Update app.py

app.py

@@ -5,8 +5,6 @@ import PyPDF2
 import gradio as gr
 from langchain.prompts import PromptTemplate
 from langchain.chains.summarize import load_summarize_chain
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain_community.document_loaders import DirectoryLoader
 from langchain_core.documents import Document
 from pathlib import Path
 from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint
@@ -31,16 +29,11 @@ def summarize(file, n_words):
     # Read the content of the uploaded file
     file_path = file.name
     if file_path.endswith('.pdf'):
-        file_content = read_pdf(file_path)
+        text = read_pdf(file_path)
     else:
         with open(file_path, 'r', encoding='utf-8') as f:
-            file_content = f.read()
+            text = f.read()
             
-    document = Document(file_content)
-    # Generate the summary
-    text = document.page_content
-    text_splitter = RecursiveCharacterTextSplitter(chunk_size=3000, chunk_overlap=200)
-    chunks = text_splitter.create_documents([text])
     template = '''
     You are a commentator. Your task is to write a report on an essay.
 When presented with the essay, come up with interesting questions to ask, and answer each question.
@@ -62,13 +55,18 @@ Generate three distinct and thought-provoking questions that can be asked about
 ## Write a report
 Using the essay summary and the answers to the interesting questions, create a comprehensive report in Markdown format.
     '''
+    
     prompt = PromptTemplate(
         template=template,
         input_variables=['TEXT']    
     )
-    formatted_prompt = prompt.format(TEXT=text)
-    output_summary = llm_engine_hf.invoke(formatted_prompt)
-    return output_summary.content
+    
+    summary = ""
+    while len(summary.split()) < 100:
+        formatted_prompt = prompt.format(TEXT=text)
+        output_summary = llm_engine_hf.invoke(formatted_prompt)
+        summary = output_summary.content
+    return summary
 
 def download_summary(output_text):
     if output_text: