🇮🇳Releasing resources for Multilingual Search in 11 Indian languages! 1⃣INDIC-MARCO (Translated version of MSMARCO in 11 Indian Languages): huggingface.co/datasets/saif… 2⃣Indic-ColBERT (11 Multilingual ColBERT Models): huggingface.co/saifulhaq9/in… Paper: arxiv.org/abs/2312.09508

dspy.GEPA used in pretraining data curation in the new Microsoft AI effort :-)

overwhelming evidence for late interaction / multi-vector models yet again :-) > even after finetuning, single-vector models lag far behind multi-vector embeddings, which achieve significant performance gains and exhibit greater robustness to catastrophic forgetting.

The “grep-is-all-you-need” nonsense arguments arise from the fact that too many people think neural search means single-vector IR, which do in fact suck. But we’ve known that since 2019. Quoting @aaxsh18, CEO of Mixedbread: > late interaction cant stop winning

Hackathon alert: The Financial needle in theHaystack. Join us! luma.com/3dk8wzx3 via @LumaHQ #bangalore #financeAI #documents #startups

Makes me wonder if Omar sees the rest of the world with this much clarity or just ML/AI let’s hear some hot political takes haha

Dspy.RLM("Given all his papers reverse engineer and extract author's mental models") 😅

Of course not. In fact, my lab is simultaneously building RLMs as the next paradigm for LLMs *and* developing the next paradigm for retrieval (stay tuned!). Retrieval will not go anywhere: if you have a large corpus with, say, billions of tokens over which you issue many queries, you necessarily need to build some index data structures that enable fast sub-linear access. RLMs may internally choose to build such an index when it proves to be an effective tool, but fundamentally RLMs are about long one-off context. You wouldn’t typically put an RLM over a million documents and expect that to be the optimal system design. (Thank you for the question @jayitabhattac11 !)

For those interested in making OSS contributions to the RLM repo, I've added a bunch of random thoughts and TODOs of what to add in a *messy* Markdown file on the GH repo. Feel free to tackle any of them, or any other things you think are meaningful. I'll be pretty active here or on the repo. Once I finish some other related work, I might open up a Discord channel or something for people who want to make longer standing contributions to the repo / discuss the direction of where to take it. Cheers! github.com/alexzhang13/rlm/b…

IMO, RLMs are as “language model”-y as modern “LLMs” or Reasoning Models are truly “statistical models of language”. All three are a bit of a stretch BUT in the same way. Pedantically, all three are language processing systems, eg recursive/reasoning language processing system.

Check out our text leaderboard at yupp.ai/leaderboard/text and our SVG leaderboard at yupp.ai/leaderboard/svg!

Awesome!

> You’ll implement ColBERT to understand multi-vector search [and] apply ColPali for patch-level image retrieval. So happy to see the great folks at @DeepLearningAI @AndrewYNg host a course on late interaction (ColBERT, ColPali et al) after their short course on DSPy :D

Please consider applying to the program. Over two years, my research skills, perspective on research have all been broadened and sharpened. This is an exceptional group, in the way they groom you, and allow you a room for exploring wild ideas. Pls reach out if you have questions!

Martin @martin_casado and I had a fun hour-long chat about why we need an AI software layer, and why that's true even if AGI arrives. This is basically my take on why "the model" is definitely NOT "the product", though models are one way you may decide to implement some products

Happy Friday Everyone, DSPyWeekly Issue #11 is live! 🚀 Highlights: 🔹 A cookbook for Self-Evolving Agents 🔹 Teaching local models tool-calling 🔹 New DSPy Neo4j integration 🔹 A new "Events" section to track DSPy meetups! Plus new projects like codex_dspy & AUTODSPy. #DSPy #AI #LLMs #AgenticAI #Neo4j

The labs don't want you to know this (jk) but they have no clue how to best prompt their own models either. To some approximation, you just pre-/post-train it on a lot of data, intervene on certain behaviors, and what comes out is what comes out.

Ok, I'll say it. One of the biggest challenges facing DSPy is the lack of competition. As far as I can tell, there's just no other serious programming model for general-purpose, declarative AI programming. I can spend hours listing the costs/downsides of this, not the least of which is the implicit comparison against LLM libraries in too many people's minds. Another downside is that it's really hard for an entity to improve by competing against baselines that suck. Too easy to be complacent, so we have to start & keep challenging ourselves.

New paper out in collaboration with @LakshyAAAgrawal which: 1. Compares rollout efficiency of prompt optimizers and GRPO on DSPy LM programs 2. introduces a new reflective prompt optimizer, GEPA, which will be live on DSPy soon Lots more exciting work coming soon!

Methods that may not have even existed when you wrote your DSPy program... Policy gradient RL (GRPO) vs Bayesian search over grounded instruction/fewshot proposals (MIPRO) vs Reflective prompt learning (GEPA) All optimizing identical DSPy programs! And better optimizers to come