twilwa / 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

100% Private, 75% Cheaper & 23x Faster Assistants. Same API/SDK.

---

🖼️ Infra ✨ Feature? ❤️‍🩹 Bug?

---

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

📏 Principles

Assistants is a tool that is in continuous development, with the aim of always offering better infrastructure for Edge LLMs. To achieve this, it is based on several principles that define its functionality and scope.

Edge-first

Assistants does not require internet access by focusing on open source LLMs. Which means you own your data and your models.

OpenAI-compatible

OpenAI spent a large amount of the best brain power to design this API, which makes it an incredible experience for developers.

Reliable and deterministic

Assistants focus on reliability and being as deterministic as possible by default. That's why everything has to be tested and benchmarked.

Flexible

A minimal number of hard-coded prompts and behaviors, a wide range of models, infrastructure components and deployment options and it play well with the open-source ecosystem, while only integrating projects that have stood the test of time.

⭐️ Latest News

• [2024/01/19] 🔥 Action tool. Let your Assistant make requests to APIs.
• [2023/12/19] 🔥 New example: Open source LLM with code interpreter. Learn more.
• [2023/12/08] 🔥 New example: Open source LLM with function calling. Learn more.
• [2023/11/29] 🔥 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.
• Actions: Execute requests to external APIs, automatically.
• File Handling: Supports a range of file formats.

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:

• MC-LLM
• 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.

Assistants is focused on edge use cases with high reliability requirements.

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.