Introducing Toast 1

arm32

Damn, now I'm hungry. All this bread talk.

trjordan

I deeply love this idea of specialized LLMs for search. It's also extremely confusing to me how rough Google's entrance here is. When I, a human, need an answer to anything moderately complex, it's unlikely that I get it on the first (pre-AI) round of google searching. Simple stuff, sure, but more likely I'll need to go 2-5 rounds. Maybe click a few links. Double-check my assumptions. An LLM that can do that quickly seems like a slam dunk. I wonder what other problems benefit from that 10x-100x increase in context + 2-5 rounds with the LLM.

tolugenius

I guess someone who has used a search agent (or a dedicated subagent) can speak when I'd reach for a tool like this vs either just 1) a smaller general model or 2) a non-llm approach to the problem? Like it's interesting I'm just curious how a search agent compares to say a model with dedicated rag pipelines is that much different?

ChrisArchitect

Dunno about this branding/naming scheme - every time it comes up we have to double-check that it isn't some spoof/joke page

andai

Article should probably explain what "Mixedbread Search" is.

cryo32

Some days I have no idea what the fuck I am looking at.

amazingamazing

I know everyone loves to hate on google but i find search overviews and asking gemini to search for things way faster than any alternative. I was curious about a development near me and asked literally that and gemini pulled court records in about 20 seconds Anyway, back to this - it seems to be more like the AI equivalent of algolia than google

moffkalast

> performs best with Mixedbread Search, but it can work with any search backend Bread-first search, is it?

docheinestages

Are the benchmarks comparing just the models while keeping the harness the same (the open-source Toast harness)?

GPerson

I’m disappointed this is some AI thing and not a breadboard company.

jrflowers

I love to spend a dollar for a 70% correct search result

kelvinjps10

What are these names? before opening I thought it was going to be about bread

mfrye0

Long time user of your embedding models. I'm trying to understand how this works and if I can leverage it. It sounds like this is a new layer on top of your existing storage layer? So to use this, would I need to give you all of my data first? Or is there a version that can be run on prem?

msie

Bah, i was looking forward to a new toaster!

satvikpendem

Looks good as I use something similar with the SearXNG MCP, but a shame this isn't an open weight model. There are some wrappers around SearXNG which seem to reduce the token counts returned thus making it easier for the calling model to understand, but a full dedicated model for search is nice. How does it compare with Perplexity, Gemini with search, and Parallel AI? Those are the cloud providers of search based models that I've seen so far.

blitzar

I really wanted this to be a hardware startup - the Juicero of toast. Sadly its another software company.

precompute

Nice, a model for google-fu.

dmix

I've been using https://www.voyageai.com/ for this in production. Might try this out to see how it compares.