') as fIn:
        img_names, img_emb = pickle.load(fIn)  


def search_text(query, top_k=1):
    """"

    Args:
        query ([string]): [query you want search for]
        top_k (int, optional): [Amount of images o return]. Defaults to 1.

    Returns:
        [list]: [list of images that are related to the query.]
    """
    # First, we encode the query.
    inputs = tokenizer([query],  padding=True, return_tensors="pt")
    query_emb = model.get_text_features(**inputs)
    
    # Then, we use the util.semantic_search function, which computes the cosine-similarity
    # between the query embedding and all image embeddings.
    # It then returns the top_k highest ranked images, which we output
    hits = util.semantic_search(query_emb, img_emb, top_k=top_k)[0]
    
    image=[]
    for hit in hits:
        print(img_names[hit['corpus_id']])
        object = Image.open(os.path.join("photos/", img_names[hit['corpus_id']]))
        image.append(object)

    return image

iface = gr.Interface(
    title = "Text to Image using CLIP Model",
    description = "Gradio Demo fo CLIP model. \n This demo is based on assessment for the :hugging:  Huggingface course 2. \n To use it, simply write which image you are looking for. Read more at the links below.",
    fn=search_text, 
    inputs=[gr.inputs.Textbox(lines=2, 
        label="Write what you are looking for...",
        placeholder="Name Here..."),
        gr.inputs.Slider(0, 5, step=1)], 
    outputs=gr.outputs.Carousel(gr.outputs.Image(type="pil"))
    ,examples=[[("Dog in the beach"), 2], 
        [("Paris during night."), 1], 
        [("A cute kangaroo"), 5],
        [("Dois cachorros"), 2],
        [("un homme marchant sur le parc")], 3]
    ).launch(debug=True)