Update app.py

app.py

@@ -7,6 +7,7 @@ import plotly.express as px
 import plotly.io as pio
 import numpy as np
 import dotenv
+import json
 
 dotenv.load_dotenv()
 
@@ -18,7 +19,7 @@ def fetch_market_data(state=None, district=None, market=None, commodity=None):
     Filters (state, district, market, commodity) are applied manually on CSV data.
     """
     api_key = "579b464db66ec23bdd000001189bbb99e979428764bdbe8fdd44ebb7"
-    base_url = "https://api.data.gov.in/resource/9ef84268-d588-465a-a308-a864a43d0070"
+    base_url = "https://api.data.gov.in/resource/9ef84268-d588-465a-a308-a864a43d007"
     
     params = {
         "api-key": api_key,
@@ -91,26 +92,43 @@ def fetch_market_data(state=None, district=None, market=None, commodity=None):
     
     return df
 
-def get_ai_insights(market_data, state, district):
-    """Get enhanced insights from LLM API with focus on profitable suggestions for farmers.
+def get_ai_insights(market_data, state, district, market=None, commodity=None, language="English"):
+    """Get enhanced insights from Gemini API with focus on profitable suggestions for farmers.
+       Supports multiple languages through the prompt.
        Returns dynamic insights only. If something goes wrong, returns an empty string.
     """
     if not state or not district or market_data.empty:
         return ""
     
     try:
+        # Filter data based on provided parameters
         district_data = market_data[market_data['district'] == district]
         if district_data.empty:
             return ""
         
+        # Apply market filter if provided
+        if market and not market_data[market_data['market'] == market].empty:
+            market_specific = True
+            district_data = district_data[district_data['market'] == market]
+        else:
+            market_specific = False
+            
+        # Apply commodity filter if provided
+        if commodity and not market_data[market_data['commodity'] == commodity].empty:
+            commodity_specific = True
+            district_data = district_data[district_data['commodity'] == commodity]
+        else:
+            commodity_specific = False
+        
+        # Calculate price trends
         price_trends = district_data.groupby('commodity').agg({
             'modal_price': ['mean', 'min', 'max', 'std']
         }).round(2)
         
-        # Using a hard-coded API key for testing; replace with your environment variable as needed.
-        api_key = os.getenv("HUGGINGFACE_API_KEY")
+        # Using environment variable for Gemini API key
+        api_key = os.environ.get('GEMINI_API_KEY')
         if not api_key:
-            print("Warning: Hugging Face API key not set")
+            print("Warning: Gemini API key not set")
             return ""
             
         price_trends['price_stability'] = (price_trends['modal_price']['std'] / 
@@ -123,46 +141,110 @@ def get_ai_insights(market_data, state, district):
         market_competition = len(district_data['market'].unique())
         top_commodities = district_data.groupby('commodity')['modal_price'].mean().nlargest(5).index.tolist()
         
-        # Improved prompt for better structured output
+        # Get min and max prices for key commodities
+        price_range_info = {}
+        for commodity in top_commodities[:3]:
+            comm_data = district_data[district_data['commodity'] == commodity]
+            if not comm_data.empty:
+                price_range_info[commodity] = {
+                    'min': comm_data['modal_price'].min(),
+                    'max': comm_data['modal_price'].max(),
+                    'avg': comm_data['modal_price'].mean()
+                }
+        
+        # Calculate market-specific metrics if market is selected
+        market_details = ""
+        if market_specific:
+            market_details = f"""
+            Market-specific information for {market}:
+            - Number of commodities: {len(district_data['commodity'].unique())}
+            - Most expensive commodity: {district_data.groupby('commodity')['modal_price'].mean().idxmax()}
+            - Cheapest commodity: {district_data.groupby('commodity')['modal_price'].mean().idxmin()}
+            """
+        
+        # Commodity-specific details if commodity is selected
+        commodity_details = ""
+        if commodity_specific:
+            commodity_data = district_data[district_data['commodity'] == commodity]
+            best_market = commodity_data.loc[commodity_data['modal_price'].idxmin()]['market']
+            worst_market = commodity_data.loc[commodity_data['modal_price'].idxmax()]['market']
+            
+            commodity_details = f"""
+            Commodity-specific information for {commodity}:
+            - Best market to buy (lowest price): {best_market}
+            - Highest priced market: {worst_market}
+            - Price variance across markets: {commodity_data['modal_price'].std().round(2)}
+            """
+        
+        # Improved prompt for better structured output with language support
         prompt = f"""
-        Analyze the following market data for {district}, {state}:
+        Analyze the following agricultural market data for {district}, {state} and provide insights in {language} language.
+        
+        Market data:
         - Active markets: {market_competition}
         - Top crops: {', '.join(top_commodities[:5])}
         - Data from {len(price_trends.index)} crops and {len(monthly_trends)} monthly entries.
-        read the data and provide insights on crop profitability and market price trends and i want the same values from the data.
+        
+        Price information:
+        {json.dumps(price_range_info, indent=2)}
+        
+        {market_details}
+        {commodity_details}
+        
+        Analyze this data and provide insights about crop market trends and profitability. 
+        Include specific numbers from the data about prices.
+        
         Provide structured insights with clear sections. Use this exact format with bullet points:
         
         Crop Profitability Analysis:
-        * [First insight about profitable crops]
+        * [First insight about profitable crops with specific prices mentioned]
         * [Second insight]
         
         Market Price Analysis:
-        * [First insight about markets]
+        * [First insight about markets with specific price ranges]
         * [Second insight]
         
-        Recommendations:
+        Recommendations for Farmers:
         * [Action item 1]
         * [Action item 2]
         """
         
-        api_url = "https://router.huggingface.co/hf-inference/models/meta-llama/Llama-3.2-3B-Instruct/v1/chat/completions"
-        headers = {"Authorization": f"Bearer {api_key}"}
+        api_url = "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-pro:generateContent"
+        headers = {"Content-Type": "application/json"}
+        
         payload = {
-            "messages": [
-                {"role": "user", "content": prompt}
-            ]
+            "contents": [
+                {
+                    "parts": [
+                        {"text": prompt}
+                    ]
+                }
+            ],
+            "generationConfig": {
+                "temperature": 0.4,
+                "maxOutputTokens": 1024
+            }
         }
         
-        response = requests.post(api_url, headers=headers, json=payload, timeout=15)
+        response = requests.post(
+            f"{api_url}?key={api_key}", 
+            headers=headers, 
+            json=payload, 
+            timeout=20
+        )
+        
         if response.status_code == 200:
             response_data = response.json()
-            if isinstance(response_data, dict):
-                if 'choices' in response_data and len(response_data['choices']) > 0:
-                    message = response_data['choices'][0].get('message', {})
-                    insights = message.get('content', "")
+            if 'candidates' in response_data and len(response_data['candidates']) > 0:
+                content = response_data['candidates'][0]['content']
+                if 'parts' in content and len(content['parts']) > 0:
+                    insights = content['parts'][0]['text']
                     return format_ai_insights(insights)
-            print(f"API Response issue: {response.status_code} - {response.text[:100]}")
-            return ""
+            print(f"API Response issue: {response.text[:100]}")
+        else:
+            print(f"Gemini API Error: {response.status_code} - {response.text[:100]}")
+        
+        return ""
     
     except Exception as e:
         print(f"Error generating insights: {str(e)}")
@@ -294,10 +376,12 @@ def filter_data():
     district = request.form.get('district')
     market = request.form.get('market')
     commodity = request.form.get('commodity')
+    language = request.form.get('language', 'English')  # Default to English
     
     df = fetch_market_data(state, district, market, commodity)
     plots = generate_plots(df)
-    insights = get_ai_insights(df, state, district) if state and district and not df.empty else ""
+    # Pass market and commodity to get_ai_insights
+    insights = get_ai_insights(df, state, district, market, commodity, language) if state and district and not df.empty else ""
     
     market_table_html = """
     <div class="table-responsive">
@@ -427,4 +511,4 @@ def get_commodities():
 
 if __name__ == '__main__':
     app.run(debug=True, host='0.0.0.0', port=7860)
-    pio.templates.default = "plotly_white"
+    pio.templates.default = "plotly_white"