Biblos 2.0 – Enhanced Semantic Bible Search with Instructor Embeddings
biblos.appI'm pleased to present an update to Biblos, a semantic search tool designed for in-depth Bible study. This release incorporates community suggestions and introduces instructor-large embeddings to enhance the precision of verse retrieval.
Biblos aims to facilitate a deeper exploration of biblical texts, offering nuanced search capabilities for those delving into themes or seeking interpretations of theological nuances. The updated version is now available for use at https://biblos.app/
Technical Insights:
- Utilizes Chroma for vector search, now powered by instructor-large embeddings for improved semantic accuracy.
- Features Anthropic's Claude LLM model to generate summaries that provide context and clarity for search results.
- Developed with a Retrieval Augmented Generation (RAG) architecture, the app offers a streamlined user experience through a Streamlit Web UI, all orchestrated with Python.
Feel free to review or fork the source code here: https://github.com/dssjon/biblos
Your feedback has been instrumental in shaping this update, and I look forward to your thoughts on the enhancements.
"introduces instructor-large embeddings to enhance the precision of verse retrieval."
Do you have examples of how this functions different / better? I'm really curious on the difference between the two.