Update app.py

app.py

@@ -7,15 +7,32 @@ import openai
 import gradio as gr
 import os
 from sklearn.neighbors import NearestNeighbors
+from jina import Document, DocumentArray
+
+# Create a new DocumentArray for file storage
+doc_array = DocumentArray()
 
 def download_pdf(url, output_path):
     urllib.request.urlretrieve(url, output_path)
 
+
 def preprocess(text):
     text = text.replace('\n', ' ')
     text = re.sub('\s+', ' ', text)
     return text
 
+# Store a file in the DocumentArray
+def store_file_in_docarray(file_name, file_content):
+    doc = Document(id=file_name, content=file_content)
+    doc_array.append(doc)
+
+# Retrieve a file from the DocumentArray
+def get_file_from_docarray(file_name):
+    for doc in doc_array:
+        if doc.id == file_name:
+            return doc.content
+    return None
+
 def pdf_to_text(path, start_page=1, end_page=None):
     doc = fitz.open(path)
     total_pages = doc.page_count
@@ -110,9 +127,6 @@ def load_recommender(paths, start_page=1):
     recommender.fit(chunks)
     return 'Corpus Loaded.'
 
-
-
-    
 def generate_text(openAI_key, prompt, engine="text-davinci-003"):
     openai.api_key = openAI_key
     completions = openai.Completion.create(
@@ -174,7 +188,16 @@ def question_answer(url, files, question, openAI_key):
     if question.strip() == '':
         return '[ERROR]: Question field is empty'
 
+    # Store the PDF content in the DocumentArray
+    for pdf_path in pdf_paths:
+        with open(pdf_path, "rb") as f:
+            content = f.read()
+            store_file_in_docarray(pdf_path, content)
+
+    # Load the recommender
     load_recommender(pdf_paths)
+    
+    # Generate an answer
     return generate_answer(question, openAI_key)
 
 recommender = SemanticSearch()