alt Hacker NewsApologies if it felt that way! I used OpenAI in the examples just because it's the quickest 'Hello World' for embeddings right now, but the library itself is completely agnostic.
HNSW is just the indexing algorithm. It doesn't care where the vectors come from. You can generate them using Ollama (locally) HuggingFace, Gemini...
As long as you feed it an array of floats, it will index it. The dependency on OpenAI is purely in the example code, not in the engine logic.
I think you'd get a lot more people interested in trying your project out if you included steps on how to generate vectors for the search as a document.
I love PHP, but I will realistically admit that most people interested in using PHP probably don't have the experience to know how to do such a thing offhand.