Update app.py

app.py

@@ -12,6 +12,10 @@ OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
 PROXYCURL_API_KEY = os.getenv("PROXYCURL_API_KEY")
 FIRECRAWL_API_KEY = os.getenv("FIRECRAWL_API_KEY")
 
+# Function to sanitize data by ensuring it's safe and clean for use
+def sanitize_data(data, default_value=""):
+    return data.strip() if isinstance(data, str) and data.strip() else default_value
+
 # Function to fetch LinkedIn data using the Proxycurl API
 def fetch_linkedin_data(linkedin_url):
     api_key = os.getenv("PROXYCURL_API_KEY")
@@ -19,16 +23,20 @@ def fetch_linkedin_data(linkedin_url):
     api_endpoint = 'https://nubela.co/proxycurl/api/v2/linkedin'
     
     logging.info("Fetching LinkedIn data...")
-    response = requests.get(api_endpoint,
-                            params={'url': linkedin_url},
-                            headers=headers,
-                            timeout=10)
-    if response.status_code == 200:
-        logging.info("LinkedIn data fetched successfully.")
-        return response.json()
-    else:
-        logging.error(f"Error fetching LinkedIn data: {response.text}")
-        return {"error": f"Error fetching LinkedIn data: {response.text}"}
+    try:
+        response = requests.get(api_endpoint,
+                                params={'url': linkedin_url},
+                                headers=headers,
+                                timeout=10)
+        if response.status_code == 200:
+            logging.info("LinkedIn data fetched successfully.")
+            return response.json()
+        else:
+            logging.error(f"Error fetching LinkedIn data: {response.text}")
+            return {"error": f"Error fetching LinkedIn data: {response.text}"}
+    except Exception as e:
+        logging.error(f"Exception during LinkedIn data fetch: {e}")
+        return {"error": f"Exception during LinkedIn data fetch: {e}"}
 
 # Function to fetch company information using Firecrawl API
 def fetch_company_info(company_url):
@@ -48,53 +56,60 @@ def fetch_company_info(company_url):
     }
     
     logging.info("Fetching company information...")
-    response = requests.post(api_endpoint, json=data, headers=headers, timeout=15)
-    if response.status_code == 200:
-        logging.info("Company information fetched successfully.")
-        return response.json()
-    else:
-        logging.error(f"Error fetching company information: {response.text}")
-        return {"error": f"Error fetching company information: {response.text}"}
+    try:
+        response = requests.post(api_endpoint, json=data, headers=headers, timeout=15)
+        if response.status_code == 200:
+            logging.info("Company information fetched successfully.")
+            return response.json()
+        else:
+            logging.error(f"Error fetching company information: {response.text}")
+            return {"error": f"Error fetching company information: {response.text}"}
+    except Exception as e:
+        logging.error(f"Exception during company info fetch: {e}")
+        return {"error": f"Exception during company info fetch: {e}"}
 
 # Function to structure the email dynamically based on inputs and fetched data
 def structure_email(user_data, linkedin_info, company_info):
-    # Fetch relevant information from the LinkedIn profile and company information
-    linkedin_role = linkedin_info.get('current_role', 'a professional')
-    linkedin_skills = linkedin_info.get('skills', 'various relevant skills')
-    company_mission = company_info.get('mission', 'your mission')
-    company_goal = company_info.get('goal', 'achieving excellence in the field')
-
-    # Construct the dynamic email content based on the provided and fetched information
-    email_content = (
-        f"Dear Hiring Manager,\n\n"
-        f"I am writing to express my enthusiasm for the {user_data['role']} position at {user_data['company_url']}. "
-        f"The mission of {company_mission} resonates deeply with me, as my professional experience aligns closely with this vision.\n\n"
-        f"Having worked as {linkedin_role}, I have developed skills in {linkedin_skills}. These skills match the needs of your organization, "
-        f"and I am confident in my ability to contribute effectively to {company_goal}.\n\n"
-        f"I am eager to bring my expertise in {linkedin_skills} to your team, focusing on achieving key objectives and supporting your projects. "
-        f"My goal is to make a meaningful impact and collaborate with like-minded professionals committed to excellence.\n\n"
-        f"I would appreciate the opportunity to discuss how my background and skills align with the needs of {user_data['company_url']}. "
-        f"Please find my resume attached for a more detailed overview of my qualifications.\n\n"
-        f"Thank you for your time and consideration. I look forward to the possibility of contributing to your team.\n\n"
-        f"Best regards,\n"
-        f"{user_data['name']}"
-    )
-    return email_content
+    # Sanitize and extract the required information
+    linkedin_role = sanitize_data(linkedin_info.get('current_role', user_data['role']))
+    linkedin_skills = sanitize_data(linkedin_info.get('skills', 'relevant skills'))
+    linkedin_industry = sanitize_data(linkedin_info.get('industry', 'the industry'))
+    company_name = sanitize_data(user_data['company_url'] or company_info.get('company_name', 'the company'))
+    company_mission = sanitize_data(company_info.get('mission', f"{company_name}'s mission"))
+    company_goal = sanitize_data(company_info.get('goal', 'achieving excellence'))
+
+    # Construct the email dynamically based on the sanitized and available data
+    email_body = f"Dear Hiring Manager,\n\n"
+
+    # Introduction and relevance
+    email_body += f"I am writing to express my interest in the {sanitize_data(user_data['role'])} position at {company_name}. "
+    if company_mission:
+        email_body += f"{company_mission} strongly aligns with my passion and experience in {linkedin_industry}. "
+    
+    # Skills and experience section
+    if linkedin_role:
+        email_body += f"As a {linkedin_role}, I have honed my skills in {linkedin_skills}. These experiences make me confident that I can contribute effectively to your team. "
+    else:
+        email_body += f"My experience in {linkedin_skills} equips me with the skills necessary to excel in this role. "
+    
+    # Contribution and impact section
+    if company_goal:
+        email_body += f"I am excited about the opportunity to bring my expertise to {company_name} and support your team in achieving {company_goal}. "
+
+    # Call to action
+    email_body += f"I would welcome the chance to discuss how my background and skills align with the needs of your organization. "
+    email_body += "Thank you for your time and consideration. I look forward to the possibility of contributing to your team.\n\n"
+    email_body += f"Best regards,\n{sanitize_data(user_data['name'])}"
+    
+    return email_body
 
-# Function to validate the generated email for professional tone and completeness
+# Function to validate the generated email for completeness and professionalism
 def validate_email(email_content):
     logging.info("Validating email content...")
     logging.info(f"Email Content for Validation: {email_content}")
 
-    # Check if the generated email contains essential elements
-    if ("enthusiasm" in email_content and
-        "skills" in email_content and
-        "contribute" in email_content):
-        logging.info("Email content validation passed.")
-        return True
-    else:
-        logging.info("Email content validation failed.")
-        return False
+    # Check if essential elements exist in the email content
+    return all(keyword in email_content for keyword in ["interest", "skills", "experience", "contribute", "Best regards"])
 
 # Function to generate email content using Nvidia Nemotron LLM (non-streaming for simplicity)
 def generate_email_content(api_key, prompt):
@@ -113,13 +128,12 @@ def generate_email_content(api_key, prompt):
             temperature=0.5,
             top_p=1,
             max_tokens=1024,
-            stream=False  # Disable streaming for simplicity
+            stream=False
         )
         
         if hasattr(response, 'choices') and len(response.choices) > 0:
             email_content = response.choices[0].message.content
             logging.info("Email content generated successfully.")
-            logging.info(f"Generated Email Content: {email_content}")
             return email_content
         else:
             logging.error("Error: No choices found in the response.")