Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| import json | |
| import openai | |
| import os | |
| from dotenv import load_dotenv | |
| os.getenv('openai.api_key') | |
| load_dotenv() | |
| # Function to generate CV content using OpenAI with Harvard template style | |
| def generate_cv_content(user_data): | |
| MODEL = "gpt-3.5-turbo" | |
| try: | |
| response = openai.ChatCompletion.create( | |
| model=MODEL, | |
| messages=[{ | |
| "role": "system", | |
| "content": """provide assistance in creating a comprehensive CV in Harvard style format. Please follow these guidelines: | |
| 1. Start with a clear and concise personal statement summarizing my career objectives and unique qualifications. | |
| 2. List my educational background, starting with the most recent degree. Include the name of the institutions, degree titles, and the years attended. | |
| 3. Detail my professional experience, highlighting key responsibilities and achievements in each role. Organize this section in reverse chronological order. | |
| 4. Include a section for skills, making sure to emphasize those that are relevant to my career goals. | |
| 5. Add any relevant certifications, publications, or awards, with a focus on those that enhance my professional profile. | |
| 6. Ensure the CV is formatted neatly, with consistent font and spacing, and is easy to read. | |
| 7. Keep the language formal and professional throughout."""}, | |
| {"role": "user", "content": "Create a professional CV according to the following user data in Harvard template style: " + json.dumps(user_data)} | |
| ], | |
| temperature=0.7, | |
| ) | |
| # Print response in json to console | |
| return response['choices'][0]['message']['content'] | |
| except Exception as e: | |
| print("An error occurred: ", e) | |
| return None | |
| def process_data(name, email, phone, address, highest_education, skills, experience, achievements, linkedin, portfolio, applying_for): | |
| # Create a dictionary to hold the data | |
| cv_data = { | |
| "Name": name, | |
| "Email": email, | |
| "Phone": phone, | |
| "Address": address, | |
| "Highest Education": highest_education.to_dict(orient='records'), | |
| "Skills": skills, | |
| "Experience": experience.to_dict(orient='records'), | |
| "Achievements": achievements, | |
| "LinkedIn Profile": linkedin, | |
| "Portfolio Link": portfolio, | |
| "Applying for Role": applying_for | |
| } | |
| # Write the dictionary to a JSON file | |
| with open('app.json', 'w') as json_file: | |
| json.dump(cv_data, json_file, indent=4) | |
| # Return the response of generate_cv_content | |
| return generate_cv_content(cv_data) | |
| # Define the form components | |
| name = gr.components.Textbox(label="Name") | |
| email = gr.components.Textbox(label="Email") | |
| phone = gr.components.Textbox(label="Phone Number") | |
| address = gr.components.Textbox(label="Address") | |
| highest_education = gr.components.DataFrame( | |
| headers=["Qualification" , "Insititute", "Passing year", "Obtain marks", "Total marks"], | |
| datatype=["str", "str", "number", "number", "number"], | |
| col_count=(5, 'fixed'), | |
| label="Education", | |
| ) | |
| skills = gr.components.Textbox(label="Skills") | |
| experience = gr.components.Dataframe( | |
| headers=["Role", "Company", "Start Date", "End Date"], | |
| label="Work Experience", | |
| datatype=["str", "str", "date", "date"], | |
| col_count=(4, 'fixed'), # to fix the number of columns | |
| ) | |
| achievements = gr.components.Textbox(label="Key Achievements") | |
| linkedin = gr.components.Textbox(label="LinkedIn Profile") | |
| portfolio = gr.components.Textbox(label="Portfolio Link") | |
| applying_for = gr.components.Textbox(label="Role Applying For") | |
| # Create the interface | |
| # Create the interface | |
| demo = gr.Interface( | |
| fn=process_data, | |
| inputs=[name, email, phone, address, highest_education, skills, experience, achievements, linkedin, portfolio, applying_for], | |
| outputs=gr.components.Textbox(label="Generated CV") | |
| ) | |
| demo.launch() |