Let’s face it — vanilla RAG is pretty dumb. There’s no guarantee responses returned are relevant. Learn how Self-RAG can significantly help — Large language models (LLMs) are all set to revolutionize various industries. Let’s take the example of the financial sector, wherein LLMs can be used to pore over troves of documents and find trends in a fraction of time and at a fraction of the cost of analysts doing the same…

xAI has just unveiled Grok, LLM inspired by Hitchhiker’s Guide to the Galaxy! Grok’s unique feature is its ability to access real-time knowledge, a capability powered by Qdrant — open-source vector similarity search engine and vector database written in Rust. You can think of Qdrant as a specialized tool for…

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…

In the ever-evolving landscape of AI, OpenAI’s ChatGPT with vision capabilities has opened a new chapter. It’s an exciting time for developers and creators as we explore the fusion of visual understanding with conversational AI. …

In my previous article, I showed you different prompts designing techniques and also demonstrated the same with a Python example. If you have not checked that or the initial article on OpenAI api, I would suggest taking a look at both. In this article, we will learn about a few…

Running Llama-2 on your laptop using llama.cpp and Go — Writing a ChatGPT clone is pretty simple, it’s almost like the “Hello World” of LLM applications. At the heart of it is simply calling any one of the LLM APIs offered by OpenAI, Google, Anthropic and many others. But what if you don’t want to be tied to any of…

An in-depth tutorial on how to use popular models with Langchain. This can be used with private data too! — Langchain has been becoming one of the most popular NLP libraries, with around 30K starts on GitHub. I have recently tried it myself, and it is honestly amazing. If you are not familiar with Langchain, it is a library that helps developers build applications powered by large language models (LLMs)…

We’re excited to share with you the thought process and solution design of NewsGPT (Neotice) — Clickbait Buster, a Streamlit LLM hackathon-winning app powered by LlamaIndex, Streamlit, and Qdrant. In this article, we’ll define the problem we’re trying to solve and discuss how we approached it. Lastly, we offer a…

Today, we are announcing the release of Ragna, a new open source project from Quansight designed to allow organizations to explore the power of Retrieval-Augmented Generation (RAG) based AI tools. …

Retrieval-Augmented Generation (RAG) experiences significant enhancements through targeted pre-training on raw text. Currently, only ThirdAI’s NeuralDB offers push-button pre-training and/or fine-tuning capabilities for any text during insertion. RAG is currently the most dependable and proven technique for creating grounded AI-agents over any specific collection of text. To learn more about…

With The Amazing Power of Embeddings and Vector Search — Introduction Large language models like ChatGPT have revolutionized the field of natural language processing, offering impressive performance in a variety of tasks. However, they have their limitations, such as lacking knowledge on topics not covered in their training data and a tendency to hallucinate answers when asked about unfamiliar subjects.

Step-by-step guide to use chains and agents in langchain — Chains and agents are fundamental building blocks of large language model development using langchain. In the previous article, we discussed key components of langchain with a focus on models, prompts, and output parsers. In this article, we will discuss chains and agents for large…

Upgrading RAG Performance with LlamaIndex’s Guide to fine-tuning options, when to use it, how to use it correctly and the best practices. When I started this post, I wondered if I should write another formal one, which is a guide on fine-tuning your RAG on specific data. However, given the…

The definitive guide for choosing the right method for your use case — Prologue As the wave of interest in Large Language Models (LLMs) surges, many developers and organisations are busy building applications harnessing their power. However, when the pre-trained LLMs out of the box don’t perform as expected or hoped, the question on how to improve the performance of the…

And how you should tune it properly — With the rise of LLMs, the Retrieval Augmented Generation (RAG) framework also gained popularity by making it possible to build question-answering systems over data. We’ve all seen those demos of chatbots conversing with PDFs or emails. While these systems are certainly impressive, they might not be reliable in production without…

Llama 2 is a Gamechanger Llama 2 is the latest text-generation model from Meta which currently outperforms every opensource alternative. It beats out Falcon-40B (the previous best opensource foundation model) and is on par with GPT-3.5, only falling short of GPT-4 and PALM 2 (both closed source models, owned by OpenAI and Google respectively).

A comprehensive evaluation of a commercial semantic search system reveals that the ability to continuously fine-tune retrieval models with behavioral data far exceeds the benefits from any foundation models or vector databases The ongoing frenzy of Generative AI (GenAI), and, in particular, Retrieval Augmented Generation (RAG) has created a desire…

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? It’s a bit like being wowed by a black box machine, even though we don’t understand…

The War Goes Multimodal — I’ve talked about the AI war between open-source and private models many times, but the outcome seems to be the same. Open-source seems great and full of promises, but is often a whole lot of wishful thinking and impracticality. Now, things might have changed.