Create constants.py

constants.py

@@ -0,0 +1,51 @@
+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-T5-223M"
+
+# 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'
+])