You are here so you probably already know about “behat” and “symfony”, 👏 But do you know about “ behat and symfony ” ❓ Soon you will 💪 Here is a simple tutorial on how to integrate behat in a symfony rest api project and perform your first functional tests. …

Summary This blog post outlines some of the core abstractions we have created in LlamaIndex around LLM-powered retrieval and reranking, which helps to create enhancements to document retrieval beyond naive top-k embedding-based lookup. LLM-powered retrieval can return more relevant documents than embedding-based retrieval, with the tradeoff being much higher latency and…

Keeping a record of when was a table last modified is very crucial and important for us. Unlike MySql, Postgres doesn’t come with inbuilt functionality for this. So to solve this problem we will be using Triggers and Procedures. Triggers allow us to define functions that execute whenever a certain type…

Introduction In the fast-evolving landscape of AI, French start-up Mistral AI has emerged as a pioneering force. Their recent development, Mistral 7B, stands as a testament to their commitment to pushing the boundaries of open-source language models. This article explore how you can swiftly deploy Mistral 7B, a 7.3 billion parameter…

Introduction In today’s world of impressive AI technology, we’re amazed by what Language Learning Models (LLMs) can do. They can talk to us almost like humans. But do we really know how they do it? …

There is more to Postgres performance than setting up indexes. — So you have set up your indexes correctly, but your API latency is still high due to the database. What else can you do? Well, you can reduce the number of database calls that you make. Read on. Queries have overhead Many things are going on when you query a database, such as…

It’s not the best tool for the job, but it might be the best for your situation — A message queue is a foundational architectural building block. Typically, it’s used for offloading workloads with high latency and needs resilience. For example, sending a receipt via email when a customer has placed an order. Many queue systems are available: RabbitMQ, Kafka, or Amazon SQS. Using a relational database as…

Introduction: In the world of Natural Language Processing (NLP), text embeddings have emerged as a powerful technique for converting textual data into numerical representations that can be easily processed by machine learning models. This article dives into the exciting realm of generating text embeddings using Azure OpenAI and explores how these…

Introduction: Imagine this scenario: You’re faced with a crucial task — finding a specific answer buried deep within a voluminous document or a sprawling wiki page. You know the information exists, but the sheer size and complexity of the content make pinpointing it an arduous task. …

Exploring OpenAI Embedding API and Semantic search What we are gonna explore? Idea is to understand what is Semantic Search and Embedding is all about and try out a sample project using Node.Js to see both in action using OpenAI API. “Semantic search” is a search technique that aims to improve the accuracy and relevance…

Designing full-text search based on Postgres with event-driven architecture — Software projects of all sizes and complexity share the challenge of building scalable search solutions. Who hasn’t seen an application that runs searches using RDBMS SQL statements? You might be wondering if this is a good solution. Well, it depends. Performing searches using SQL could be sufficient for your use…

A conceptual overview with example Python code — This is the 5th article in a series on using Large Language Models (LLMs) in practice. In this post, we will discuss how to fine-tune (FT) a pre-trained LLM. …

A Step-by-Step Guide to Discover and Harness the Power of Vector Databases — Table of Contents Intro What is so special about Vector Databases? How do we map the meaning of a sentence to a numerical representation? How does that help our LLM app? Why can’t we just give the LLM all the data we have? Hands-On Tutorial — Text to Embeddings and Distance Metrics 1…

Over the past few weeks, I have been playing around with several large language models (LLMs) and exploring their potential with all sorts of methods available on the internet, but now it’s time for me to share what I have learned so far! I was super excited to know that…

Are you ready to dive into the world of flash loan arbitrage using Aave and Hardhat? If you’re looking to leverage the power of decentralized finance (DeFi) to profit from price discrepancies, you’re in the right place. …

Introduction: Full-Text Search searches the documents that match with a query and, optionally, sort the records according to their relevance to the query. A document, such as a magazine article, email, or database table serves as the search unit in a full-text search system. The most common type of search returns…

This post is the continuation of my previous about key derivation. So we already know how to create an huge amount of wallets using a recovery seed or an extended private key, the well-known derivation method described in BIP32 and the derivation paths of BIP44. However, generating keys based on…

At Qonto, we noticed that it is powerful for business owners to grant cards for one-off expenses to their employees. That’s why we created Flash cards. With this feature, a customer can create a temporary card with a specific budget and time validity that corresponds to a specific need. The…

I only recently found out about the realm of MEVs despite having traded in the crypto space for some time already. My work mainly revolved around trading in spots and futures markets in CeFi, so I never really bothered to look into DeFi that much. But one of my clients…

An in-depth overview of plugins for JetBrains IDEs that may make your daily work easier — JetBrains IDE-s based on the IntelliJ platform are probably one of the most common IDEs in existence nowadays. Their popularity is especially visible within the JVM languages community, where IntelliJ IDEA remains the right away IDE pick for most developers. All of this is despite some new competitors showing up…