adding chatbot with advanced options

app.py

@@ -34,13 +34,13 @@ def process_documents(documents,data_chunk=1500,chunk_overlap=100):
     texts = text_splitter.split_documents(documents)
     return texts
 
-def get_hugging_face_model(model_id,API_key,temperature=0.1):
+def get_hugging_face_model(model_id,API_key,temperature=0.1,max_tokens=4096):
     chat_llm = HuggingFaceHub(huggingfacehub_api_token=API_key,
                                       repo_id=model_id,
-                                      model_kwargs={"temperature": temperature, "max_new_tokens": 4096})
+                                      model_kwargs={"temperature": temperature, "max_new_tokens": max_tokens})
     return chat_llm
 
-def chat_application(llm_service,key):
+def chat_application(llm_service,key,temperature=0.1,max_tokens=1024):
     if llm_service == 'HuggingFace':
         llm = get_hugging_face_model(model_id='tiiuae/falcon-7b-instruct',API_key=key)
     else:
@@ -51,7 +51,7 @@ def summarize_contents():
     question = "Generate a summary of the contents. Do not return the response in json format"
     return qa.run(question)
 
-def document_loader(file_path,api_key,doc_type='pdf',llm='Huggingface'):
+def document_loader(file_path,api_key,doc_type='pdf',llm='Huggingface',temperature=0.1,max_tokens=4096):
     document = None
     if doc_type == 'pdf':
         document = process_pdf_document(document_file=file_path)
@@ -69,7 +69,9 @@ def document_loader(file_path,api_key,doc_type='pdf',llm='Huggingface'):
         texts = process_documents(documents=document)
         vector_db = FAISS.from_documents(documents=texts, embedding= embedding_model)
      
-        qa = RetrievalQA.from_chain_type(llm=chat_application(llm_service=llm,key=api_key),
+        qa = RetrievalQA.from_chain_type(llm=chat_application(llm_service=llm,key=api_key,
+                                                              temperature=temperature,
+                                                              max_tokens=max_tokens),
                                     chain_type='stuff',
                                     retriever=vector_db.as_retriever(),
                                 #  chain_type_kwargs=chain_type_kwargs,
@@ -151,11 +153,28 @@ with gr.Blocks(css=css) as demo:
             with gr.Box():
                 gr.Row()
                 LLM_option = gr.Dropdown(['HuggingFace','OpenAI'],label='Large Language Model Selection',info='LLM Service')
-                file_extension = gr.Dropdown(FILE_EXT, label="File Extensions", info="Select your files extensions!")
-            API_key = gr.Textbox(label="Add API key", type="password")
+                API_key = gr.Textbox(label="Add API key", type="password")
+                
+                
             with gr.Column():
                 with gr.Box():
+                    file_extension = gr.Dropdown(FILE_EXT, label="File Extensions", info="Select your files extensions!")
                     pdf_doc = gr.File(label="Upload File to start QA", file_types=FILE_EXT, type="file")
+                    with gr.Accordion(label='Advanced options', open=False):
+                        max_new_tokens = gr.Slider(
+                            label='Max new tokens',
+                            minimum=1,
+                            maximum=MAX_MAX_NEW_TOKENS,
+                            step=1,
+                            value=DEFAULT_MAX_NEW_TOKENS,
+                            )
+                        temperature = gr.Slider(
+                        label='Temperature',
+                        minimum=0.1,
+                        maximum=4.0,
+                        step=0.1,
+                        value=1.0,
+                        )
                     with gr.Row():
                         langchain_status = gr.Textbox(label="Status", placeholder="", interactive = False)
                         load_pdf = gr.Button("Upload File & Generate Embeddings",).style(full_width = False)
@@ -165,7 +184,7 @@ with gr.Blocks(css=css) as demo:
         # submit_button = gr.Button("Send Message")
 
     load_pdf.click(loading_file, None, langchain_status, queue=False)    
-    load_pdf.click(document_loader, inputs=[pdf_doc,API_key,file_extension,LLM_option], outputs=[langchain_status], queue=False)
+    load_pdf.click(document_loader, inputs=[pdf_doc,API_key,file_extension,LLM_option,temperature,max_new_tokens], outputs=[langchain_status], queue=False)
         
     with gr.Group():
         chatbot = gr.Chatbot(height=300)
@@ -177,23 +196,6 @@ with gr.Blocks(css=css) as demo:
     question.submit(add_text, [chatbot, question], [chatbot, question]).then(bot, chatbot, chatbot)
     submit_btn.click(add_text, [chatbot, question], [chatbot, question]).then(bot, chatbot, chatbot)
 
-    with gr.Accordion(label='Advanced options', open=False):
-        system_prompt = gr.Textbox(label='System prompt',
-                                   value=DEFAULT_SYSTEM_PROMPT,
-                                   lines=6)
-        max_new_tokens = gr.Slider(
-            label='Max new tokens',
-            minimum=1,
-            maximum=MAX_MAX_NEW_TOKENS,
-            step=1,
-            value=DEFAULT_MAX_NEW_TOKENS,
-        )
-        temperature = gr.Slider(
-            label='Temperature',
-            minimum=0.1,
-            maximum=4.0,
-            step=0.1,
-            value=1.0,
-        )
-        
+    
+
 demo.launch()