Ashwin benchmarked Jev as a replacement for LLM-based reranking in Ramp's accounting product, and the results are very promising Jev matches current accuracy on GPT-5.6 Luna, but decreases tail latency by 10x to 300ms at 3x lower cost We're excited to get this into production for 70k customers as soon as we stop running into rate limits :)

We had Jev score Elasticsearch hybrid search results and let a short Python policy do the reranking. • nDCG@10 went from 0.9351 to 0.9565 (250 Amazon Queries) • Latency: 70–500ms end-to-end • Cost: $0.042/M input tokens (outputs free) No text parsing, just structured probabilities feeding business logic.

Ready to identify molecules from mass spectra in the Enveda CASMI 2026 competition? 🧪 Check out this starter notebook by haideptry. It walks you through candidate retrieval and reranking across four evidence channels, and is a great starting point to search spectral libraries, match structural analogs, simulate fragmentation, and rank candidates with a neural fingerprint model.

We benchmarked Jev against 19 reranker configs across 5 datasets. A few results: • HotpotQA Hit@1 improved 63.52% → 72.87% vs. no reranking • A better relevance prompt pushed it to 85.24% • 92.59% Hit@10 on GooAQ @ifoundanifty + @loldedxd dig in:

What if you could leave your recommendation retriever completely untouched and just bolt on one lightweight "verifier" to significantly boost recall? A team at Meta just showed exactly that. Title: Recommendation Retrievers Need Verifiers: Universal Generative Reranking for Sequential Recommendations URL: The idea is a "drafter-verifier" pipeline: freeze the existing retrieval model (the drafter) entirely, and add a lightweight verifier that generatively scores candidate items via their identifier tokens. 🌐 Highlight 1: It scales with catalog size On the YaMBDa music recommendation dataset, gains grew larger as the catalog got bigger — at the largest scale (4.65B interactions), Recall@10 improved by up to 29.8%. 🧩 Highlight 2: Works across wildly different drafters The same training recipe worked on 4 architecturally distinct drafters: attention-based SASRec, recurrent GRU4Rec, convolutional NextItNet, and even the LLM-based MiniOneRec. 🔬 Highlight 3: The gain really comes from generative verification Injecting content embeddings directly into the drafter actually hurt standalone performance, but adding the verifier on top recovered it — proving the improvement comes from the output-side generative verification process itself, not simple feature injection. The fact that it bolts on without touching the retrieval index feels like a big deal for adopting this in large-scale production. #RecSys# #MachineLearning#

The @latentspacepod team and I will be speaking at Mongodb's .local buildfest today 10a-4pmish, come by! We'll be covering: - tba Agent infra with @BazeleyMikiko! - the state of embeddings/reranking with @frankzliu @VoyageAI head of Applied ML - wearable AI with @a_israelov, CTO of Mentra! - their state of managed MCP with Gaurab Aryal - Jim Scharf, CTO MongoDB - AIE top speaker Apoorva Joshi click on only if you are gonna come... take one of my tix MDBLCL26INSIDER!

# Weaviate Features and Practical Usage 🚀 Ever wished you could delete all the embedding-API plumbing from your app code? Weaviate's model provider integrations let you wire up vectorization, generation, and reranking just by writing it into your collection config. 📌 Title and Feature URL Title: Model provider integrations URL: 📝 Overview Weaviate integrates with 20+ model providers including OpenAI, Cohere, Google, AWS, Azure OpenAI, Mistral, Anthropic, Hugging Face, and Ollama. You can plug them into automatic embedding at import, automatic embedding of query text, generation for RAG, and reranking of search results. The big win is that your application no longer needs code to call an embedding API and pass vectors in. 🔧 How It Works Integrations fall into three roles: - Vectorizer (embeddings): text or multimodal vectorization. - Generative (LLM): text generation for RAG pipelines. - Reranker: result refinement (offered by Cohere, Jina AI, NVIDIA, Voyage AI). There are also two delivery forms. API-based providers (OpenAI, Google, Cohere, AWS Bedrock, etc.) call external services, while locally hosted options (Ollama, Hugging Face Transformers, Model2vec) run on your own infrastructure. API-based modules are enabled by default in v1.33+. 🛠 Practical Usage - Specify an embedding provider with Configure.Vectors at collection creation, and Weaviate vectorizes automatically at both import and query time. - Configure generation with Configure.Generative to run RAG over your search results. - Configure a reranker with Configure.Reranker. - Automatic vectorization targets text / text[] properties. Weaviate sorts property names alphabetically, concatenates them, optionally prepends the collection name, and sends the string to the model (you can also exclude properties per-field). 🎯 Use Cases - Internal document search: auto-vectorize body text at import, and auto-vectorize the query with the same model so they stay consistent. - Model swapping: change vendor or model by editing collection config only. - Closed-network requirements: use a locally hosted option like Ollama to keep data in-house through embedding generation. - RAG chat: combine retrieval and generation within the same configuration, minimizing external orchestration. ⚠️ Caveats - API-based providers require API keys and incur usage charges. - Rate limits follow each provider's policy; watch out during bulk imports. - For versions before v1.27, the concatenated string is lowercased before being sent to the model. - For versions before v1.33, set ENABLE_API_BASED_MODULES to use API-based modules. #Weaviate# #Embeddings#