Update app.py

app.py

@@ -1,8 +1,28 @@
 import os
+import requests
 import gradio as gr
+from dotenv import load_dotenv, find_dotenv
 from transformers import pipeline
 
-client = pipeline("text-generation", model="upstage/Llama-2-70b-instruct", api_url=os.environ['API_URL'])
+# Load environment variables
+_ = load_dotenv(find_dotenv()) 
+hf_api_key = os.environ['HF_API_KEY']
+
+class Client:
+    def __init__(self, base_url, headers, timeout):
+        self.base_url = base_url
+        self.headers = headers
+        self.timeout = timeout
+
+    def generate(self, prompt, max_new_tokens):
+        # Your text generation code here.
+        return {'generated_text': 'Placeholder text'}
+      
+    def generate_stream(self, prompt, max_new_tokens, stop_sequences, temperature):
+        # Your streaming text generation code here.
+        pass
+
+client = Client(os.environ['HF_API_FALCOM_BASE'], headers={"Authorization": f"Basic {hf_api_key}"}, timeout=120)
 
 def format_chat_prompt(message, chat_history, instruction):
     prompt = f"System:{instruction}"
@@ -15,25 +35,14 @@ def format_chat_prompt(message, chat_history, instruction):
 def respond(message, chat_history, instruction, temperature=0.7):
     prompt = format_chat_prompt(message, chat_history, instruction)
     chat_history = chat_history + [[message, ""]]
-    stream = client.generate_stream(prompt,
-                                      max_new_tokens=1024,
-                                      stop_sequences=["\nUser:", "<|endoftext|>"],
-                                      temperature=temperature)
-                                      #stop_sequences to not generate the user answer
+    stream = client.generate_stream(prompt, max_new_tokens=1024, stop_sequences=["\nUser:", ""], temperature=temperature)
     acc_text = ""
-    #Streaming the tokens
     for idx, response in enumerate(stream):
             text_token = response.token.text
-
             if response.details:
                 return
-
             if idx == 0 and text_token.startswith(" "):
                 text_token = text_token[1:]
-
-            if any(word in text_token for word in SAFETY_GUIDELINES):
-                continue
-
             acc_text += text_token
             last_turn = list(chat_history.pop(-1))
             last_turn[-1] += acc_text
@@ -41,16 +50,7 @@ def respond(message, chat_history, instruction, temperature=0.7):
             yield "", chat_history
             acc_text = ""
 
-with gr.Blocks() as demo:
-    chatbot = gr.Chatbot(height=240) #just to fit the notebook
-    msg = gr.Textbox(label="Prompt")
-    with gr.Accordion(label="Advanced options",open=False):
-        system = gr.Textbox(label="System message", lines=2, value="A conversation between a user and an LLM-based AI assistant. The assistant gives helpful and honest answers.")
-        temperature = gr.Slider(label="temperature", minimum=0.1, maximum=1, value=0.7, step=0.1)
-    btn = gr.Button("Submit")
-    clear = gr.ClearButton(components=[msg, chatbot], value="Clear console")
-
-    btn.click(respond, inputs=[msg, chatbot, system], outputs=[msg, chatbot])
-    msg.submit(respond, inputs=[msg, chatbot, system], outputs=[msg, chatbot]) #Press enter to submit
-gr.close_all()
-demo.queue().launch(share=True, server_port=int(os.environ['PORT4']))
+iface = gr.Interface(fn=respond, inputs=[gr.Textbox(label="Prompt"), gr.Chatbox(label="Chat History", height=240), gr.Textbox(label="System message", lines=2, value="A conversation between a user and an LLM-based AI assistant. The assistant gives helpful and honest answers."), gr.Slider(label="temperature", minimum=0.1, maximum=1, value=0.7, step=0.1)], outputs=[gr.Textbox(label="Prompt"), gr.Chatbox(label="Chat History", height=240)])
+
+if __name__ == "__main__":
+    iface.launch()