final edits

README.md

@@ -26,60 +26,40 @@
 
 <p></p>
 
-## Easily understand code sections
+## Chat
 
-![understand](docs/static/img/understand.gif)
+[Chat](https://continue.dev/docs/chat/how-to-use-it) makes it easy to ask for help from an LLM without needing to leave the IDE
 
-VS Code: `cmd+L` (MacOS) / `ctrl+L` (Windows)
+![chat](docs/static/img/chat.gif)
 
-JetBrains: `cmd+J` (MacOS) / `ctrl+J` (Windows)
+## Autocomplete
 
-## Tab to autocomplete code suggestions
+[Autocomplete](https://continue.dev/docs/autocomplete/how-to-use-it) provides inline code suggestions as you type
 
 ![autocomplete](docs/static/img/autocomplete.gif)
 
-VS Code: `tab` (MacOS) / `tab` (Windows)
+## Edit
 
-JetBrains: `tab` (MacOS) / `tab` (Windows)
+[Edit](https://continue.dev/docs/edit/how-to-use-it) is a convenient way to modify code without leaving your current file
 
-## Refactor functions where you are coding
+![edit](docs/static/img/edit.gif)
 
-![inline](docs/static/img/inline.gif)
+## Actions
 
-VS Code: `cmd+I` (MacOS) / `ctrl+I` (Windows)
+[Actions](https://continue.dev/docs/actions/how-to-use-it) are shortcuts for common use cases.
 
-JetBrains: `cmd+I` (MacOS) / `ctrl+I` (Windows)
-
-## Ask questions about your codebase
-
-![codebase](docs/static/img/codebase.gif)
-
-VS Code: `cmd+enter` (MacOS) / `ctrl+enter` (Windows)
-
-JetBrains: `cmd+enter` (MacOS) / `ctrl+enter` (Windows)
-
-## Quickly use documentation as context
-
-![docs](docs/static/img/docs.gif)
-
-VS Code: `@docs` (MacOS) / `@docs` (Windows)
-
-JetBrains: `@docs` (MacOS) / `@docs` (Windows)
+![actions](docs/static/img/actions.gif)
 
 </div>
 
 ## Getting Started
 
-### Download for [VS Code](https://marketplace.visualstudio.com/items?itemName=Continue.continue) and [JetBrains](https://plugins.jetbrains.com/plugin/22707-continue-extension)
-
-You can try out Continue with our free trial models before configuring your setup.
-
-Learn more about the models and providers [here](https://continue.dev/docs/setup/overview).
+Learn about how to install and use Continue in the docs [here](https://continue.dev/docs/getting-started)
 
 ## Contributing
 
 Check out the [contribution ideas board](https://github.com/orgs/continuedev/projects/2), read the [contributing guide](https://github.com/continuedev/continue/blob/main/CONTRIBUTING.md), and join [#contribute on Discord](https://discord.gg/vapESyrFmJ)
 
 ## License
 
-[Apache 2.0 © 2023 Continue Dev, Inc.](./LICENSE)
+[Apache 2.0 © 2023 Continue Dev, Inc.](./LICENSE)

docs/docs/customize/changelog.mdx

@@ -6,7 +6,7 @@ hide_table_of_contents: true
 ---
 
 import VSCodeChangelog from "../../../extensions/vscode/CHANGELOG.md";
-import IntelliJChangelog from "../../../extensions/intellij/CHANGELOG.md";
+import JetBrainsChangelog from "../../../extensions/intellij/CHANGELOG.md";
 
 Below are the changelogs for the latest releases of the VSCode and JetBrains extensions. Prior to 2024-07-02, the changelogs do not reflect all updates.
 
@@ -15,7 +15,7 @@ import TOCInline from "@theme/TOCInline";
 <TOCInline
   toc={toc.filter(
     (node) =>
-      node.value === "VSCode Changelog" || node.value === "IntelliJ Changelog",
+      node.value === "VSCode Changelog" || node.value === "JetBrains Changelog",
   )}
 />
 
@@ -25,6 +25,6 @@ import TOCInline from "@theme/TOCInline";
 
 <VSCodeChangelog />
 
-## IntelliJ Changelog
+## JetBrains Changelog
 
-<IntelliJChangelog />
+<JetBrainsChangelog />

docs/docs/customize/model-providers/top-level/bedrock.md

@@ -78,3 +78,13 @@ To setup Bedrock using custom imported models, add the following to your `config
   ]
 }
 ```
+
+Authentication will be through temporary or long-term credentials in
+~/.aws/credentials under a configured profile (e.g. "bedrock").
+
+```title="~/.aws/credentials
+[bedrock]
+aws_access_key_id = abcdefg
+aws_secret_access_key = hijklmno
+aws_session_token = pqrstuvwxyz # Optional: means short term creds.
+```

docs/docs/customize/model-types/autocomplete.md

@@ -2,14 +2,15 @@
 title: Autocomplete model
 description: Autocomplete model
 keywords: [autocomplete]
+sidebar_position: 1
 ---
 
-An "Autocomplete model" is an LLM that is trained on a special format called fill-in-the-middle (FIM). This format is designed to be given the prefix and suffix of a code file and predict what goes between. This task is very specific, which on one hand means that the models can be smaller (even a 3B parameter model can perform well). On the other hand, this means that Chat models, though larger, will perform poorly.
+An "autocomplete model" is an LLM that is trained on a special format called fill-in-the-middle (FIM). This format is designed to be given the prefix and suffix of a code file and predict what goes between. This task is very specific, which on one hand means that the models can be smaller (even a 3B parameter model can perform well). On the other hand, this means that Chat models, though larger, will perform poorly.
 
 In Continue, these models are used to display inline [Autocomplete](../../docs/chat/how-to-use-it.md) suggestions as you type.
 
 ## Recommended Autocomplete models
 
 If you have the ability to use any model, we recommend [Codestral](../model-providers/top-level/mistral.md) from Mistral.
 
-If you want to run a model locally, we recommend [Starcoder2-3B] with [Ollama](../model-providers/top-level/ollama.md).
+If you want to run a model locally, we recommend [Starcoder2-3B] with [Ollama](../model-providers/top-level/ollama.md).

docs/docs/customize/model-types/chat.md

@@ -2,9 +2,10 @@
 title: Chat model
 description: Chat model
 keywords: [chat]
+sidebar_position: 2
 ---
 
-A "Chat model" is an LLM that is trained to respond in a conversational format. Because they should be able to answer general questions and generate complex code, the best chat models are typically large, often 405B+ parameters. In Continue, these models are used for [the Chat sidebar](../../docs/chat/how-to-use-it.md) and [Actions](../../docs/actions/how-to-use-them.md).
+A "chat model" is an LLM that is trained to respond in a conversational format. Because they should be able to answer general questions and generate complex code, the best chat models are typically large, often 405B+ parameters. In Continue, these models are used for [Chat](../../docs/chat/how-to-use-it.md), [Edit](../../docs/edit/how-to-use-it.md), and [Actions](../../docs/actions/how-to-use-it.md).
 
 ## Recommended Chat models
 
@@ -14,4 +15,4 @@ Otherwise, some of the next best options are:
 
 - [GPT-4o](../model-providers/top-level/openai.md)
 - [Gemini 1.5 Pro](../model-providers/top-level/gemini.md)
-- [Llama3.1 405B](../tutorials/llama3.1.md)
+- [Llama3.1 405B](../tutorials/llama3.1.md)

docs/docs/customize/model-types/embeddings.md

@@ -2,6 +2,7 @@
 title: Embeddings model
 description: Embeddings model
 keywords: [embedding]
+sidebar_position: 3
 ---
 
 An "embeddings model" is trained to convert a piece of text into a vector, which can later be rapidly compared to other vectors to determine similarity between the pieces of text. Embeddings models are typically much smaller than LLMs, and will be extremely fast and cheap in comparison.
@@ -67,4 +68,4 @@ See [here](../model-providers/more/cohere.md#embeddings-model) for instructions
 
 ### Gemini
 
-See [here](../model-providers/top-level/gemini.md#embeddings-model) for instructions on how to use Gemini for embeddings.
+See [here](../model-providers/top-level/gemini.md#embeddings-model) for instructions on how to use Gemini for embeddings.

docs/docs/customize/model-types/reranking.md

@@ -2,6 +2,7 @@
 title: Reranking model
 description: Reranking model
 keywords: [rerank]
+sidebar_position: 4
 ---
 
 A "reranking model" is trained to take two pieces of text (often a user question and a document) and return a relevancy score between 0 and 1, estimating how useful the document will be in answering the question. Rerankers are typically much smaller than LLMs, and will be extremely fast and cheap in comparison.
@@ -88,4 +89,4 @@ Continue offers a free trial of Voyage AI's reranking model.
     "name": "free-trial"
   }
 }
-```
+```

docs/docs/customize/overview.md

@@ -4,9 +4,9 @@ description: Introduction to customizing Continue
 keywords: [customize, configure, config]
 ---
 
-Continue can be deeply customized by editing a local file located at `~/.continue/config.json` (or `%USERPROFILE%\.continue\config.json` on Windows). `config.json` is created the first time you use Continue.
+Continue can be deeply customized. This is primarily accomplished by editing a local file located at `~/.continue/config.json` (MacOS / Linux) or `%USERPROFILE%\.continue\config.json` (Windows). `config.json` is created the first time you use Continue.
 
-## Basics
+## Getting started
 
 To open `config.json`, click the "gear" icon in the bottom right corner of the Continue Chat sidebar. When editing this file, you can use IntelliSense to see the available options as you type, or you can check the [full reference](./config.mdx).
 
@@ -18,6 +18,6 @@ If you'd like to scope certain settings to a particular workspace, you can add a
 
 ## Programmatic configuration
 
-`config.json` can handle the vast majority of necessary configuration, so we recommend using it whenever possible. However, if you need to programmatically configure Continue, you can use `config.ts`, which is located at `~/.continue/config.ts` (or `%USERPROFILE%\.continue\config.ts` on Windows).
+`config.json` can handle the vast majority of necessary configuration, so we recommend using it whenever possible. However, if you need to programmatically configure Continue, you can use `config.ts`, which is located at `~/.continue/config.ts` (MacOS / Linux) or `%USERPROFILE%\.continue\config.ts` (Windows).
 
-For examples of how to use `config.ts`, see [writing custom slash commands](./tutorials/build-your-own-slash-command.md#custom-slash-commands) or [writing custom context providers](./tutorials/build-your-own-context-provider.md).
+For examples of how to use `config.ts`, see [writing custom slash commands](./tutorials/build-your-own-slash-command.md#custom-slash-commands) or [writing custom context providers](./tutorials/build-your-own-context-provider.md).

docs/docs/docs/actions/how-they-work.md → docs/docs/docs/actions/how-it-works.md

@@ -1,12 +1,12 @@
 ---
-title: How they work
-description: Actions \-how it works
+title: How it works
+description: How Actions work
 keywords: [how, slash, commands, prompt, right click, quick fix, debug, action]
 sidebar_position: 4
 ---
 
-While many actions are based on templated prompts and can be customized with .prompt files, there are a number that execute more complex code under the hood.
+While many Actions are based on templated prompts and can be customized with .prompt files, there are a number that execute more complex code under the hood.
 
 Actions that generate inline diffs, like “/edit”, “/comment”, or right click actions, use the same prompt and response processing logic as [Edit](../edit/how-it-works.md).
 
-To learn how other slash commands work, see the full reference [here](../reference/slash-commands).
+To learn how other slash commands work, see the full reference [here](../reference/slash-commands).

docs/docs/docs/actions/advanced-configuration.md → docs/docs/docs/actions/how-to-customize.md

@@ -1,7 +1,7 @@
 ---
-title: Advanced configuration
-description: Advanced configuration
-keywords: [configuration, advanced]
+title: How to customize
+description: How to customize Actions
+keywords: [customize, actions]
 sidebar_position: 5
 ---
 
@@ -52,3 +52,5 @@ For full `config.ts` reference, see [here](../reference/config-ts.md).
 ## Other custom actions
 
 Currently the other action triggers are not open for configuration, but we plan to allow this via .prompt files in the future.
+
+<!-- For any actions defined in a .prompt file, you can [configure a specific model](TODO). -->

docs/docs/docs/actions/how-to-use-them.md → docs/docs/docs/actions/how-to-use-it.md

@@ -1,26 +1,26 @@
 ---
 title: Actions
-description: Actions \- how to use it
-sidebar_label: How to use them
+description: How to use Actions
+sidebar_label: How to use it
 keywords: [how, slash, commands, prompt, right click, quick fix, debug, action]
 sidebar_position: 1
 ---
 
-![action](/img/action.gif)
+![actions](/img/actions.gif)
 
-## How to use them
+## How to use Actions
 
 Actions are shortcuts for common use cases. For example, you might want to review code, write tests, or add a docstring.
 
-## Slash commands
+### Slash commands
 
 The most common way to invoke an action is with a slash command. These are shortcuts that can be activated by typing '/' and selecting from the dropdown. For example, the built-in '/edit' slash command lets you stream edits directly into your editor.
 
 ![slash-commands](/img/slash-commands.png)
 
 A few of the most useful slash commands are available by default, like “/edit”, “/comment”, and “/share”, but Continue has a large built-in library of other options. To enable these, learn more [here](TODO).
 
-## Prompt files
+### Prompt files
 
 It is also possible to write your own slash command by defining a “.prompt file.” Prompt files can be as simple as a text file, but also include templating so that you can refer to files, URLs, highlighted code, and more.
 
@@ -52,33 +52,33 @@ Now to use this prompt, you can highlight code and use `cmd/ctrl+L` to select it
 
 Then, type "/" to see the list of slash commands and choose the one called "test". Press enter and the LLM will respond given the instructions from your prompt file.
 
-## Other triggers for actions (VS Code)
+### Other triggers for Actions (VS Code)
 
 :::info
 Currently all of these are only available in VS Code
 :::
 
 To make common use cases even more accessible, we provide a handful of other ways to invoke actions.
 
-### Quick actions
+#### Quick actions
 
 Quick Actions are displayed as buttons above top-level classes and functions in your source code, letting you invoke actions with one click. They can also be customized with .prompt files to perform custom actions.
 
 ![quick-actions](/img/quick-actions.png)
 
 By default, quick actions are disabled, but can be enabled with the “Continue: Enable Quick Actions” in VS Code settings.
 
-### Right click actions
+#### Right click actions
 
 Right click actions let you highlight a desired region of code, right click, and then select an action from the dropdown menu.
 
 ![context-menu](/img/context-menu.png)
 
-### Debug action
+#### Debug action
 
 The debug action is a special built-in keyboard shortcut in the VS Code extension. Use `cmd/ctrl+shift+R` to instantly copy the contents of the current terminal into the chat sidebar and get debugging advice.
 
-### Quick fixes
+#### Quick fixes
 
 Whenever you see red/yellow underlines in your code indicating errors, you can place your cursor nearby and VS Code will display a lightbulb icon. Either clicking the lightbulb or using the keyboard shortcut `cmd/ctrl+.` will show a dropdown menu of quick fixes. One of these will be the “Ask Continue” action. Either click or use `cmd/ctrl+.` again and Continue will attempt to help solve the problem.
 

docs/docs/docs/actions/model-setup.md

@@ -1,10 +1,8 @@
 ---
 title: Model setup
-description: Actions \-model setup
+description: Actions model setup
 keywords: [model]
 sidebar_position: 2
 ---
 
-By default, actions uses the same model as Chat since we recommend a similar, 400B+ parameter model for the complex instructions that will be carried out.
-
-<!-- For any actions defined in a .prompt file, you can [configure a specific model](TODO). -->
+By default, Actions uses the same model as [Chat](../chat/model-setup.mdx) since we recommend a similar, 400B+ parameter model or one of the frontier models for the complex instructions that will be carried out.

docs/docs/docs/autocomplete/context-selection.md

@@ -1,6 +1,6 @@
 ---
 title: Context selection
-description: Autocomplete \-context selection
+description: Autocomplete context selection
 keywords: [context, autocomplete, lsp, recent]
 sidebar_position: 3
 ---

docs/docs/docs/autocomplete/how-it-works.md

@@ -1,11 +1,11 @@
 ---
 title: How it works
-description: Autocomplete \-how it works
+description: How Autocomplete works
 keywords: [how, autocomplete, context]
 sidebar_position: 4
 ---
 
-Continue’s autocomplete is a [compound AI system](https://bair.berkeley.edu/blog/2024/02/18/compound-ai-systems/) that uses a combination of retrieval methods and response processing techniques. The system can be understood in roughly three parts.
+Autocomplete is a [compound AI system](https://bair.berkeley.edu/blog/2024/02/18/compound-ai-systems/) that uses a combination of retrieval methods and response processing techniques. The system can be understood in roughly three parts.
 
 ## Timing
 
@@ -27,3 +27,5 @@ Language models aren't perfect, but can be made much closer by adjusting their o
 - fixing indentation
 
 We will also occasionally entirely filter out responses if they are bad. This is often due to extreme repetition.
+
+You can learn more about how it works in the [Autocomplete deep dive](../../customize/deep-dives/autocomplete.md).