---
title: "ollama"
output: rmarkdown::html_vignette
vignette: >
  %\VignetteIndexEntry{ollama}
  %\VignetteEngine{knitr::rmarkdown}
  %\VignetteEncoding{UTF-8}
---

```{r, include = FALSE}
knitr::opts_chunk$set (
    collapse = TRUE,
    comment = "#>"
)
```

The "pkgmatch" package does not access language model (LM) embeddings through external APIs,
for reasons explained in
[`vignette("why-local-lms")`](https://docs.ropensci.org/pkgmatch/articles/why-local-lms.html).
The LM embeddings are extracted from a locally-running instance of
[ollama](https://ollama.com). That means you need to download and install
ollama on your own computer in order to use this package. The following
sub-sections describe two distinct ways to do this. You will generally need to
follow one and only one of these sections.

## Local installation

This sub-section describes how to install and run ollama on your local
computer. This may not be possible for everybody, in which case the following
sub-section describes how to run ollama within a docker container.

General download instructions are given at https://ollama.com/download. Once
downloaded, ollama can be started by calling `ollama serve &`, where the final
`&` starts the process in the background.

The particular models used to extract the embeddings will be automatically
downloaded by this package if needed, or you can do this manually by running
the following two commands (in a system console; not in R):

``` bash
ollama pull jina/jina-embeddings-v2-base-en
ollama pull ordis/jina-embeddings-v2-base-code
```

You'll likely need to wait a few tens of minutes for the models to
download before proceeding. Once downloaded, both models should appear in the
output of `ollama list`.

## Docker

This package comes with a "Dockerfile" containing all code needed to build and
run the necessary ollama models within a docker container. This can be either
built locally, or downloaded from the GitHub container registry.

### Building the Docker container locally

To build the container locally, download the [Dockerfile from this
link](https://github.com/ropensci-review-tools/pkgmatch/blob/main/Dockerfile).
Then from the same directory as that file, run these lines:

``` bash
docker build . -t pkgmatch-ollama
```

### Downloading the pre-build Docker container

Alternatively, the Docker container including the ollama models used to run
this package is stored in the GitHub container registry, and can be downloaded
by running this line:

``` bash
docker pull ghcr.io/ropensci-review-tools/pkgmatch-ollama:latest
```

### Running the Docker container

Whether you've locally built the Docker container, or downloaded the pre-built
version, the container needs to be started with the following command:

``` bash
docker run --rm -d -p 11434:11434 ollama-models
```

The running container can be stopped by calling `docker stop` followed the the
"CONTAINER ID" listed on the output of `docker ps`.