I helped work on the RAG part of this :-)<p>We used <a href="https://github.com/pgvector/pgvector">https://github.com/pgvector/pgvector</a> under the hood and found it extremely easy to integrate with our database schema - being able to just specify the structure of a table and have metadata fields alongside the embeddings made the code very easy to reason about.
This is powered by Helix API's. Bots represent the intelligent search agents that your users will interact with. When you create one, it pulls in information from websites and feeds that to a sophisticated language model. This model is then exposed via an API, which is then called by your users.
Not mentioned on the website (because it’s targeted at general website owners rather than a technical audience) but we are using a 100% open source AI stack for this, with llamaindex, pgvector and llama3:instruct running on ollama hosted on a stack of GPUs we have mostly in our houses.
Under the hood right now it's on-prem llama3 + a pretty basic RAG pipeline. The coolest thing about this technically is that it's all running totally privately.<p>But the main goal is to make websites more efficient. To get your customers to the answer they need faster.