Update app.py

app.py

@@ -4,45 +4,18 @@ from langchain.prompts import PromptTemplate
 from langchain_community.llms import HuggingFaceEndpoint
 from pdfminer.high_level import extract_text
 import docx2txt
-import os
+import io
 import re
 from typing import List
-from langchain.chains import LLMChain
-from langchain.prompts import PromptTemplate
-from langchain_community.llms import HuggingFaceEndpoint
-from pdfminer.high_level import extract_text
 from langchain.vectorstores import Chroma
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain.embeddings import SentenceTransformerEmbeddings
-import os
-import re
 from sentence_transformers import SentenceTransformer
 from sklearn.metrics.pairwise import cosine_similarity
 import numpy as np
-from google.oauth2.credentials import Credentials
-from google_auth_oauthlib.flow import InstalledAppFlow
-from googleapiclient.discovery import build
-from googleapiclient.http import MediaIoBaseDownload
-import io
+import os
 
 HUGGINGFACEHUB_API_TOKEN = os.getenv("HUGGINGFACEHUB_API_TOKEN")
-GOOGLE_DRIVE_SCOPES = ['https://www.googleapis.com/auth/drive.readonly']
-CLIENT_SECRET_FILE = 'client_secret_64686904440-0a015tg0h941o993tif67c9mq1jr4mio.apps.googleusercontent.com.json'
-
-def authenticate_google_drive():
-    flow = InstalledAppFlow.from_client_secrets_file(CLIENT_SECRET_FILE, GOOGLE_DRIVE_SCOPES)
-    creds = flow.run_local_server(port=0)
-    return build('drive', 'v3', credentials=creds)
-
-def get_file_from_google_drive(drive_service, file_id):
-    request = drive_service.files().get_media(fileId=file_id)
-    file_content = io.BytesIO()
-    downloader = MediaIoBaseDownload(file_content, request, chunksize=1024*1024)
-    done = False
-    while done is False:
-        status, done = downloader.next_chunk()
-    file_content.seek(0)
-    return file_content.read()
 
 def extract_text_from_pdf(pdf_content):
     return extract_text(io.BytesIO(pdf_content))
@@ -95,7 +68,7 @@ def answer_query_with_similarity(query, file_contents):
 
         if not docs:
             print("No documents match the query.")
-            return None, None
+            return None
 
         docs_content = [doc.page_content for doc in docs]
         for i, content in enumerate(docs_content, start=1):
@@ -131,32 +104,14 @@ def answer_query_with_similarity(query, file_contents):
         cleaned_answer = answer.split("Answer:")[-1].strip()
         print(f"\n\nAnswer: {cleaned_answer}")
 
-        return cleaned_answer,
+        return cleaned_answer
     except Exception as e:
-        print("An error occurred to get the answer: ", str(e))
-        return None, None
+        print("An error occurred while getting the answer: ", str(e))
+        return None
 
 def main():
     st.title("Document Query App")
 
-    # Get user input for authentication method
-    #auth_method = st.radio("Choose authentication method", ("Google Drive", "Upload Files"))
-
-    #if auth_method == "Google Drive":
-        # Authenticate with Google Drive
-        #drive_service = authenticate_google_drive()
-
-        # Get file IDs from user input
-        #file_ids = st.text_input("Enter the file IDs (comma-separated):")
-        #file_ids = [file_id.strip() for file_id in file_ids.split(",")]
-
-        # Get file contents from Google Drive
-        #file_contents = []
-        #for file_id in file_ids:
-            file_content = get_file_from_google_drive(drive_service, file_id)
-            file_contents.append(file_content)
-    #else:
-        # Allow user to upload files directly
     uploaded_files = st.file_uploader("Upload files", accept_multiple_files=True)
     file_contents = [file.read() for file in uploaded_files]
 
@@ -166,7 +121,7 @@ def main():
         if file_contents and query:
             response = answer_query_with_similarity(query, file_contents)
             if response:
-                st.write("Answer:", response[0])
+                st.write("Answer:", response)
             else:
                 st.write("No answer found.")
         else: