Enabling Multi-Model Support

pinacai / PINAC_Workspace

OpenSource & Cross-Platform alternative of "Copilot for Windows"

GNU General Public License v3.0

13 stars 15 forks source link

Enabling Multi-Model Support #5

Closed RajeshTechForge closed 4 weeks ago

RajeshTechForge commented 1 month ago

Description

We need to implement the functionality to utilize multiple AI models using LangChain and seamlessly switch between them in our application.

Models to be added to our App (Initial List)

Cloud Models

[ ] ChatGPT 4
[x] ChatGPT 3.5 turbo
[ ] Gemini Ultra
[x] Gemini 1.5 Pro
[x] Gemini 1.0 Pro
[x] Gemini 1.5 Flash
[ ] Gemini Vision Pro

Local Models (Ollama)

[ ] Google Gemma
[ ] Llama 2 / Llama 3
[ ] Mistral AI
[ ] Other possible Open-Source models

RajeshTechForge commented 1 month ago

Added support of Gemini Flash 1.5

I have added support for Gemini Flash 1.5 but the option to switch to ChatGPT 3.5 Turbo is available for users. This option will be added in upcoming updates.

Gemini Flash 1.5 features:

Faster response than ChatGPT 3.5 turbo
Much better accuracy in task execution on smaller data shot
Efficient

RajeshTechForge commented 1 month ago

Added support of Gemini 1.5 Pro/Gemini 1.0 Pro

Gemini 1.5 Pro: Complex reasoning tasks such as code and text generation, text editing, problem-solving, data extraction and generation (Text, Image & Video Input)

Gemini 1.0 Pro: Natural language tasks, multi-turn text and code chat, and code generation (Only text input)