Orion is a web-based chat interface that simplifies interactions with multiple AI model providers. It provides a unified platform for chatting and exploring multiple large language models (LLMs), including:
- 🛠️ Ollama – An open-source tool for running LLMs locally 🏡
- 🐳 DeepSeek (DeepSeek-R1 rivaling OpenAI's o1 model)
- 🤖 OpenAI (GPTs and o's models)
- 🎯 Cohere (Command-r models)
- 🌌 Google (Gemini models)
- 🟡 Anthropic (Claude models)
- 🚀 Groq Inc. – Optimized for fast inference (open source models) ⚡️
- ⚡️ Cerebras – Also optimized for fast inference 🚀
- 🟣 SambaNova - Fast inference and support for Meta-Llama-3.1-405B-Instruct 🦙🦙🦙.🦙
- ♾️ OpenRouter - A unified interface for LLMs
- ☁️ Together AI - The AI Acceleration Cloud
- 📡 Deep Infra
- Light theme:
Dark Theme:
With Orion, you can easily navigate and assess the strengths and limitations of different AI models through an intuitive, user-friendly interface.
- 🖥️ Browser - No need to download anything ⚡️
- ✅ Code Execution (Execute code with Google Gemini)
- 🗣️ TTS - Realistic text-to-speech using ElevenLabs
- 🎙️ STT - Speech-to-Text using Groq/Whisper ️
- 🔄 Seamless integration with multiple AI models
- ✨ Clean and responsive web interface 🌐
- 🌈 Syntax highlighting for code snippets 🖌️
- ⬇️ One-click download for AI-generated code outputs
- 🎛️ Customizable system prompts to tailor responses 🛠️
- 🌐 Special command for quick and easy language translation tasks
- 📁 Upload a variety of documents (text, PDF, images, video) to Google Gemini for analysis and processing
- 🧠 Awesome Prompts 150+ awesome prompts most of them from Awesome ChatGPT Prompts to select with one click.
Your API keys are stored locally using localStorage, and requests are sent directly to the official provider's API
(OpenAI, Anthropic, Google, Groq, Cerebras) without routing through any external proxy.
Some companies offer free API access. Check their terms and conditions before you get started.
- Google Gemini: Get your Gemini API key - 🟢 free
- Cerebras: Get your Cerebras API key - 🟢 free
- Cohere: Get your Cohere API key - 🟢 free
- Groq: Get your Groq API key - 🟢 free
- SambaNova: Get your SambaNova API key - 🟢 free
- Together AI: 🟢 Free for deepseek-ai/DeepSeek-R1-Distill-Llama-70B-free Get your Together AI API key
- OpenAI: OpenAI key
- Anthropic: Anthropic API key
- DeepSeek: DeepSeek API Key
Use special commands to perform an action quickly and easily.
Translate: Translate text with ease using special command.
- To translate "Hello everyone!" into Spanish, use:
translate:spanish Hello everyone!or its short formt:spanish Hello everyone!. - AI will automatically detect the source language, requiring only the target language specification.
YouTube Summary Ask AI to summarize a YouTube video or answer any question based on the video caption. See an example of use below.
Summarize this video https://www.youtube.com/watch?v=r7pEdhnS3tIWhat is this video about? https://www.youtube.com/watch?v=qQviI1d_hFAIt is recommended to use a larger context window model when using this functionality, such as Google Gemini.
- Press
Ctrl + Qto close the current chat and start a new one. - Press
Shift + Ton your keyboard to switch between the dark and light theme modes.
Search: Perform quick searches and retrieve relevant information with ease from Google.
- Example:
search: What is the latest news?ors: What is the latest news?
Please perform this functionality with caution and always check code before accepting execution.
- Example:
javascript: How Many R's in 'Strawberry'?orjs: How Many R's in 'Strawberry'? - This will allow the AI to generate Javascript code that will run in your browser.
- When using Google Gemini you can ask it to execute codes directly in Google's own remote environment. For now only Python codes are executed. The code and output will be returned.
- Command example:
py: Run a python code to write "tseb eht sI noirO" in the inverse order - Another example:
py: The United States has a population of 342,524,968, of which 480,000 die annually due to tobacco use. What percentage is that?
To run Orion first download this repository.
You can download it by running the following command in your terminal:
git clone https://github.com/EliasPereirah/OrionChat.gitOr download the zip file from the repository by clicking on the green button "Code" and then Download ZIP.
After downloading, just open the folder and click on index.html if you don't have a server. If you do, just access the directory where the project was saved. It's that simple.
Sometimes you might want AI to search the web and respond based on that information.
To allow AI to search using Google, you will need Google CSE (Custom Search Engine) API Key and CX.
- First, create a custom search here Google CSE Panel
- Copy your CX ID
- Go to Google Developers and click on Get a Key to get your API Key
- Now just enter CX and API key in Orion. for that go to Options -> More Options and make the configuration.
- To use the functionality in chat, you need to put an "s:" at the beginning of your prompt, e.g. "s: what's today's news"
- *Note: Google Search will only return snippets of search results, which may not have enough context for AI to respond. It is recommended to implement the solution below for best results.
For better search results, you can configure a "RAG endpoint".
Just follow the instructions at https://github.com/EliasPereirah/SearchAugmentedLLM/
After that you can enter the search endpoint you just created in the Orion Chat interface. Click on "Options" -> "Advanced" enter the "RAG endpoint" and click "Activate".
Now whenever you want the AI to do a search to answer your question, write at the beginning of your prompt "s:" + your question, e.g. "s: what's the news today?", The AI will search the web and respond based on the information found.
To get around CORS errors when working with SambaNova the API request will pass through cors-proxy.php
which will forward the request to the desired platform. This will not hide your IP address, just forward the request.
This is necessary because direct requests via JavaScript in the browser to these platform are not possible.
You can simply share the URL of a YouTube video in the chat to be able to ask something about the video content, or ask the AI to make a summary.
To do this, you will need to use this other project: https://github.com/EliasPereirah/YoutubeSubtitlesDownloader/
You can run it on localhost or on a remote server.
After activating the mentioned project, go to "Options" -> "YouTube Captions" and point to the URL where you deployed the project, for example: http://localhost/YoutubeSubtitlesDownloader/
