Update app.py

app.py

@@ -3,43 +3,46 @@ import os
 import streamlit as st
 from langchain.document_loaders import PyPDFLoader
 from langchain.vectorstores import FAISS
-from langchain_community.embeddings.groq import GroqEmbedding  # Corrected import
+from langchain.embeddings.huggingface import HuggingFaceEmbeddings  # Updated to HuggingFaceEmbeddings
 
-# Function to process PDF
+# Function to process the uploaded PDF and save it temporarily
 def process_pdf(file):
-    # Save the uploaded file into a temporary file
     with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmpfile:
-        tmpfile.write(file.read())  # Write the uploaded file's content
-        tmpfile_path = tmpfile.name  # Get the file path
+        tmpfile.write(file.read())  # Write the uploaded file's content to the temp file
+        tmpfile_path = tmpfile.name  # Get the temporary file path
     return tmpfile_path
 
-# Main function to run the app
+# Main function to run the Streamlit app
 def main():
     st.title("PDF Embedding and Query System")
-    
+
+    # File uploader for the user to upload a PDF
     uploaded_file = st.file_uploader("Upload a PDF file", type=["pdf"])
-    
+
     if uploaded_file is not None:
-        # Process the uploaded PDF file
+        # Process the uploaded PDF and get its file path
         tmp_file_path = process_pdf(uploaded_file)
-        
-        # Load the PDF content
+
+        # Load the PDF content using the PyPDFLoader
         loader = PyPDFLoader(tmp_file_path)
         documents = loader.load()
-        
-        # Use Groq embeddings (assuming Groq API key is set correctly)
-        embeddings = GroqEmbedding(api_key="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")
-        
-        # Create a vector database
+
+        # Initialize HuggingFace embeddings (replace this with your desired model)
+        embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")  # Example model
+
+        # Create a FAISS vector store using the loaded documents and generated embeddings
         vector_db = FAISS.from_documents(documents, embeddings)
-        
-        # Perform search or other actions
+
+        # Query input field for users to enter their search queries
         query = st.text_input("Enter a query to search:")
+        
         if query:
+            # Perform similarity search based on the query
             results = vector_db.similarity_search(query, k=5)
+            # Display the results
             for result in results:
                 st.write(result["text"])
 
-# Run the app
+# Run the app if this script is executed directly
 if __name__ == "__main__":
     main()