From dfc87fc319d2cfb84fa547726999b936a1d3e315 Mon Sep 17 00:00:00 2001 From: Gustaf Rydholm Date: Sun, 5 May 2024 22:13:13 +0200 Subject: Update rag text --- content/projects/retrieval-augmented-generation.md | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/content/projects/retrieval-augmented-generation.md b/content/projects/retrieval-augmented-generation.md index d3316d3..673a5c3 100644 --- a/content/projects/retrieval-augmented-generation.md +++ b/content/projects/retrieval-augmented-generation.md @@ -15,16 +15,16 @@ draft: false I implemented a retrieval augmented generation (RAG) [program](https://github.com/aktersnurra/rag) for fun with the goal of being able to search my personal library. My focus was to make this run locally with only open -source models. This was achieved with [`ollama`](ollama.com) and +source models. This was achieved with [`ollama`](https://ollama.com) and [`sentence-transformers`](https://github.com/UKPLab/sentence-transformers) for downloading and running these models locally. However, the project was expanded to -integrate with cohere and their rerank and command-r+ models, since I was curious about -the command-r+ performance. These models can be downloaded and run locally, but it took -ages for my computer to generate any output, since the command-r+ is 104B parameter -model. The obvious and cool benefit of the command-r+ is that it generates citations -from the context in the answer. +integrate with cohere and their rerank and command-r+ models, since I was especially +curious about the command-r+'s performance. These models can be downloaded and run +locally, but it took ages for my computer to generate any output, since the command-r+ +model is 104B parameters. The obvious and impressive benefit of the command-r+ is that +it generates citations from the context in its answer. Here is a [presentation](/rag.html) that gives a brief overview of what a RAG system is, and how it can be improved with reranking. -- cgit v1.2.3-70-g09d2