Update app.py

app.py

@@ -1,306 +1,60 @@
-import os
-import requests
-import json
-import logging
-from datetime import datetime
-from simple_salesforce import Salesforce, SalesforceAuthenticationFailed
-from flask import Flask, jsonify, request, render_template, redirect, url_for
+from flask import Flask, request, jsonify
+from transformers import pipeline
+from simple_salesforce import Salesforce
+import datetime
 
-# Set up logging to capture errors and debug information
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__name__)
-
-app = FastAPI()
-
-# Salesforce credentials
-SF_USERNAME = os.getenv("SF_USERNAME", "Ai@Coach.com")
-SF_PASSWORD = os.getenv("SF_PASSWORD", "Teja90325@")
-SF_SECURITY_TOKEN = os.getenv("SF_SECURITY_TOKEN", "clceSdBgQ30Rx9BSC66gAcRx")
-SF_DOMAIN = os.getenv("SF_DOMAIN", "login")
-
-# Verify API key is set
-API_KEY = os.getenv("HUGGING_FACE_API_KEY")
-if not API_KEY:
-    logger.error("HUGGING_FACE_API_KEY environment variable not set")
-    raise ValueError("HUGGING_FACE_API_KEY environment variable not set")
-
-# Connect to Salesforce
-try:
-    sf = Salesforce(
-        username=SF_USERNAME,
-        password=SF_PASSWORD,
-        security_token=SF_SECURITY_TOKEN,
-        domain=SF_DOMAIN
-    )
-    logger.info("Successfully connected to Salesforce")
-except Exception as e:
-    logger.error(f"Failed to connect to Salesforce: {str(e)}")
-    raise
-
-
-
-
-# Validate configuration
-if not HUGGING_FACE_API_TOKEN:
-    logger.error("HUGGING_FACE_API_TOKEN is not set")
-    raise ValueError("HUGGING_FACE_API_TOKEN must be provided")
-if not HUGGING_FACE_API_URL.startswith("https://api-inference.huggingface.co/models/"):
-    logger.error("Invalid HUGGING_FACE_API_URL: %s", HUGGING_FACE_API_URL)
-    raise ValueError("HUGGING_FACE_API_URL must point to a valid Hugging Face model")
-if not all([SALESFORCE_USERNAME, SALESFORCE_PASSWORD, SALESFORCE_SECURITY_TOKEN]):
-    logger.error("Salesforce credentials are incomplete")
-    raise ValueError("Salesforce credentials must be set")
-
-# Initialize Flask app
 app = Flask(__name__)
 
-def test_salesforce_connection():
-    """
-    Test the Salesforce connection and log the result.
-    """
-    try:
-        logger.debug("Attempting to connect to Salesforce with username: %s, domain: %s", SALESFORCE_USERNAME, SALESFORCE_DOMAIN)
-        sf = Salesforce(
-            username=SALESFORCE_USERNAME,
-            password=SALESFORCE_PASSWORD,
-            security_token=SALESFORCE_SECURITY_TOKEN,
-            domain=SALESFORCE_DOMAIN
-        )
-        logger.info("Successfully connected to Salesforce. Session ID: %s", sf.session_id)
-        # Test a simple query to verify object access
-        sf.query("SELECT Id FROM Account LIMIT 1")
-        logger.info("Successfully queried Account object. Connection is working.")
-        return True
-    except SalesforceAuthenticationFailed as e:
-        logger.error("Salesforce authentication failed: %s", e)
-        return False
-    except Exception as e:
-        logger.error("Salesforce connection error: %s", e)
-        return False
-
-def fetch_salesforce_input(supervisor_id, project_id):
-    """
-    Fetch input data from Salesforce for a given supervisor and project.
-    """
-    try:
-        logger.debug("Connecting to Salesforce to fetch input data")
-        sf = Salesforce(
-            username=SALESFORCE_USERNAME,
-            password=SALESFORCE_PASSWORD,
-            security_token=SALESFORCE_SECURITY_TOKEN,
-            domain=SALESFORCE_DOMAIN
-        )
-        logger.info("Connected to Salesforce for input fetch")
-        query = f"""
-            SELECT Supervisor_ID__c, Role__c, Project_ID__c, Weather__c, Milestones__c, Reflection_Log__c
-            FROM Supervisor_AI_Coaching__c
-            WHERE Supervisor_ID__c = '{supervisor_id}' AND Project_ID__c = '{project_id}'
-            ORDER BY Generated_Date__c DESC
-            LIMIT 1
-        """
-        logger.debug("Executing Salesforce query: %s", query)
-        result = sf.query(query)
-        if result['totalSize'] > 0:
-            record = result['records'][0]
-            logger.info("Fetched record from Salesforce: %s", record)
-            return {
-                'supervisor_id': record['Supervisor_ID__c'] or '',
-                'role': record['Role__c'] or '',
-                'project_id': record['Project_ID__c'] or '',
-                'weather': record['Weather__c'] or '',
-                'milestones': record['Milestones__c'] or '',
-                'reflection': record['Reflection_Log__c'] or ''
-            }
-        else:
-            logger.info("No input data found for supervisor %s and project %s", supervisor_id, project_id)
-            return None
-    except Exception as e:
-        logger.error("Salesforce fetch error: %s", e)
-        return None
+# Initialize Hugging Face LLM (simulated for this example)
+generator = pipeline("text-generation", model="distilgpt2")
 
-def generate_coaching_output(data):
-    """
-    Generate daily checklist and tips using Hugging Face LLM.
-    """
-    logger.info("Generating coaching output for supervisor %s", data['supervisor_id'])
-    milestones_json = json.dumps(data['milestones'], indent=2)
-    prompt = f"""You are an AI Coach for construction site supervisors. Based on the following data, generate a daily checklist, three focus tips, and a motivational quote. Ensure outputs are concise, actionable, and tailored to the supervisor's role, project status, and reflection log.Supervisor Role: {data['role']}Project Milestones: {milestones_json}Reflection Log: {data['reflection_log']}Weather: {data['weather']}Format the response as JSON:{{    "checklist": ["item1", "item2", ...],    "tips": ["tip1", "tip2", "tip3"],    "quote": "motivational quote"}}"""
-    headers = {
-        "Authorization": f"Bearer {HUGGING_FACE_API_TOKEN}",
-        "Content-Type": "application/json"
-    }
-    payload = {
-        "inputs": prompt,
-        "parameters": {
-            "max_length": 200,
-            "temperature": 0.7,
-            "top_p": 0.9,
-            "debug": True  # Enable Hugging Face debug mode
-        }
-    }
-    try:
-        logger.debug("Sending request to Hugging Face API: %s", payload)
-        response = requests.post(HUGGING_FACE_API_URL, headers=headers, json=payload, timeout=5)
-        response.raise_for_status()
-        result = response.json()
-        logger.debug("Hugging Face API response: %s", result)
-        generated_text = result[0]["generated_text"] if isinstance(result, list) else result["generated_text"]
-        start_idx = generated_text.find('{')
-        end_idx = generated_text.rfind('}') + 1
-        if start_idx == -1 or end_idx == 0:
-            logger.error("No valid JSON found in LLM output: %s", generated_text)
-            raise ValueError("No valid JSON found in LLM output")
-        json_str = generated_text[start_idx:end_idx]
-        output = json.loads(json_str)
-        logger.info("Successfully generated coaching output: %s", output)
-        return output
-    except requests.exceptions.HTTPError as e:
-        logger.error("Hugging Face API HTTP error: %s", e)
-        return None
-    except (json.JSONDecodeError, ValueError) as e:
-        logger.error("Error parsing LLM output: %s", e)
-        return None
-    except Exception as e:
-        logger.error("Unexpected error in Hugging Face API call: %s", e)
-        return None
-
-def save_to_salesforce(output, supervisor_id, project_id):
-    """
-    Save coaching output to Salesforce Supervisor_AI_Coaching__c object.
-    """
-    if not output:
-        logger.error("No coaching output to save")
-        return False
-    try:
-        logger.debug("Connecting to Salesforce to save output")
-        sf = Salesforce(
-            username=SALESFORCE_USERNAME,
-            password=SALESFORCE_PASSWORD,
-            security_token=SALESFORCE_SECURITY_TOKEN,
-            domain=SALESFORCE_DOMAIN
-        )
-        logger.info("Connected to Salesforce for saving output")
-        coaching_record = {
-            "Supervisor_ID__c": supervisor_id,
-            "Project_ID__c": project_id,
-            "Daily_Checklist__c": "\n".join(output["checklist"]),
-            "Suggested_Tips__c": "\n".join(output["tips"]),
-            "Quote__c": output["quote"],
-            "Generated_Date__c": datetime.now().strftime("%Y-%m-%d")
-        }
-        logger.debug("Saving record to Salesforce: %s", coaching_record)
-        sf.Supervisor_AI_Coaching__c.upsert(
-            f"Supervisor_ID__c/{supervisor_id}_{datetime.now().strftime('%Y-%m-%d')}",
-            coaching_record
-        )
-        logger.info("Successfully saved coaching record to Salesforce for supervisor %s", supervisor_id)
-        return True
-    except Exception as e:
-        logger.error("Salesforce save error: %s", e)
-        return False
-
-@app.route('/', methods=['GET'])
-def redirect_to_ui():
-    """
-    Redirect root URL to the UI.
-    """
-    return redirect(url_for('ui'))
-
-@app.route('/ui', methods=['GET'])
-def ui():
-    """
-    Serve the HTML user interface, fetch input from Salesforce, generate output, and save to Salesforce.
-    """
-    form_data = {}
-    output = {}
-    # Test Salesforce connection first
-    if not test_salesforce_connection():
-        logger.error("Salesforce connection test failed. Check logs for details.")
-        return "Salesforce connection failed. Check logs for details.", 500
-    # Hardcoded supervisor_id and project_id for demonstration
-    supervisor_id = "SUP-001"
-    project_id = "PROJ-123"
-    # Fetch input data from Salesforce
-    logger.info("Fetching input data from Salesforce for supervisor %s and project %s", supervisor_id, project_id)
-    sf_input = fetch_salesforce_input(supervisor_id, project_id)
-    if sf_input:
-        form_data = sf_input
-        # Prepare data for generating output
-        data = {
-            'supervisor_id': form_data['supervisor_id'],
-            'role': form_data['role'],
-            'project_id': form_data['project_id'],
-            'milestones': [m.strip() for m in form_data['milestones'].split(',') if m.strip()],
-            'reflection_log': form_data['reflection'],
-            'weather': form_data['weather']
-        }
-        # Generate output automatically
-        logger.info("Generating output for fetched Salesforce data")
-        coaching_output = generate_coaching_output(data)
-        if coaching_output:
-            # Save the generated output to Salesforce
-            logger.info("Saving generated output to Salesforce")
-            success = save_to_salesforce(coaching_output, supervisor_id, project_id)
-            if success:
-                output = coaching_output
-            else:
-                logger.error("Failed to save generated output to Salesforce")
-        else:
-            logger.error("Failed to generate coaching output")
-    else:
-        logger.warning("No input data found in Salesforce. Displaying empty fields.")
-    return render_template('index.html', form_data=form_data, output=output)
+# Salesforce credentials (to be filled by you)
+sf = Salesforce(username='YOUR_USERNAME', password='YOUR_PASSWORD', security_token='YOUR_SECURITY_TOKEN')
 
-@app.route('/health', methods=['GET'])
-def health_check():
-    """
-    Health check endpoint.
-    """
-    return jsonify({"status": "healthy", "message": "Application is running"}), 200
-
-# NEW ENDPOINT TO RECEIVE DATA FROM SALESFORCE
-@app.route('/salesforce_data', methods=['POST'])
-def salesforce_data():
-    """
-    Receives data from Salesforce, generates coaching output, and saves it.
-    """
+@app.route('/generate', methods=['POST'])
+def generate_ai_data():
     data = request.json
-    logger.debug("Received data from Salesforce: %s", data)
-
-    # Extract relevant data from the request.  Adjust these keys
-    # based on how Salesforce sends the data.
-    supervisor_id = data.get('supervisor_id')
-    project_id = data.get('project_id')
-    role = data.get('role')
-    weather = data.get('weather')
-    milestones = data.get('milestones', '').split(',')  # Handle potential empty string
-    reflection_log = data.get('reflection_log')
-
-    if not all([supervisor_id, project_id, role, milestones, reflection_log]):
-        logger.error("Missing data from Salesforce: %s", data)
-        return jsonify({"status": "error", "message": "Missing required data"}), 400
-
-    coaching_data = {
-        'supervisor_id': supervisor_id,
-        'role': role,
-        'project_id': project_id,
-        'milestones': [m.strip() for m in milestones if m.strip()],
-        'reflection_log': reflection_log,
-        'weather': weather,
+    supervisor_id = data['supervisor_id']
+    project_id = data['project_id']
+    supervisor_data = data['supervisor_data']  # Role__c, Location__c
+    project_data = data['project_data']  # Name, Start_Date__c, End_Date__c, Milestones__c, Project_Schedule__c
+
+    # Generate AI data using LLM
+    prompt = f"Generate daily checklist, tips, risk alerts, milestones, and performance trends for a {supervisor_data['Role__c']} at {supervisor_data['Location__c']} working on project {project_data['Name']} with milestones {project_data['Milestones__c']} and schedule {project_data['Project_Schedule__c']}."
+    ai_response = generator(prompt, max_length=500, num_return_sequences=1)[0]['generated_text']
+
+    # Parse AI response (simplified for this example)
+    daily_checklist = "1. Inspect concrete quality (Safety, Pending)\n2. Schedule team briefing (General, Pending)\n3. Check equipment (High Priority, Pending)"
+    suggested_tips = "1. Prioritize safety checks.\n2. Focus on delayed tasks.\n3. Schedule a team review."
+    risk_alerts = "Risk of delay: Rain expected on May 22, 2025."
+    upcoming_milestones = "Foundation completion by May 22, 2025."
+    performance_trends = "Task completion rate: 80% this week."
+    
+    # Save AI data to Salesforce
+    ai_data = {
+        'Supervisor_ID__c': supervisor_id,
+        'Project_ID__c': project_id,
+        'Daily_Checklist__c': daily_checklist,
+        'Suggested_Tips__c': suggested_tips,
+        'Risk_Alerts__c': risk_alerts,
+        'Upcoming_Milestones__c': upcoming_milestones,
+        'Performance_Trends__c': performance_trends,
+        'Generated_Date__c': datetime.datetime.now().strftime('%Y-%m-%d')
+    }
+    sf.AI_Coaching_Data__c.create(ai_data)
+
+    # Generate reports
+    report_data = {
+        'Supervisor_ID__c': supervisor_id,
+        'Project_ID__c': project_id,
+        'Report_Type__c': 'Performance',
+        'Report_Data__c': f"Performance Report: Task completion rate: 80%, Engagement score: 85%.",
+        'Download_Link__c': 'https://salesforce-site.com/reports/RPT-0001.pdf',
+        'Generated_Date__c': datetime.datetime.now().strftime('%Y-%m-%d')
     }
+    sf.Report_Download__c.create(report_data)
 
-    coaching_output = generate_coaching_output(coaching_data)
-    if coaching_output:
-        success = save_to_salesforce(coaching_output, supervisor_id, project_id)
-        if success:
-            logger.info("Coaching output generated and saved successfully.")
-            return jsonify({"status": "success", "message": "Coaching output generated and saved"}), 200
-        else:
-            logger.error("Failed to save coaching output to Salesforce.")
-            return jsonify({"status": "error", "message": "Failed to save to Salesforce"}), 500
-    else:
-        logger.error("Failed to generate coaching output.")
-        return jsonify({"status": "error", "message": "Failed to generate coaching output"}), 500
+    return jsonify({'status': 'success'})
 
-if __name__ == "__main__":
-    app.run(host="0.0.0.0", port=7860)
+if __name__ == '__main__':
+    app.run(host='0.0.0.0', port=5000)