Update app.py

app.py

@@ -1,58 +1,82 @@
 import json
 import os
+import gradio as gr
+import pandas as pd
 from openai import OpenAI
+from transformers import pipeline
 from dotenv import load_dotenv
 
-# Load environment variables
 load_dotenv()
 api_key = os.getenv("OPENAI_API_KEY")
 client = OpenAI(api_key=api_key)
 
-# Function that provides weather details
-def get_weather(city: str):
-    weather_data = {
-        "New York": "☀️ Sunny, 25°C",
-        "London": "🌧️ Rainy, 18°C",
-        "Mumbai": "⛅ Cloudy, 30°C"
-    }
-    return weather_data.get(city, "Weather data not available for this city.")
-
-# Chat function with function calling
-def chat_with_llm(user_query):
-    functions = [
-        {
-            "name": "get_weather",
-            "description": "Fetch weather details for a given city.",
-            "parameters": {
-                "type": "object",
-                "properties": {
-                    "city": {"type": "string", "description": "Name of the city"}
-                },
-                "required": ["city"]
-            }
-        }
-    ]
+pipe = pipeline("text-classification", model="cardiffnlp/twitter-roberta-base-sentiment-latest")
+
+def process_csv(file):
+    df = pd.read_csv(file)
+    if "Feedback" not in df.columns or "Employee" not in df.columns:
+        return None, "❌ Error: CSV must contain 'Employee' and 'Feedback' columns."
+    df["Sentiment"] = df["Feedback"].apply(lambda x: pipe(x)[0]["label"])
+    return {"df": df}, "✅ CSV processed!"
 
+def predict_attrition_risk(employee_name: str, sentiment: str):
+    risk_mapping = {"positive": "Low Risk", "neutral": "Medium Risk", "negative": "High Risk"}
+    return f"{employee_name}: {risk_mapping.get(sentiment.lower(), 'Unknown Sentiment')}"
+
+def analyze_attrition_with_llm(df_dict, hr_query):
+    if df_dict is None or "df" not in df_dict:
+        return "❌ Error: No processed data. Upload a CSV first."
+    
+    df = df_dict["df"]
+    employees_data = {row["Employee"].strip(): row["Sentiment"] for _, row in df.iterrows()}
+    
+    # LLM function calling
+    prompt = f"HR Query: {hr_query}\nEmployees Data: {json.dumps(employees_data, indent=2)}"
     response = client.chat.completions.create(
-        model="gpt-4o-mini",
-        messages=[{"role": "user", "content": user_query}],
-        functions=functions,
-        function_call="auto"  # GPT decides whether to call the function
+        model="gpt-4-turbo",
+        messages=[{"role": "user", "content": prompt}],
+        functions=[
+            {
+                "name": "predict_attrition_risk",
+                "description": "Predicts attrition risk based on sentiment.",
+                "parameters": {
+                    "type": "object",
+                    "properties": {
+                        "employee_name": {"type": "string", "description": "Employee's name"},
+                        "sentiment": {"type": "string", "description": "Extracted sentiment"}
+                    },
+                    "required": ["employee_name", "sentiment"]
+                }
+            }
+        ],
+        function_call="auto"
     )
-
+    
     message = response.choices[0].message
-
-    if hasattr(message, "function_call") and message.function_call:
+    if message.function_call:
         try:
-            function_args = json.loads(message.function_call.arguments)
-            city = function_args.get("city")
-            if city:
-                return get_weather(city)
+            function_call = json.loads(message.function_call.arguments)
+            employee_name = function_call.get("employee_name")
+            sentiment = function_call.get("sentiment")
+            
+            if employee_name and sentiment:
+                return predict_attrition_risk(employee_name, sentiment)
         except Exception as e:
-            return f"❌ Error processing function call: {str(e)}"
+            return f"❌ Error processing LLM function call: {str(e)}"
+    
+    return "🤖 I'm sorry, but I can only answer queries related to employee attrition risk."
+
+with gr.Blocks() as demo:
+    gr.Markdown("<h1>AI-Driven Employee Attrition Risk Analysis</h1>")
+    file_input = gr.File(label="Upload Employee Feedback CSV", file_types=[".csv"])
+    process_button = gr.Button("Process CSV")
+    process_message = gr.Markdown()
+    hr_input = gr.Textbox(label="Employee Name or HR Query")
+    analyze_button = gr.Button("Check Attrition Risk")
+    output_text = gr.Markdown()
+    df_state = gr.State()
 
-    return message.content  # Return normal LLM response if no function is called
+    process_button.click(process_csv, inputs=file_input, outputs=[df_state, process_message])
+    analyze_button.click(analyze_attrition_with_llm, inputs=[df_state, hr_input], outputs=output_text)
 
-# Example Queries
-print(chat_with_llm("What's the weather like in New York?"))  # Calls function
-print(chat_with_llm("Tell me a joke."))  # Normal LLM response
+demo.launch(share=True)