Upload folder using huggingface_hub

requirements.txt

@@ -9,4 +9,5 @@ grpcio-tools==1.54.2
 gpt_index==0.4.24
 langchain==0.0.190
 environs==9.5.0
-pypdf==3.9.1
+pypdf==3.9.1
+pypdfium2==4.18.0

src/gradio_app.py

@@ -1,9 +1,32 @@
 import gradio as gr
 from langchain.chat_models import ChatOpenAI
-from src.summarization import summarize
-from src.prompts import prompts
+from src.summarization import summarize_wrapper
 import os
 
+import pypdfium2 as pdfium
+from PIL import Image
+
+# Function to render a specific page of a PDF file as an image
+def render_file(file):
+    pdf = pdfium.PdfDocument(file.name)
+
+    page = pdf.get_page(0)
+    bitmap = page.render(
+        scale=300 / 72,  # 300dpi resolution
+        rotation=0,  # no additional rotation
+        # ... further rendering options
+    )
+    pil_image = bitmap.to_pil()
+
+    # WORK FROM HERE TO RENDER THE COMPLETE PDF
+    # bitmap = pdf.render(
+    #     pdfium.PdfBitmap.to_pil,
+    #     page_indices=[0, 1, 2],
+    #     scale=300 / 72,  # 300dpi resolution
+    # )
+    # pil_image = bitmap.to_pil()
+    return pil_image
+
 
 def switch_buttons(interactive: bool):
     """This switches the buttons to interactive or not interactive.
@@ -24,49 +47,6 @@ def switch_buttons(interactive: bool):
     )
 
 
-def summarize_wrapper(
-    file: str, llm: ChatOpenAI, summarization_type: str, summarization_kwargs: dict
-) -> str:
-    """Wrapper for the summarization function to make it compatible with gradio.
-
-    Args:
-        file (str): Path to the file. This can either be a local path or a tempfile.TemporaryFileWrapper_.
-        llm (ChatOpenAI): Language model.
-        summarization_type (str): Type of summarization. Can be either "short", "middle" or "long".
-        summarization_kwargs (dict): Keyword arguments for the summarization.
-
-    Returns:
-        str: Summarization of the file.
-    """
-    if summarization_type == "short":
-        summarization_kwargs.update(
-            dict(
-                map_prompt=prompts["short_de"]["map_prompt"],
-                combine_prompt=prompts["short_de"]["combine_prompt"],
-            )
-        )
-    elif summarization_type == "middle":
-        summarization_kwargs.update(
-            dict(
-                map_prompt=prompts["middle_de"]["map_prompt"],
-                combine_prompt=prompts["middle_de"]["combine_prompt"],
-            )
-        )
-    elif summarization_type == "long":
-        summarization_kwargs.update(
-            dict(
-                map_prompt=prompts["long_de"]["map_prompt"],
-                combine_prompt=prompts["long_de"]["combine_prompt"],
-            )
-        )
-    else:
-        raise ValueError(f"Summarization type {summarization_type} is not supported.")
-
-    return summarize(
-        file_path=file.name, llm=llm[0], summarization_kwargs=summarization_kwargs
-    )
-
-
 def run_summarization_model_gradio(
     llm: ChatOpenAI,
     share_gradio_via_link: bool = False,
@@ -91,29 +71,36 @@ def run_summarization_model_gradio(
     ) as webui:
         with gr.Row().style(equal_height=True):
             Header_box = generate_title(title=title, description=description)
+        with gr.Row().style(equal_height=True):
+            clear = gr.Button("Clear")
+            file_upload = gr.File(
+                file_count="single",
+                file_types=[".pdf", ".txt"],
+                label="Upload PDF",
+            )
         with gr.Row().style(equal_height=True):
             summary_short = gr.Button("Kurze Zusammenfassung", interactive=False)
             summary_middle = gr.Button("Mittlere Zusammenfassung", interactive=False)
             summary_long = gr.Button("Lange Zusammenfassung", interactive=False)
         with gr.Row().style(equal_height=True):
             with gr.Column(scale=1):
-                file_upload = gr.File(
-                    file_count="single",
-                    file_types=[".pdf", ".txt"],
-                    label="Upload PDF",
+                summary_output = (
+                    gr.Textbox(label="Zusammenfassung")
+                    .style(show_copy_button=True)
+                    .style(height=680)
                 )
-            with gr.Column(scale=4):
-                summary_output = gr.Textbox(label="Zusammenfassung").style(
-                    show_copy_button=True
+            with gr.Column(scale=1):
+                show_img = gr.Image(label="Uploaded PDF", tool="select").style(
+                    height=680
                 )
 
-        # Once a file is uploaded, enable the summarization buttons
+        # Once a file is uploaded, enable the summarization buttons and visualize the uploaded file
         file_upload.upload(
             switch_buttons,
             [gr.State(True)],
             [summary_short, summary_middle, summary_long],
             queue=False,
-        )
+        ).then(fn=render_file, inputs=[file_upload], outputs=[show_img])
 
         # If you click any button first disable all buttons, then summarzize and then enable the clicked button
         for s, summarization_type in [
@@ -144,7 +131,6 @@ def run_summarization_model_gradio(
             )
 
         # The clear button clears the dashboard
-        clear = gr.Button("Clear")
         clear.click(lambda: None, None, summary_output, queue=False).then(
             lambda: None, None, file_upload, queue=False
         ).then(
@@ -167,6 +153,7 @@ def run_summarization_model_gradio(
 
 
 def generate_title(title: str, description: str):
+    """THIS IS AN EXAMPLE HTML CODE FOR A TITLE"""
     return gr.HTML(
         (
             """

src/summarization.py

@@ -2,6 +2,7 @@ from langchain.document_loaders import PyPDFLoader, TextLoader
 from langchain.chains.summarize import load_summarize_chain
 from langchain.chat_models import ChatOpenAI
 from langchain.docstore.document import Document
+from src.prompts import prompts
 from typing import Dict, List
 
 
@@ -49,3 +50,46 @@ def summarize(
     )
     summary = chain.run(docs)
     return summary
+
+
+def summarize_wrapper(
+    file: str, llm: ChatOpenAI, summarization_type: str, summarization_kwargs: dict
+) -> str:
+    """Wrapper for the summarization function to make it compatible with gradio.
+
+    Args:
+        file (str): Path to the file. This can either be a local path or a tempfile.TemporaryFileWrapper_.
+        llm (ChatOpenAI): Language model.
+        summarization_type (str): Type of summarization. Can be either "short", "middle" or "long".
+        summarization_kwargs (dict): Keyword arguments for the summarization.
+
+    Returns:
+        str: Summarization of the file.
+    """
+    if summarization_type == "short":
+        summarization_kwargs.update(
+            dict(
+                map_prompt=prompts["short_de"]["map_prompt"],
+                combine_prompt=prompts["short_de"]["combine_prompt"],
+            )
+        )
+    elif summarization_type == "middle":
+        summarization_kwargs.update(
+            dict(
+                map_prompt=prompts["middle_de"]["map_prompt"],
+                combine_prompt=prompts["middle_de"]["combine_prompt"],
+            )
+        )
+    elif summarization_type == "long":
+        summarization_kwargs.update(
+            dict(
+                map_prompt=prompts["long_de"]["map_prompt"],
+                combine_prompt=prompts["long_de"]["combine_prompt"],
+            )
+        )
+    else:
+        raise ValueError(f"Summarization type {summarization_type} is not supported.")
+
+    return summarize(
+        file_path=file.name, llm=llm[0], summarization_kwargs=summarization_kwargs
+    )