Docker

Motivation

Until now, I’ve been launching JupyterLab containers on a remote workstation equipped with a GPU, connecting via browser from my local MacBook Air to develop Python code. For example, see this article. Recently, since I’ve been using VSCode frequently, I tried connecting to the same Python development environment on the GPU-equipped remote workstation from VSCode.

Introduction

It has been almost a year since Ubuntu 24.04 LTS Noble Numbat was released. Since it seems to be stable enough, I decided to migrate from 22.04 to 24.04 with a clean install.

I usually installed from the Japanese Remix ISO image, but since this version Japanese Remix is not released, I downloaded the image from Canonical’s page and installed it.

Introduction

Yesterday in this post I summarized launching ollama in a docker container and using LLMs from JupyterLab. In this post, I summarize launching Open WebUI in a container and using it as a front end to connect from a browser at hand to use ollama’s LLMs.

Motivation

In this post, I mentioned that the LLMs that can build knowledge graphs are OpenAI and Mistral (via API). On the Internet, I have seen examples of GraphRAG environments being built using ollama, as in this post.

I would like to try to build a knowledge graph using LLM in a local environment. In this post, I will summarize the process of installing ollama.

Motivation

Half a month ago in this post, I tried six LLMs for using the Knowledge Graph. As I wrote there, the LLMs available at this time are OpenAI and Mistral.　So, I tried to run MistarlAI’s LLM on my PC (local environment). In fact, I found that it is not usable for the knowledge graph. In this post, I tried to use MistaralAI via Langchain via API to see if it can be used in the knowledge graph.

Introduction

A while ago in this post, I described how I installed neo4j in a local environment (as a docker container) in order to use the knowledge graph.

In this post, I would like to summarize the contents of the simple knowledge graph that I built and used as a RAG, referring to an article on the Internet. I titled this post as first steps because I did exactly what the article on the internet said.

Motivation

So far, we have built RAG system using FAISS and BM25. Although vector search is relatively easy to construct, there are cases where the necessary information is not found in “k” documents, and I was looking for ways to improve the accuracy. I happened to read this article and became interested in the knowledge graph and decided to try it myself.

In this post, I will summarize the process of installing nao4j in my local environment and trying to use it from a browser in order to use the knowledge graph.

Introduction.

NumPy 2.0.0 was released on June 16. I first noticed it the other day when I tried RAG with using langchain and got an error when building the docker container. Later, I encountered another error in CMake when trying to incorporate llama-cpp-python.

This article summarizes my responses to the two errors I recently experienced.

Dealing with errors related to NumPy 2.0.0

Background

I recently decided to learn RAG properly, I purchased a japanese book called LLM fine tuning and RAG. The book uses langchain, so I decided to create a docker container for jupyterlab that incorporates the langchain library.

Introduction

I have changed the hostfile that determines the order of OpenMPI execution nodes and re-measured OpenMPI performance on the Himeno benchmark as this article I posted it. After posting, I thought about it again and decided to use objective figures instead of my own judgments based on CPU and clock performance.

So this time, I decided to measure the performance of each individual workstation (node), and then decide the order of hostfile according to the results, and measure them again.

Introduction

A month ago in this post, I measured the performance of OpenMPI with the HIMENO benchmark. My friend who saw that post pointed out some improvements regarding the order of the hostfile. In this post, I summarized the results of the performance measurement again after modifying the hostfile.