VirtualAssistant Kit
by rn8154 Updated: Oct 2, 2021
Solution Kit
This starter kit has all the required kits/libraries for creating your own virtual assistant. It contains various kits for getting started such as follows: 1. Development environment 2. Exploratory data analysis 3. Machine learning 4. Text Mining 5. NLP - sentence embedding, cosine similarities
Development Environment
Jupyter notebook and vscode are used for development and are known as IDEs. To write any code it is necessary to have an development environment setup. Jupyter notebook is web based interactive environment.
notebookby jupyter
Jupyter Interactive Notebook
notebookby jupyter
Jupyter Notebook
9901
Version:v7.0.0a18
License: Permissive (BSD-3-Clause)
Exploratory data analysis
Libraries that deal with arrays and help in data analysis for data engineering. Arrays can be manipulated meaning the dimensions, reshaping, etc.
pandasby pandas-dev
Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more
pandasby pandas-dev
Python
37439
Version:v2.0.0rc1
License: Permissive (BSD-3-Clause)
numpyby numpy
The fundamental package for scientific computing with Python.
numpyby numpy
Python
23036
Version:v1.24.2
License: Permissive (BSD-3-Clause)
Machine Learning
Basic machine learning libraries that creates a model and also trains the model using the dataset. Also is used for prediction purposes to test whether model trained is accurate or not.
faissby facebookresearch
A library for efficient similarity search and clustering of dense vectors.
faissby facebookresearch
C++
20015
Version:v1.7.3
License: Permissive (MIT)
scikit-learnby scikit-learn
scikit-learn: machine learning in Python
scikit-learnby scikit-learn
Python
53572
Version:1.2.2
License: Permissive (BSD-3-Clause)
Exploratory data analysis
Libraries which are used for analysis and processing of unprocessed natural language.
spaCyby explosion
💫 Industrial-strength Natural Language Processing (NLP) in Python
spaCyby explosion
Python
25639
Version:v3.5.1
License: Permissive (MIT)
NLP
Libraries in this group are used to clean the dataset by removing all punctuations, digits, symbols, etc. After data preprocessing, the user query is compared with dataset queries via cosine similarity algorithm which will give us the record in dataset which is similar to user query.
sentence-transformersby UKPLab
Multilingual Sentence & Image Embeddings with BERT
sentence-transformersby UKPLab
Python
9823
Version:v2.2.2
License: Permissive (Apache-2.0)
bert-cosine-simby beekbin
Fine-tune BERT to generate sentence embedding for cosine similarity
bert-cosine-simby beekbin
Python
61
Version:Current
License: No License