opaiui 0.8.0

Opinionated Pydantic.AI User Interface

opaiui: Opinionated Pydantic.AI User Interface

Opaiui (oh-pie-you-eye) provides a simple but flexible Streamlit user interface for Pydantic.AI agents. The following features are supported:

• Streaming responses
• Realtime tool-calling status display
• Agent selection
• Shareable sessions (Upstash key required)
• Customizable sidebar user interface
• In-chat rendering of streamlit components via agent tool call
• Toggleable full message context

Installation

Usage

An opaiui application consists of:

1. A list of AgentConfig objects, each specifying:

2. Basic agent metadata, such as avatar and initial greeting

3. A Pydantic.AI agent, with or without tools (including MCP)

4. A deps object to use with the agent, as described by Pydantic.AI. The deps may also be used to store agent state

5. A sidebar function for agent-specific sidebar rendering

6. An AppConfig, specifying:

7. Global page metadata, such as tab title and icon

8. A set of Streamlit-based rendering functions, which an agent may execute to display widgets

Basic Application

We'll start with some imports and a basic agent, assuming we have a defined OPENAI_API_KEY in .env (or the key stored in an environment variable or secret, if deploying in the cloud).

from pydantic_ai import Agent
from opaiui import AgentConfig, AppConfig, AgentState
from opaiui.app import call_render_func
import streamlit as st
import dotenv

# put OPENAI_API_KEY=<key> in .env
dotenv.load_dotenv()

basic_agent = Agent('openai:gpt-4o')

We can optionally define a function to render a sidebar component for the agent when active. This function must be async, and take a deps (which will be passed from the agent deps, see below).

async def agent_sidebar(deps):
    st.markdown("", allow_unsafe_html = True)

If we like, we could define multiple agents, and a unique sidebar rendering function for each. To use them with the app, we collect them into a dictionary of AgentConfigs. Keys are used for identifying the agent by name in the UI:

agent_configs = {
    "Basic Agent": AgentConfig(
        agent = basic_agent,
        deps = None,
        description = "A basic agent.",

    )
}

Changelog

• 0.8.0: First public release