Update app.py

app.py

@@ -43,8 +43,8 @@ def get_text_chunks(text):
 
 
 
-def get_vector_store(text_chunks):
-    api_key = switch_api_key()
+def get_vector_store(text_chunks, user_api_key=None):
+    api_key = user_api_key if user_api_key else switch_api_key()
     embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001", google_api_key=api_key)
     vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
     vector_store.save_local("faiss_index")
@@ -52,8 +52,8 @@ def get_vector_store(text_chunks):
 
 
 
-def get_conversational_chain():
-    api_key = switch_api_key()
+def get_conversational_chain(api_key):
+    #api_key = switch_api_key()
     prompt_template = """
     You are a helpful assistant that only answers based on the context provided from the PDF documents.
     Do not use any external knowledge or assumptions. If the answer is not found in the context below, reply with "I don't know."
@@ -77,13 +77,11 @@ def get_conversational_chain():
 
 
 
-def user_input(user_question):
-    api_key = switch_api_key()
+def user_input(user_question, api_key):
     embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001", google_api_key=api_key)
     new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
     docs = new_db.similarity_search(user_question)
-    chain = get_conversational_chain()
-
+    chain = get_conversational_chain(api_key)
 
     response = chain({"input_documents": docs, "question": user_question}, return_only_outputs=True)
     st.write("Reply: ", response["output_text"])
@@ -95,22 +93,25 @@ def user_input(user_question):
 def main():
     st.set_page_config("Chat PDF")
     st.header("CSC 121: Computers and Scientific Thinking (Chatbot)")
-    st.subheader("Ask a question ONLY from the CSC 121 textbook of Dr. Reed",divider=True)
+    st.subheader("Ask a question ONLY from the CSC 121 textbook of Dr. Reed", divider=True)
 
+    user_api_key = st.text_input("Enter your API key (optional)")
 
     user_question = st.text_input("Ask a question")
 
-
     if user_question:
-        user_input(user_question)
-
+        if user_api_key:
+            api_key = user_api_key
+        else:
+            api_key = switch_api_key()
+        user_input(user_question, api_key)
 
     pdf_docs = st.file_uploader("Upload PDF files", accept_multiple_files=True)
     if st.button("Submit & Process"):
         with st.spinner("Processing..."):
             raw_text = get_pdf_text(pdf_docs)
             text_chunks = get_text_chunks(raw_text)
-            get_vector_store(text_chunks)
+            get_vector_store(text_chunks, user_api_key)
             st.success("Done")