rasa-sdk

What it is and what it does

Rasa SDK is a Python library that lets you write custom actions—discrete business logic units—that Rasa conversational AI systems can call during dialogue. When a chatbot or voice assistant needs to query a database, call an API, validate user input, or perform any custom computation, you implement an Action subclass and deploy it as a server that Rasa communicates with over HTTP or gRPC. The SDK handles the protocol layer, letting you focus on the action logic itself.

The package is built on Sanic (a web framework), gRPC, and OpenTelemetry, and is designed to run as a separate microservice alongside your Rasa deployment. It's actively maintained, supports modern Python versions, and integrates with the broader Rasa ecosystem for NLU, dialogue management, and channel connectors (Slack, Facebook, etc.). The framework is production-stable and used in commercial deployments.

Use it for:

• Build a customer support chatbot that queries a ticket database or CRM when users ask about their account status.
• Implement a booking assistant that validates dates, checks availability, and integrates with a reservation system.
• Create a voice assistant that fetches real-time data (weather, stock prices, news) from external APIs during conversation.
• Deploy a multi-turn dialogue system that performs form validation, payment processing, or authentication before confirming user requests.
• Extend a conversational AI with custom NLP preprocessing or post-processing logic specific to your domain.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Rasa SDK provides a Python framework for developing custom actions that extend Rasa conversational AI systems, enabling integration of business logic and external services into chatbots and voice assistants.

Yes. Rasa SDK is worth installing if you are building a Rasa-based chatbot or voice assistant and need custom business logic beyond Rasa's built-in capabilities. It has low install friction, active maintenance, no known vulnerabilities, permissive licensing, and is production-stable. Install it only if you plan to deploy custom actions; if you're using Rasa's pre-built connectors and dialogue flows alone, you don't need it.

Install

rasa-sdk on PyPI

pip install rasa-sdk

uv add rasa-sdk

poetry add rasa-sdk

Installing rasa-sdk

Before you install

Low install friction with a pure-Python wheel distribution. Active maintenance with a release 25 days ago and commits through August 2026. Supports current Python versions (3.10–3.13) and has 15 runtime dependencies including Sanic, gRPC, and OpenTelemetry, all standard ecosystem packages.

License in practice

Licensed under Apache-2.0 (permissive), allowing commercial use, modification, and distribution with minimal restrictions. Suitable for proprietary projects when you include the license notice.

Quickstart

pip install rasa-sdk

from rasa_sdk import Action, ActionExecutor
from rasa_sdk.interfaces import ActionValueError

class CustomAction(Action):
    def name(self) -> str:
        return "action_custom"
    def run(self, dispatcher, tracker, domain):
        dispatcher.utter_message(text="Hello")
        return []

Requires Python 3.10 or later (3.14+ not supported). Custom actions are typically deployed as a separate action server process communicating with Rasa via HTTP/gRPC.

Verify before relying

• Specific version compatibility matrix between rasa-sdk 3.18.0 and Rasa core versions beyond the general 1.0.x guidance in the description.
• Performance characteristics or throughput limits when running action servers with many concurrent requests.
• Whether all 15 runtime dependencies are required for basic usage or if some are optional for specific features.

Package facts

Evidence: rasa_sdk-3.18.0-py3-none-any.whl

Keywords: nlp, machine-learning, machine-learning-library, bot, bots, botkit, rasa conversational-agents, conversational-ai, chatbot, chatbot-framework, bot-framework

Tags

More Libraries packages