Update app.py

app.py

@@ -14,6 +14,10 @@ from gtts import gTTS
 import sys
 import pytesseract
 from pdf2image import convert_from_path
+from huggingface_hub import Repository
+from huggingface_hub import hf_hub_download
+
+
 
 
 # Load environment variables
@@ -41,6 +45,29 @@ def load_pdf(file_path):
         documents.append(text)
     return documents
 
+
+import os
+from langchain.vectorstores import FAISS
+from huggingface_hub import Repository
+
+def save_faiss_index_to_hub(vectorstore, repo_id="MohammedNasser/faiss-index"):
+    index_dir = "faiss_index"
+    
+    # Ensure the index directory exists
+    if not os.path.exists(index_dir):
+        os.makedirs(index_dir)
+    
+    # Save FAISS index locally
+    vectorstore.save_local(index_dir)
+    
+    # Initialize Hugging Face repository
+    repo = Repository(local_dir=index_dir, clone_from=repo_id)
+    
+    # Push the FAISS index files to the Hugging Face Hub
+    repo.push_to_hub(commit_message="Pushing FAISS index")
+
+    print(f"FAISS index saved to Hugging Face Hub: {repo_id}")
+
 def prepare_vectorstore(data):
     index_dir = "faiss_index"
     if not os.path.exists(index_dir):
@@ -48,16 +75,21 @@ def prepare_vectorstore(data):
     text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=20, separator="\n")
     texts = data
     vectorstore = FAISS.from_texts(texts, embeddings)
-    vectorstore.save_local(index_dir)
-    
+    save_faiss_index_to_hub(vectorstore)
     return vectorstore
+    
 
-def load_vectorstore():
+def load_vectorstore(repo_id="MohammedNasser/faiss-index"):
     index_dir = "faiss_index"
     
-    # Ensure the directory exists before trying to load the index
+    # Ensure the index directory exists
     if not os.path.exists(index_dir):
-        raise RuntimeError(f"FAISS index directory '{index_dir}' does not exist.")
+        os.makedirs(index_dir)
+
+    
+    
+    # Download the FAISS index files from Hugging Face Hub
+    hf_hub_download(repo_id=repo_id, filename="index.faiss", local_dir=index_dir)
 
     vectorstore = FAISS.load_local(index_dir, embeddings, allow_dangerous_deserialization=True)
     return vectorstore