Update app.py

app.py

@@ -10,7 +10,7 @@ from langchain_community.document_loaders import PyPDFLoader
 from langchain_community.embeddings import HuggingFaceEmbeddings
 from dotenv import load_dotenv
 
-# Load the environment variables
+# Load environment variables
 load_dotenv()
 
 # Load the GROQ API key
@@ -46,22 +46,35 @@ def process_pdf(file):
         return "PDF processed and added to the knowledge base."
     return "No file uploaded."
 
+# Function to clear the knowledge base
+def clear_knowledge_base():
+    global vectors
+    vectors = None  # Reset the vector store
+    return "Knowledge base cleared."
+
 # Function to process questions
 def process_question(question):
+    global vectors
     if vectors is None:
         return "Please upload a PDF first.", "", 0
     
-    document_chain = create_stuff_documents_chain(llm, prompt)
-    retriever = vectors.as_retriever()
-    retrieval_chain = create_retrieval_chain(retriever, document_chain)
-    
-    response = retrieval_chain.invoke({'input': question})
-    context = "\n\n".join([doc.page_content for doc in response["context"]])
+    # Create document retrieval chain
+    retriever = vectors.as_retriever(search_type="similarity", search_kwargs={"k": 5})
+    documents = retriever.get_relevant_documents(question)
     
-    # Calculate a confidence score based on the relevance of retrieved documents
-    confidence_score = sum([doc.metadata.get('score', 0) for doc in response["context"]]) / len(response["context"])
+    if not documents:
+        return "No relevant context found.", "", 0
     
-    return response['answer'], context, round(confidence_score, 2)
+    # Create context from retrieved documents
+    context = "\n\n".join([doc.page_content for doc in documents])
+
+    # Use the LLM to answer the question
+    response = llm({"context": context, "input": question})
+
+    # Confidence score as average relevance
+    confidence_score = sum([doc.metadata.get('score', 0) for doc in documents]) / len(documents)
+
+    return response, context, round(confidence_score, 2)
 
 # CSS styling
 CSS = """
@@ -89,6 +102,7 @@ with gr.Blocks(css=CSS, theme="Nymbo/Nymbo_Theme") as demo:
     with gr.Tab("PDF Uploader"):
         pdf_file = gr.File(label="Upload PDF")
         upload_button = gr.Button("Process PDF")
+        clear_button = gr.Button("Clear Knowledge Base")  # New button to clear the knowledge base
         upload_output = gr.Textbox(label="Upload Status")
 
     with gr.Tab("Q&A System"):
@@ -101,6 +115,9 @@ with gr.Blocks(css=CSS, theme="Nymbo/Nymbo_Theme") as demo:
     # Button actions
     upload_button.click(process_pdf, inputs=[pdf_file], outputs=[upload_output])
     submit_button.click(process_question, inputs=[question_input], outputs=[answer_output, context_output, confidence_output])
+    
+    # Action to clear the knowledge base
+    clear_button.click(clear_knowledge_base, outputs=[upload_output])
 
     gr.HTML(FOOTER_TEXT)