constants.py

from streamlit import secrets

VESRION = "1.0.1"

API_URL_summary = "https://api-inference.huggingface.co/models/facebook/bart-large-cnn"
API_URL_name = "https://api-inference.huggingface.co/models/dbmdz/bert-large-cased-finetuned-conll03-english"
API_URL_qna = "https://api-inference.huggingface.co/models/deepset/tinyroberta-squad2"
API_TOKEN = secrets["API_TOKEN"]

HEADERS = {"Authorization": f"Bearer {API_TOKEN}"}

SENTENCE_TRANSFORMER_MODEL = "paraphrase-distilroberta-base-v1"
LLM_REPO_ID = "MBZUAI/LaMini-Flan-T5-783M"

# A custom exception-like class to show a streamlit-styled error
class StreamlitException:
    def __init__(self, message):
        self.message = message

# A set of technical skills
TECH_SKILLS = set([
    'Python', 'R', 'SQL', 'Java', 'MATLAB', 'Mathematica', 'C#', 'C++', 'Javascript', 
    'NumPy', 'SciPy', 'Pandas', 'Theano', 'Caffe', 'SciKit-learn', 'Matplotlib', 'Seaborn', 
    'Plotly', 'TensorFlow', 'Keras', 'NLTK', 'PyTorch', 'Gensim', 'Urllib', 'BeautifulSoup4', 
    'PySpark', 'PyMySQL', 'SQAlchemy', 'MongoDB', 'sqlite3', 'Flask', 'Deeplearning4j', 'EJML', 
    'dplyr', 'ggplot2', 'reshape2', 'tidyr', 'purrr', 'readr', 'Apache', 'Spark', 'Git', 'GitHub', 
    'GitLab', 'Bitbucket', 'SVN', 'Mercurial', 'Trello', 'PyCharm', 'IntelliJ', 'Visual Studio', 
    'Sublime', 'JIRA', 'TFS', 'Linux', 'Unix', 'Hadoop HDFS', 'Google Cloud Platform', 'MS Azure Cloud', 
    'SQL', 'NoSQL', 'Data Warehouse', 'Data Lake', 'SWL', 'HiveQL', 'AWS', 'RedShift', 'Kinesis', 'EMR', 
    'EC2', 'Lambda', 'Data Analysis', 'Data Mining', 'Data Visualization', 'Statistical Analysis', 
    'Multivariate Analysis', 'Stochastic Optimization', 'Linear Regression', 'ANOVA', 
    'Hypothesis Testing', 'Forecasting', 'ARIMA', 'Sentiment Analysis', 'Predictive Analysis', 
    'Pattern Recognition', 'Classification', 'Behavioural Modelling', 'Supervised Machine Learning Algorithms', 
    'Linear Regression', 'Logistic Regression', 'Support Vector Machines', 'Decision Trees and Random Forests', 
    'Naïve Bayes Classifiers', 'K Nearest Neighbors', 'Unsupervised Machine Learning Algorithms', 'K Means Clustering', 
    'Gaussian Mixtures', 'Hidden Markov Models', 'Auto Encoders', 'Imbalanced Learning', 'SMOTE', 'AdaSyn', 'NearMiss', 
    'Deep Learning Artificial Neural Networks', 'Machine Perception', 'Document Tokenization', 'Token Embedding', 
    'Word Models', 'Word2Vec', 'Doc2Vec', 'FastText', 'Bag of Words', 'TF/IDF', 'Bert', 'Elmo', 'LDA', 
    'Machine Language Comprehension', 'Sentiment Analysis', 'Predictive Maintenance', 'Demand Forecasting', 
    'Fraud Detection', 'Client Segmentation', 'Marketing Analysis', 'AWS', 'MS Azure', 'Google Cloud Platform', 
    'CI/CD', 'IaaC', 'big data', 'h2o', 'gbm', 'pytorch', 'caffe', 'opencv', 'deeplearning4j', 'neo4j', 
    'decision-trees', 'decision trees', 'programming', 'jira', 'excel', 'sas', 'vba', 'random forest', 
    'xgboost', 'xgb', 'regression', 'logistic regression', 'linear regression', 'clustering', 'pca', 
    'hypothesis testing', 'ab testing', 'ab-testing', 'bigquery', 'vertexai','amazon web services', 
    'google cloud services', 'node.js', 'linux', 'unix', 'hive', 'spark', 'pyspark', 'java', 'c++', 
    'python', 'r', 'database', 'algorithm', 'data structure', 'ai', 'ml', 'machine learning', 'python', 
    'keras', 'tensorflow', 'tf', 'sql', 'aws', 'azure', 'gcp', 'cloud', 'deep learning', 'neural network', 
    'computer vision', 'optimization', 'statistics', 'time series', 'time series', 'time series forecasting', 
    'time series forecasting', 'modelling', 'forecasting', 'etl', 'mlops', 'natural language processing', 
    'computer vision', 'knn', 'image processing', 'nlp'
])