Love this approach for seeing if ChatGPT is used in a document: See if `utm_source=chatgpt.com` appears in any URLs. Doesn't prove that ChatGPT wrote it, but at least shows they used ChatGPT when researching.

Great guide here by Ed for using sqlite-vec + OpenAI embeddings in a RAG system! Includes great use of the new auxiliary columns feature for storing metadata (further evidence that the LA tech scene is elite)

NEW BLOG POST: Been testing out 20 LLMs at extracting data from political fundraising emails. See the process and results here: thescoop.org/archives/202...

Please merge my +321,000 line PR, it's only a few small changes 🥺

let's goooo

If you're interested in embeddings and SQLite you should be paying attention to sqlite-vec Lots of neat stuff in this release - and the blog post provides a very clear explanation of what it can do

sqlite-vec v0.1.6 is now out, with metadata support! SQLite vector search w/ metadata filters 👀 - Perform extra filtering w/ WHERE clause in KNN queries - Internally shard vector indexes with partition keys - Aux columns for easy lookups read more: alexgarcia.xyz/blog/2024/sq...

metadata filtering has been merged in sqlite-vec. Release coming soon!

Next week I'll be hosting a sqlite-vec online event about metadata filtering, which is coming VERY soon — come through! Wednesday November 20th at 10am PST, in the @mozilla.ai Discord (will be recorded) discord.gg/4ZMAgmrwqf?e...

Sqlite now with vector search! github.com/asg017/sqlit... courtesy of @alexgarcia.xyz