Update app.py

app.py

@@ -1,154 +1,70 @@
-import gradio as gr
-import numpy as np
-import random
-
-# import spaces #[uncomment to use ZeroGPU]
-from diffusers import DiffusionPipeline
-import torch
-
-device = "cuda" if torch.cuda.is_available() else "cpu"
-model_repo_id = "stabilityai/sdxl-turbo"  # Replace to the model you would like to use
-
-if torch.cuda.is_available():
-    torch_dtype = torch.float16
-else:
-    torch_dtype = torch.float32
-
-pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
-pipe = pipe.to(device)
-
-MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 1024
-
-
-# @spaces.GPU #[uncomment to use ZeroGPU]
-def infer(
-    prompt,
-    negative_prompt,
-    seed,
-    randomize_seed,
-    width,
-    height,
-    guidance_scale,
-    num_inference_steps,
-    progress=gr.Progress(track_tqdm=True),
-):
-    if randomize_seed:
-        seed = random.randint(0, MAX_SEED)
-
-    generator = torch.Generator().manual_seed(seed)
-
-    image = pipe(
-        prompt=prompt,
-        negative_prompt=negative_prompt,
-        guidance_scale=guidance_scale,
-        num_inference_steps=num_inference_steps,
-        width=width,
-        height=height,
-        generator=generator,
-    ).images[0]
-
-    return image, seed
-
-
-examples = [
-    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
-    "An astronaut riding a green horse",
-    "A delicious ceviche cheesecake slice",
-]
+from transformers import pipeline
 
-css = """
-#col-container {
-    margin: 0 auto;
-    max-width: 640px;
-}
-"""
-
-with gr.Blocks(css=css) as demo:
-    with gr.Column(elem_id="col-container"):
-        gr.Markdown(" # Text-to-Image Gradio Template")
-
-        with gr.Row():
-            prompt = gr.Text(
-                label="Prompt",
-                show_label=False,
-                max_lines=1,
-                placeholder="Enter your prompt",
-                container=False,
-            )
-
-            run_button = gr.Button("Run", scale=0, variant="primary")
-
-        result = gr.Image(label="Result", show_label=False)
-
-        with gr.Accordion("Advanced Settings", open=False):
-            negative_prompt = gr.Text(
-                label="Negative prompt",
-                max_lines=1,
-                placeholder="Enter a negative prompt",
-                visible=False,
-            )
-
-            seed = gr.Slider(
-                label="Seed",
-                minimum=0,
-                maximum=MAX_SEED,
-                step=1,
-                value=0,
-            )
-
-            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
-
-            with gr.Row():
-                width = gr.Slider(
-                    label="Width",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
-
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
-
-            with gr.Row():
-                guidance_scale = gr.Slider(
-                    label="Guidance scale",
-                    minimum=0.0,
-                    maximum=10.0,
-                    step=0.1,
-                    value=0.0,  # Replace with defaults that work for your model
-                )
-
-                num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
-                    minimum=1,
-                    maximum=50,
-                    step=1,
-                    value=2,  # Replace with defaults that work for your model
-                )
-
-        gr.Examples(examples=examples, inputs=[prompt])
-    gr.on(
-        triggers=[run_button.click, prompt.submit],
-        fn=infer,
-        inputs=[
-            prompt,
-            negative_prompt,
-            seed,
-            randomize_seed,
-            width,
-            height,
-            guidance_scale,
-            num_inference_steps,
-        ],
-        outputs=[result, seed],
-    )
+import fitz 
+import gradio as gr
+import requests
+import io
+import re
+import os
+from PIL import Image
+
+summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
+qa_model = pipeline("question-answering", model="distilbert-base-cased-distilled-squad")
+
+os.environ["HUGGINGFACE_HUB_TOKEN"] = "ctp-hw"
+my_key = os.environ["HUGGINGFACE_HUB_TOKEN"]
+
+def extract_text_from_pdf(pdf_file):
+    with fitz.open(pdf_file) as pdf:
+        text = ""
+        for page in pdf:
+            text += page.get_text("text")
+
+    text = re.sub(r'\s+', ' ', text)
+    text = text.strip()
+    return text
+
+def summarize_pdf(pdf_file):
+    text = extract_text_from_pdf(pdf_file)
+    
+    if len(text) > 1000:
+        chunks = [text[i:i+1000] for i in range(0, len(text), 1000)]
+        summary = ""
+        for chunk in chunks:
+            summary += summarizer(chunk, max_length=150, min_length=50, do_sample=False)[0]['summary_text'] + " "
+    else:
+        summary = summarizer(text, max_length=150, min_length=50, do_sample=False)[0]['summary_text']
+    
+    return summary
+
+def answer_question(pdf_file, question):
+    text = extract_text_from_pdf(pdf_file)
+    answer = qa_model(question=question, context=text)
+    return answer['answer']
+
+API_URL = "https://api-inference.huggingface.co/models/stable-diffusion-v1-5/stable-diffusion-v1-5"
+headers = {"Authorization": f"Bearer {my_key}"}
+
+def query(payload):
+	response = requests.post(API_URL, headers=headers, json=payload)
+	return response.content
+
+def summarize_and_qa(pdf_file, question):
+    summary = summarize_pdf(pdf_file)
+    answer = answer_question(pdf_file, question)
+    image_bytes = query({
+        "inputs": answer,
+    })
+    image = Image.open(io.BytesIO(image_bytes))
+    return summary, answer, image
+
+gr.Interface(
+    fn=summarize_and_qa,
+    inputs=["file", "text"],
+    outputs=["textbox", "textbox", "image"],
+    title="PDF Summary and Q&A",
+    description="Upload a PDF to get a summary and answer questions based on the content. It will also give a picture to help you better understand the content."
+).launch()
 
 if __name__ == "__main__":
     demo.launch()