Rasa
Official@rasahq · San Francisco
Rasa is a conversational AI framework for building reliable, scalable AI agents.
Agent Skills by Rasa
Showing 13 vetted skills indexed across 1 GitHub repositories.
RasaHQrasa-setting-up-enterprise-search
Configure Rasa assistants with EnterpriseSearchPolicy for vector store knowledge base search.
RasaHQrasa-configuring-model-groups
Configures model groups in endpoints.yml for LLM and embedding providers.
RasaHQrasa-configuring-mcp-server
Configure MCP servers for Rasa CALM assistants in endpoints.yml.
RasaHQrasa-rephrasing-responses
Configure the Contextual Response Rephraser in Rasa CALM via endpoints.yml.
RasaHQrasa-configuring-assistant
Configure Rasa CALM pipeline components, policies, and endpoints in config.yml and endpoints.yml.
RasaHQrasa-setting-up-a2a-agents
Connect external sub-agents to Rasa CALM assistants via the A2A protocol.
RasaHQrasa-writing-e2e-tests
Generate YAML end-to-end tests for Rasa CALM assistants.
RasaHQrasa-managing-slots
Configure slot types, mappings, and validation in Rasa CALM domain files.
RasaHQrasa-writing-responses
Generate structured Rasa response templates with variations and conditional logic in domain YAML files.
RasaHQrasa-setting-up-react-agents
Configure ReAct sub-agents in Rasa CALM with MCP tool filtering.
RasaHQrasa-building-flows
Create and modify Rasa CALM conversational flows using YAML.
RasaHQrasa-writing-custom-actions
Create custom Python actions for Rasa CALM assistants using the Rasa SDK.
RasaHQrasa-calling-mcp-tools-from-flows
Call MCP tools from Rasa flow steps with input and output mappings.
Frequently Asked Questions About Rasa
FAQPage SchemaWhat specific tasks can be performed using Rasa's conversational framework?▼
Rasa enables the construction of complex dialogue systems by defining conversational flows in YAML, managing slot validation, and configuring contextual response rephrasing. It supports integrating external knowledge bases via vector stores and connecting sub-agents through the A2A protocol to handle multi-step reasoning tasks.
Which technical personas are the primary users of this framework?▼
The framework is designed for conversational engineers, backend developers, and machine learning practitioners. These professionals utilize the system to configure pipeline components, manage stateful slot mappings, and implement custom logic for enterprise-grade dialogue systems requiring high reliability and scalable sub-agent orchestration.
What are the core prerequisites for deploying a Rasa-based assistant?▼
Deployment requires a configured environment with defined endpoints.yml and config.yml files to manage pipeline components and model groups. Users must also maintain domain YAML files for response templates and slot definitions, alongside an infrastructure capable of supporting vector stores and MCP server connections.