Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- There are lots of fair use translations available here at https://www.crosswire.org/sword/index.jspby jupr
- Ah very interesting. For this one, I had to dig up an older repo I made where I converted WEB translation into one big json file to make it easier to work with. Not sure the formats exposed and how... pliable? they are. (https://github.com/jacksonStone/Bible_as_JSON)
- Would love to use if you can get it back up! Sounds like an awesome idea for a way to converse with the Bibleby sputknick
- Nevermind, it eventually loadedby sputknick
- I built a Bible scholar agent using RAG grounded in the Berean Standard Bible. Is the same concept but an LLM discern the text for you.
Here is the link to the demo: https://safi.selfalignmentframework.com/
Choose the Bible Scholar agent and use deepseek or Gemini 3.5 for the LLM.
by jnamaya - Did you include the Deuterocanonical books?by regus
- They are now optionally included based on the canon you pick
- It would be nice if there was a listing of exactly what was included somewhere.by zoogeny
- Ah no it doesn't but could be added. The books are listed in the checkbox list
- No, and it's not KJV. Maybe NKJV? I searched
Eccl7:13 "Consider the work of God: for who can make that straight, which he hath made crooked?"
and it came back with:
Ecclesiastes 7:12-15 For wisdom is a defense, even as money is a defense; but the excellency of knowledge is that wisdom preserves the life of him who has it. Consider the work of God, for who can make that straight which he has made crooked? In the day of prosperity be joyful, and in the day of adversity consider; yes, God has made the one side by side with the other, to the end that man should not find out anything after him. All this I have seen in my days of vanity: there is a righteous man who perishes in his righteousness, and there is a wicked man who lives long in his evildoing.
by smitty1e - I vibed up something similar, comparing the verses of the big 3 religions. Cloudflare vectorize for embeddings db. https://crazy.church
- Can I ask what you’re using for voice AI?
- That's impressive and really fast. I asked it what it thought about vector databases:
Finally, brethren, whatsoever things are true, whatsoever things {are} honest, whatsoever things {are} just, whatsoever things {are} pure, whatsoever things {are} lovely, whatsoever things {are} of good report; if {there be} any virtue, and if {there be} any praise, think on these things. {honest: or, venerable}
- First result for "Jesus":
>Jacob kissed Rachel, and lifted up his voice, and wept. Jacob told Rachel that he was her father’s relative, and that he was Rebekah’s son. She ran and told her father. When Laban heard the news of Jacob, his sister’s son, he ran to meet Jacob, and embraced him, and kissed him, and brought him to his house. Jacob told Laban all these things. Laban said to him, “Surely you are my bone and my flesh.” Jacob stayed with him for a month. Laban said to Jacob, “Because you are my relative, should you therefore serve me for nothing? Tell me, what will your wages be?”
by gaiagraphia - Hypothesis:
This passage lists a lot of names repeatedly, and Jacob is in the genealogy of Jesus. Genealogies also list a lot of names. So perhaps somehow it’s jumping from Jesus to Jacob?
by jact - Nice project. The 4GB index / ~15s search part made me think zvec might be a good fit here: https://github.com/alibaba/zvec
It’s an in-process vector DB, so the “local corpus, no separate server” shape is pretty much what it’s designed for. Its benchmark numbers are quite strong, and recent versions also support full-text + hybrid retrieval and DiskANN.
This would be an interesting case to try with zvec: same corpus, same embedding model, then compare indexing time, index size, memory usage, and query latency on normal hardware.
by bigggbob - > The king profits from the field
For the solution, read Henry George!
- Slow, but interesting. I used the query "government" and got back passages in Romans 13 (as I expected), but also passages in Daniel and Ezra describing decrees by government officials, which made sense.by mcswell
- 6x'd the speed if you wanted to try again
- For completeness, this should include all possible books, including Ethiopian, and then it should include a drop-down with pre-defined sets one could choose from (Protestant, Catholic, Orthodox...).by atmanactive
- Yeah a drop down list like that would be sweet. I think you'd have to format / find the open source version / translation of that text. Finding a well formatted and readable, public use (not just nkjv for example) was tricky For WEB I had to do a good b it of data massaging to get it in a consumable format..
- Got the protestant and catholic now. Orthodox I am discovering is not a simple matter of "just include the canon"!
- This is really cool...great job! It's a favorite pastime of mine to index various large corpora.
As for speed, this might help for code referencing: https://github.com/deepbluedynamics/lume
Blog post: https://deepbluedynamics.com/blog/lume-retrieval-primitives
I use a small local model to extract entities for the graph, but it's not necessary.
You can optionally use GTR-T5 which is a few years old now, but still good for generating fast and free embeddings. That step is only run once if you run it in hybrid mode.
Feel free to take and remix or use!
- That's cool! I did the same for the Quran to see how RAG works. I also indexed related works called "Hadith" and the names of Allah. It initially required indexing everything using OpenAI embeddings and then powered by it.
It's also open source
by asim - This is wonderful! Thank you!
My friend has been looking for a good transliterated version of the Quran. I see I can hover/click over a word to view the transliteration, is it possible to have an option to show transliteration, like word-by-word translation?
I added an issue https://github.com/asim/reminder/issues/111
Thanks again!
by mero22 - Yes! looks like yours has more features (I considered generating the audio) FWIW I observed that the embedding gives the most signal when I pass whole paragraphs (for all I know the Quran is in lyrical verse so maybe that doesn't work)