Spice AI

A few weeks ago, we introduced hybrid SQL search and the performance and productivity benefits of combining vector, keyword, and full-text search in a single SQL query (more here: https://hubs.ly/Q03M7P8b0). With this week's v1.7.1 release, we’re building on this with support for Reciprocal Rank Fusion (RRF) as a user-defined table function. RFF makes it even more simple to combine results from multiple search modalities in one query for better ranking and relevance. 🔹 Fuse vector_search, text_search, and other UDTFs 🔹 Tune per-query weights & recency boosting 🔹 Optimize with join keys or let Spice handle it automatically To get started, Spice Principal Engineer David S. authored a cookbook showing how to use RRF to power advanced search pipelines in real-time data. Check it out: https://hubs.ly/Q03M7y9r0

Building on last week’s v1.7.0 release, we're excited to announce v1.7.1! The latest release delivers big improvements to hybrid search and observability: ✔️Reciprocal Rank Fusion (RRF) UDTF: Combine results from multiple search methods for better relevance and ranking ✔️New Prometheus Acceleration Metrics: Deeper insight into dataset refresh and ingestion lag ✔️Runtime & Connector Fixes: Reliability improvements across full-text search, vector search, and Databricks Full release notes 👉 https://hubs.ly/Q03LYQLd0

In this 2-minute walkthrough, Ellison Dykes demonstrates how to use Spice to join and accelerate data across S3, PostgreSQL, and Dremio in a single SQL query. You’ll learn how Spice simplifies access to both analytical and operational data, eliminates the need to move or duplicate data, and boosts performance with local acceleration. Follow along in the Federated SQL Query cookbook: https://hubs.ly/Q03LS61p0

We’re hosting our second Release Community Call to demo what’s new in Spice v1.7! 📅 Thursday, October 2nd at 4:00 pm PT 💡 Some of the highlights we'll cover: - Faster queries & smarter optimization with DataFusion v49 - Real-time full-text search indexing + embedding caching - New Reciprocal Rank Fusion (RRF) support for advanced hybrid search - Improved reliability across connectors & query engine Bring your questions and we look forward to seeing you on Zoom! Register here: https://hubs.ly/Q03LxYQC0

v1.7.0 In 2 Minutes! ✌️ Get all of the details in the full release blog: https://hubs.ly/Q03L9gnX0 And be sure to join us for the Spice Release Community Call on Thurs, Oct 2 @ 4PM PST for live demos and Q&A with the Spice engineering team. Register here: https://hubs.ly/Q03L9gl00

🎉 Announcing Spice v1.7.0! v1.7.0 introduces major improvements in performance, search, embeddings, and model integration. Highlights: ✔️Apache DataFusion v49 Upgrade: Faster query planning, dynamic filters, TopK pushdown, compressed spill files, new ordered-set aggregates, and regex functions. ✔️Real-Time Full-Text Search: Index CDC streams instantly for low-latency search on new data. ✔️EmbeddingGemma Support: Use Google’s high-quality embedding model for semantic search and retrieval. ✔️/v1/search API Improvements: Backed by new text_search and vector_search table functions for greater performance. ✔️Embedding Request Caching: Reduce cost and latency by caching repeated embedding requests. ✔️OpenAI Responses API Enhancements: Tool calls with streaming for real-time interactions. 📖 Check out the release blog for all of the updates and more info: https://hubs.ly/Q03K_zcq0

Why do most enterprise AI projects fail? Often, it's because accessing the right data with the appropriate search function, embedding that into an agentic workflow, and serving it with low latency has generally been unreasonably complex and/or cost prohibitive. Spice has taken a new approach to solving this problem - read our latest blog to learn more: https://hubs.ly/Q03KVn4q0

Why do most enterprise AI projects fail? Often, it's because accessing the right data with the appropriate search function, embedding that into an agentic workflow, and serving it with low latency has generally been unreasonably complex and/or cost prohibitive. Spice has taken a new approach to solving this problem - read our latest blog to learn more: https://hubs.ly/Q03KVn4q0

“We were wrangling with the embeddings for some weeks and found it quite frustrating. As soon as we deployed Spice, those problems were gone.” - Rachel Wong, CTO at Basis Set Basis Set needed to search continuously refreshed data on 10,000+ people and companies without the burden of managing embeddings or pipelines. Using Spice's data and AI engine, Basis Set investors can now run natural language searches directly against real-time & disparate datasets - ultimately delivering accurate, data-grounded insights that help them spot opportunities earlier and act faster. Read the case study for the full story: https://lnkd.in/ghFPJegH

Instead of wiring together separate systems and ETL pipelines for data and AI, you can do it all in Spice in one runtime. In this demo, Advay Patil demonstrates querying and accelerating data in Spice - and then calling OpenAI's Responses API endpoint from the same interface for additional insights. All it takes is a few lines of YAML! 📺 Watch the full demo: https://hubs.ly/Q03J-lmC0 📖 Docs: https://hubs.ly/Q03J-t7W0