Integration Overview

TaskingAI has integrated a variety of third-party services and tools to provide a seamless experience for developers. These integrations are designed to be easy to use and flexible, allowing developers to access and deploy a wide range of services in their AI projects.

Models

Models are at the core of any AI application. TaskingAI provides a wide range of models from various providers, including large language models (LLMs) and embedding models. TaskingAI has unified the APIs of these models, making it easy to access and switch them in your projects.

Large Language Models (LLMs)

Large Language Models (LLMs) serve as the foundational intellect of your AI assistants, akin to their cerebral cortex. These models are not only capable of 'thinking'—processing and understanding complex natural language—but also adept at seeking external information as required.

For a full list of supported models and their required credentials, please refer to Large Language Models.

Embedding models

Embedding models convert textual data to numerical vectors, which can be used for various tasks such as similarity search, and knowledge retrieval.

For a full list of supported models and their required credentials, please refer to Providers and Models.

Bundles and Plugins

Plugins are TaskingAI approved integrations with third-party services, providing a seamless and user-friendly way to connect and interact with external services.

A third party provider may provide multiple plugins, each of which can be used to interact with a different service or API. Plugins from the same provider with similar functionalities are be grouped into a bundle.

For example, a weather info provider may provide 3 endpoints: one for getting current weather, another one for getting weather forecast, and another one for getting historical weather data. Each of them are provided as a separate plugin in the weather bundle.