Mixedbread (@mixedbreadai) / X

Mixedbread

124 posts

Mixedbread

@mixedbreadai

Building retrieval for agents.

San Francisco, CA

Joined March 2024

Pinned
Mixedbread
@mixedbreadai
Mar 12
Introducing Mixedbread Wholembed v3, our new SOTA retrieval model across all modalities and 100+ languages. Wholembed v3 brings best-in-class search to text, audio, images, PDFs, videos... You can now get the best retrieval performance on your data, no matter its format.
202K
Mixedbread
@mixedbreadai
Jun 10
Replying to @mixedbreadai
Agents can inspect file metadata in a store to understand available filters. docs: mixedbread.com/docs/stores/se…
203
Mixedbread
@mixedbreadai
Jun 10
New: Metadata explorer Adding metadata to files enables filtering during search. Now, you can browse metadata fields and values across your store.
00:00
1.5K
Mixedbread
@mixedbreadai
Jun 2
Replying to @mixedbreadai
Read more here:
Dense Retrievers Know More Than They Can Express
From mixedbread.com
1.4K
Mixedbread
@mixedbreadai
Jun 2
Replying to @mixedbreadai
Having language-adjacent properties means that tools designed for lexical approaches "just work". BM25, always refusing to exit the scene, is strong here: applied over the Latent Terms extracted from nomic-embed-v1.5, it results in a near state-of-the-art sparse retriever.
2.6K
Mixedbread
@mixedbreadai
Jun 2
Replying to @mixedbreadai
Our setup is simple: we use Sparse Autoencoders, common in interpretability, to project token representations from common embedders into a sparse latent space. It turns out that the activations in this sparse latent space follow the same distribution as natural language.
1.8K
Mixedbread
@mixedbreadai
Jun 2
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.
00:00
40K
Mixedbread
@mixedbreadai
May 27
Replying to @mixedbreadai
docs:
mixedbread.com
Grep Store Chunks
Match store chunks against a regular expression. Unlike `/stores/search`, this runs your regex against the literal text of each chunk. Use it to find chunks containing a specific token, identifier,...
599
Mixedbread
@mixedbreadai
May 27
New: grep for exact matching grep → keyword / regex matching search → 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.
5.5K
Mixedbread
@mixedbreadai
May 25
Replying to @mixedbreadai
View and export traces directly from your dashboard:
630
Mixedbread
@mixedbreadai
May 25
Replying to @mixedbreadai
Steer search with more instructions. Docs: mixedbread.com/docs/stores/se…
812
Mixedbread
@mixedbreadai
May 25
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 → Topped MADQA @Snowflake with 93.4% accuracy across 18,000 PDF
8.9K
Mixedbread
@mixedbreadai
May 24
New: Traces for Mixedbread agentic search See every search call an agent makes directly in the dashboard, and tune instructions for better retrieval quality.
00:00
6.6K