Update app.py

app.py

@@ -1,64 +1,56 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from utils import is_financial_text, load_qa_data
 
-"""
-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}]
+# Load CSV Q&A pairs (if you want to use them later)
+qa_pairs = load_qa_data()
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+# Hugging Face client
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
+# Define system message template
+DEFAULT_SYSTEM_MSG = "You are a helpful assistant that answers only finance-related questions. Respond truthfully and avoid unrelated topics."
+
+def respond(message, history, system_message, max_tokens, temperature, top_p):
+    # Check if user question is finance-related before asking the model
+    if not is_financial_text(message):
+        yield "I'm specialized in finance and can't assist with that question."
+        return
+
+    # Prepare messages for Zephyr
+    messages = [{"role": "system", "content": system_message or DEFAULT_SYSTEM_MSG}]
+    for user_msg, bot_msg in history:
+        if user_msg:
+            messages.append({"role": "user", "content": user_msg})
+        if bot_msg:
+            messages.append({"role": "assistant", "content": bot_msg})
     messages.append({"role": "user", "content": message})
 
+    # Get model response (streamed)
     response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
+    for msg in client.chat_completion(
+        messages=messages,
         stream=True,
+        max_tokens=max_tokens,
         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
-"""
+        token = msg.choices[0].delta.content
+        if token:
+            response += token
+            yield response
+# Gradio interface
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Textbox(value=DEFAULT_SYSTEM_MSG, 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)"),
     ],
+    title="💰 Finance Assistant",
+    description="Ask finance-related questions only. The assistant will not respond to unrelated topics.",
 )
 
-
 if __name__ == "__main__":
     demo.launch()