Some LLMs (Large Language Models) can act as useful programming assistants when provided with a project’s source code, but experimenting with this can get a little tricky if the chatbot has n…

Combining retrieval-augmented generation (RAG) with SQL makes it easier to apply LLMs to wring more insights from your company data.

Pretty much every company I know is looking for a way to benefit from Large Language Models. Even if their executives don’t see much applicability, their investors likely do, so they’re staring at the blank page nervously trying to come up with an idea. It’s straightforward to make an argument for LLMs improving internal efficiency somehow, but it’s much harder to describe a believable way that LLMs will make your product more useful to your customers.

In this article we explore how to combine a large language model (LLM) with a relational database to allow users to ask questions about their data in a natural way. It demonstrates a Retrieval-Augmented Generation (RAG) system built with Go that utilizes PostgreSQL and pgvector for data storage and retrieval. The provided code showcases the core functionalities. This is an overview of how the

Revisiting a documentation sprint to explore how LLM-powered tools like Unblocked can help us understand and explain complex codebases.

Researchers in Japan have effectively developed a diverse range of personality traits in dialogue AI using a large-scale language model (LLM). Using the prisoner's dilemma from game theory, Professor Takaya Arita and Associate Professor Reiji Suzuki from Nagoya University's Graduate School of Informatics' team created a framework for evolving AI agents that mimics human behavior by switching between selfish and cooperative actions, adapting its strategies through evolutionary processes. Their findings were published in Scientific Reports.

Learn how to use local LLM models to Chat with Cody without an Internet connection powered by Ollama.

We look at an open source method to run large language models locally. LocalAI is an alternative to Ollama, a private company.

Data contamination (or data leakage) in AI occurs when the data used to train the model has been "contaminated" with overlapping data.

In this article, we will look at the limitations of RAG and domain-specific Fine-tuning to adapt LLMs to existing knowledge and how a team of UC Berkeley..

We demonstrate how to combine LangChain and Google's Gemini LLM to summarize blog posts and articles on the internet.

If you're a developer needing to write a business document, Jon Udell explores the benefits (and quirks) of LLM-assisted copy editing.

A feature-rich self-hosted WebUI for LLMs, supported LLM runners include Ollama and OpenAI-compatible APIs.

Tools like Ollama let you experiment with large language models on an average PC

The promise of LLMs for the software development world is to transform coders into architects. Not all LLMs are created equal, though.

Learn how your organization can customize its LLM-based solution through retrieval augmented generation and fine-tuning.

Research from MIT's CSAIL shows that getting a group of LLM systems to work together results in a more factually accurate answer.

Last week I posted about coming off the cloud, and this week I’m looking at running an open source LLM

Automatic Differentiation

Microsoft is transforming retrieval-augmented generation with GraphRAG, using LLM-generated knowledge graphs to significantly improve Q&A when analyzing complex information and consistently outperforming baseline RAG. Get the details.

AutoGen is a versatile framework that facilitates the creation of LLM applications by employing multiple agents capable of interacting with…

For rapid prototyping of LLM-backed tools, GPT Creator is a dream come true, says Jon Udell. He shows how he made — and used — a custom GPT.

First part of a series of blog posts that dive deep into what AI and LLMs really are, and why you should care.

How to parse content from a tool that is made to speak in human sentences.

The Instructor Elixir library lets you retrieve structured output from LLMs like the OpenAI GPT models.

Understanding vectors, tokens and embeddings is fundamental to grokking how large language models process language.

These are the main potential bottlenecks that negatively impact the performance of RAG pipelines targeting production LLM environments.

We dig into the technology behind Perplexity’s Copilot, which was inspired by the FreshLLMs paper that proposed search engine-augmented LLMs.

The path toward hands-on autonomous learning is through large language models (LLMs). Jon Udell shows how the EdTech sector can use AI.