yujunjun/autogen
1
0
Fork 0
mirror of https://github.com/microsoft/autogen.git synced 2025-11-16 10:04:36 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md for improved clarity and formatting (#5714)

Browse Source 
This pull request includes updates to the `README.md` file for the
`autogen-studio` package to improve clarity and accuracy. The most
important changes include a minor rewrite of the project structure
section and updates to the installation instructions (better tabbing).
This commit is contained in:
gagb 2025-02-25 19:28:05 -08:00 committed by GitHub
parent b37c192424
commit 173e649aa6
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 25 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

50
python/packages/autogen-studio/README.md
View File

@ -18,18 +18,18 @@ Code for AutoGen Studio is on GitHub at [microsoft/autogen](https://github.com/m
- **2024-04-17:** April 17: AutoGen Studio database layer is now rewritten to use [SQLModel](https://sqlmodel.tiangolo.com/) (Pydantic + SQLAlchemy). This provides entity linking (skills, models, agents and workflows are linked via association tables) and supports multiple [database backend dialects](https://docs.sqlalchemy.org/en/20/dialects/) supported in SQLAlchemy (SQLite, PostgreSQL, MySQL, Oracle, Microsoft SQL Server). The backend database can be specified a `--database-uri` argument when running the application. For example, `autogenstudio ui --database-uri sqlite:///database.sqlite` for SQLite and `autogenstudio ui --database-uri postgresql+psycopg://user:password@localhost/dbname` for PostgreSQL. - **2024-04-17:** April 17: AutoGen Studio database layer is now rewritten to use [SQLModel](https://sqlmodel.tiangolo.com/) (Pydantic + SQLAlchemy). This provides entity linking (skills, models, agents and workflows are linked via association tables) and supports multiple [database backend dialects](https://docs.sqlalchemy.org/en/20/dialects/) supported in SQLAlchemy (SQLite, PostgreSQL, MySQL, Oracle, Microsoft SQL Server). The backend database can be specified a `--database-uri` argument when running the application. For example, `autogenstudio ui --database-uri sqlite:///database.sqlite` for SQLite and `autogenstudio ui --database-uri postgresql+psycopg://user:password@localhost/dbname` for PostgreSQL.
- **2024-03-12:** Default directory for AutoGen Studio is now /home/\<USER\>/.autogenstudio. You can also specify this directory using the `--appdir` argument when running the application. For example, `autogenstudio ui --appdir /path/to/folder`. This will store the database and other files in the specified directory e.g. `/path/to/folder/database.sqlite`. `.env` files in that directory will be used to set environment variables for the app. - **2024-03-12:** Default directory for AutoGen Studio is now /home/\<USER\>/.autogenstudio. You can also specify this directory using the `--appdir` argument when running the application. For example, `autogenstudio ui --appdir /path/to/folder`. This will store the database and other files in the specified directory e.g. `/path/to/folder/database.sqlite`. `.env` files in that directory will be used to set environment variables for the app.
Project Structure: ## Project Structure:
- _autogenstudio/_ code for the backend classes and web api (FastAPI) - `autogenstudio/` contains code for the backend classes and web api (FastAPI)
- _frontend/_ code for the webui, built with Gatsby and TailwindCSS - `frontend/` contains code for the webui, built with Gatsby and TailwindCSS
## Installation ## Installation
There are two ways to install AutoGen Studio - from PyPi or from source. We **recommend installing from PyPi** unless you plan to modify the source code. There are two ways to install AutoGen Studio - from PyPi or from the source. We **recommend installing from PyPi** unless you plan to modify the source code.
### Install from PyPi (Recommended) ### Install from PyPi (Recommended)
We recommend using a virtual environment (e.g., conda) to avoid conflicts with existing Python packages. With Python 3.10 or newer active in your virtual environment, use pip to install AutoGen Studio: We recommend using a virtual environment (e.g., venv) to avoid conflicts with existing Python packages. With Python 3.10 or newer active in your virtual environment, use pip to install AutoGen Studio:
```bash ```bash
pip install -U autogenstudio pip install -U autogenstudio
@ -43,31 +43,31 @@ You have two options for installing from source: manually or using a dev contain
#### A) Install from source manually #### A) Install from source manually
1. Ensure you have Python 3.10+ and Node.js (version above 14.15.0) installed. 1. Ensure you have Python 3.10+ and Node.js (version above 14.15.0) installed.
2. Clone the AutoGen Studio repository and install its Python dependencies using `pip install -e .` 2. Clone the AutoGen Studio repository and install its Python dependencies using `pip install -e .`
3. Navigate to the `python/packages/autogen-studio/frontend` directory, install the dependencies, and build the UI: 3. Navigate to the `python/packages/autogen-studio/frontend` directory, install the dependencies, and build the UI:
```bash ```bash
npm install -g gatsby-cli npm install -g gatsby-cli
npm install --global yarn npm install --global yarn
cd frontend cd frontend
yarn install yarn install
yarn build yarn build
# Windows users may need alternative commands to build the frontend: # Windows users may need alternative commands to build the frontend:
gatsby clean && rmdir /s /q ..\\autogenstudio\\web\\ui 2>nul & (set \"PREFIX_PATH_VALUE=\" || ver>nul) && gatsby build --prefix-paths && xcopy /E /I /Y public ..\\autogenstudio\\web\\ui gatsby clean && rmdir /s /q ..\\autogenstudio\\web\\ui 2>nul & (set \"PREFIX_PATH_VALUE=\" || ver>nul) && gatsby build --prefix-paths && xcopy /E /I /Y public ..\\autogenstudio\\web\\ui
``` ```
#### B) Install from source using a dev container #### B) Install from source using a dev container
1. Follow the [Dev Containers tutorial](https://code.visualstudio.com/docs/devcontainers/tutorial) to install VS Code, Docker and relevant extensions. 1. Follow the [Dev Containers tutorial](https://code.visualstudio.com/docs/devcontainers/tutorial) to install VS Code, Docker and relevant extensions.
2. Clone the AutoGen Studio repository. 2. Clone the AutoGen Studio repository.
3. Open `python/packages/autogen-studio/`in VS Code. Click the blue button in bottom the corner or press F1 and select _"Dev Containers: Reopen in Container"_. 3. Open `python/packages/autogen-studio/`in VS Code. Click the blue button in bottom the corner or press F1 and select _"Dev Containers: Reopen in Container"_.
4. Build the UI: 4. Build the UI:
```bash ```bash
cd frontend cd frontend
yarn build yarn build
``` ```
### Running the Application ### Running the Application