Update app.py

app.py

@@ -11,7 +11,7 @@ from langchain.chains import RetrievalQA # for conversing with chatGPT
 from langchain.chat_models import ChatOpenAI # the LLM model we'll use (ChatGPT)
 from langchain import PromptTemplate
 
-def load_pdf_and_generate_embeddings(pdf_doc, open_ai_key):
+def load_pdf_and_generate_embeddings(pdf_doc, open_ai_key, relevant_pages='all'):
     if openai_key is not None:
         os.environ['OPENAI_API_KEY'] = open_ai_key
         #Load the pdf file
@@ -21,10 +21,11 @@ def load_pdf_and_generate_embeddings(pdf_doc, open_ai_key):
         #Create an instance of OpenAIEmbeddings, which is responsible for generating embeddings for text
         embeddings = OpenAIEmbeddings()
 
-        #To create a vector store, we use the Chroma class, which takes the documents (pages in our case), the embeddings instance, and a directory to store the vector data
-        vectordb = Chroma.from_documents(pages, embedding=embeddings)
+        if relevant_pages == 'all':    
+            #To create a vector store, we use the Chroma class, which takes the documents (pages in our case) and the embeddings instance
+            vectordb = Chroma.from_documents(pages, embedding=embeddings)
         
-        #Finally, we create the bot using the RetrievalQAChain class
+        #Finally, we create the bot using the RetrievalQA class
         global pdf_qa
 
         prompt_template = """Use the following pieces of context to answer the question at the end. If you do not know the answer, just return N/A. If you encounter a date, return it in mm/dd/yyyy format.
@@ -129,7 +130,7 @@ with gr.Blocks(css=css,theme=gr.themes.Monochrome()) as demo:
             submit_query = gr.Button("Submit your own question to gpt-4").style(full_width=False)
         
  
-    load_pdf.click(load_pdf_and_generate_embeddings, inputs=[pdf_doc, openai_key], outputs=status)
+    load_pdf.click(load_pdf_and_generate_embeddings, inputs=[pdf_doc, openai_key, relevant_pages], outputs=status)
 
     answers_for_predefined_question_set.click(answer_predefined_questions, document_type, answers)