Skip to content

Commit

Permalink
Refactor setting up development environment
Browse files Browse the repository at this point in the history
  • Loading branch information
@kumaranvpl
kumaranvpl committed Jan 30, 2025
1 parent 84c3526 commit 3dbb20f
Showing 1 changed file with 113 additions and 49 deletions.
162 changes: 113 additions & 49 deletions website/contributor-guide/docker.mdx
View file
Original file line number Diff line number Diff line change
@@ -1,66 +1,130 @@
---
title: Setting up the Development Environment
title: Setting up Development Environment
---

## Setting up LLM Keys

If you are contributing to the AG2 project, you will need an LLM key depending on the submodule you are working on.

If you are working on OpenAI related code, you need to setup an environment variable called `OAI_CONFIG_LIST` in JSON format. Following is an example of the `OAI_CONFIG_LIST` environment variable:

```bash
export OAI_CONFIG_LIST='[{"model": "gpt-4o","api_key": "<your_api_key>","tags": ["gpt-4o", "tool", "vision"]},{"model": "gpt-4o-mini","api_key": "<your_api_key>","tags": ["gpt-4o-mini", "tool", "vision"]}]'
```

You need to add a separate entry for each OpenAI model you are using.
<Tabs>
<Tab title="Using OAI_CONFIG_LIST">
AG2 uses an environment variable called `OAI_CONFIG_LIST` in JSON format to store the LLM keys. `OAI_CONFIG_LIST` is a list of dictionaries where each dictionary contains the following keys:
- `model`(required): The name of the OpenAI/LLM model.
- `api_key`(optional): The API key for the OpenAI/LLM model.
- `api_type`(optional): The type of the API key. It is used for non-OpenAI LLMs.
- `api_version`(optional): The version of the API key. It is used for Azure API.
- `base_url`(optional): The base URL for the OpenAI/LLM model.
- `tags`(optional): A list of tags for the OpenAI/LLM model which can be used for filtering.

Following is an example of the `OAI_CONFIG_LIST` in JSON format which consists of two OpenAI models and a gemini model:
```bash
[
{
"model": "gpt-4o",
"api_key": "<your_api_key>",
"tags": ["gpt-4o", "tool", "vision"]
},
{
"model": "gpt-4o-mini",
"api_key": "<your_api_key>",
"tags": ["gpt-4o-mini", "tool", "vision"]
},
{
"model": "gemini-pro",
"api_key": "<your_gemini_api_key>",
}
]
```

If you are working on other LLMs such as Gemini, Anthropic, Together, etc., you need to setup an environment variable for the respective LLM's key. Following is an example of the environment variable for Gemini:
Further, this `OAI_CONFIG_LIST` can be set in two ways:
<Tabs>
<Tab title="As environment variable">
Simply set the `OAI_CONFIG_LIST` environment variable in your terminal:
```bash
export OAI_CONFIG_LIST='[{"model": "gpt-4o","api_key": "<your_api_key>","tags": ["gpt-4o", "tool", "vision"]},{"model": "gpt-4o-mini","api_key": "<your_api_key>","tags": ["gpt-4o-mini", "tool", "vision"]},{"model": "gemini-pro","api_key": "<your_gemini_api_key>",}]'
```
</Tab>
<Tab title="As file">
Or you can save the `OAI_CONFIG_LIST` in a file and set the path of the file as an environment variable.
For example, let's say you have saved the `OAI_CONFIG_LIST` in a file called `OAI_CONFIG_LIST.json` at the root of the project. You can set the `OAI_CONFIG_LIST` environment variable as follows:
```bash
export OAI_CONFIG_LIST="./OAI_CONFIG_LIST.json"
```
</Tab>
</Tabs>

<div class="tip">
<Tip>
Learn more about OAI_CONFIG_LIST
[here](/docs/topics/llm_configuration).
</Tip>
</div>
</Tab>
<Tab title="Using LLM keys directly">
Alternatively, you can set up the LLM keys directly as environment variables. Following is an example of setting up the Gemini api key as an environment variable:
```bash
export GEMINI_API_KEY="<your_api_key>"
```
</Tab>
</Tabs>

```bash
export GEMINI_API_KEY="<your_api_key>"
```

## Setting up the Development Environment

To contribute to the AG2 project, AG2 provides three different method to setup the development environment:

### Developing with Devcontainers

1. Setup the necessary LLM keys as mentioned above in your terminal.
2. Clone the AG2 repository and cd into the repository.
3. Open the project in Visual Studio Code by running the following command from the root of the repository:
```bash
code .
```
4. Press `Ctrl+Shift+P` and select `Dev Containers: Reopen in Container`.
5. Select the desired python environment and wait for the container to build.
6. Once the container is built, you can start developing AG2.
<Tabs>
<Tab title="Devcontainers">
1. Setup the necessary LLM keys as mentioned above in your terminal.
2. Clone the AG2 repository and cd into the repository.
3. Open the project in Visual Studio Code by running the following command from the root of the repository:
```bash
code .
```
4. Press `Ctrl+Shift+P` and select `Dev Containers: Reopen in Container`.
5. Select the desired python environment and wait for the container to build.
6. Once the container is built, you can start developing AG2.
</Tab>
<Tab title="Codespaces">
1. Open the AG2 repository on GitHub and fork the repository.
2. Navigate to Settings -> Secrets and variables -> Codespaces.
3. Add the necessary LLM keys as mentioned above by clicking on the `New repository secret` button.
4. Navigate back to the forked repository.
5. Click on the `Code` button and select `Open with Codespaces`.
6. Once the container is built, you can start developing AG2.
</Tab>
<Tab title="Virtual Environment">
1. Setup the necessary LLM keys as mentioned above in your terminal.
2. Fork the AG2 repository and clone the forked repository.
3. Create a virtual environment by running the following command from the root of the repository:
```bash
python3 -m venv venv
```
4. Activate the virtual environment by running the following command:
```bash
source venv/bin/activate
```
5. Install the required dependencies by running the following command:
```bash
pip install -e ".[dev]" && pre-commit install
```
6. Once the dependencies are installed, you can start developing AG2.
</Tab>
</Tabs>


## Verifying the Development Environment

To make sure that we have set up the development environment correctly, we can run the pre-commit hooks and tests.

To run the pre-commit hooks, run the following command:

### Developing with Codespaces

The provided devcontainer files can be used with GitHub Codespaces. To use the devcontainer with GitHub Codespaces, follow the steps below:

1. Open the AG2 repository on GitHub and fork the repository.
2. Navigate to Settings -> Secrets and variables -> Codespaces.
3. Add the necessary LLM keys as mentioned above by clicking on the `New repository secret` button.
4. Navigate back to the forked repository.
5. Click on the `Code` button and select `Open with Codespaces`.
6. Once the container is built, you can start developing AG2.
```bash
pre-commit run --all-files
```

### Developing with Virtual Environment
To run the non-llm tests, run the following command:

1. Setup the necessary LLM keys as mentioned above in your terminal.
2. Fork the AG2 repository and clone the forked repository.
3. Create a virtual environment by running the following command from the root of the repository:
```bash
python3 -m venv venv
```
4. Activate the virtual environment by running the following command:
```bash
source venv/bin/activate
```
5. Install the required dependencies by running the following command:
```bash
pip install -e ".[dev]"
```
6. Once the dependencies are installed, you can start developing AG2.
```bash
bash scripts/test-core-skip-llm.sh
```

0 comments on commit 3dbb20f

Please sign in to comment.