Update app.py

app.py

@@ -8,39 +8,29 @@ from langchain_community.embeddings import HuggingFaceEmbeddings
 from langchain_community.vectorstores import FAISS
 from groq import Groq
 import streamlit as st
-from googleapiclient.discovery import build
-from googleapiclient.http import MediaIoBaseDownload
-from google.oauth2.service_account import Credentials
 
 # Initialize Groq client
 client = Groq(api_key=os.getenv("GROQ_API_KEY"))
 
-# Google Drive API authentication and setup
-SCOPES = ['https://www.googleapis.com/auth/drive.readonly']
-SERVICE_ACCOUNT_FILE = 'tonal-vector-446915-a1-013785a5b8ac.json'
-credentials = Credentials.from_service_account_file(SERVICE_ACCOUNT_FILE, scopes=SCOPES)
-service = build('drive', 'v3', credentials=credentials)
-
-# Predefined Google Drive folder link
-folder_id = "1lYWZwxr-4IBhxKV4siVO2nKCwbO-RMO7"
-
-# Function to list files in the folder
-def list_files_in_folder(folder_id):
-    query = f"'{folder_id}' in parents"
-    results = service.files().list(q=query).execute()
-    files = results.get('files', [])
-    return files
-
-# Function to download PDF from Google Drive by file ID
-def download_pdf_from_drive(file_id):
-    request = service.files().get_media(fileId=file_id)
-    fh = BytesIO()
-    downloader = MediaIoBaseDownload(fh, request)
-    done = False
-    while done is False:
-        status, done = downloader.next_chunk()
-    fh.seek(0)
-    return fh
+# if client:
+#     st.write(f"API KEY FOUND!!!{client}")
+# else:
+#     st.write("API KEY NOT FOUND")
+
+# Predefined list of Google Drive links
+drive_links = [
+    "https://drive.google.com/file/d/1xswnMcJH4KRWFICjUpszYBQCsPTykZp0/view?usp=sharing"
+]
+
+# Function to download PDF from Google Drive
+def download_pdf_from_drive(drive_link):
+    file_id = drive_link.split('/d/')[1].split('/')[0]
+    download_url = f"https://drive.google.com/uc?id={file_id}&export=download"
+    response = requests.get(download_url)
+    if response.status_code == 200:
+        return BytesIO(response.content)
+    else:
+        raise Exception("Failed to download the PDF file from Google Drive.")
 
 # Function to extract text from a PDF
 def extract_text_from_pdf(pdf_stream):
@@ -65,9 +55,11 @@ def create_embeddings_and_store(chunks):
 
 # Function to query the vector database and interact with Groq
 def query_vector_db(query, vector_db):
+    # Retrieve relevant documents
     docs = vector_db.similarity_search(query, k=3)
     context = "\n".join([doc.page_content for doc in docs])
 
+    # Interact with Groq API
     chat_completion = client.chat.completions.create(
         messages=[
             {"role": "system", "content": f"Use the following context:\n{context}"},
@@ -78,24 +70,30 @@ def query_vector_db(query, vector_db):
     return chat_completion.choices[0].message.content
 
 # Streamlit app
-st.title("RAG-based ChatBot (Advanced Triangle Solver)")
+st.title("RAG-Based ChatBot (Already having Document)")
 
 st.write("Processing the Data links...")
 
 all_chunks = []
 
-# Process all files in the Google Drive folder
-try:
-    files = list_files_in_folder(folder_id)
-    for file in files:
-        if file['mimeType'] == 'application/pdf':  # Only process PDF files
-            st.write(f"Processing file: {file['name']}")
-            pdf_stream = download_pdf_from_drive(file['id'])
-            text = extract_text_from_pdf(pdf_stream)
-            chunks = chunk_text(text)
-            all_chunks.extend(chunks)
-except Exception as e:
-    st.write(f"Error processing folder: {e}")
+# Process each predefined Google Drive link
+for link in drive_links:
+    try:
+        # st.write(f"Processing link: {link}")
+        # Download PDF
+        pdf_stream = download_pdf_from_drive(link)
+        # st.write("PDF Downloaded Successfully!")
+
+        # Extract text
+        text = extract_text_from_pdf(pdf_stream)
+        # st.write("PDF Text Extracted Successfully!")
+
+        # Chunk text
+        chunks = chunk_text(text)
+        # st.write(f"Created {len(chunks)} text chunks.")
+        all_chunks.extend(chunks)
+    except Exception as e:
+        st.write(f"Error processing link {link}: {e}")
 
 if all_chunks:
     # Generate embeddings and store in FAISS