- 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.
https://reminder.dev/search
It's also open source
https://github.com/asim/reminder
by kordlessagain
0 subcomment
- 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!
by atmanactive
2 subcomments
- 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 Reuben_Santoso
0 subcomment
- this is great. I now could find passages that fits semantically
- 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.
- 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 ReactiveJelly
0 subcomment
- > The king profits from the field
For the solution, read Henry George!
by gaiagraphia
1 subcomments
- 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 benjaminhays
0 subcomment
- Would love to see this for Jewish legal texts via Sefaria. A RAG database for Talmud Bavli and Yerushalayim would be super neat.
by andrethegiant
2 subcomments
- I vibed up something similar, comparing the verses of the big 3 religions. Cloudflare vectorize for embeddings db. https://crazy.church
- Did you include the Deuterocanonical books?
by sputknick
2 subcomments
- Would love to use if you can get it back up! Sounds like an awesome idea for a way to converse with the Bible
- There are lots of fair use translations available here at https://www.crosswire.org/sword/index.jsp
- Thanks for creating this, this is really fun to play around with! Is the code for this out in the open if someone would want to peek under the hood?
- Excellent! Just searching "giants" pops our many more of these characters than just Nephilim and Goliath.
by yjftsjthsd-h
1 subcomments
- Any chance you wrote it up anywhere? I'm somewhat interested in RAG and a worked example would be nice.
- This is really cool. Thank you for sharing.
- Not super impressed with this considering you can get better results in seconds from any basic LLM workflow.
- Looking for slavery, it comes up with Leviticus 25:46-49 but misses the context that starts at verse 44.
- "artificial intelligence" chuckled
- Very happy you built this. I was thinking about building this myself.
- Pretty effective. You can even type in "child murder" and "genocide" and get relevant passages
- My search returned what might as well have been a random assortment of bible verses. It made me wonder what Terry Davis would have thought of modern AI. Would it be the natural evolution of his shortcut for random bible verses that he built into TempleOS, or would it be the opposite and a voice of evil?
by stevefan1999
0 subcomment
- just how far are we from the machine god in the Warhammer 40K universe
- Cool. What rag techniques did you use?
- The site is not loading for me! Interesting project
by BuenosDiaz
0 subcomment
- This is really cool! I like the idea :)
by dredmorbius
1 subcomments
- RAG, for those unfamiliar, retrievel-augmented generation:
<https://en.wikipedia.org/wiki/Retrieval-augmented_generation>
by cluckindan
0 subcomment
- Can we have apocryphal books too, like Moses 6 & 7 :)
- pg-vector with hnsw is still 15 seconds?
- [flagged]
by ahmet_ozel
0 subcomment
- [flagged]
- [dead]
- [dead]
- [dead]
- [dead]
by condwanaland
2 subcomments
- Searched for "sexual exploration". One of the results i got returned was from corinthians and read:
The wife doesn’t have authority over her own body, but the husband does. Likewise also the husband doesn’t have authority over his own body, but the wife does.
I'm so glad this religion of peace sees consent as profoundly unimportant
Hacker News