DataChild

• Data
• Programming
• Machine learning

/python - articles

• Searching images based on text using CLIP model

  What is CLIP and common image/text vector space? How to install and run CLIP? How to compare image and text embeddings to find corresponding images based on text query?

  Published half a year ago in #machinelearning about #clip, #embeddings, #vector search and #python
• What is a text embedding and how to use it for text search

  What is a text embedding? How to get embeddings from a lot of text data? How to search within text data using text embeddings? What is the difference between vector-based text search and full-text search?

  Published half a year ago in #machinelearning about #embeddings, #vector search, #python and #openai
• Image similarity search based on embeddings and sentence_transformers

  How to get image embeddings using sentence_transformers models. How to store vectors in the database. How to find similar images to the given query image.

  Published half a year ago in #machinelearning about #embeddings, #sentence_transformers, #clip, #vector search, #python and #clickhouse
• Efficient vector similarity search with Annoy library based on ANN

  What is vector search? Performance issues with vector search on large amounts of data. ANN strategy to get fast vector search at scale.

  Published half a year ago in #data about #vector search, #ann, #annoy and #python
• Formatting unstructured data using OpenAI API and Python

  How to use OpenAI to format unstructured text data, e.g. CSV. Setting additional formatting requirements to format specific values in the resulting CSV.

  Published 2 years ago in #machinelearning about #python and #openai
• Quick start OpenAI API example using Python

  How to start using OpenAI API with Python. A simple example of a Python script that generates data based on the OpenAI language model.

  Published 2 years ago in #machinelearning about #python and #openai
• What is a function derivative and how to optimize functions

  The article explains what a function derivative is on a very basic level. Starting from the concept of the function, we move along function changes and finally, look at a Python example of optimizing a function based on its derivative.

  Published 2 years ago in #machinelearning about #math, #derivative and #python
• Creating a bigram language model for text generation with Python

  Understanding bigram language models, which are statistical models that predict the likelihood of a word given its preceding word. Includes an example of a simple bigram language model in Python.

  Published 2 years ago in #machinelearning about #nlp, #language-models and #python
• Using csvkit to format, clean, and fix CSV files

  Formatting CSV, TSV, and other files, converting CSV delimiters, converting CSV quoting symbols, fixing invalid CSV files, working with compressed CSV files

  Published 2 years ago in #programming about #python and #csv

Denys Golotiuk · golotyuk@gmail.com · my github