This blog post details how we designed and scaled semantic search to power safer, more intelligent healthcare experiences.

HaloDoc is a healthcare technology platform that offers telemedicine services, online pharmacy, and health information resources to users in Indonesia. Through its platform, HaloDoc aims to improve access to healthcare services, empower patients to take control of their health, and facilitate collaboration between healthcare providers. Developers can learn from HaloDoc's innovative use of technology to address healthcare challenges, leveraging telemedicine, artificial intelligence, and data analytics to enhance patient care and outcomes.

Halodoc

Halodoc, Indonesia's leading healthcare app, shares how they built a semantic retrieval layer on top of their existing keyword-based search to power RAG-driven AI systems like a prescription assistance platform and Healthcare Q&A assistant. Using OpenSearch with HNSW-based k-NN vector search and 768-dimensional embeddings from Hugging Face sentence-transformers, they created an ingest pipeline that automatically generates embeddings at indexing time. The architecture complements rather than replaces keyword search, forming a hybrid retrieval system. Key lessons include the importance of offline embedding generation for scale, hybrid retrieval improving results, and retrieval quality directly impacting hallucination rates. The system has validated ~21K prescriptions and driven ~32K bookings from Q&A assistant users.

Semantic Search in Healthcare: Inside Halodoc’s RAG Retrieval Architecture