Update app.py

app.py

@@ -1,70 +1,50 @@
-
 import gradio as gr
-import requests
+from google import generativeai as genai  # Gemini GenAI SDK :contentReference[oaicite:0]{index=0}
 import os
 
-# Fetch your Groq API key securely from HF Secrets
-groq_api_key = os.getenv("GROQ_API_KEY")
+# — Load and configure Gemini API key from HF Secrets
+gemini_api_key = os.getenv("GEMINI_API_KEY")
+if not gemini_api_key:
+    raise ValueError("GEMINI_API_KEY not set in environment")  # secure secret 
+genai.configure(api_key=gemini_api_key)
 
-# Path to local business.txt (uploaded in your Space repo)
+# — Path to your uploaded business.txt in the Space
 business_file = os.path.join(os.path.dirname(__file__), "business.txt")
 
 def chat_with_business(message, history):
-    try:
-        # Read business knowledge from local file
-        with open(business_file, "r", encoding="utf-8") as f:
-            business_info = f.read().strip()
-
-        # System prompt including business details
-        system_prompt = (
-            "You are a helpful customer care assistant. "
-            "Use only the following business information to answer the user's query:\n\n" +
-            business_info +
-            "\n\nIf the answer is not in the knowledge, reply 'Yeh information abhi available nahi hai.'"
-        )
-
-        # Prepare Groq API payload
-        headers = {
-            "Authorization": f"Bearer {groq_api_key}",
-            "Content-Type": "application/json"
-        }
-        payload = {
-            "model": "llama3-70b-8192",
-            "messages": [
-                {"role": "system", "content": system_prompt},
-                {"role": "user", "content": message}
-            ],
-            "temperature": 0.7
-        }
-
-        # Call Groq chat endpoint
-        response = requests.post(
-            "https://api.groq.com/openai/v1/chat/completions",
-            headers=headers,
-            json=payload
-        )
-        response.raise_for_status()
-        data = response.json()
-        reply = data["choices"][0]["message"]["content"]
-        return reply
-
-    except Exception as e:
-        return f"Error: {e}"
-
-# Build Gradio interface
+    # 1️⃣ Read the business knowledge
+    with open(business_file, "r", encoding="utf-8") as f:
+        business_info = f.read().strip()
+
+    # 2️⃣ Build the system prompt
+    system_prompt = (
+        "You are a helpful customer-care assistant. "
+        "Use only the information below to answer questions. "
+        "If the answer is not present, reply 'Yeh information abhi available nahi hai.'\n\n"
+        f"{business_info}\n\n"
+    )
+
+    # 3️⃣ Call Gemini 2.5 Flash to generate response :contentReference[oaicite:1]{index=1}
+    model = genai.GenerativeModel(model_name="gemini-2.5-flash-preview-04-17")
+    response = model.generate_content(
+        system_prompt + "User: " + message
+    )
+
+    # 4️⃣ Return the assistant’s reply
+    return response.text
+
+# — Build Gradio frontend (Blocks API for future customization)
 with gr.Blocks(theme="soft") as demo:
     gr.Markdown("## 🌿 My Business Bot")
     gr.Markdown("*Ask anything about your business in Hindi-English*")
     chatbot = gr.Chatbot(elem_id="chatbox", height=400)
     user_input = gr.Textbox(placeholder="Type your question here...", show_label=False)
 
-    def handle_interaction(message, chat_history):
-        bot_reply = chat_with_business(message, chat_history)
-        chat_history = chat_history + [(message, bot_reply)]
-        return chat_history, ""
-
-    user_input.submit(handle_interaction, [user_input, chatbot], [chatbot, user_input])
+    user_input.submit(
+        lambda msg, hist: (chat_with_business(msg, hist), ""), 
+        [user_input, chatbot], 
+        [chatbot, user_input]
+    )
 
-# Launch app
 if __name__ == "__main__":
     demo.launch()