Update app.py

app.py

@@ -15,6 +15,9 @@ from langchain_core.runnables import RunnablePassthrough
 # Initialize the FAISS vector store
 vector_store = None
 
+# Sample PDF file
+sample_filename = "Attention Is All You Need.pdf"
+
 template = \
 """Use the following pieces of context to answer the question at the end.
 If you don't know the answer, just say that you don't know, don't try to make up an answer.
@@ -47,19 +50,24 @@ def index_pdf(pdf):
 
     return "PDF indexed successfully!"
 
-# # Function to handle chatbot queries
-# def chatbot_query(query):
-#     if vector_store is None:
-#         return "Please upload and index a PDF first."
-    
-#     # Create a retrieval-based QA chain
-#     retriever = vector_store.as_retriever()
-#     qa_chain = RetrievalQA(llm=OpenAI(), retriever=retriever)
-    
-#     # Get the response from the QA chain
-#     response = qa_chain.run(query)
+def load_sample_pdf():
+    global vector_store
     
-#     return response
+    # Load the PDF
+    loader = PyPDFLoader(sample_filename)
+    documents = loader.load()
+
+    # Split the documents into chunks
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+    texts = text_splitter.split_documents(documents)
+
+    # Embed the chunks 
+    embeddings = HuggingFaceEmbeddings(model_name="bert-base-uncased", encode_kwargs={"normalize_embeddings": True})
+
+    # Store the embeddings in the vector store
+    vector_store = FAISS.from_documents(texts, embeddings)
+
+    return "Sample PDF indexed successfully!"
 
 
 def format_docs(docs):
@@ -104,8 +112,10 @@ with gr.Blocks(theme="Nymbo/Alyx_Theme") as demo:
     with gr.Tab("Indexing"):
         pdf_input = gr.File(label="Upload PDF", file_types=[".pdf"])
         index_button = gr.Button("Index PDF")
+        load_sample = gr.Button("Or load "Attention Is All You Need.pdf" as a Sample")
         index_output = gr.Textbox(label="Indexing Status")
         index_button.click(index_pdf, inputs=pdf_input, outputs=index_output)
+        load_sample.click(load_sample_pdf, inputs=None, outputs=index_output)
     
     with gr.Tab("Chatbot"):
         # query_input = gr.Textbox(label="Enter your question")