Update app.py

app.py

@@ -48,7 +48,6 @@ def extract_job_description(job_link):
         response = requests.get(job_link, headers=headers)
         response.raise_for_status()
         soup = BeautifulSoup(response.text, 'html.parser')
-        # You might need to adjust the selectors based on the website's structure
         job_description = soup.get_text(separator='\n')
         return job_description.strip()
     except Exception as e:
@@ -71,7 +70,7 @@ def extract_requirements(job_description):
 
     prompt = PromptTemplate.from_template(prompt_text)
     chain = prompt | llm
-    response = chain.invoke({})
+    response = chain.invoke(prompt)  # Changed from dict to string
 
     requirements = response.content.strip()
     return requirements
@@ -103,7 +102,7 @@ def generate_email(job_description, requirements, resume_text):
 
     prompt = PromptTemplate.from_template(prompt_text)
     chain = prompt | llm
-    response = chain.invoke({})
+    response = chain.invoke(prompt)  # Changed from dict to string
 
     email_text = response.content.strip()
     return email_text
@@ -139,7 +138,7 @@ def generate_cover_letter(job_description, requirements, resume_text):
 
     prompt = PromptTemplate.from_template(prompt_text)
     chain = prompt | llm
-    response = chain.invoke({})
+    response = chain.invoke(prompt)  # Changed from dict to string
 
     cover_letter = response.content.strip()
     return cover_letter
@@ -159,7 +158,7 @@ def extract_skills(text):
 
     prompt = PromptTemplate.from_template(prompt_text)
     chain = prompt | llm
-    response = chain.invoke({})
+    response = chain.invoke(prompt)  # Changed from dict to string
 
     skills = response.content.strip()
     # Clean and split the skills
@@ -184,23 +183,19 @@ def suggest_keywords(resume_text, job_description=None):
 
     prompt = PromptTemplate.from_template(prompt_text)
     chain = prompt | llm
-    response = chain.invoke({})
+    response = chain.invoke(prompt)  # Changed from dict to string
 
     keywords = response.content.strip()
     keywords_list = [keyword.strip() for keyword in re.split(',|\n', keywords) if keyword.strip()]
     return keywords_list
 
-def get_job_recommendations(resume_text, location="India"):
+def get_job_recommendations(job_title, location="India"):
     """
-    Fetches job recommendations using the JSearch API based on the user's skills.
+    Fetches salary estimates using the JSearch API based on the job title and location.
     """
-    # Extract skills from resume
-    skills = extract_skills(resume_text)
-    query = " ".join(skills) if skills else "Software Engineer"
-
     url = "https://jsearch.p.rapidapi.com/estimated-salary"
     querystring = {
-        "job_title": query,
+        "job_title": job_title,
         "location": location,
         "radius": "100"  # Adjust radius as needed
     }
@@ -226,7 +221,7 @@ def get_job_recommendations(resume_text, location="India"):
             "max_salary": max_salary
         }
     except Exception as e:
-        st.error(f"Error fetching job recommendations: {e}")
+        st.error(f"Error fetching salary data: {e}")
         return {}
 
 def create_skill_distribution_chart(skills):
@@ -256,7 +251,7 @@ def create_experience_timeline(resume_text):
 
     prompt = PromptTemplate.from_template(prompt_text)
     chain = prompt | llm
-    response = chain.invoke({})
+    response = chain.invoke(prompt)  # Changed from dict to string
 
     table_text = response.content.strip()
     # Parse the table_text to create a DataFrame
@@ -395,7 +390,7 @@ def generate_learning_path(career_goal, current_skills):
     **Learning Path:**
     """
 
-    response = llm.invoke({"input": prompt})
+    response = llm.invoke(prompt)  # Changed from dict to string
     learning_path = response.content.strip()
     return learning_path
 
@@ -658,7 +653,7 @@ def interview_preparation_module():
             prompt = f"""
             Generate a list of 10 interview questions for a {job_title} position at {company}. Include a mix of technical and behavioral questions.
             """
-            questions = llm.invoke({"input": prompt}).content.strip()
+            questions = llm.invoke(prompt).content.strip()  # Changed from dict to string
             st.subheader("Mock Interview Questions:")
             st.write(questions)
 
@@ -672,7 +667,7 @@ def interview_preparation_module():
 
                 Sample Answers:
                 """
-                sample_answers = llm.invoke({"input": sample_prompt}).content.strip()
+                sample_answers = llm.invoke(sample_prompt).content.strip()  # Changed from dict to string
                 st.subheader("Sample Answers:")
                 st.write(sample_answers)
 
@@ -715,7 +710,7 @@ def networking_opportunities_module():
             prompt = f"""
             Based on the following skills: {user_skills}, and industry: {industry}, suggest relevant LinkedIn groups, professional organizations, and industry events for networking.
             """
-            suggestions = llm.invoke({"input": prompt}).content.strip()
+            suggestions = llm.invoke(prompt).content.strip()  # Changed from dict to string
             st.subheader("Recommended Networking Groups and Events:")
             st.write(suggestions)
 
@@ -762,10 +757,11 @@ def salary_estimation_module():
                 else:
                     st.error("Salary data not available for the provided job title and location.")
 
+                # Generate negotiation tips using Groq
                 tips_prompt = f"""
                 Provide a list of 5 effective tips for negotiating a salary for a {job_title} position in {location}.
                 """
-                tips = llm.invoke({"input": tips_prompt}).content.strip()
+                tips = llm.invoke(tips_prompt).content.strip()  # Changed from dict to string
                 st.subheader("Negotiation Tips:")
                 st.write(tips)
             else:
@@ -789,6 +785,8 @@ def feedback_and_improvement_module():
             if not name or not email or not feedback:
                 st.error("Please fill in all the fields.")
             else:
+                # Here you can implement logic to store feedback, e.g., in a database or send via email
+                # For demonstration, we'll print to the console
                 print(f"Feedback from {name} ({email}): {feedback_type} - {feedback}")
                 st.success("Thank you for your feedback!")
 
@@ -817,10 +815,10 @@ def gamification_module():
             st.info(f"🔜 {achievement}")
 
     # Progress Bar
-    progress = min(num_apps / 10 * 100, 100)  # Assuming 10 applications for full progress
+    progress = min(num_apps / 10, 1.0)  # Changed from num_apps / 10 * 100 to num_apps / 10
     st.write("**Overall Progress:**")
     st.progress(progress)
-    st.write(f"{progress:.0f}% complete")
+    st.write(f"{progress * 100:.0f}% complete")  # Adjusted percentage display
 
 def resource_library_page():
     st.header("Resource Library")
@@ -916,10 +914,10 @@ def chatbot_support_page():
             st.session_state['chat_history'].append(f"You: {user_input}")
             prompt = f"""
             You are a helpful assistant for a Job Application Assistant app. Answer the user's query based on the following context:
-            
+
             {user_input}
             """
-            response = llm.invoke({"input": prompt}).content.strip()
+            response = llm.invoke(prompt).content.strip()  # Changed from dict to string
             st.session_state['chat_history'].append(f"Assistant: {response}")
 
     # Display chat history
@@ -929,6 +927,10 @@ def chatbot_support_page():
         else:
             st.markdown(f"<p style='color:green;'>{message}</p>", unsafe_allow_html=True)
 
+# -------------------------------
+# Main App with Sidebar Navigation
+# -------------------------------
+
 def main():
     st.set_page_config(page_title="Job Application Assistant", layout="wide")