Together AI: Advancing the Frontier of AI With Open Source Embeddings, Inference, and MongoDB Atlas

Founded in San Francisco in 2022, Together AI is on a mission to create the fastest cloud platform for building and running generative AI (gen AI). The company has so far raised over $120 million, counting Nvidia, Kleiner Perkins, Lux, and NEA as investors.

Ce Zhang, Founder & CTO at Together AI says, “Together AI is a research-driven artificial intelligence company. We contribute leading open-source research, models, and datasets to advance the frontier of AI. Our cloud services empower developers and researchers at organizations of all sizes to train, fine-tune, and deploy generative AI models. We believe open and transparent AI systems will drive innovation and create the best outcomes for society."

The company has recently introduced its Together Embeddings endpoint — a new service for developers building a variety of applications, including one that is top of mind for nearly all gen AI-powered apps: retrieval-augmented generation (RAG). With the RAG pattern, developers can feed gen AI models with their own up-to-date, domain-specific data. The results are more reliable gen AI outputs that are customized for the business along with reduced risks of hallucinations.

The Together Embeddings endpoint offers access to eight leading open-source embedding models at up to 12x cheaper price than proprietary alternatives. The list of the models includes top models from the MTEB leaderboard (Massive Text Embedding Benchmark), such as UAE-Large-v1 and BGE models, and state-of-the-art long context retrieval models. Together Embeddings also offers integrations to MongoDB Atlas, LangChain, and LlamaIndex for RAG.

To demonstrate this integration, the engineering team at Together AI created a tutorial for developers exploring how to build a RAG application with MongoDB Atlas. This tutorial shows how to use Together Embeddings and Together Inference to generate embeddings and language responses. Atlas Vector Search is used to store and index embeddings and then perform semantic search to retrieve relevant data examples for natural language queries against a sample Airbnb listing dataset. With this RAG pattern, the gen AI model can recommend properties that meet the user’s criteria while adhering to factual information.

“Bringing together live application data synchronized right alongside vector embeddings in a single platform, MongoDB Atlas helps developers reduce complexity and cost, and bring cutting-edge apps to market faster,” says Prakash. “This is one example, and we are looking forward to seeing many amazing applications that will be built using Together AI and MongoDB’s Atlas Vector Search.” To learn more about its RAG integrations, take a look at Together AI’s documentation.

To get started with MongoDB and Together AI, register for MongoDB Atlas and read the tutorial. If your team is building AI apps, sign up for the AI Innovators Program. Successful companies get access to free Atlas credits and technical enablement, as well as connections into the broader AI ecosystem.