pdxjohnny / assistants

The ⭐️ Open Source Assistants API allows you to build AI assistants within your own applications with your own models. 75% Cheaper & 23x Faster Assistants. Same API/SDK. Written in Rust

⭐️ Open Source Assistants API

Build Powerful AI Assistants In-House, On Your Terms

75% Cheaper & 23x Faster Assistants. Same API/SDK.

---

📞 Need Support? We're here for you.
🖼️ How it Works – Visual Guide
✨ Suggest a Feature
❤️‍🩹 Found a Bug? Let us know.

Quickstart

Get started in less than a minute through GitHub Codespaces:

Or:

git clone https://github.com/stellar-amenities/assistants
cd assistants
cp .env.example .env

To get started quickly, let's use Perplexity API. Get an API key from Perplexity. You can get it here. Replace in .env the MODEL_API_KEY with your API key

Install OpenAI SDK: npm i openai

Start the infra:

docker-compose --profile api -f docker/docker-compose.yml up -d

Run the quickstart:

node examples/quickstart.js

Table of contents

Table of Contents

1. Why Open Source Assistants API?
2. What's Cooking? – Latest News
3. Key Features
4. What Can You Build with Assistants?
5. Join the Movement
6. Deployment
7. FAQ

Why Open Source Assistants API?

• Full Control: Own your data, your models, and your destiny.
• No Hidden Costs: Absolutely free. Seriously, no strings attached.
• Customizable: Tailor the AI to your specific needs and use cases.
• Offline Capabilities: Perfect for edge cases or internet-free zones.
• OpenAI Compatibility: Love OpenAI's API? We play nice with that too.
• Simplicity: Easy setup, no steep learning curve.
• Non-woke style: Get rid of OpenAI Woke/Brainwashed/PC models.
• Unleashed code interpreter: OpenAI Code interpreter is not allowed to do other things than processing data (e.g. cannot do web scrapping, etc.). This one is unleashed.

What's Cooking? – Latest News

• [2023/08/19] 🔥 New example: Open source LLM with code interpreter. Learn more.
• [2023/08/12] 🔥 New example: Open source LLM with function calling. Learn more.
• [2023/29/11] 🔥 New example: Using mistral-7b, an open source LLM. Check it out.

Key Features

• Code Interpreter: Runs Python code in a sandboxed environment. (beta)
• Knowledge Retrieval: Retrieves external knowledge or documents.
• Function Calling: Defines and executes custom functions.
• File Handling: Supports a range of file formats.
• Multimodal: Supports audio, images, and text.
  • image audio text
  • audio text
  • image text (soon)
  • text

Join the Movement

• For Developers: We've got the docs, tools, and a community ready to help you build what's next.
• For Innovators: Looking for an edge in AI? Here's where you leapfrog the competition.
• For the Visionaries: Dreamt of a custom AI assistant? Let's make it a reality.

Deployment

Please follow this documentation.

FAQ

Which LLM API can I use?

Examples of LLM APIs that does not support OpenAI API-like, that you can't use:

• ollama
• llama.cpp server example

Examples of LLM APIs that does support OpenAI API-like, that you can use:

• FastChat (good if you have a mac)
• vLLM (good if you have a modern gpu)
• Perplexity API
• Mistral API
• anyscale
• together ai

What's the difference with LangChain?

LangChain offers detailed control over AI conversations, while OpenAI's Assistants API simplifies the process, managing conversation history, data/vector store, and tool switching for you.

Are you related to OpenAI?

No.

I don't use Assistants API. Can I use this?

We recommend switching to the Assistants API for a more streamlined experience, allowing you to focus more on your product than on infrastructure.

Does the Assistants API support audio and images?

Images soon, working on it. Audio in a few weeks.