32 docs tagged with "Agents SDK"

The SignalWire Agents SDK includes a powerful local search system that provides

State Management

The SignalWire AI Agents SDK is built on a modular architecture that combines AI capabilities with web service functionality.

Introduction

This document provides a comprehensive reference for all public APIs in the SignalWire AI Agents SDK.

This guide covers deploying SignalWire AI Agents to Google Cloud Functions and Azure Functions.

Learn about the unified configuration system for SignalWire AI Agents SDK, including JSON configuration files and environment variable substitution.

Overview

You can create your own prefab agents by extending AgentBase or any existing prefab. Custom prefabs can be created directly within your project or packaged as reusable libraries.

Create a new skill by extending SkillBase with parameter support:

The DataMap system provides a declarative approach to creating SWAIG tools that integrate with REST APIs without requiring custom webhook infrastructure. DataMap tools execute on SignalWire's server infrastructure, simplifying deployment and eliminating the need to expose webhook endpoints.

The DataMap system allows you to create SWAIG tools that integrate directly with REST APIs without requiring custom webhook endpoints. DataMap tools execute on the SignalWire server, making them simpler to deploy and manage than traditional webhook-based tools.

Use the datetime skill to access current date and time information.

Dynamic agent configuration allows you to configure agents per-request based on parameters from the HTTP request (query parameters, body data, headers). This enables powerful patterns like multi-tenant applications, A/B testing, personalization, and localization.

This document provides a complete reference for all methods available in the SwaigFunctionResult class. These methods provide convenient abstractions for SWAIG actions, eliminating the need to manually construct action JSON objects.

Create an Agent

Multilingual Support

Use the math skill to perform mathematical calculations.

This document comprehensively details all possible keys that can be present in the postdata JSON object sent to SWAIG functions, based on analysis of the executeuserfunction implementation in servercode/mod_openai.c.

Prefab agents are pre-configured agent implementations designed for specific use cases. They provide ready-to-use functionality with customization options, saving development time and ensuring consistent patterns.

There are several ways to build prompts for your agent:

Python Agents SDK

The SignalWire Agents SDK includes optional local search capabilities that can be installed separately to avoid adding large dependencies to the base installation.

Comprehensive security configuration guide for SignalWire AI Agents SDK, covering HTTPS, authentication, CORS, and production best practices.

<InstallHero

The Agents SDK includes a powerful, modular skills system that allows you to add capabilities to your agents with simple one-liner calls and configurable parameters.

This document describes all supported SWAIG actions that can be returned from function calls, their expected JSON parameters, and proposed Python helper methods for the SwaigFunctionResult class.

SWAIG functions allow the AI agent to perform actions and access external systems. There are two types of SWAIG functions you can define:

Introduction

A comprehensive command-line tool for testing SignalWire AI Agents SWAIG functions and SWML generation locally with complete environment simulation and real API execution.

Use the nativevectorsearch skill to search local document collections using vector similarity and keyword search.

Search the internet and extract content from web pages with the web_search skill.