Software

Introduction.

Continuing with this post from yesterday, I summarized the construction of a GraphRAG system using hybrid search.

I had imagined connecting pipes “|” like LangChain’s LCEL, but it was not what I had imagined. Please check it out below.

Introduction.

In this post, I created a knowledge graph using neo4j and built a RAG system using the knowledge graph as external information.

In this post, I have tried to build a RAG system easily using the neo4j library.

Motivation

In this post, I built GraphRAG with Neo4j and LangChain on a trial basis. I am studying bedrock with this book. Since I’ve just started touching AWS, I decided to build GraphRAG on AWS.

Introduction

I built a RAG using HyDE (Hypothetical Document Embeddings), a method to improve RAGs. This post summarizes my trial of HyDE. The LLM used was gpt-4o-mini to keep costs down.

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.

Introduction

I read this article on August 8th. According to the article, a subsidiary of Preferred Networks (PFE) will start offering a free trial of LLM, which has Japanese language performance that exceeds GPT-4, prior to offering a commercial version.

I immediately applied for the free trial, received an email of acceptance, and waited for the notification of account issuance. I had received the notification e-mail on August 9th, but I had overlooked it and completely forgot that I had applied for it. Recently, after reading this post, I remembered about the free trial, rechecked my email, and found the account notification.

In this post, I will summarize what I tried of the free trial version.

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

By yesterday, I had extracted astronomy-related entries from Wikipedia and created a vector database and keyword base for RAG. Here, I will use those databases to build the RAG system.

The LLMs used are ChatGPT (gpt-4o) and Llama-3-ELYZA-JP-8B.

Introduction.

Create a databases that can be used by RAG from the text data created yesterday, prepare a few specific strings, and search and evaluate them.