This is the first commit which provides all the first stack for a working chat. This is a first implementation with: - Vercel SDK for the frontend part - OpenAI Agent SDK for the backend The stack can use a local LLM with docker ot a remote one. This implementation is more a draft, but it provides the project structure. All tests are working even if we lack a lot of them.
Self-host
🚀 Conversations is easy to install on your own servers
Available methods: Helm chart, soon Nix package
In the works: Docker Compose, soon YunoHost
Getting started 🔧
Test it
You can test Conversations on your browser by visiting this => TBD
Run Docs locally
⚠️ The methods described below for running Docs locally is for testing purposes only. It is based on building Docs using Minio as an S3-compatible storage solution. Of course you can choose any S3-compatible storage solution.
Prerequisite
Make sure you have a recent version of Docker and Docker Compose installed on your laptop, then type:
$ docker -v
Docker version 20.10.2, build 2291f61
$ docker compose version
Docker Compose version v2.32.4
⚠️ You may need to run the following commands with
sudo, but this can be avoided by adding your user to the localdockergroup.
Project bootstrap
The easiest way to start working on the project is to use GNU Make:
$ make bootstrap FLUSH_ARGS='--no-input'
This command builds the app-dev and frontend-dev containers, installs dependencies, performs database migrations and compiles translations. It's a good idea to use this command each time you are pulling code from the project repository to avoid dependency-related or migration-related issues.
Your Docker services should now be up and running 🎉
You can access the project by going to http://localhost:3000.
You will be prompted to log in. The default credentials are:
username: conversations
password: conversations
📝 Note that if you need to run them afterwards, you can use the eponymous Make rule:
$ make run
⚠️ For the frontend developer, it is often better to run the frontend in development mode locally.
To do so, install the frontend dependencies with the following command:
$ make frontend-development-install
And run the frontend locally in development mode with the following command:
$ make run-frontend-development
To start all the services, except the frontend container, you can use the following command:
$ make run-backend
Adding content
You can create a basic demo site by running this command:
$ make demo
Finally, you can check all available Make rules using this command:
$ make help
Django admin
You can access the Django admin site at:
You first need to create a superuser account:
$ make superuser
Licence 📝
This work is released under the MIT License (see LICENSE).
While Conversations is a public-driven initiative, our licence choice is an invitation for private sector actors to use, sell and contribute to the project.
Contributing 🙌
You can help us with translations on Crowdin.
If you intend to make pull requests, see CONTRIBUTING for guidelines.
Directory structure:
docs
├── bin - executable scripts or binaries that are used for various tasks, such as setup scripts, utility scripts, or custom commands.
├── crowdin - for crowdin translations, a tool or service that helps manage translations for the project.
├── docker - Dockerfiles and related configuration files used to build Docker images for the project. These images can be used for development, testing, or production environments.
├── docs - documentation for the project, including user guides, API documentation, and other helpful resources.
├── env.d/development - environment-specific configuration files for the development environment. These files might include environment variables, configuration settings, or other setup files needed for development.
├── gitlint - configuration files for `gitlint`, a tool that enforces commit message guidelines to ensure consistency and quality in commit messages.
└── src - main source code directory, containing the core application code, libraries, and modules of the project.
Credits ❤️
Stack
Conversations is built on top of Django Rest Framework, Next.js, Vercel‘s AI SDK and OpenAI Agents SDK. We thank the contributors of all these projects for their awesome work!
