docs(README): improve contributing docs (#42)

* docs: improve contributing docs
* fix: make dev env work on Windows
* docs: add mdn links to generated documentation

CONTRIBUTING.md

@@ -1,3 +1,6 @@
+## Development
+To set up your development environment, read [DEVELOPMENT.md](https://github.com/withcatai/node-llama-cpp/blob/master/DEVELOPMENT.md).
+
 ## <a name="commit"></a> Commit Message Guidelines
 
 This repository has very precise rules over how git commit messages can be formatted.

DEVELOPMENT.md

@@ -0,0 +1,59 @@
+# How to contribute to `node-llama-cpp`
+This document describes how to set up your development environment to contribute to `node-llama-cpp`.
+
+## Prerequisites
+- [Git](https://git-scm.com/). [GitHub's Guide to Installing Git](https://help.github.com/articles/set-up-git) is a good source of information.
+- [Node.js](https://nodejs.org/en/) (v18 or higher)
+- [cmake dependencies](https://github.com/cmake-js/cmake-js#installation:~:text=projectRoot/build%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%5Bstring%5D-,Requirements%3A,-CMake) - make sure the required dependencies of `cmake` are installed on your machine. More info is available [here](https://github.com/cmake-js/cmake-js#installation:~:text=projectRoot/build%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%5Bstring%5D-,Requirements%3A,-CMake) (you don't necessarily have to install `cmake`, just the dependencies)
+
+## Setup
+1. [Fork `node-llama-cpp` repo](https://github.com/withcatai/node-llama-cpp/fork)
+2. Clone your forked repo to your local machine
+3. Install dependencies:
+    ```bash
+    npm install
+    ```
+4. Build the CLI, use the CLI to clone the latest release of `llama.cpp`, and build it from source:
+    ```bash
+    npm run dev:setup
+    ```
+
+## Development
+Whenever you add a new functionality to `node-llama-cpp`, consider improving the CLI to reflect this change.
+
+To test whether you local setup works, download a model and try using it with the `chat` command.
+
+### Get a model file
+We recommend you to get a GGUF model from the [TheBloke on Hugging Face](https://huggingface.co/TheBloke?search_models=GGUF).
+
+We recommend you to start by getting a small model that doesn't have a lot of parameters just to ensure that your setup works, so try downloading a `7B` parameters model first (search for models with both `7B` and `GGUF` in their name).
+
+For improved download speeds, you can use [`ipull`](https://www.npmjs.com/package/ipull) to download the model:
+```bash
+npx ipull <model-file-ul>
+```
+
+### Validate your setup by chatting with a model
+To validate that your setup works, run the following command to chat with the model you downloaded:
+```bash
+npx run dev:build; node ./dist/cli/cli.js chat --model <path-to-model-file-on-your-computer>
+```
+
+Try telling the model `Hi there` and see how it reacts. Any response from the model means that your setup works.
+If the response looks weird or doesn't make sense, try using a different model.
+
+If the model doesn't stop generating output, try using a different chat wrapper. For example:
+```bash
+npx run dev:build; node ./dist/cli/cli.js chat --wrapper llamaChat --model <path-to-model-file-on-your-computer>
+```
+
+> **Important:** Make sure you always run `npm run dev:build` before running the CLI to make sure that your code changes are reflected in the CLI.
+
+### Debugging
+To run a chat session with a debugger, configure your IDE to run the following command with a debugger:
+```bash
+node --loader ts-node/esm ./src/cli/cli.ts chat --model <path-to-model-file-on-your-computer>
+```
+
+## Opening a pull request
+To open a pull request, read the [CONTRIBUTING.md](https://github.com/withcatai/node-llama-cpp/blob/master/CONTRIBUTING.md) guidelines.

README.md

@@ -322,6 +322,9 @@ Options:
   -v, --version  Show version number                                                       [boolean]
 ```
 
+## Contributing
+To contribute to `node-llama-cpp` read [CONTRIBUTING.md](https://github.com/withcatai/node-llama-cpp/blob/master/DEVELOPMENT.md).
+
 ## Acknowledgements
 * llama.cpp: [ggerganov/llama.cpp](https://github.com/ggerganov/llama.cpp)