Documentation

Get notified when things happen. Subscribe to agent events and receive signed HTTP callbacks — message received, message sent, thread created, and more.

Agents that act on their own schedule. Set up reminders, recurring reports, and automated check-ins — your agent runs in the background and delivers results to Slack, Telegram, WhatsApp, or any connected channel.

Put your agent on Slack, Telegram, WhatsApp, Discord, Teams, or Gmail. Connect a channel, and your agent receives messages and replies natively on each platform — with proper formatting, threading, and session management.

Turn documents into structured, queryable knowledge. Upload files, define a schema, and let your agents traverse entities and relationships — not just match keywords.

Build agents that remember. Ragwalla Memory stores give your agents long-term memory — shared across a team, or scoped to individual users. Write once, read from any agent you authorize.

Vector Store API Documentation This document provides instructions on how to interact with the Vector Store API endpoints. All API endpoints are prefixed with `/v1`.

Retrieving Vectors from Vector Store Files Ragwalla now supports retrieving the actual vector embeddings for files in your vector stores. This feature gives you direct access to the processed...

# OpenAI Files API: Complete Guide to Upload, Manage & Delete Files The OpenAI Files API allows you to upload, manage, and delete files for use with Assistants, fine-tuning, and...

OpenAI is shutting down the Assistants API on August 26, 2026. Learn how to migrate to Responses API + Conversations API or use wire-compatible alternatives.

Custom Functions and Secrets Management Guide This guide covers how to create secure custom functions for Ragwalla agents and manage secrets safely. ## Table of Contents - [Overview](#overview) -...

Choosing the right text embedding model is crucial for building effective AI applications like chatbots and retrieval systems. This guide is aimed at developers familiar with OpenAI’s Assistant and highlights how Ragwalla gives you the freedom to select different embedding models – a flexibility not available in the standard OpenAI Assistant.

When using OpenAI Assistants, developers typically must manage their own mapping between file identifiers (file_id), URLs, and titles due to OpenAI's lack of metadata support on files. Ragwalla's Assistants API provides a simple solution by allowing developers to create and manage these mappings easily.

The Ragwalla Assistants API is designed to be fully wire-compatible with OpenAI's Assistants API, providing developers seamless integration through familiar SDKs and interfaces. This guide helps you quickly provision your own unique endpoint and start building intelligent applications.