Streamlit is a great tool for building micro front-ends. You can use it to build user interfaces, internal dashboards or tools for internal use.

The streamlit-app template provides codebase with Streamlit & PostgreSQL, a stack we love for its simplicity. Its simple but not to be underestimated.



Create a virtual environment

Open the Terminal and create a python virtual environment.

python3 -m venv ~/.venvs/aienv
source ~/.venvs/aienv/bin/activate

Install phidata

Install phidata using pip

pip install -U "phidata[aws]"

Install docker

Install docker desktop to run your app locally

Create your codebase

Create your codebase using the streamlit-app template

phi ws create -t streamlit-app -n streamlit-app

This will create a folder streamlit-app with the following structure:

streamlit-app                 # root directory for your streamlit-app
├── ai                      # directory for AI components
    ├── assistants          # AI assistants
    ├──   # assistant knowledge base
    └──          # assistant storage
├── app                     # directory for Streamlit apps
├── db                      # directory for database components
├── Dockerfile              # Dockerfile for the application
├── pyproject.toml          # python project definition
├── requirements.txt        # python dependencies generated by pyproject.toml
├── scripts                 # directory for helper scripts
├── tests                   # directory for unit tests
├── utils                   # directory for shared utilities
└── workspace               # phidata workspace directory
    ├──    # dev resources running locally
    ├──    # production resources running on AWS
    ├── secrets             # directory for storing secrets
    └──         # phidata workspace settings

Set OpenAI Key

Set your OPENAI_API_KEY as an environment variable. You can get one from OpenAI.

export OPENAI_API_KEY=sk-***

Local Streamlit App

Streamlit allows us to build micro front-ends and is an extremely useful tool for building basic applications in pure python. Start your workspace using:

phi ws up

Press Enter to confirm and give a few minutes for the image to download (only the first time). Verify container status and view logs on the docker dashboard.

Follow these steps to only run Streamlit without Postgres.

PDF Assistant

  • Open localhost:8501 to view your AI Apps.
  • Click on PDF Assistant in the sidebar
  • Enter a username and wait for the knowledge base to load.
  • Ask "How do I make pad thai?"
  • Choose the RAG or Autonomous Assistant type.
  • Clear the knowledge base, upload your own PDF and ask questions

Chat with pdf

Image Assistant

  • Click on Image Assistant in the sidebar and upload an image of your choice.
  • Click on "Generate Caption" or "Describe Image" to explore multimodal capabilities.

Image assistant

Website Assistant

  • Click on Website Assistant in the sidebar and add a domain you'd like to chat with. For example:

  • Ask questions like what is phidata?

Website Assistant

If you run into issues, check the docker dashboard for logs or message us

Add your data

The PDF Assistant uses the pdf_knowledge_base defined in the ai/ file. To add your own PDFs:


Create a folder with your data

Create a folder data/pdfs in the root directory of your app


Add your data

Add your files to the data/pdfs folder


Update Knowledge Base

Click on the Update Knowledge Base button to load the knowledge base.

Checkout the ai/ file for more information.

How this App works

The streamlit apps are defined in the app folder and the Assistants powering these apps are defined in the ai/assistants folder. Checkout the files in the ai/assistants folder for more information.

Delete local resources

Play around and stop the workspace using:

phi ws down


Congratulations on running your Streamlit App locally. Next Steps: