Update resume_generation_gemini_pro.py (#2)

- Update resume_generation_gemini_pro.py (a0bde6d779ea1929b6ff69e97c08b7ab9cf56148)


Co-authored-by: Anushka Bhat <[email protected]>

resume_generation_gemini_pro.py

@@ -31,6 +31,7 @@ Original file is located at
 
 import docx2txt
 import PyPDF2
+
 def extract_text(file_path):
     if file_path.endswith(".docx"):
         # Extract text from DOCX file
@@ -68,6 +69,7 @@ from langchain_community.vectorstores.faiss import FAISS
 from docx import Document
 import google.generativeai as genai
 from datetime import datetime
+from docx.enum.text import WD_PARAGRAPH_ALIGNMENT
 
 api_key_google = os.environ.get('GOOGLE_GEMINI_KEY')
 genai.configure(api_key=api_key_google)
@@ -88,61 +90,107 @@ def read_docx(file_path):
     doc = Document(file_path)
     return "\n".join([para.text for para in doc.paragraphs])
 
-def generate_resume_text(resume_text):
-    prompt = f"""
-Given the following resume content:
-
-[Resume Start]
-{resume_text}
-[Resume End]
-
-Format this resume content with appropriate section titles. Only use the information provided and avoid placeholders like "[Your Name]". Ensure it retains the structure and details exactly as shown.
-"""
-    try:
-        response = model.generate_content(prompt)
-        print(response)
-        # Accessing the generated text content
-        return response.candidates[0].content.parts[0].text
-    except Exception as e:
-        print("Error in generating resume text:", e)
-        return None
+# def generate_resume_text(resume_text):
+#     prompt = f"""
+# Given the following resume content:
+
+# [Resume Start]
+# {resume_text}
+# [Resume End]
+
+# Format this resume content with appropriate section titles. Only use the information provided and avoid placeholders like "[Your Name]". Ensure it retains the structure and details exactly as shown.
+# """
+#     try:
+#         response = model.generate_content(prompt)
+#         print(response)
+#         # Accessing the generated text content
+#         return response.candidates[0].content.parts[0].text
+#     except Exception as e:
+#         print("Error in generating resume text:", e)
+#         return None
 
 def tailor_resume(resume_text, job_description):
     # Use the generate_resume_text function to get the formatted resume content
-    formatted_resume = generate_resume_text(resume_text)
-    print("formatted resume:",formatted_resume)
-    if formatted_resume:
+    # formatted_resume = generate_resume_text(resume_text)
+    # print("formatted resume:",resume_text)
         prompt = f"""
-Below is the candidate's original formatted resume content:
-
+Below is the candidate's original  resume content:
 [Resume Start]
-{formatted_resume}
+{resume_text}
 [Resume End]
-
 Using the candidate's resume above and the job description below, create a tailored resume.
-
 [Job Description Start]
 {job_description}
 [Job Description End]
 
+
 Please generate a resume that:
 1. Uses real data from the candidate's resume, including name, and education.
-2. Avoids placeholders like "[Your Name]" and includes actual details.
+2. Avoids placeholders like "[Your Name]" and includes actual details. This is important.
 3. In the experience section, emphasizes professional experiences and skills that are directly relevant to the job description.
 4. Keeps only a maximum of the top three accomplishments/ responsibilities for each job position held so as to make the candidate standout in the new job role
-5. Removes special characters from the section titles
-6. Only includes publications if the job description is research based
-7. Summarizes the skills and technical skills section into a brief profile
-8. Does not include courses, certification, references, skills and a technical skills sections
+5. Removes special characters from the section titles.
+6. Only includes publications if the job description is research based.
+7. Summarizes the skills and technical skills section into a brief profile.
+8. Does not include courses, certification, references, skills and a technical skills sections if they are not relevant.
+9. Only includes true information about the candidate.
+10.Provide the text in markdown format that clearly identifies the headings and subheadings.
 """
+
+
         try:
             response = model.generate_content(prompt)
+            print(response.candidates[0].content.parts[0].text)
             return response.candidates[0].content.parts[0].text
         except Exception as e:
             print("Error in tailoring resume:", e)
             return None
-    else:
-        return "Failed to generate resume text."
+
+def add_bold_and_normal_text(paragraph, text):
+    """Adds text to the paragraph, handling bold formatting."""
+    while "**" in text:
+        before, bold_part, after = text.partition("**")
+        if before:
+            paragraph.add_run(before)
+        if bold_part == "**":
+            bold_text, _, text = after.partition("**")
+            paragraph.add_run(bold_text).bold = True
+        else:
+            text = after
+    if text:
+        paragraph.add_run(text)
+        
+def convert_resume_to_word(markdown_text,output_file):
+    # Create a new Word document
+    doc = Document()
+
+    # Split the text into lines for processing
+    lines = markdown_text.splitlines()
+
+    for line in lines:
+        if line.startswith("## "):  # Main heading (Level 1)
+            paragraph = doc.add_heading(line[3:].strip(), level=1)
+            paragraph.alignment = WD_PARAGRAPH_ALIGNMENT.JUSTIFY
+        elif line.startswith("### "):  # Subheading (Level 2)
+            paragraph = doc.add_heading(line[4:].strip(), level=2)
+            paragraph.alignment = WD_PARAGRAPH_ALIGNMENT.JUSTIFY
+        elif line.startswith("- "):  # Bullet points
+            paragraph = doc.add_paragraph()
+            add_bold_and_normal_text(paragraph, line[2:].strip())
+            paragraph.alignment = WD_PARAGRAPH_ALIGNMENT.JUSTIFY
+        elif line.startswith("* "):  # Sub-bullet points or normal list items
+            paragraph = doc.add_paragraph(style="List Bullet")
+            add_bold_and_normal_text(paragraph, line[2:].strip())
+            paragraph.alignment = WD_PARAGRAPH_ALIGNMENT.JUSTIFY
+        elif line.strip():  # Normal text (ignores blank lines)
+            paragraph = doc.add_paragraph()
+            add_bold_and_normal_text(paragraph, line.strip())
+            paragraph.alignment = WD_PARAGRAPH_ALIGNMENT.JUSTIFY
+
+    # Save the Word document
+
+    doc.save(output_file)
+    print(f"Markdown converted and saved as {output_file}")
 
 #Entry function for the model
 def generate_gemini(current_resume,job_description):
@@ -154,19 +202,13 @@ def generate_gemini(current_resume,job_description):
 
     # Tailor resume based on job description
     tailored_resume = tailor_resume(resume_text, job_description)
-    tailored_resume = tailored_resume.replace('*', '').replace('#', '')
-    st.write("**Tailored Resume:**")
-    st.write(tailored_resume)
-    print(tailored_resume)
-
-        # Save the tailored resume to a .docx file
-    if tailored_resume:
-        file_path = f"Tailored_Resume_{datetime.now().strftime('%Y%m%d_%H%M%S')}.docx"
-        save_resume_to_docx(tailored_resume, file_path)
-        # st.success(f"Download tailored resume")
-        # st.success(f"Tailored resume saved to {file_path}")        
-
-    return tailored_resume, file_path
+    output_file = f"Tailored_Resume_{datetime.now().strftime('%Y%m%d_%H%M%S')}.docx"
+    convert_resume_to_word(tailored_resume,output_file)
+
+    st.success(f"Tailored resume saved to {output_file}")
+
+    return tailored_resume, output_file        
+
 
 # Main function for Streamlit app
 # def Gemini_pro_main(current_resume,job_description):