docs changes

continuedev · Jun 23, 2024 · c102261 · c102261
1 parent 447ef47
commit c102261
Show file tree

Hide file tree

Showing 9 changed files with 86 additions and 106 deletions.
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
@@ -110,8 +110,23 @@ Pre-requisite: You should use the Intellij IDE, which can be downloaded [here](h
 
    a. If you change code from the `core` or `binary` directories, make sure to run `npm run build` from the `binary` directory to create a new binary.
 
+   b. If you change code from the `gui` directory, make sure to run `npm run build` from the `gui` directory to create a new bundle.
+
+   c. Any changes to the Kotlin coded in the `extensions/intellij` directory will be automatically included when you run "Build Plugin"
+
+##### Debugging
+
 Continue's JetBrains extension shares much of the code with the VS Code extension by utilizing shared code in the `core` directory and packaging it in a binary in the `binary` directory. The Intellij extension (written in Kotlin) is then able to communicate over stdin/stdout in the [CoreMessenger.kt](./extensions/intellij/src/main/kotlin/com/github/continuedev/continueintellijextension/continue/CoreMessenger.kt) file.
 
+For the sake of rapid development, it is also possible to configure this communication to happen over local TCP sockets:
+
+1. In [CoreMessenger.kt](./extensions/intellij/src/main/kotlin/com/github/continuedev/continueintellijextension/continue/CoreMessenger.kt), change the `useTcp` variable to `true`.
+2. Open a VS Code window (we recommend this for a preconfigured Typescript debugging experience) with the `continue` repository. Select the "Core Binary" debug configuration and press play.
+3. Run the "Run Plugin" Gradle configuration.
+4. You can now set breakpoints in any of the TypeScript files in VS Code. If you make changes to the code, restart the "Core Binary" debug configuration and reload the _Host IntelliJ_ window.
+
+If you make changes to Kotlin code, they can often be hot-reloaded with "Run -> Debugging Actions -> Reload Changed Classes".
+
 ### Formatting
 
 Continue uses [Prettier](https://marketplace.visualstudio.com/items?itemName=esbenp.prettier-vscode) to format JavaScript/TypeScript. Please install the Prettier extension in VS Code and enable "Format on Save" in your settings.

diff --git a/README.md b/README.md
@@ -8,7 +8,7 @@
 
 <div align="center">
 
-**[Continue](https://docs.continue.dev) keeps developers in flow. Our open-source [VS Code](https://marketplace.visualstudio.com/items?itemName=Continue.continue) and [JetBrains](https://plugins.jetbrains.com/plugin/22707-continue-extension) extensions enable you to easily create your own modular AI software development system that you can improve.**
+**[Continue](https://docs.continue.dev) is the leading open-source AI code assistant. You can connect any models and any context to build custom autocomplete and chat experiences inside [VS Code](https://marketplace.visualstudio.com/items?itemName=Continue.continue) and [JetBrains](https://plugins.jetbrains.com/plugin/22707-continue-extension)**
 
 </div>
 
@@ -68,45 +68,13 @@ JetBrains: `@docs` (MacOS) / `@docs` (Windows)
 
 </div>
 
-## Task and tab autocomplete
-
-### Answer coding questions
-
-Highlight + select sections of code and ask Continue for another perspective
-
-- “what does this forRoot() static function do in nestjs?”
-- “why is the first left join in this query necessary here?”
-- “how do I run a performance benchmark on this rust binary?”
-
-### Edit in natural language
-
-Highlight + select a section of code and instruct Continue to refactor it
-
-- “/edit rewrite this to return a flattened list from a 3x3 matrix”
-- “/edit refactor these into an angular flex layout on one line"
-- “/edit define a type here for a list of lists of dictionaries”
-
-### Generate files from scratch
-
-Open a blank file and let Continue start new Python scripts, React components, etc.
-
-- “/edit get me started with a basic supabase edge function”
-- “/edit implement a c++ shortest path algo in a concise way”
-- “/edit create a docker compose file with php and mysql server"
-
-### And much more!
-
-- Try out [experimental support for local tab autocomplete](https://docs.continue.dev/walkthroughs/tab-autocomplete) in VS Code
-- Use [built-in context providers](https://docs.continue.dev/customization/context-providers#built-in-context-providers) or create your own [custom context providers](https://docs.continue.dev/customization/context-providers#building-your-own-context-provider)
-- Use [built-in slash commands](https://arc.net/l/quote/zbhwfjmp) or create your own [custom slash commands](https://docs.continue.dev/customization/slash-commands#custom-slash-commands)
-
 ## 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.
 
-Once you're ready to use your own API key or a different model / provider, press the `+` button in the bottom left to add a new model to your `config.json`. Learn more about the models and providers [here](https://docs.continue.dev/model-setup/overview).
+Learn more about the models and providers [here](https://continue.dev/docs/setup/overview).
 
 ## Contributing
 

diff --git a/core/autocomplete/README.md b/core/autocomplete/README.md
@@ -38,21 +38,35 @@ Example:
 
 ## Setting up a custom model
 
-All of the configuration options available for chat models are available to use for tab-autocomplete. For example, if you wanted to use a remote Ollama instance you would edit your `config.json` like this (note that it is not inside the models array):
+All of the configuration options available for chat models are available to use for tab-autocomplete. For example, if you wanted to use a remote vLLM instance you would edit your `config.json` like this (note that it is not inside the models array), filling in the correct model name and vLLM endpoint:
+
+```json title=~/.continue/config.json
+{
+    "tabAutocompleteModel": {
+        "title": "Tab Autocomplete Model",
+        "provider": "openai",
+        "model": "<MODEL_NAME>",
+        "apiBase": "<VLLM_ENDPOINT_URL>"
+    },
+    ...
+}
+```
+
+As another example, say you want to use a different model, `deepseek-coder:6.7b-base`, with Ollama:
 
 ```json title=~/.continue/config.json
 {
     "tabAutocompleteModel": {
         "title": "Tab Autocomplete Model",
         "provider": "ollama",
-        "model": "starcoder:3b",
+        "model": "deepseek-coder:6.7b-base",
         "apiBase": "https://<my endpoint>"
     },
     ...
 }
 ```
 
-If you aren't yet familiar with the available options, you can learn more in our [overview](../model-setup/overview.md).
+If you aren't yet familiar with the available options, you can learn more in our [overview](../setup/overview.md).
 
 ### What model should I use?
 

diff --git a/docs/docs/setup/select-model.md b/docs/docs/setup/select-model.md
@@ -55,7 +55,7 @@ You likely want to use a model that is 1-15B parameters for autocomplete.
 
 #### Codestral from Mistral
 
-Our current recommendation for autocomplete, if you are able to choose any model, is `codestral-latest` from Mistral's API.
+Our current recommendation for autocomplete, if you are able to choose any model, is `codestral-latest` from [Mistral's API](../walkthroughs/set-up-codestral.md).
 
 ### Open-source LLMs
 

diff --git a/docs/docs/setup/select-provider.md b/docs/docs/setup/select-provider.md
@@ -1,6 +1,6 @@
 ---
-title: Select a provider
-description: Swap out different LLM providers
+title: Select providers
+description: Configure LLM providers
 keywords: [openai, anthropic, gemini, ollama, ggml]
 ---
 
@@ -40,7 +40,8 @@ You can deploy a model in your [AWS](https://github.com/continuedev/deploy-os-co
 ## SaaS
 
 You can access both open-source and commercial LLMs via:
-* [OpenRouter](../reference/Model%20Providers/openrouter.md)
+
+- [OpenRouter](../reference/Model%20Providers/openrouter.md)
 
 ### Open-source models
 
@@ -60,8 +61,9 @@ You can run open-source LLMs with cloud services like:
 You can use commercial LLMs via APIs using:
 
 - [Anthrophic API](../reference/Model%20Providers/anthropicllm.md)
+- [OpenAI API](../reference/Model%20Providers/openai.md)
+- [Azure OpenAI Service](../reference/Model%20Providers/openai.md)
 - [Google Gemini API](../reference/Model%20Providers/geminiapi.md)
-- [OpenAI free trial](../reference/Model%20Providers/freetrial.md)
 - [Mistral API](../reference/Model%20Providers/mistral.md)
 - [Voyage AI API](../walkthroughs/codebase-embeddings.md#openai)
 - [Cohere API](../reference/Model%20Providers/cohere.md)

diff --git a/docs/docs/walkthroughs/set-up-codestral.md b/docs/docs/walkthroughs/set-up-codestral.md
@@ -23,18 +23,49 @@ keywords: [codestral, mistral, model setup]
   "models": [
     {
       "title": "Codestral",
-      "provider": "mistral"
+      "provider": "mistral",
+      "model": "codestral-latest",
+      "apiKey": "[API_KEY]"
+    }
+  ],
+  "tabAutocompleteModel": {
+    "title": "Codestral",
+    "provider": "mistral",
+    "model": "codestral-latest",
+    "apiKey": "[API_KEY]"
+  }
+}
+```
+
+5. If you run into any issues or have any questions, please join our Discord and post in the `#help` channel [here](https://discord.gg/EfJEfdFnDQ)
+
+## Trobleshooting
+
+### Temporary workaround for JetBrains
+
+Mistral AI recently changed the API endpoint to `codestral.mistral.ai` instead of `api.mistral.ai`, and our updated JetBrains extension is waiting on approval from the store. In the meantime, you will have to specify apiBase as "https://codestral.mistral.ai/v1" in the config.json like this:
+
+```json title="~/.continue/config.json"
+{
+  "models": [
+    {
+      "title": "Codestral",
+      "provider": "mistral",
       "model": "codestral-latest",
       "apiKey": "[API_KEY]",
+      "apiBase": "https://codestral.mistral.ai/v1/"
     }
   ],
   "tabAutocompleteModel": {
     "title": "Codestral",
     "provider": "mistral",
-    "model": "codestral-latest"
+    "model": "codestral-latest",
     "apiKey": "[API_KEY]",
+    "apiBase": "https://codestral.mistral.ai/v1/"
   }
 }
 ```
 
-5. If you run into any issues or have any questions, please join our Discord and post in the `#help` channel [here](https://discord.gg/EfJEfdFnDQ)
+### Ask for help on Discord
+
+Please join our Discord and post in the `#help` channel [here](https://discord.gg/EfJEfdFnDQ) if you are having problems using Codestral
diff --git a/docs/docs/walkthroughs/tab-autocomplete.md b/docs/docs/walkthroughs/tab-autocomplete.md
@@ -102,7 +102,7 @@ This object allows you to customize the behavior of tab-autocomplete. The availa
 - `multilineCompletions`: Whether to enable multiline completions ("always", "never", or "auto"). Defaults to "auto".
 - `useCache`: Whether to cache and reuse completions when the prompt is the same as a previous one. May be useful to disable for testing purposes.
 - `useOtherFiles`: Whether to include context from files outside of the current one. Turning this off should be expected to reduce the accuracy of completions, but might be good for testing.
-- `disable`: Disable autocomplete (can also be done from IDE settings)
+- `disableInFiles`: A list of glob patterns for files in which you want to disable tab autocomplete.
 
 ### Full example
 

diff --git a/extensions/intellij/README.md b/extensions/intellij/README.md
@@ -1,6 +1,6 @@
 <!-- Plugin description -->
 
-**[Continue](https://docs.continue.dev) is the open-source autopilot for software development—an extension that brings the power of ChatGPT to your IDE**
+![readme](../../media/readme.png)
 
 <h1 align="center">Continue</h1>
 
@@ -42,6 +42,10 @@
 
 You can try out Continue with our free trial models before configuring your setup.
 
-Once you're ready to use your own API key or a different model / provider, press the `+` button in the bottom left to add a new model to your `config.json`. Learn more about the models and providers [here](https://docs.continue.dev/model-setup/overview).
+Learn more about the models and providers [here](https://continue.dev/docs/setup/overview).
+
+## License
+
+[Apache 2.0 © 2023 Continue Dev, Inc.](./LICENSE)
 
 <!-- Plugin description end -->
diff --git a/extensions/vscode/README.md b/extensions/vscode/README.md
@@ -1,26 +1,16 @@
-> 🎉 **Tab autocomplete now available in pre-release (experimental)**
-
-![Continue logo](media/readme.png)
+![readme](media/readme.png)
 
 <h1 align="center">Continue</h1>
 
 <div align="center">
 
-**[Continue](https://docs.continue.dev) is an open-source autopilot for VS Code and JetBrains—the easiest way to code with any LLM**
+**[Continue](https://docs.continue.dev) is the leading open-source AI code assistant. You can connect any models and any context to build custom autocomplete and chat experiences inside [VS Code](https://marketplace.visualstudio.com/items?itemName=Continue.continue) and [JetBrains](https://plugins.jetbrains.com/plugin/22707-continue-extension)**
 
 </div>
 
 <div align="center">
 
-<a target="_blank" href="https://opensource.org/licenses/Apache-2.0" style="background:none">
-    <img src="https://img.shields.io/badge/License-Apache_2.0-blue.svg" style="height: 20px;" />
-</a>
-<a target="_blank" href="https://docs.continue.dev" style="background:none">
-    <img src="https://img.shields.io/badge/continue_docs-%23BE1B55" style="height: 20px;" />
-</a>
-<a target="_blank" href="https://discord.gg/vapESyrFmJ" style="background:none">
-    <img src="https://img.shields.io/badge/discord-join-continue.svg?labelColor=191937&color=6F6FF7&logo=discord" style="height: 20px;" />
-</a>
+## Easily understand code sections
 
 ![understand](docs/static/img/understand.gif)
 
@@ -56,51 +46,7 @@
 
 You can try out Continue with our free trial models before configuring your setup.
 
-![Editing With Continue](media/readme.gif)
-
-Highlight + select code sections and ask a question to get another perspective
-
-- “how can I set up a Prisma schema that cascades deletes?”
-- “where in the page should I be making this request to the backend?”
-- “how can I communicate between these iframes?”
-
-# 🪄 Reference context inline
-
-![Reference context inline](media/image.gif)
-
-- "@diff check my commit for mistakes"
-- "how does @server.py stream responses?"
-- "how do i fix this error in the @terminal?"
-
-# ⚡️ Get completions directly in your editor
-
-![Continue autocomplete](media/autocomplete.gif)
-
-# ✏️ Edit in natural language
-
-Highlight + select a section of code and instruct Continue to refactor it
-
-- “/edit migrate this digital ocean terraform file into one that works for GCP”
-- “/edit change this plot into a bar chart in this dashboard component”
-- “/edit rewrite this function to be async”
-
-![Above line edit](media/above-line-edit.gif)
-
-# 🚀 Generate files from scratch
-
-![Generate files from scratch](media/scratch.gif)
-
-Open a blank file, <kbd>Cmd/Ctrl</kbd> + <kbd>Shift</kbd> + <kbd>L</kbd>, and let Continue start new Python scripts, React components, etc.
-
-- “here is a connector for postgres, now write one for kafka”
-- “make an IAM policy that creates a user with read-only access to S3”
-- “use this schema to write me a SQL query that gets recently churned users”
-
-# Getting Started
-
-You can try out Continue for free using a proxy server that securely makes calls with our API key to models like GPT-4, Gemini Pro, and Phind CodeLlama via OpenAI, Google, and Together respectively.
-
-Once you're ready to use your own API key or a different model / provider, press the `+` button in the bottom left to add a new model to your `config.json`. Learn more about the models and providers [here](https://docs.continue.dev/model-setup/overview).
+Learn more about the models and providers [here](https://continue.dev/docs/setup/overview).
 
 ## License