Digital Storytelling for Data, AI, B2B & SaaS | Content in Picsellia, Yellowfin, V2 Cloud, Cognizer, Atlan, Restack, Idera | Patent for Hazen.ai | MS Data Science
How to Implement RAG With Amazon Bedrock and LangChain
In this article, we will explore Amazon Bedrock for developing a large language model (LLM) application and harnessing RAG. We will focus on setting up Amazon Bedrock and highlight the potent Amazon Titan model using LangChain. We will also look at how using pgvector on Timescale's PostgreSQL cloud platform, makes it easier to set up a vector database optimized for efficient storage and powering LLM applications with RAG.
PostgreSQL Hybrid Search Using Pgvector and Cohere
In this article, we will combine keyword and semantic search to achieve better search results. Keyword search matches words directly or to synonyms, while semantic search seeks to match the meaning behind the words in the query. We will leverage Cohere and pgvector to implement hybrid search on PostgreSQL and see how they make our work easier.
Tracking LangChain Projects with Comet
LangChain is an open-source framework that facilitates the construction of LLM-based applications. It hosts various open-source and paid models, including fine-tuning and model integration features.
It also supports easy experimentation logging with Comet using the Callback Handler. Comet automatically logs all experiment metrics and inputs and outputs received. It also compiles various experiments under a single project for easy comparison.
How To Connect Google BigQuery to Salesforce
This article explores the step-by-step process of sending data from Google BigQuery to Salesforce. It will cover the method for manual connection methods as well as the method for automated connection via Dataddo—a data integration tool.
Using Pgvector With Python
Have you ever wondered how artificial intelligence (AI) systems can understand our language? The key concept is embeddings, where words and phrases are converted into high-dimensional vectors that capture their meanings and relationships. These vectors allow computers to perform mathematical operations on language data. The challenge then becomes storing these high-dimensional vectors efficiently.
RAG: Techniques and Use Cases
The article delves deeper into the workings of RAG and how it significantly improves LLM performance. It will also demonstrate implementing RAG and discuss practical tips for beginners.
AI in Radiology: Pros & Cons, Applications, and 4 Examples
What benefits does AI hold for radiologists? Can machines be trusted to make critical healthcare decisions? Learn all that AI offers for radiology and what the future looks like.
Fine-tuning YOLOv8 Model with Comet
Let’s explore image segmentation, the limitations of segmentation models, and the process of fine-tuning YOLOv8 for image segmentation.
Mastering Locality Sensitive Hashing: A Comprehensive Tutorial and Use Cases
Mastering Locality Sensitive Hashing: A Comprehensive Tutorial and Use Cases
Understand Locality Sensitive Hashing as an effective similarity search technique. Learn practical applications, challenges, and Python implementation of LSH.
KL Divergence in Machine Learning
Kullback-Leibler (KL) divergence, or relative entropy, is a metric used to compare two data distributions. It is a concept of information theory that contrasts the information contained in two probability distributions. It has various practical use cases in data science, including assessing dataset and model drift, information retrieval for generative models, and reinforcement learning.
This article is an intro to KL divergence, its mathematics, how it benefits machine learning practitioners,...
Data Loss Prevention in the Age of Generative AI (with Lakera's Insights)
This article will discuss the importance of data loss prevention in the GenAI ecosystem, how modern solutions cater to GenAI problems, and mention some best practices for implementing a DLP infrastructure optimally.
Generating Knowledge Graphs from Unstructured Text: How Information Extraction Works
A graph data structure extracts knowledge from various sources, creates connections between entities, and forms an entwined net called the ‘Knowledge graph.’ A common source of information for knowledge graphs is text. The text to graph approach builds a representation of the knowledge and provides a birds-eye view of the entire corpus.
Key Metrics To Monitor Computer Vision Solutions
In computer vision (CV), high-quality training data does not ensure high-performing production models. The real work begins after production deployment when the model’s performance starts deteriorating due to multiple factors that we’ll discuss in this article.
Reverse ETL vs. CDP: Does Your Organization Need Both?
Operationalizing data means using the data from repositories like data warehouses to add business value - and two popular solutions enable it — reverse ETL tools and customer data platforms (CDP).
Reverse ETL is a data integration process that pulls data from data warehouses or lakes into business applications. Meanwhile, a customer data platform (CDP) is a platform that merges customer data from various sources.
As products, Reverse ETL tools and CDPs are not mutually exclusive. So, reverse ...
8 Reasons Why Docker Matter For Devs
IT
"But it was running on my machine!". Every developer has said this in his/her life while shipping his/her app to a friend or an app tester. Now you would say: “It just takes some minutes to install the dependencies and configure it to run it on another system, it’s okay, I can handle it”. But, it’s not about me or you. Tech giants with hundreds and thousands of users cannot bear a downtime of even a millisecond. Similarly, collaboration in large teams is not even possible if you cannot sim...