Update app.py

app.py

@@ -1,64 +1,54 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+import fitz  # PyMuPDF
+import requests
+from transformers import pipeline
+
+# Carrega o modelo de resumo (pode ser um modelo do Hugging Face Hub)
+# Exemplo:  "facebook/bart-large-cnn" (bom para inglês, mas há modelos melhores para português)
+#          "unicamp-dl/mt5-base-multi-pt-br-summary" (modelo em português)
+summarizer = pipeline("summarization", model="unicamp-dl/mt5-base-multi-pt-br-summary")
+
+
+def download_pdf(url):
+    """Baixa o PDF da URL."""
+    response = requests.get(url)
+    response.raise_for_status()  # Lança um erro se a URL for inválida
+    return response.content
+
+
+def extract_text_from_pdf(pdf_bytes):
+    """Extrai o texto do PDF usando PyMuPDF."""
+    text = ""
+    with fitz.open(stream=pdf_bytes, filetype="pdf") as doc:
+        for page in doc:
+            text += page.get_text()
+    return text
+
+def summarize_pdf(url):
+    """Baixa, extrai o texto e resume o PDF."""
+    try:
+        pdf_bytes = download_pdf(url)
+        text = extract_text_from_pdf(pdf_bytes)
+
+        # Resume o texto.  Ajuste max_length e min_length conforme necessário.
+        summary = summarizer(text, max_length=500, min_length=100, do_sample=False)[0]['summary_text']
+        return summary
+    except requests.exceptions.RequestException as e:
+        return f"Erro ao baixar o PDF: {e}"
+    except Exception as e:
+        return f"Erro ao processar o PDF: {e}"
+
+
+
+# Cria a interface Gradio
+iface = gr.Interface(
+    fn=summarize_pdf,
+    inputs=gr.Textbox(label="URL do PDF", value="https://ww2.trt2.jus.br/fileadmin/memorial/CMV/ACORDAOS/1966/3901.4200/AC_1966_03902.pdf"),  # URL padrão
+    outputs=gr.Textbox(label="Resumo do PDF"),
+    title="Resumidor de PDF",
+    description="Insira a URL de um PDF para obter um resumo.",
 )
 
+iface.launch()
+
 
-if __name__ == "__main__":
-    demo.launch()