Update app.py

app.py

@@ -9,14 +9,14 @@ from langchain.chains.question_answering import load_qa_chain
 from langchain.prompts import PromptTemplate
 from dotenv import load_dotenv
 import traceback
-from transformers import pipeline
-from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain.embeddings import HuggingFaceEmbeddings
+import tensorflow as tf  # Ensure TensorFlow is imported
 
 # Load environment variables
 load_dotenv()
 
 # Ensure the Google API key is loaded
-google_api_key = 'AIzaSyBPC1o6NSGFT2LumpdompngjOOzzUNwGqk'
+google_api_key = os.getenv('GOOGLE_API_KEY')  # Fetch from .env
 if not google_api_key:
     raise ValueError("Google API key not found. Please check your .env file.")
 
@@ -47,17 +47,17 @@ def get_text_chunks(text):
 # Function to create an in-memory FAISS vector store
 def get_vector_store(text_chunks):
     try:
-        # Create an instance of HuggingFaceEmbeddings
+        # Initialize HuggingFace embeddings
         embedding_function = HuggingFaceEmbeddings(model_name="jinaai/jina-embeddings-v2-base-code")
 
-        # Using FAISS to create vector store with the embeddings class instance
+        # Using FAISS to create vector store with the Hugging Face embeddings
         vector_store = FAISS.from_texts(text_chunks, embedding=embedding_function)
-
         return vector_store
     except Exception as e:
         st.error(f"Error creating vector store: {e}")
         traceback.print_exc()
         return None
+
 # Function to create a conversation chain with Google Generative AI
 def get_conversational_chain():
     try:
@@ -118,7 +118,6 @@ def main():
             font-size: 18px;
             margin-bottom: 20px;
         }
-        
         </style>
         """,
         unsafe_allow_html=True