DSRs, @DSPyOSS for Rust is here๐
Happy to finally announce the stable release of DSRs. Over the past few months, Iโve been building DSRs with incredible support and contributions from folks Maguire Papay, @tech_optimist, and @joshmo_dev.
A big shout out to @lateinteraction and @ChenMoneyQ who were the first people to hear my frequent rants on this!! Couldn't have done this without all of them.
DSRs originally started as a passion project to explore true compilation and as it progressed I saw it becoming more. I canโt wait to see what the community builds with it.
DSRs is a 3 phase project:
1. API Stabilization. We are nearly done with this and it was mostly implementing the API design. We kept the DSPy style in mind and tried to keep it close to it so it's easier to onboard and while at it we tried to improve it and make it a bit more idiomatic and intuitive!
2. Performance Optimisation with benchmarking vs DSPy. We want to benchmark LLMs performance vs DSPy, with API design finalized we want to improve performance in every front. We'll improve the latency and improve the templates and optimizers in DSRs.
3. True Module Compilation. Why should you optimize signature when you can optimize and fuse much more? This is the idea of the final phase of DSRs. A true LLM workflow compiler. More on this after Phase 2.
Really grateful for @PrimeIntellect offering compute to drive Phase 2 and 3 experimentation for this! Big shoutout to them and @johannes_hage for this!!!
But what is DSRs? What does it offer? Let's see.
By now, everyone knows that single-vector embedding models are hugely limiting for modern workflows.
But they contain than you think: you can extract sparse Latent Terms from them.
And it turns out that BM25 is all you need to turn this vocabulary into a strong retriever.
The dominant story in AI has been the growing cloud: bigger clusters, larger models, more gigawatts.
We believe the future is in the opposite direction: on-device inference, smaller models, watts instead of gigawatts.
Today we're releasing @OpenJarvisAI v1.0: a personal AI assistant that lives, learns, and works on your device.
A pretty late update, but I've graduated from @Stanford and joined @mixedbreadai as a Research Engineer!
Excited to help build and optimize the future of search ๐๐
Itโs been such a fun place to work! Every day, I wake up excited to learn more and more!!
Big thanks to @lateinteraction, @JonSaadFalcon and everyone who helped me throughout this journey!! As I always say my achievements are barely mine and much more of the people around me.
Grateful to all of them๐. This is just the beginning.
New: grep for exact matching
grep โ keyword / regex matching
search โ fine-grained semantic retrieval
Works across uploaded content, including text, PDFs (OCR) and audio/video (transcription).
Give your agents both retrieval primitives to perform at their best.
Feature: Native agentic search on Mixedbread
Search with auto-planning, exploration, and multi-hop reasoning across documents.
Built for:
- evidence discovery
- exhaustive search
- cross-document reasoning
โ Topped MADQA @snowflake with 93.4% accuracy across 18,000 PDF pages.
Introducing mxbai-rerank-v3-listwise: reranking that goes beyond binary relevance.
It reads the whole candidate set, resolves conflicts, and ranks by directives like recency, source priority, and multi-step rules.
+11% NDCG@10 on average across multiple domains, modalities, and languages in runs with Wholembed v3.
Available today in preview in Mixedbread.