Documentation now talks about installing models more, closes #100

README.md

@@ -29,7 +29,7 @@ brew install simonw/llm/llm
 
 If you have an [OpenAI API key](https://platform.openai.com/account/api-keys) you can get started using the OpenAI models right away.
 
-(You can [install plugins](https://github.com/simonw/llm-plugins) to access models by other providers, including models that can be installed and run on your own device.)
+As an alternative to OpenAI, you can [install plugins](https://llm.datasette.io/en/stable/plugins/installing-plugins.html) to access models by other providers, including models that can be installed and run on your own device.
 
 Save your OpenAI API key like this:
 

docs/changelog.md

@@ -3,7 +3,7 @@
 (v0_5)=
 ## Unreleased
 
-LLM now supports **additional language models**, thanks to a new {ref}`plugins` mechanism for registering additional models.
+LLM now supports **additional language models**, thanks to a new {ref}`plugins mechanism <installing-plugins>` for installing additional models.
 
 Plugins are available for 19 models in addition to the default OpenAI ones:
 

docs/index.md

@@ -6,18 +6,20 @@
 [![License](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](https://github.com/simonw/llm/blob/main/LICENSE)
 [![Discord](https://img.shields.io/discord/823971286308356157?label=discord)](https://datasette.io/discord-llm)
 
-A command-line utility for interacting with Large Language Models, such as OpenAI's GPT series.
+A command-line utility for interacting with Large Language Models, including OpenAI, PaLM and local models installed on your own machine.
 
 ## Quick start
 
-You'll need an [OpenAI API key](https://platform.openai.com/account/api-keys) for this:
+First, install LLM using `pip` or Homebrew:
 
 ```bash
 # Install LLM
 pip install llm
 # Or use: brew install simonw/llm/llm
-
-# Paste your OpenAI API key into this:
+```
+If you have an [OpenAI API key](https://platform.openai.com/account/api-keys) key you can run this:
+```bash
+# Paste your OpenAI API key into this
 llm keys set openai
 
 # Run a prompt
@@ -26,9 +28,14 @@ llm "Ten fun names for a pet pelican"
 # Run a system prompt against a file
 cat myfile.py | llm -s "Explain this code"
 ```
+Or you can {ref}`install a plugin <installing-plugins>` and use models that can run on your local device:
+```bash
+# Install the plugin
+llm install llm-gpt4all
 
-You can also [install plugins](https://github.com/simonw/llm-plugins) to access models by other providers, including models that can be installed and run on your own device.
-
+# Download and run a prompt against the Vicuna model
+llm -m ggml-vicuna-7b-1 'What is the capital of France?'
+```
 
 ## Contents
 

docs/plugins/installing-plugins.md

@@ -1,3 +1,4 @@
+(installing-plugins)=
 # Installing plugins
 
 Plugins must be installed in the same virtual environment as LLM itself.
@@ -6,14 +7,27 @@ You can find names of plugins to install in the [llm-plugins](https://github.com
 
 Use the `llm install` command (a thin wrapper around `pip install`) to install plugins in the correct environment:
 ```bash
-llm install llm-hello-world
+llm install llm-gpt4all
 ```
 Plugins can be uninstalled with `llm uninstall`:
 ```bash
-llm uninstall llm-hello-world -y
+llm uninstall llm-gpt4all -y
 ```
 The `-y` flag skips asking for confirmation.
 
+You can see additional models that have been added by plugins by running:
+```bash
+llm models list
+```
+Or add `--options` to include details of the options available for each model:
+```bash
+llm models list --options
+```
+To run a prompt against a newly installed model, pass its name as the `-m/--model` option:
+```bash
+llm -m ggml-vicuna-7b-1 'What is the capital of France?'
+```
+
 ## Listing installed plugins
 
 Run `llm plugins` to list installed plugins:
@@ -24,15 +38,34 @@ llm plugins
 ```json
 [
   {
-    "name": "llm-hello-world",
+    "name": "llm-mpt30b",
     "hooks": [
-      "register_commands"
+      "register_commands",
+      "register_models"
+    ],
+    "version": "0.1"
+  },
+  {
+    "name": "llm-palm",
+    "hooks": [
+      "register_commands",
+      "register_models"
+    ],
+    "version": "0.1"
+  },
+  {
+    "name": "llm.default_plugins.openai_models",
+    "hooks": [
+      "register_commands",
+      "register_models"
+    ]
+  },
+  {
+    "name": "llm-gpt4all",
+    "hooks": [
+      "register_models"
     ],
     "version": "0.1"
   }
 ]
 ```
-You can see additional models that have been added by plugins by running:
-```bash
-llm models list
-```

docs/usage.md

@@ -2,7 +2,7 @@
 
 The default command for this is `llm prompt` - you can use `llm` instead if you prefer.
 
-## Executing a prompt
+## Executing a prompt against OpenAI
 
 To run a prompt, streaming tokens as they come in:
 ```bash
@@ -30,49 +30,66 @@ Some models support options. You can pass these using `-o/--option name value` -
 llm 'Ten names for cheesecakes' -o temperature 1.5
 ```
 
+## Installing and using a local model
+
+{ref}`LLM plugins <plugins>` can provide local models that run on your machine.
+
+To install [llm-gpt4all](https://github.com/simonw/llm-gpt4all), providing 17 models from the [GPT4All](https://gpt4all.io/) project, run this:
+
+```bash
+llm install llm-gpt4all
+```
+Run `llm models list` to see the expanded list of available models.
+
+To run a prompt through one of the models from GPT4All specify it using `-m/--model`:
+```bash
+llm -m ggml-vicuna-7b-1 'What is the capital of France?'
+```
+The model will be downloaded and cached the first time you use it.
+
 ## Continuing a conversation
 
 By default, the tool will start a new conversation each time you run it.
 
 You can opt to continue the previous conversation by passing the `-c/--continue` option:
-
-    llm 'More names' --continue
-
+```bash
+llm 'More names' --continue
+```
 This will re-send the prompts and responses for the previous conversation as part of the call to the language model. Note that this can add up quickly in terms of tokens, especially if you are using expensive models.
 
 `--continue` will automatically use the same model as the conversation that you are continuing, even if you omit the `-m/--model` option.
 
 To continue a conversation that is not the most recent one, use the `--cid/--conversation <id>` option:
-
-    llm 'More names' --cid 01h53zma5txeby33t1kbe3xk8q
-
+```bash
+llm 'More names' --cid 01h53zma5txeby33t1kbe3xk8q
+```
 You can find these conversation IDs using the `llm logs` command.
 
 ## Using with a shell
 
 To generate a description of changes made to a Git repository since the last commit:
-
-    llm "Describe these changes: $(git diff)"
-
+```bash
+llm "Describe these changes: $(git diff)"
+```
 This pattern of using `$(command)` inside a double quoted string is a useful way to quickly assemble prompts.
 
 ## System prompts
 
 You can use `-s/--system '...'` to set a system prompt.
-
-    llm 'SQL to calculate total sales by month' \
-      --system 'You are an exaggerated sentient cheesecake that knows SQL and talks about cheesecake a lot'
-
+```bash
+llm 'SQL to calculate total sales by month' \
+  --system 'You are an exaggerated sentient cheesecake that knows SQL and talks about cheesecake a lot'
+```
 This is useful for piping content to standard input, for example:
-
-    curl -s 'https://simonwillison.net/2023/May/15/per-interpreter-gils/' | \
-      llm -s 'Suggest topics for this post as a JSON array'
-
+```bash
+curl -s 'https://simonwillison.net/2023/May/15/per-interpreter-gils/' | \
+  llm -s 'Suggest topics for this post as a JSON array'
+```
 ## Listing available models
 
 The `llm models list` command lists every model that can be used with LLM, along with any aliases:
 
-```
+```bash
 llm models list
 ```
 Example output: