Update app.py

app.py

@@ -16,9 +16,14 @@ def extract_text_from_pdf(file):
         text += page.extract_text()
     return text
 
+def parse_score(score_text):
+    try:
+        return float(score_text.strip('%').strip()) / 100
+    except ValueError:
+        return None
+
 def ats_friendly_checker(file):
     resume_text = extract_text_from_pdf(file)
-    # Implement ATS-friendly checker logic using LLM
     system_message = "Evaluate the following resume for ATS-friendliness and provide a score and feedback."
     message = resume_text
     response = client.chat_completion(
@@ -28,8 +33,9 @@ def ats_friendly_checker(file):
         top_p=0.95
     ).choices[0].message.content
     
-    score = response.split("\n")[0].split(":")[-1].strip()
+    score_text = response.split("\n")[0].split(":")[-1].strip()
     feedback = "\n".join(response.split("\n")[1:])
+    score = parse_score(score_text) * 100  # Convert to percentage
     return score, feedback
 
 def scrape_job_description(url):
@@ -41,7 +47,6 @@ def scrape_job_description(url):
 def resume_match_checker(file, job_url):
     resume_text = extract_text_from_pdf(file)
     job_description = scrape_job_description(job_url)
-    # Implement resume match checker logic using LLM
     system_message = "Compare the following resume with the job description and provide a match score."
     message = f"Resume: {resume_text}\n\nJob Description: {job_description}"
     response = client.chat_completion(
@@ -51,12 +56,12 @@ def resume_match_checker(file, job_url):
         top_p=0.95
     ).choices[0].message.content
 
-    match_score = response.split(":")[-1].strip()
+    match_score_text = response.split(":")[-1].strip()
+    match_score = parse_score(match_score_text) * 100  # Convert to percentage
     return match_score
 
 def resume_quality_score(file):
     resume_text = extract_text_from_pdf(file)
-    # Implement resume quality scoring logic using LLM
     system_message = "Evaluate the following resume for overall quality and provide a score and interpretation."
     message = resume_text
     response = client.chat_completion(
@@ -67,12 +72,12 @@ def resume_quality_score(file):
     ).choices[0].message.content
 
     score_lines = response.split("\n")
-    quality_score = score_lines[0].split(":")[-1].strip()
+    quality_score_text = score_lines[0].split(":")[-1].strip()
     interpretation = "\n".join(score_lines[1:])
+    quality_score = parse_score(quality_score_text) * 100  # Convert to percentage
     return quality_score, interpretation
 
 def text_to_overleaf(resume_text):
-    # Implement the conversion to Overleaf code using LLM
     system_message = "Convert the following resume text to Overleaf code."
     message = resume_text
     response = client.chat_completion(
@@ -120,6 +125,3 @@ with gr.Blocks() as demo:
 
 if __name__ == "__main__":
     demo.launch(share=True)
-
-
-