Release v2.0.1

🚀 Features

• Implement backend with DLLs (PR: #163)
• Separate LLM from LLMClient functionality (PR: #163)
• Add sample with RAG and LLM integration (PR: #170)

Release v1.2.9

🐛 Fixes

• disable GPU compilation when running on CPU (PR: #159)

Release v1.2.8

🚀 Features

• Switch to llamafile v0.8.6 (PR: #155)
• Add phi-3 support (PR: #156)

Release v1.2.7

🚀 Features

• Add Llama 3 and Vicuna chat templates (PR: #145)

📦 General

• Use the context size of the model by default for longer history (PR: #147)

Release v1.2.6

🚀 Features

• Add documentation (PR: #135)

🐛 Fixes

• Add server security for interceptions from external llamafile servers (PR: #132)
• Adapt server security for macOS (PR: #137)

📦 General

• Add sample to demonstrates the async functionality (PR: #136)

Release v1.2.5

🐛 Fixes

• Add to chat history only if the response is not null (PR: #123)
• Allow SetTemplate function in Runtime (PR: #129)

Release v1.2.4

🚀 Features

• Use llamafile v0.6.2 (PR: #111)
• Pure text completion functionality (PR: #115)
• Allow change of roles after starting the interaction (PR: #120)

🐛 Fixes

• use Debug.LogError instead of Exception for more verbosity (PR: #113)
• Trim chat responses (PR: #118)
• Fallback to CPU for macOS with unsupported GPU (PR: #119)
• Removed duplicate EditorGUI.EndChangeCheck() (PR: #110)

📦 General

• Provide access to LLMUnity version (PR: #117)
• Rename to "LLM for Unity" (PR: #121)

Release v1.2.3

🐛 Fixes

• Fix async server 2 (PR: #108)

Release v1.2.2

🐛 Fixes

• use namespaces in all classes (PR: #104)
• await separately in StartServer (PR: #107)

Release v1.2.1

🐛 Fixes

• Kill server after Unity crash (PR: #101)
• Persist chat template on remote servers (PR: #103)