Update app.py

app.py

@@ -1,44 +1,66 @@
+
 import gradio as gr
-from llama_cpp import Llama
-
-llm = Llama(
-    "AstroMLab/AstroSage-8B-GGUF",
-    n_ctx=8192,
-    n_threads=4,
-    seed=42,
-    f16_kv=True,
-    logits_all=False,
-    use_mmap=True,
-    use_gpu=True
-)
+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("https://huggingface.co/AstroMLab/AstroSage-8B-GGUF/blob/main/AstroSage-8B-Q8_0.gguf")
 
-def respond(message, history, system_message, max_tokens, temperature, top_p):
+
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
     messages = [{"role": "system", "content": system_message}]
-    for user_msg, assistant_msg in history:
-        if user_msg:
-            messages.append({"role": "user", "content": user_msg})
-        if assistant_msg:
-            messages.append({"role": "assistant", "content": assistant_msg})
+
+    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 = llm.generate_chat(
+
+    response = ""
+
+    for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
+        stream=True,
         temperature=temperature,
-        top_p=top_p
-    )
-    
-    return response
+        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="Assume the role of AstroSage, a helpful chatbot designed to answer user queries about astronomy, astrophysics, and cosmology.", 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)"),
-    ]
+        gr.Slider(
+            minimum=0.1,
+            maximum=1.0,
+            value=0.95,
+            step=0.05,
+            label="Top-p (nucleus sampling)",
+        ),
+    ],
 )
 
+
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()
+