Skip to content

Commit

Permalink
feat(docs): Add concepts page for AI Engine personalities (#835)
Browse files Browse the repository at this point in the history
  • Loading branch information
FelixNicolaeBucsa authored Aug 8, 2024
1 parent f193891 commit c1a8960
Show file tree
Hide file tree
Showing 2 changed files with 59 additions and 1 deletion.
3 changes: 2 additions & 1 deletion pages/concepts/ai-engine/_meta.json
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
{
"ai-engine-intro": "Introduction",
"powering-connections-and-smart-operations-in-deltav": "Powering connections and smart operations in DeltaV",
"deltav": "DeltaV"
"deltav": "DeltaV",
"ai-engine-personalities": "AI Engine Personalities"
}
57 changes: 57 additions & 0 deletions pages/concepts/ai-engine/ai-engine-personalities.mdx
Original file line number Diff line number Diff line change
@@ -0,0 +1,57 @@
# AI Engine Personalities

## Introduction

This guide explores the **AI Engine personalities** within Fetch.ai's ecosystem. Let's delve into how these personalities enhance user interactions when operating with AI Engine and DeltaV!

## The AI Engine personalities: Powering Fetch.ai's Intelligence

The [AI Engine ↗️](/concepts/ai-engine/ai-engine-intro) stands as the heart of Fetch.ai's AI infrastructure, translating human language inputs into actionable [functions ↗️](/guides/agents/intermediate/agent-functions) for a network of [Agents ↗️](/guides/agents/getting-started/whats-an-agent) to fulfill them. The AI Engine bridges the gap between users and AI by leveraging powerful Large Language Models (LLMs) to understand complex requests. Here's how it works:

1. **User input**: the user provide instructions via [DeltaV ↗️](/concepts/ai-engine/deltav) which facilitates smooth interaction with the AI Engine.
2. **Understanding the request**: the AI Engine employs LLMs to analyze the user's request, grasping the intent and identifying the necessary actions.
3. **Function delegation**: based on the analysis, the AI Engine breaks down the user's request into executable functions.
4. **Agent coordination**: the AI Engine then orchestrates a network of agents registered on the Fetch Network to execute those functions, ultimately achieving the initial user's objective.

AI Engine personalities are not primarily about user experience or preference. Instead, they represent different versions or iterations of the AI Engine itself, each with its own set of features and capabilities.

The primary reason for introducing different personalities is to manage the development and rollout of new features without disrupting existing functionality. By creating a new personality, developers can experiment with and test new features without affecting the core system. Once these features are stable and mature, they can be integrated into the default personality.

## A Journey through personality types evolution

The following AI Engine personality types are available for users: **Talkative V3** and **NextGeneration**.

- With version **v0.22**, the NextGeneration personality received significant updates, including support for classical [`UAgentResponse` ↗️](/guides/agents/intermediate/ai-engine-compatible-agent) type agents, secondary function execution, and interactive UI elements. Notably, Talkative V3 was set to be replaced by NextGeneration in future updates.
- Version **v0.23** introduced enhanced session-level memory, tracking credit usage, parallel execution in sync worker, and session termination control within the NextGeneration personality.
- Version **v0.24** deployed **NextGeneration personality as the default**, and thus replacing **Talkative V3** personality type. This version focuses on significant stability and scalability improvements, supporting millions of agents. This version also introduced immediate agent registration, enhanced message reliability, UI enhancements, privacy compliance, robust timeout and monitoring systems, infrastructure upgrades, and database and deployment improvements.

## Exploring the Feature Set of AI Engine Personalities

Here's a breakdown of the key functionalities offered by each personality:

### Talkative V3 - AI Engine V1

**Focus**: General conversation and task handling.

**Key Functionalities**:
- Enhanced Function recommendations for improved efficiency.
- Improved context building for natural conversation flow.
- Agent health checks to ensure optimal performance.

### NextGeneration - AI Engine V2

**Focus**: Broad conversational capabilities, advanced functionalities, and scalability.

**Key Functionalities**:
- _Supports a variety of [Dialogue ↗️](/guides/agents/advanced/dialogues) protocols_ for flexible user interactions and thus allows for agent interactions with websites and PDFs.
- Tracks resource usage for transparency.
- Increased processing speed for faster responses.
- Manages session endings efficiently.
- Offers superior stability and scalability for large-scale applications.
- Completely revamped AI Engine backend for improved performance and future-proofing.
- Utilizes a more sophisticated LLM for enhanced context understanding.
- Employs an advanced recommender system to select optimal functions based on your needs.

## Choosing the right personality

We encourage everyone operating on DeltaV to select the **Next Generation** AI Engine personality type. This AI Engine personality stands as a significant personality type offering _enhanced scalability_, _reliability_, and _flexibility_. The major key features include advanced context understanding, improved function recommendations, and most importantly, **the ability to handle multiple dialogue formats**.

0 comments on commit c1a8960

Please sign in to comment.