ChatStream Guide

[ChatStream] Creation and Initialization

Hello from the Product Development Division at Qualiteg. In this article, we explain how to create and initialize ChatStream. The ChatStream class is the core class of the ChatStream package. It receives a FastAPI/Starlette Request and is responsible for sending a streaming response to the client while controlling the

DIY GPU Machines

Building a GPU PC, Part 6: Choosing Memory

This time, let's choose the memory and other peripheral parts. Memory selection has its own pitfalls, and Jun managed to fall right into one. Let's take a look. Phew. I finally managed to buy the CPU and the motherboard. What else do I need to buy?

AI Mathematics

AI Math Basics: Does AI Math Dream of Minecraft?

Hello everyone, this is the Research Department at Qualiteg. When reading papers on LLMs, do you ever feel dizzy from the sheer number of mysterious formulas and symbols? I studied neural networks back in my student days, and I remember being taken aback by how the mathematical background needed to

ChatStream Guide

[ChatStream] Configuring the HTTP Session Middleware

Hello from the Product Development Department at Qualiteg. In this article, we explain how to set up a session middleware in ChatStream and make your web application stateful. ChatStream uses a proprietary session middleware developed by Qualiteg, which offers greater flexibility than the standard session middleware for Starlette. (Its approach

AI-Business

[AI-Driven New Business Creation] Qualiteg's Three Points for Generating High-Quality Ideas

In our new business consulting, many clients ask how to generate high-quality ideas. Drawing on years of experience, Qualiteg emphasizes requirements definition, industry research, and effective facilitation, which raise the quality of ideas and keep brainstorming from missing the mark.

ChatStream Guide

[ChatStream] How to Load a Model

Hello, this is the Product Development Department at Qualiteg Inc. In this article, we explain the approach for loading Hugging Face models into ChatStream. Loading a Hugging Face Model Load the Hugging Face model using the method specified for each model. model_path = "togethercomputer/RedPajama-INCITE-Chat-3B-v1" device = "cuda&

DIY GPU Machines

Building a GPU PC, Part 5: Which Motherboard to Choose?

This time, we select the motherboard. Before we follow the rest of Jun's shopping trip, let's quickly review chipsets once more. Both 12th- and 13th-generation Intel Core CPUs use the LGA 1700 socket, and in many cases a 12th-generation chipset is also compatible with 13th-generation CPUs.

Blog

The GPU-Rich and the Reality in Japan

The global GPU shortage is becoming increasingly severe, and securing high-performance graphics processing units (GPUs) in particular has become difficult. This shortage is having a major impact on many technology industries, beginning with AI research and development, and is giving rise to a new form of competition among companies and

ChatStream Guide

[ChatStream] Implementing ChatPrompt

What Is ChatPrompt? Hello, this is the Product Development Department at Qualiteg Inc. In this article, we walk through how to implement a ChatPrompt in concrete terms. ChatPrompt is a class for generating prompts for a pretrained language model (hereafter, "the model"). We call it a prompt class.

AI-Business

[AI-Driven New Business Creation] The Challenges of New Business Development

In new business development, common problems include a shortage of good ideas and uncertainty about how to commercialize them. Specific challenges include unclear methods for exploring business opportunities, generating ideas, and turning them into a business.

DIY GPU Machines

Building a GPU PC, Part 4: Off to Akihabara! Choosing a CPU

Hello, and welcome. Let's get started on building a PC. For this series, we asked Jun, a young engineer at Qualiteg, to share a candid, first-hand account of building a GPU machine from scratch. I'm Jun, a software engineer. One morning I arrived at the office

ChatStream Guide

[ChatStream] Quickstart

Hello from the Product Development Division at Qualiteg Inc. The summer heat just keeps going, doesn't it? Let's jump right in and build a real-time streaming chat server using ChatStream, which we announced yesterday. Installing the package First, install the ChatStream package. pip install chatstream Installing

AI-Business

[AI-Driven New Business Creation] How to Streamline Office Operations with Generative AI

Michele answers a common client question: how to start using ChatGPT for operational efficiency. She recommends beginning with automated internal document generation, highlights the gains in customer support, and suggests back-office reform as the first step.

DIY GPU Machines

Building a GPU PC, Part 3: The Dream of Running Two Graphics Cards

Hello again. Today's topic is lane bifurcation and running two graphics cards. As we saw last time, on Intel Core series CPUs, the PCI Express connection coming directly from the CPU is PCIe Gen 5 x16 (16 lanes). PCIe Gen 5 is extremely fast, and since 16 of

IT & AI Technology

Google Cloud Text-to-Speech Voice List

Google Cloud Text-to-Speech Voice List Total languages: 0 Total voices: 0 Showing: 0 Language All Country/Region All Model All Gender All FEMALE MALE Search Reset filters Language Country/Region Language code Voice name Gender

AI-Business

[AI-Driven New Business Creation] What Is an LLM?

Michele introduces a blog series answering questions about AI-powered business and marketing. This post explains large language models (LLMs), uses ChatGPT to illustrate business applications and technical aspects of LLMs, and introduces a dedicated PC and Japanese-capable models.