Update app.py

app.py

@@ -1,63 +1,47 @@
+import os
+from groq import Groq 
 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)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+    
+client = Groq(api_key = os.environ.get("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"), )
+
+system_prompt = {
+                "role": "system",
+                "content":
+                "You are a useful assistant. You reply with efficient answers. "
+                }
+
+async def chat_groq(message, history):
+    
+    messages = [system_prompt]
+    
+    for msg in history:
+        messages.append({"role": "user", "content": str(msg[0])})
+        messages.append({"role": "assistant", "content": str(msg[1])})
+        
+    messages.append({"role": "user", "content": str (message)})
+    
+    response_content = ''
+    
+    stream = client.chat.completions.create(
+                                            model="llama3-70b-8192",
+                                            messages=messages,
+                                            max_tokens=1024,
+                                            temperature=1.3,
+                                            stream=True
+                                        )
+
+    for chunk in stream:
+        content = chunk.choices[0].delta.content
+        if content:
+            response_content += chunk. choices[0].delta.content 
+        yield response_content
+
+with gr. Blocks(theme=gr.themes.Monochrome(), fill_height=True) as demo:
+    gr.ChatInterface(chat_groq,
+                     clear_btn=None, 
+                     undo_btn=None, 
+                     retry_btn=None,
+                    )
+
+demo.queue()
+demo.launch()