From 5eb297cd32f47c3c2e5693eea6285ae5562ea140 Mon Sep 17 00:00:00 2001 From: chigkim Date: Sun, 18 Feb 2024 03:25:34 -0500 Subject: [PATCH] Putting back docker instruction. --- README.md | 26 +++++++++++++++++++++++++- changelog.md | 2 +- 2 files changed, 26 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index f50162b..ea83db0 100644 --- a/README.md +++ b/README.md @@ -14,6 +14,30 @@ ollama pull openhermes Finally, Run VOLlama.exe +## Ollama with Docker + +Instead of using Windows previous build, if you use Ollama with Docker, you might get a faster speed. + +Run the command below in the command line to install Ollama: +``` +docker run -d -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama +``` + +To download a model, execute the command below, replacing `openhermes` with a [different model](https://ollama.ai/library) as needed: +``` +docker exec ollama ollama pull openhermes +``` + +To stop Ollama, execute the command below. +``` +docker stop ollama +``` + +To run Ollama again, execute the command below. +``` +docker start ollama +``` + ## Shortcuts On Mac, press command key instead of control key. @@ -26,7 +50,7 @@ If you're operating Ollama on a different machine, you can configure the host ad ## [Retrieval-Augmented Generation](https://blogs.nvidia.com/blog/what-is-retrieval-augmented-generation/) -* Go to Rag menu > Attach url. +* Go to Rag menu > index an url. * Enter https://www.apple.com/apple-vision-pro/ * Wait until the document is indexed. * In the message field, type "/q What can you do with Vision Pro?" without the quotes. diff --git a/changelog.md b/changelog.md index 5ee0cfe..a42dac5 100644 --- a/changelog.md +++ b/changelog.md @@ -9,7 +9,7 @@ * Option to display context sent to RAG system * Epub reader * Global settings improvement -* [Retrieval-Augmented Generation](https://blogs.nvidia.com/blog/what-is-retrieval-augmented-generation/) (RAG): See below for insturction on how to use it. +* [Retrieval-Augmented Generation](https://blogs.nvidia.com/blog/what-is-retrieval-augmented-generation/) (RAG): See below for instruction on how to use it. * Many bug fixes * Generation parameters in advance menu * Voice and rate gets saved into persistent settings