Top 9 Vector Databases You Should Know

Introduction In recent times, Vector Databases have gained quite a popularity, especially after the arrival of the RAG architecture to work efficiently with LLMs. The concept of vector databases is not new, however, as they were already used in recommendation engines, personalization, Ad targeting, etc. Vector databases are used to save, index, and retrieve complex data like text, images, or other unstructured formats in vectors. The vectors are mathematical representations of data in a high-dimensional space enabling high-quality similarity and […]

Read more

Detailed Guide to LangChain Text Splitters with Examples

What are LangChain Text Splitters In recent times LangChain has evolved into a go-to framework for creating complex pipelines for working with LLMs. One of its important utility is the langchain_text_splitters package which contains various modules to split large textual data into more manageable chunks. Usually, LangChain Text Splitters are used in RAG architecture to chunk a large document and convert these chunks into embeddings to be stored in Vector DB. For LLMs with limited context-size windows, it is quite […]

Read more

Transformers vs RNN – A Detailed Comparison

Introduction Recurrent Neural Networks (RNN) and Transformers have emerged as two popular deep learning models, especially in the field of Natural Language Processing (NLP). Although research on RNNs goes back to the 1980s the Transformer research paper first came out in 2017 only and its models have become highly successful in recent times. In this post, we will compare Transformers vs RNN and understand their similarities and differences point-wise. Recurrent Neural Networks (RNN) Recurrent Neural Networks (RNN) are a type […]

Read more

3 Ways of Image Subtraction in Python with NumPy, OpenCV and Pillow Libraries

Introduction In this post, we will see various ways of doing image subtraction in Python by using NumPy, OpenCV, and Pillow libraries. The subtraction of images may sound a bit strange to beginners but images consist of numeric pixels hence we can perform pixel-wise subtraction between two images. Subtraction of Images When one image is subtracted from another it does pixel-wise subtraction where the pixel of the 2nd image is subtracted from the 1st image resulting in a new 3rd […]

Read more

3 Ways of Image Addition in Python with NumPy, OpenCV and Pillow Libraries

Introduction Addition of images might sound weird but people forget that an image is essentially a collection of numeric pixels. So we can do pixel-wise addition of the two images resulting in a new image. In this article, we will see multiple ways we can perform the addition of images in Python by using NumPy, OpenCV, and PIL libraries. Addition of Images When we add two images it does pixel-wise addition where each pixel in one image is added to […]

Read more

4 Ways to Crop Image in Python using NumPy, Pillow and OpenCV

Introduction In image processing & computer vision, cropping of images is a common task where we keep a specific region of interest from an image and discard the rest. In this article, we will see various ways you can crop an image in Python by using libraries like OpenCV, Pillow, and NumPy. Input Image In this tutorial, we will use the below image in all the examples of cropping image with Python.   Visualizing the Cropping Area on Image Before […]

Read more

Affine Transformation in OpenCV with cv2.warpAffine()

Introduction In this article, we will learn how to perform the affine transformation on images using the OpenCV cv2.warpAffine() function. First, we will understand what is affine transformation, and its uses. Then we shall cover a few examples of warpAffine() by performing transformations such as rotation, translation, scaling, and shearing. What is Affine Transformation In image processing the affine transformation is a geometric transformation that preserves collinearity (the property of points lying on a straight line) and ratios of distances […]

Read more

GGUF vs GGML : Understanding the Differences

Introduction The year 2023 was a landmark year for the Large Language Models (LLMS) ecosystem which saw a large number of proprietary models and open-source models becoming accessible to the public at large. It also saw LLMs getting published for CPUs in GGML format thus making LLMs accessible to people who lacked powerful GPUs. Soon in August 2023, another format called GGUF was released for CPU-based LLMs. With such rapid changes in the ecosystem many people especially beginners are confused […]

Read more

3 Examples of Monte Carlo Simulation in Python

Introduction In this post, we will understand what is Monte Carlo Simulation, what are its typical steps along with benefits and limitations. We will also take a look at its real-world application followed by a few examples of Monte Carlo simulation in Python along with visualization for better clarity. What is Monte Carlo Simulation Monte Carlo simulation is a computational technique to approximate the behavior or output of a complex system or problem by repeated random sampling. This method relies […]

Read more

Future of OTT: Exploring AI’s Impact on Streaming

Video streaming platforms are embracing artificial intelligence (AI) tools to enhance content recommendations, tailoring the viewing experience for individual users and simplifying content discovery. Industry experts anticipate AI’s expansion into scripting, dubbing, and even allowing users to participate directly in content streaming. Manish Kalra, Chief Business Officer at ZEE5 India, highlights the active use of AI in content recommendation, personalization, cross-device compatibility, and audience analytics across over-the-top (OTT) platforms. AI’s impact extends to social media marketing through creative content and […]

Read more
1 2 3