Update app.py

app.py

@@ -1,63 +1,63 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+from llama_cpp import Llama
+from typing import Optional
+import gradio as gr
+
+llm = Llama.from_pretrained(
+    repo_id="Haary/USK_Mistral_7B_Unsloth_GGUF",
+    filename="unsloth.Q4_K_M.gguf"
 )
 
 
+class Chat:
+
+    def __init__(self, system: Optional[str] = None):
+        self.system = system
+        self.messages = []
+        
+        if system is not None:
+            self.messages.append({
+                "role": "system",
+                "content": system
+            })
+
+    def prompt(self, content: str) -> str:
+          self.messages.append({
+              "role": "user",
+              "content": content
+          })
+          response = llm.create_chat_completion(
+              messages = [
+                {
+                  "role": "user",
+                  "content": "sertifikat akreditasi bisa dicari dimana yaa?"
+                }
+              ]
+          )
+          response_content = response["choices"][0]["message"]["content"]
+          self.messages.append({
+              "role": "assistant",
+              "content": response_content
+          })
+          return response_content
+
+chat = Chat(system="You are a helpful assistant.")
+
+
+def respond(message, chat_history):
+    bot_message = chat.prompt(content=message)
+    chat_history.append((message, bot_message))
+    return "", chat_history
+
+
+with gr.Blocks() as demo:
+    chatbot = gr.Chatbot()
+    msg = gr.Textbox()
+    clear = gr.Button("Clear")
+
+    msg.submit(respond, [msg, chatbot], [msg, chatbot])
+    clear.click(lambda: None, None, chatbot, queue=False)
+
+
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch(debug=True)