Skip to content

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

docs(online/offline): #8887 Move to a single source of truth for docs — Remove duplicate info from backend readme[.advanced].md (#9580)

MK4070fa97632eaede
diff --git a/autogpt_platform/backend/README.advanced.md b/autogpt_platform/backend/README.advanced.md
index 09e0f90fcc..5d5333e134 100644
--- a/autogpt_platform/backend/README.advanced.md
+++ b/autogpt_platform/backend/README.advanced.md
@@ -1,75 +1 @@
-# AutoGPT Agent Server Advanced set up
-
-This guide walks you through a dockerized set up, with an external DB (postgres)
-
-## Setup
-
-We use the Poetry to manage the dependencies. To set up the project, follow these steps inside this directory:
-
-0. Install Poetry
- ```sh
- pip install poetry
- ```
-
-1. Configure Poetry to use .venv in your project directory
- ```sh
- poetry config virtualenvs.in-project true
- ```
-
-2. Enter the poetry shell
-
- ```sh
- poetry shell
- ```
-
-3. Install dependencies
-
- ```sh
- poetry install
- ```
-
-4. Copy .env.example to .env
-
- ```sh
- cp .env.example .env
- ```
-
-5. Generate the Prisma client
-
- ```sh
- poetry run prisma generate
- ```
-
-
- > In case Prisma generates the client for the global Python installation instead of the virtual environment, the current mitigation is to just uninstall the global Prisma package:
- >
- > ```sh
- > pip uninstall prisma
- > ```
- >
- > Then run the generation again. The path *should* look something like this:
- > `<some path>/pypoetry/virtualenvs/backend-TQIRSwR6-py3.12/bin/prisma`
-
-6. Run the postgres database from the /rnd folder
-
- ```sh
- cd autogpt_platform/
- docker compose up -d
- ```
-
-7. Run the migrations (from the backend folder)
-
- ```sh
- cd ../backend
- prisma migrate deploy
- ```
-
-## Running The Server
-
-### Starting the server directly
-
-Run the following command:
-
-```sh
-poetry run app
-```
+[Advanced Setup (Dev Branch)](https://dev-docs.agpt.co/platform/advanced_setup/#autogpt_agent_server_advanced_set_up)
\ No newline at end of file
diff --git a/autogpt_platform/backend/README.md b/autogpt_platform/backend/README.md
index 18969d9d24..d8c275e7b6 100644
--- a/autogpt_platform/backend/README.md
+++ b/autogpt_platform/backend/README.md
@@ -1,210 +1 @@
-# AutoGPT Agent Server
-
-This is an initial project for creating the next generation of agent execution, which is an AutoGPT agent server.
-The agent server will enable the creation of composite multi-agent systems that utilize AutoGPT agents and other non-agent components as its primitives.
-
-## Docs
-
-You can access the docs for the [AutoGPT Agent Server here](https://docs.agpt.co/server/setup).
-
-## Setup
-
-We use the Poetry to manage the dependencies. To set up the project, follow these steps inside this directory:
-
-0. Install Poetry
- ```sh
- pip install poetry
- ```
-
-1. Configure Poetry to use .venv in your project directory
- ```sh
- poetry config virtualenvs.in-project true
- ```
-
-2. Enter the poetry shell
-
- ```sh
- poetry shell
- ```
-
-3. Install dependencies
-
- ```sh
- poetry install
- ```
-
-4. Copy .env.example to .env
-
- ```sh
- cp .env.example .env
- ```
-
-5. Generate the Prisma client
-
- ```sh
- poetry run prisma generate
- ```
-
-
- > In case Prisma generates the client for the global Python installation instead of the virtual environment, the current mitigation is to just uninstall the global Prisma package:
- >
- > ```sh
- > pip uninstall prisma
- > ```
- >
- > Then run the generation again. The path *should* look something like this:
- > `<some path>/pypoetry/virtualenvs/backend-TQIRSwR6-py3.12/bin/prisma`
-
-6. Migrate the database. Be careful because this deletes current data in the database.
-
- ```sh
- docker compose up db -d
- poetry run prisma migrate deploy
- ```
-
-## Running The Server
-
-### Starting the server without Docker
-
-To run the server locally, start in the autogpt_platform folder:
-
-```sh
-cd ..
-```
-
-Run the following command to run database in docker but the application locally:
-
-```sh
-docker compose --profile local up deps --build --detach
-cd backend
-poetry run app
-```
-
-### Starting the server with Docker
-
-Run the following command to build the dockerfiles:
-
-```sh
-docker compose build
-```
-
-Run the following command to run the app:
-
-```sh
-docker compose up
-```
-
-Run the following to automatically rebuild when code changes, in another terminal:
-
-```sh
-docker compose watch
-```
-
-Run the following command to shut down:
-
-```sh
-docker compose down
-```
-
-If you run into issues with dangling orphans, try:
-
-```sh
-docker compose down --volumes --remove-orphans && docker-compose up --force-recreate --renew-anon-volumes --remove-orphans
-```
-
-## Testing
-
-To run the tests:
-
-```sh
-poetry run test
-```
-
-## Development
-
-### Formatting & Linting
-Auto formatter and linter are set up in the project. To run them:
-
-Install:
-```sh
-poetry install --with dev
-```
-
-Format the code:
-```sh
-poetry run format
-```
-
-Lint the code:
-```sh
-poetry run lint
-```
-
-## Project Outline
-
-The current project has the following main modules:
-
-### **blocks**
-
-This module stores all the Agent Blocks, which are reusable components to build a graph that represents the agent's behavior.
-
-### **data**
-
-This module stores the logical model that is persisted in the database.
-It abstracts the database operations into functions that can be called by the service layer.
-Any code that interacts with Prisma objects or the database should reside in this module.
-The main models are:
-* `block`: anything related to the block used in the graph
-* `execution`: anything related to the execution graph execution
-* `graph`: anything related to the graph, node, and its relations
-
-### **execution**
-
-This module stores the business logic of executing the graph.
-It currently has the following main modules:
-* `manager`: A service that consumes the queue of the graph execution and executes the graph. It contains both pieces of logic.
-* `scheduler`: A service that triggers scheduled graph execution based on a cron expression. It pushes an execution request to the manager.
-
-### **server**
-
-This module stores the logic for the server API.
-It contains all the logic used for the API that allows the client to create, execute, and monitor the graph and its execution.
-This API service interacts with other services like those defined in `manager` and `scheduler`.
-
-### **utils**
-
-This module stores utility functions that are used across the project.
-Currently, it has two main modules:
-* `process`: A module that contains the logic to spawn a new process.
-* `service`: A module that serves as a parent class for all the services in the project.
-
-## Service Communication
-
-Currently, there are only 3 active services:
-
-- AgentServer (the API, defined in `server.py`)
-- ExecutionManager (the executor, defined in `manager.py`)
-- ExecutionScheduler (the scheduler, defined in `scheduler.py`)
-
-The services run in independent Python processes and communicate through an IPC.
-A communication layer (`service.py`) is created to decouple the communication library from the implementation.
-
-Currently, the IPC is done using Pyro5 and abstracted in a way that allows a function decorated with `@expose` to be called from a different process.
-
-
-By default the daemons run on the following ports:
-
-Execution Manager Daemon: 8002
-Execution Scheduler Daemon: 8003
-Rest Server Daemon: 8004
-
-## Adding a New Agent Block
-
-To add a new agent block, you need to create a new class that inherits from `Block` and provides the following information:
-* All the block code should live in the `blocks` (`backend.blocks`) module.
-* `input_schema`: the schema of the input data, represented by a Pydantic object.
-* `output_schema`: the schema of the output data, represented by a Pydantic object.
-* `run` method: the main logic of the block.
-* `test_input` & `test_output`: the sample input and output data for the block, which will be used to auto-test the block.
-* You can mock the functions declared in the block using the `test_mock` field for your unit tests.
-* Once you finish creating the block, you can test it by running `poetry run pytest -s test/block/test_block.py`.
+[Getting Started (Released)](https://docs.agpt.co/platform/getting-started/#autogpt_agent_server)
\ No newline at end of file
diff --git a/docs/content/platform/advanced_setup.md b/docs/content/platform/advanced_setup.md
index cfe8f9ae9b..2d6827fa0a 100644
--- a/docs/content/platform/advanced_setup.md
+++ b/docs/content/platform/advanced_setup.md
@@ -64,3 +64,79 @@ You can then run the migrations from the `backend` directory.
cd ../backend
prisma migrate dev --schema postgres/schema.prisma
```
+
+## AutoGPT Agent Server Advanced set up
+
+This guide walks you through a dockerized set up, with an external DB (postgres)
+
+### Setup
+
+We use the Poetry to manage the dependencies. To set up the project, follow these steps inside this directory:
+
+0. Install Poetry
+ ```sh
+ pip install poetry
+ ```
+
+1. Configure Poetry to use .venv in your project directory
+ ```sh
+ poetry config virtualenvs.in-project true
+ ```
+
+2. Enter the poetry shell
+
+ ```sh
+ poetry shell
+ ```
+
+3. Install dependencies
+
+ ```sh
+ poetry install
+ ```
+
+4. Copy .env.example to .env
+
+ ```sh
+ cp .env.example .env
+ ```
+
+5. Generate the Prisma client
+
+ ```sh
+ poetry run prisma generate
+ ```
+
+
+ > In case Prisma generates the client for the global Python installation instead of the virtual environment, the current mitigation is to just uninstall the global Prisma package:
+ >
+ > ```sh
+ > pip uninstall prisma
+ > ```
+ >
+ > Then run the generation again. The path *should* look something like this:
+ > `<some path>/pypoetry/virtualenvs/backend-TQIRSwR6-py3.12/bin/prisma`
+
+6. Run the postgres database from the /rnd folder
+
+ ```sh
+ cd autogpt_platform/
+ docker compose up -d
+ ```
+
+7. Run the migrations (from the backend folder)
+
+ ```sh
+ cd ../backend
+ prisma migrate deploy
+ ```
+
+### Running The Server
+
+#### Starting the server directly
+
+Run the following command:
+
+```sh
+poetry run app
+```
diff --git a/docs/content/platform/getting-started.md b/docs/content/platform/getting-started.md
index 7ec256c9d4..16c82bae30 100644
--- a/docs/content/platform/getting-started.md
+++ b/docs/content/platform/getting-started.md
@@ -23,7 +23,7 @@ To setup the server, you need to have the following installed:
- [Docker](https://docs.docker.com/get-docker/)
- [Git](https://git-scm.com/downloads)
-#### Checking if you have Node.js & NPM installed
+### Checking if you have Node.js & NPM installed
We use Node.js to run our frontend application.
@@ -42,7 +42,7 @@ npm -v
Once you have Node.js installed, you can proceed to the next step.
-#### Checking if you have Docker & Docker Compose installed
+### Checking if you have Docker & Docker Compose installed
Docker containerizes applications, while Docker Compose orchestrates multi-container Docker applications.
@@ -61,6 +61,8 @@ docker compose -v
Once you have Docker and Docker Compose installed, you can proceed to the next step.
+## Setup
+
### Cloning the Repository
The first step is cloning the AutoGPT repository to your computer.
To do this, open a terminal window in a folder on your computer and run:
@@ -129,7 +131,7 @@ Frontend UI Server: 3000
Backend Websocket Server: 8001
Execution API Rest Server: 8006
-#### Additional Notes
+### Additional Notes
You may want to change your encryption key in the `.env` file in the `autogpt_platform/backend` directory.
@@ -146,3 +148,214 @@ poetry run cli gen-encrypt-key
```
Then, replace the existing key in the `autogpt_platform/backend/.env` file with the new one.
+
+!!! Note
+ *The steps below are an alternative to [Running the backend services](#running-the-backend-services)*
+
+<details>
+<summary><strong>Alternate Steps</strong></summary>
+
+#### AutoGPT Agent Server (OLD)
+This is an initial project for creating the next generation of agent execution, which is an AutoGPT agent server.
+The agent server will enable the creation of composite multi-agent systems that utilize AutoGPT agents and other non-agent components as its primitives.
+
+##### Docs
+
+You can access the docs for the [AutoGPT Agent Server here](https://docs.agpt.co/#1-autogpt-server).
+
+##### Setup
+
+We use the Poetry to manage the dependencies. To set up the project, follow these steps inside this directory:
+
+0. Install Poetry
+
+```sh
+pip install poetry
+```
+
+1. Configure Poetry to use .venv in your project directory
+
+```sh
+ poetry config virtualenvs.in-project true
+```
+
+2. Enter the poetry shell
+
+```sh
+poetry shell
+```
+
+3. Install dependencies
+
+```sh
+poetry install
+```
+
+4. Copy .env.example to .env
+
+```sh
+cp .env.example .env
+```
+
+5. Generate the Prisma client
+
+```sh
+poetry run prisma generate
+```
+
+> In case Prisma generates the client for the global Python installation instead of the virtual environment, the current mitigation is to just uninstall the global Prisma package:
+>
+> ```sh
+> pip uninstall prisma
+> ```
+>
+> Then run the generation again. The path *should* look something like this:
+> `<some path>/pypoetry/virtualenvs/backend-TQIRSwR6-py3.12/bin/prisma`
+
+6. Migrate the database. Be careful because this deletes current data in the database.
+
+```sh
+docker compose up db -d
+poetry run prisma migrate deploy
+```
+
+</details>
+
+
+### Starting the AutoGPT server without Docker
+
+To run the server locally, start in the autogpt_platform folder:
+
+```sh
+cd ..
+```
+
+Run the following command to run database in docker but the application locally:
+
+```sh
+docker compose --profile local up deps --build --detach
+cd backend
+poetry run app
+```
+
+### Starting the AutoGPT server with Docker
+
+Run the following command to build the dockerfiles:
+
+```sh
+docker compose build
+```
+
+Run the following command to run the app:
+
+```sh
+docker compose up
+```
+
+Run the following to automatically rebuild when code changes, in another terminal:
+
+```sh
+docker compose watch
+```
+
+Run the following command to shut down:
+
+```sh
+docker compose down
+```
+
+If you run into issues with dangling orphans, try:
+
+```sh
+docker compose down --volumes --remove-orphans && docker-compose up --force-recreate --renew-anon-volumes --remove-orphans
+```
+
+## Development
+
+### Formatting & Linting
+Auto formatter and linter are set up in the project. To run them:
+
+Install:
+```sh
+poetry install --with dev
+```
+
+Format the code:
+```sh
+poetry run format
+```
+
+Lint the code:
+```sh
+poetry run lint
+```
+
+### Testing
+
+To run the tests:
+
+```sh
+poetry run test
+```
+
+## Project Outline
+
+The current project has the following main modules:
+
+#### **blocks**
+
+This module stores all the Agent Blocks, which are reusable components to build a graph that represents the agent's behavior.
+
+#### **data**
+
+This module stores the logical model that is persisted in the database.
+It abstracts the database operations into functions that can be called by the service layer.
+Any code that interacts with Prisma objects or the database should reside in this module.
+The main models are:
+* `block`: anything related to the block used in the graph
+* `execution`: anything related to the execution graph execution
+* `graph`: anything related to the graph, node, and its relations
+
+#### **execution**
+
+This module stores the business logic of executing the graph.
+It currently has the following main modules:
+* `manager`: A service that consumes the queue of the graph execution and executes the graph. It contains both pieces of logic.
+* `scheduler`: A service that triggers scheduled graph execution based on a cron expression. It pushes an execution request to the manager.
+
+#### **server**
+
+This module stores the logic for the server API.
+It contains all the logic used for the API that allows the client to create, execute, and monitor the graph and its execution.
+This API service interacts with other services like those defined in `manager` and `scheduler`.
+
+#### **utils**
+
+This module stores utility functions that are used across the project.
+Currently, it has two main modules:
+* `process`: A module that contains the logic to spawn a new process.
+* `service`: A module that serves as a parent class for all the services in the project.
+
+## Service Communication
+
+Currently, there are only 3 active services:
+
+- AgentServer (the API, defined in `server.py`)
+- ExecutionManager (the executor, defined in `manager.py`)
+- ExecutionScheduler (the scheduler, defined in `scheduler.py`)
+
+The services run in independent Python processes and communicate through an IPC.
+A communication layer (`service.py`) is created to decouple the communication library from the implementation.
+
+Currently, the IPC is done using Pyro5 and abstracted in a way that allows a function decorated with `@expose` to be called from a different process.
+
+## Adding a New Agent Block
+
+To add a new agent block, you need to create a new class that inherits from `Block` and provides the following information:
+* All the block code should live in the `blocks` (`backend.blocks`) module.
+* `input_schema`: the schema of the input data, represented by a Pydantic object.
+* `output_schema`: the schema of the output data, represented by a Pydantic object.
+* `run` method: the main logic of the block.
+* `test_input` & `test_output`: the sample input and output data for the block, which will be used to auto-test the block.
+* You can mock the functions declared in the block using the `test_mock` field for your unit tests.
+* Once you finish creating the block, you can test it by running `poetry run pytest -s test/block/test_block.py`.