Choere AI Model with Multiple prompts

[abdelkareemkobo]

Hey all, i have been working with cohere AI model and there is the summary of what i reached:

---

There is multiple models we can use :
Command Vs Base
I found that the base is week than the command and the answer are very short and he is not created as the Command

---

I have tried Choere AI with multiple solutions:

1. Give it both the extracted keywords from the resume and job description -> The result was bad
2. Give it the cleaned text from the resume and extracted keywords and extracted keyterms -> The result was he show the resume with some suggestions in a general way but didn't tell you what to change from resume
   3.Give it only the keyword description and a good prompt and he gives me some pharses that i should add in to my resume and the result is normal

---

only the keyword description from the job description

prompt = f"""Suggest keywords or phrases from the following {selected_jd["clean_data"]} that should be added into a resume to increase the cosine similiarty and be able to pass the ATS resume Checking process and use both long-form and acronym vesion of keywords
"""
Here is an example of using only the key_word description from the job descirption Here is what to do to increase the similiarty of your resume Here are some keywords and phrases that you may want to consider including in the job description for a Java Developer with 3 years of experience:

1. Java development
2. Java EE application development
3. Software development lifecycle
4. Object-oriented analysis and design
5. Design patterns
6. Database management
7. SQL
8. ORM technologies
9. Web application development
10. Popular web frameworks
11. Test-driven development

Here are some additional keywords and phrases that you may want to consider including to increase the cosine similarity and improve the chances of the resume passing the ATS resume checking process:

1. BS/MS degree in Computer Science, Engineering, or a related subject
2. Proven hands-on software development experience
3. Java/Java EE application management
4. Software analysis
5. Programming
6. Testing
7. Debugging
8. Release management
9. Continuous improvement
10. Technical solutions

It's also important to include both the long-form and acronym versions of keywords and phrases, as some ATS systems may not recognize the acronym version. In addition, including a brief explanation of the candidate's relevant experience can help to further demonstrate their qualifications for the role

Extracted keywords from job description only and the clean data from resume file

prompt = f"""Suggest keywords or phrases from the following {selected_jd["extracted_keywords"]} that should be added into my resume {selected_file["clean_data"]} to increase the cosine similiarty and be able to pass the ATS resume Checking process and use both long-form and acronym vesion of keywords
"""

• MLOps: This term refers to the practice of deploying and maintaining machine learning models in production environments. It involves the development of tools and processes for model versioning, deployment, monitoring, and scaling.
• Cloud computing: Experience with cloud platforms such as Amazon Web Services (AWS), Google Cloud Platform (GCP), or Microsoft Azure can be valuable for machine learning engineers, as it allows for the deployment and scaling of machine learning models in the cloud.
• Data pipelines: Experience with building data pipelines for machine learning models, including data collection, preprocessing, and feature engineering, can be valuable for machine learning engineers.
• Model monitoring and maintenance: Experience with monitoring and maintaining machine learning models in production environments, including the development of tools and processes for model performance monitoring, anomaly detection, and retraining, can be valuable for machine learning engineers.
• Automation: Experience with automating machine learning model development, training, and deployment processes can be valuable for machine learning engineers.
• Natural Language Processing (NLP): Experience with NLP tasks such as text classification, sentiment analysis, and language translation can be valuable for machine learning engineers.
• Deep learning: Experience with deep learning models and frameworks such as TensorFlow, PyTorch, and Keras can be valuable for machine learning engineers.
• Reinforcement learning: Experience with reinforcement learning algorithms and models can be valuable for machine learning engineers.
• Computer Vision: Experience with computer vision tasks such as image classification, object detection, and image segmentation can be valuable for machine learning engineers.
• Time series analysis: Experience with time series analysis techniques and models can be valuable for machine learning engineers.
• Signal processing: Experience with signal processing techniques and models can be valuable for machine learning engineers.
• Data science: Experience with data science tasks such as data analysis, data visualization, and machine learning model development can be valuable for machine learning engineers.
• Software development: Experience with software development tools and processes, including version control systems, testing frameworks, and deployment tools, can be valuable for machine learning engineers.
• Communication and collaboration: Experience with effectively communicating and collaborating with stakeholders, including data scientists, software developers, and business analysts, can be valuable for machine learning engineers.

---

I have tried to give the model the clean data from both the resume and job_description and asked him to the update the resume, but the result wasn't the wanted and bad! he seems gives me the resume without any real updates and he seems to start get hallucinations

[srbhr]

Thanks @abdelkareemkobo for doing research into Co:here.

[abdelkareemkobo]

you're welcome @srbhr it is just the beginning 😄