Broken search? Where do you even start? Here's my 5 Simple Steps to Fix Your Search - a lightning talk from Haystack Europe a couple of weeks ago. With juggling, naturally! #haystackconfyoutube.com/watch?v=GFhfwIy_…
Just back from #HaystackUS 2025 and the future of search is 🔥
From lexical resurgence to LLM-first architectures, here’s what we learned at #Haystackconf—and how you can apply it to build better, more scalable search.
Dive into the key insights via Algolia's @chuckm: bit.ly/4lLkTMT
Team Algolia is excited to be at #HaystackConf this week! 🔍✨
Looking forward to learning from the community and exploring the latest advances in query understanding and RAG with #AIsearch.
Let’s connect! #RAG#SearchTech
All the talk videos from #HaystackConf Europe 2024 are now publically available - some amazing insights here from leading minds in search & AI - check it out! youtube.com/playlist?list=PL…
Great talk from @macavaney at #HaystackConfyoutube.com/watch?v=e9Yh7IAX… Initializing vector index traversal given a cheap set of lexical search results makes sense. But also using that technique to gather better reranking docs?!? 🤌🧑🍳
My deck from #HaystackConf is now available!
What You See Is What You Search: Vision Language Models for PDF Retrieval
ColPali, a newly proposed retrieval model, presents a more efficient alternative using Vision Language Models (VLMs) to embed entire PDF pages, including text, figures, and charts. The resulting contextualized multi-vector representations of the PDF page improve retrieval quality while simplifying the extraction and indexing process.
docs.google.com/presentation…