UE.AIChatPlus is an Unreal Engine plugin that enables communication with various GPT AI chat services.

Ccurrently supported services include OpenAI (ChatGPT, DALL-E), Azure OpenAI (ChatGPT, DALL-E), Claude, Google Gemini, Ollama, Offline llama.cpp. It is designed to facilitate integration with these AI chat services for UE developers.

The implementation is based on asynchronous REST requests, ensuring high performance and convenience. More service providers will be supported in the future.

Documentation: Link

中文文档：Link

Documento en español: Link

If there are any issues, please leave a comment in the provided documentation link above.

Latest Version: v1.4.1

Supported APIs:

• Offline llama.cpp：integration with llama.cpp library, CAN Run AI Model Offline! Also Support Multimodal models(Experimental) Vision. Support Win64/Mac/Android/IOS.

• OpenAI: /chat/completions, /completions, /images/generations, /images/edits, /images/variations

• Azure OpenAI: /chat/completions, /images/generations

• Claude: /messages, /complete

• Gemini: :generateText, :generateContent, :streamGenerateContent

• Ollama: /api/chat, /api/generate, /api/tags

Features:

• Support OpenAI, Azure OpenAI, Claude, Gemini, Ollama

• Text Generation, Text Chat, Image Generation, Image Analysis, Image Edit, Image Variation

• Text-to-Text, Text-to-Image, Image-to-Text, Image-to-Image

• An Editor AI Chat Tool which is well-crafted and feature-rich

• Support Blueprint

• Asynchronous Tasks

• Multi Api Services and Multi GPT Models

• Global Setting Page for AI Chat Editor Tool

• Session Settings for each chat session

• Chat Content Modification

• Image Viewing, Image Saving into File, Image Saving Into Texture Asset, Image Copy on Windows Platform

• Ollama Support automatically getting Models list from API

ChangeLog:

v1.4.1 - 2025.01.04

• Chat tool supports sending only images without messages.

• Fixed the issue with sending images through the OpenAI interface.

• Fixed the missing parameters (Quality, Style, ApiVersion) in the settings of OpenAI and Azure chat tools.

v1.4.0 - 2024.12.30

• (Experimental) Cllama(llama.cpp) support Multimodal models, means support vision now.

• Add ToolTip for All the Blueprint Types.

v1.3.4 - 2024.12.05

• OpenAI support vision api

• fix OpenAI stream=false error

v1.3.3 - 2024.11.25

• support ue5.5

• Fix some blueprint error

v1.3.2 - 2024.10.10

• Fix crash when manually stopping request in cllama.

• Fix the issue of not being able to find ggml.dll and llama.dll files when packaging the Win version of the mall for download.

• When creating a request, check if it is in the GameThread.

v1.3.1 - 2024.09.30

• Added a SystemTemplateViewer, which allows viewing and using hundreds of system prompt templates

• Fixed an issue where plugins downloaded from the marketplace couldn't find the link library for llama.cpp

• Fixed the LLAMACpp path being too long

• Fixed incorrect linking of llama.dll after packaging on Windows

• Fixed file path reading issues on iOS/Android

• Fixed incorrect name setting in Cllame

v1.3.0 - 2024.09.25

• Integration with llama.cpp library, Run AI Model Offline

v1.2.0 - 2024.08.20

• Support OpenAI Image Edit/Image Variation

• Support Ollama API, support automatically getting the list of models supported by Ollama

v1.1.0 - 2024.08.07

• Support blueprints

v1.0.0 - 2024.08.05

• Basic complete functionality

• Support OpenAI, Azure, Claude, Gemini.

• Built-in feature-rich editor chat tool