### Changes 🏗️ Instead of parsing an LlmMessage by ourselves, we use raw content from the LLM as conversation history and accept any format it introduces. Example output: ``` [ { "role": "system", "content": "Thinking carefully step by step decide which function to call. Always choose a function call from the list of function signatures. The test graph is basically an all knowing answer machine you can use it to get an answer" }, { "role": "user", "content": "Hey how's the weather today" }, { "role": "assistant", "audio": null, "content": null, "refusal": null, "tool_calls": [ { "id": "call_Z7CKKIkldylmfWJdE6ZnDxjr", "type": "function", "function": { "name": "storevalueblock", "arguments": "{\"input\":\"I don't have context for your location. Could you provide one?\"}" } } ], "function_call": null } ] ``` ### Checklist 📋 #### For code changes: - [ ] I have clearly listed my changes in the PR description - [ ] I have made a test plan - [ ] I have tested my changes according to the test plan: <!-- Put your test plan here: --> - [ ] ... <details> <summary>Example test plan</summary> - [ ] Create from scratch and execute an agent with at least 3 blocks - [ ] Import an agent from file upload, and confirm it executes correctly - [ ] Upload agent to marketplace - [ ] Import an agent from marketplace and confirm it executes correctly - [ ] Edit an agent from monitor, and confirm it executes correctly </details> #### For configuration changes: - [ ] `.env.example` is updated or already compatible with my changes - [ ] `docker-compose.yml` is updated or already compatible with my changes - [ ] I have included a list of my configuration changes in the PR description (under **Changes**) <details> <summary>Examples of configuration changes</summary> - Changing ports - Adding new services that need to communicate with each other - Secrets or environment variable changes - New or infrastructure changes such as databases </details>
AutoGPT Platform
Welcome to the AutoGPT Platform - a powerful system for creating and running AI agents to solve business problems. This platform enables you to harness the power of artificial intelligence to automate tasks, analyze data, and generate insights for your organization.
Getting Started
Prerequisites
- Docker
- Docker Compose V2 (comes with Docker Desktop, or can be installed separately)
- Node.js & NPM (for running the frontend application)
Running the System
To run the AutoGPT Platform, follow these steps:
-
Clone this repository to your local machine and navigate to the
autogpt_platformdirectory within the repository:git clone <https://github.com/Significant-Gravitas/AutoGPT.git | git@github.com:Significant-Gravitas/AutoGPT.git> cd AutoGPT/autogpt_platform -
Run the following command:
git submodule update --init --recursive --progressThis command will initialize and update the submodules in the repository. The
supabasefolder will be cloned to the root directory. -
Run the following command:
cp supabase/docker/.env.example .envThis command will copy the
.env.examplefile to.envin thesupabase/dockerdirectory. You can modify the.envfile to add your own environment variables. -
Run the following command:
docker compose up -dThis command will start all the necessary backend services defined in the
docker-compose.ymlfile in detached mode. -
Navigate to
frontendwithin theautogpt_platformdirectory:cd frontendYou will need to run your frontend application separately on your local machine.
-
Run the following command:
cp .env.example .env.localThis command will copy the
.env.examplefile to.env.localin thefrontenddirectory. You can modify the.env.localwithin this folder to add your own environment variables for the frontend application. -
Run the following command:
npm install npm run devThis command will install the necessary dependencies and start the frontend application in development mode. If you are using Yarn, you can run the following commands instead:
yarn install && yarn dev -
Open your browser and navigate to
http://localhost:3000to access the AutoGPT Platform frontend.
Docker Compose Commands
Here are some useful Docker Compose commands for managing your AutoGPT Platform:
docker compose up -d: Start the services in detached mode.docker compose stop: Stop the running services without removing them.docker compose rm: Remove stopped service containers.docker compose build: Build or rebuild services.docker compose down: Stop and remove containers, networks, and volumes.docker compose watch: Watch for changes in your services and automatically update them.
Sample Scenarios
Here are some common scenarios where you might use multiple Docker Compose commands:
-
Updating and restarting a specific service:
docker compose build api_srv docker compose up -d --no-deps api_srvThis rebuilds the
api_srvservice and restarts it without affecting other services. -
Viewing logs for troubleshooting:
docker compose logs -f api_srv ws_srvThis shows and follows the logs for both
api_srvandws_srvservices. -
Scaling a service for increased load:
docker compose up -d --scale executor=3This scales the
executorservice to 3 instances to handle increased load. -
Stopping the entire system for maintenance:
docker compose stop docker compose rm -f docker compose pull docker compose up -dThis stops all services, removes containers, pulls the latest images, and restarts the system.
-
Developing with live updates:
docker compose watchThis watches for changes in your code and automatically updates the relevant services.
-
Checking the status of services:
docker compose psThis shows the current status of all services defined in your docker-compose.yml file.
These scenarios demonstrate how to use Docker Compose commands in combination to manage your AutoGPT Platform effectively.
Persisting Data
To persist data for PostgreSQL and Redis, you can modify the docker-compose.yml file to add volumes. Here's how:
-
Open the
docker-compose.ymlfile in a text editor. -
Add volume configurations for PostgreSQL and Redis services:
services: postgres: # ... other configurations ... volumes: - postgres_data:/var/lib/postgresql/data redis: # ... other configurations ... volumes: - redis_data:/data volumes: postgres_data: redis_data: -
Save the file and run
docker compose up -dto apply the changes.
This configuration will create named volumes for PostgreSQL and Redis, ensuring that your data persists across container restarts.