Update app.py

app.py

@@ -6,6 +6,7 @@ import os
 proxycurl_api_key = os.getenv("PROXYCURL_API_KEY")  # Proxycurl API key
 groq_api_key = os.getenv("GROQ_CLOUD_API_KEY")  # Groq Cloud API key
 firecrawl_api_key = os.getenv("FIRECRAWL_API_KEY")  # Firecrawl API key
+serp_api_key = os.getenv("SERP_API_KEY")  # SERP API key for fetching company URL
 
 class AutonomousEmailAgent:
     def __init__(self, linkedin_url, company_name, role, word_limit, user_name, email, phone, linkedin):
@@ -22,6 +23,7 @@ class AutonomousEmailAgent:
         self.experiences = []
         self.company_info = None
         self.role_description = None
+        self.company_url = None  # Add company URL for scraping
 
     # Reason and Act via LLM: Let the LLM control reasoning and actions dynamically
     def autonomous_reasoning(self):
@@ -78,8 +80,10 @@ class AutonomousEmailAgent:
         instruction = reasoning_output.lower().strip()
 
         if "scrape" in instruction:
-            # Action: Scrape the company's website for more information
-            self.fetch_company_info_with_firecrawl()
+            # Action: Fetch company URL via SERP API before scraping
+            self.fetch_company_url()
+            if self.company_url:
+                self.fetch_company_info_with_firecrawl(self.company_url)
             # Reflect again by invoking the LLM to reassess
             return self.autonomous_reasoning()
 
@@ -101,6 +105,24 @@ class AutonomousEmailAgent:
             print("Error: Unrecognized instruction from LLM. Proceeding with available data.")
             return self.generate_email()
 
+    # Fetch company URL using SERP API
+    def fetch_company_url(self):
+        print(f"Fetching company URL for {self.company_name} using SERP API...")
+        serp_url = f"https://serpapi.com/search.json?q={self.company_name}&api_key={serp_api_key}&num=1"
+        response = requests.get(serp_url)
+        
+        if response.status_code == 200:
+            serp_data = response.json()
+            if 'organic_results' in serp_data and len(serp_data['organic_results']) > 0:
+                self.company_url = serp_data['organic_results'][0]['link']
+                print(f"Found company URL: {self.company_url}")
+            else:
+                print("No URL found for the company via SERP API.")
+                self.company_url = None
+        else:
+            print(f"Error fetching company URL: {response.status_code}")
+            self.company_url = None
+
     # Action: Fetch LinkedIn data via Proxycurl
     def fetch_linkedin_data(self):
         if not self.linkedin_url:
@@ -124,51 +146,47 @@ class AutonomousEmailAgent:
                 self.skills = ["Adaptable", "Hardworking"]
                 self.experiences = ["Worked across various industries"]
 
-    # Action: Fetch company information via Firecrawl API
-    def fetch_company_info_with_firecrawl(self):
-        if not self.company_name:
-            print("Action: No company name provided, using default company info.")
-            self.company_info = "A leading company in its field."
+    # Action: Fetch company information via Firecrawl API using company URL
+    def fetch_company_info_with_firecrawl(self, company_url):
+        print(f"Fetching company info for {company_url} using Firecrawl.")
+        headers = {"Authorization": f"Bearer {firecrawl_api_key}"}
+        firecrawl_url = "https://api.firecrawl.dev/v1/scrape"
+        data = {
+            "url": company_url,
+            "patterns": ["description", "about", "careers", "company overview"]
+        }
+        
+        response = requests.post(firecrawl_url, json=data, headers=headers)
+        if response.status_code == 200:
+            firecrawl_data = response.json()
+            self.company_info = firecrawl_data.get("description", "No detailed company info available.")
+            print(f"Company info fetched: {self.company_info}")
         else:
-            print(f"Action: Fetching company info for {self.company_name} using Firecrawl.")
-            headers = {"Authorization": f"Bearer {firecrawl_api_key}"}
-            firecrawl_url = "https://api.firecrawl.dev/v1/scrape"
-            data = {
-                "url": f"https://{self.company_name}.com",
-                "patterns": ["description", "about", "careers", "company overview"]
-            }
-            
-            response = requests.post(firecrawl_url, json=data, headers=headers)
-            if response.status_code == 200:
-                firecrawl_data = response.json()
-                self.company_info = firecrawl_data.get("description", "No detailed company info available.")
-                print(f"Company info fetched: {self.company_info}")
-            else:
-                print(f"Error: Unable to fetch company info via Firecrawl. Using default info.")
-                self.company_info = "A leading company in its field."
+            print(f"Error: Unable to fetch company info via Firecrawl. Using default info.")
+            self.company_info = "A leading company in its field."
 
-    # Final Action: Generate the email using Groq Cloud LLM
+    # Final Action: Generate the email using Groq Cloud LLM with "Start with Why" framework
     def generate_email(self):
         print("Action: Generating the email with the gathered information.")
-        
+
         linkedin_text = f"Please find my LinkedIn profile at {self.linkedin}" if self.linkedin else ""
 
-        # Dynamic LLM prompt
+        # Updated prompt to reflect Simon Sinek's "Start with Why" approach
         prompt = f"""
-        Write a professional email applying for the {self.role} position at {self.company_name}.
-        
-        Use the following information:
+        Write a professional job application email applying for the {self.role} position at {self.company_name}.
+
+        The email should follow the "Start with Why" approach:
+        1. **Why**: Begin with the candidate’s **purpose** or **belief**—why they are passionate about this role and the company. What motivates them to apply for this role? Connect their personal mission to the company's values, mission, or goals.
+        2. **How**: Explain how the candidate’s skills, experience, and approach align with both their "why" and the company’s mission. This should show how they are uniquely qualified to contribute to the company’s success.
+        3. **What**: Provide concrete examples of the candidate’s past achievements that support their qualifications for this role. These examples should demonstrate the candidate’s ability to succeed based on their skills and experience.
+        4. **Call to Action**: End with a polite request for a meeting or further discussion to explore how the candidate can contribute to the company's success.
+
+        Use the following information to craft the email:
         - The candidate’s LinkedIn bio: {self.bio}.
         - The candidate’s most relevant skills: {', '.join(self.skills)}.
         - The candidate’s professional experience: {', '.join([exp['title'] for exp in self.experiences])}.
-        
-        Please research the company's public information. If no company-specific information is available, use general knowledge about the company's industry.
-        
-        Tailor the email dynamically to the role of **{self.role}** at {self.company_name}, aligning the candidate's skills and experiences with the expected responsibilities of the role and the company’s operations.
-
-        {linkedin_text}
-
-        Remove references to job posting sources unless provided. Use the LinkedIn URL for the candidate and do not include placeholders.
+        - Company information: {self.company_info}.
+        - Role description: {self.role_description}.
 
         End the email with this signature:
         Best regards,
@@ -179,18 +197,18 @@ class AutonomousEmailAgent:
         
         The email should not exceed {self.word_limit} words.
         """
-        
+
         url = "https://api.groq.com/openai/v1/chat/completions"
         headers = {
             "Authorization": f"Bearer {groq_api_key}",
             "Content-Type": "application/json",
         }
-        
+
         data = {
             "messages": [{"role": "user", "content": prompt}],
             "model": "llama3-8b-8192"
         }
-        
+
         response = requests.post(url, headers=headers, json=data)
         if response.status_code == 200:
             return response.json()["choices"][0]["message"]["content"].strip()