Toolkit is a deployable all-in-one RAG application that enables users to quickly build their LLM-based product.

• Try Toolkit
• About Toolkit
• Toolkit Setup
• Troubleshooting
• How to guides
  • How to set up command model providers
  • How to add tools
  • How to add auth to your tools
  • How to setup Google Drive
  • How to setup Slack Tool
  • How to setup Google Text-to-Speech
  • How to add authentication
  • How to deploy toolkit services
  • How to set up Github Actions for automated DB migrations
  • How to customize the theme
  • How to contribute
• Try Cohere's Command Showcase

There are two main ways for quickly running Toolkit: local and cloud. See the specific instructions given below.

You will need to have Docker and Docker-compose >= 2.22 installed. Go here for a more detailed setup.
Note: to include community tools when building locally, set the INSTALL_COMMUNITY_DEPS build arg in the docker-compose.yml to true.

Both options will make the frontend available at http://localhost:4000.

Use the provided Makefile to simplify and automate your development workflow with Cohere Toolkit, including Docker Compose management, testing, linting, and environment setup.

git clone https://github.com/cohere-ai/cohere-toolkit.git
cd cohere-toolkit
make first-run

Use Docker Compose directly if you want to quickly spin up and manage your container environment without the additional automation provided by the Makefile.

git clone https://github.com/cohere-ai/cohere-toolkit.git
cd cohere-toolkit
docker compose up
docker compose run --build backend alembic -c src/backend/alembic.ini upgrade head

To run this project using GitHub Codespaces, please refer to our Codespaces Setup Guide.

• Interfaces - any client-side UI, currently contains a web app and Slack bot.
  • Defaults to Cohere's Web UI at src/interfaces/coral_web - A web app built in Next.js. Includes a simple SQL database out of the box to store conversation history in the app.
  • You can turn on the Assistants view that uses src/interfaces/assistants_web instead.
• Backend API - in src/backend this follows a similar structure to the Cohere Chat API but also include customizable elements:
  • Model - you can customize with which provider you access Cohere's Command models. By default included in the toolkit is Cohere's Platform, Sagemaker, Azure, Bedrock, HuggingFace, local models. More details here.
  • Retrieval- you can customize tools and data sources that the application is run with.
• Service Deployment Guides - we also include guides for how to deploy the toolkit services in production including with AWS, GCP and Azure. More details here.

Contributions are what drive an open source community, any contributions made are greatly appreciated. To get started, check out our documentation.

Made with contrib.rocks.