Update app.py

app.py

@@ -1,22 +1,74 @@
 import gradio as gr
 import json
 import os
+from huggingface_hub import InferenceClient
 from groq import Groq
 from groq.types.chat.chat_completion_tool_param import ChatCompletionToolParam
 
 # Use the fine-tuned maritime legal model
 MODEL = "nomiChroma3.1"
-##client = Groq(api_key=os.environ["GROQ_API_KEY"])
+client = Groq(api_key=os.environ["GROQ_API_KEY"])
+
+
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    system_message: str,
+    max_tokens: int,
+    temperature: float,
+    top_p: float,
+):
+    messages = [{"role": "system", "content": system_message}]
+
+    for user_message, assistant_message in history:
+        if user_message:
+            messages.append({"role": "user", "content": user_message})
+        if assistant_message:
+            messages.append({"role": "assistant", "content": assistant_message})
+
+    messages.append({"role": "user", "content": message})
+
+    response = ""
+    for message in client.chat_completion(
+        ChatCompletionToolParam(
+            messages=messages,
+            max_tokens=max_tokens,
+            temperature=temperature,
+            top_p=top_p,
+            stream=True
+        )
+    ):
+        token = message.choices[0].delta.get("content", "")
+        response += token
+        yield response
+
+demo = gr.ChatInterface(
+    respond,
+    additional_inputs=[
+        gr.Textbox(
+            value="You are a maritime legal assistant with expertise strictly in Indian maritime law. Provide detailed legal advice and information based on Indian maritime legal principles and regulations.",
+            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)"),
+    ],
+    title="Maritime Legal Compliance",
+    description="This chatbot uses the fine-tuned Llama 3.1 which has the capabilities of responding and helping in legal advices regarding maritime.",
+)
+
+if __name__ == "__main__":
+    demo.launch()
+
 
 
-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")
-
+##client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
+"""
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -72,4 +124,5 @@ demo = gr.ChatInterface(
 
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()
+"""