31. Skip the transcript. Embed and retrieve the audio itself. This notebook shows you how to do it with... Skip the transcript. Embed and retrieve the audio itself. This notebook shows you how to do it with Weaviate and @GoogleDeepMind 's Gemini in a few simple steps: • Split raw au 07/28 23:00 ♡
32. A bigger context window won't fix a broken agentic RAG pipeline. Long contexts can introduce contra... A bigger context window won't fix a broken agentic RAG pipeline. Long contexts can introduce contradictory information, bury relevant tools, and cause later inputs to be ignore 07/24 00:01 ♡
33. 𝗙𝗶𝗿𝗲-𝗮𝗻𝗱-𝗳𝗼𝗿𝗴𝗲𝘁 𝗺𝗲𝗺𝗼𝗿𝘆 𝗳𝗼𝗿 𝗺𝘂𝗹𝘁𝗶-𝗮𝗴𝗲𝗻𝘁 𝗽𝗶𝗽𝗲𝗹𝗶𝗻𝗲𝘀? No block... 𝗙𝗶𝗿𝗲-𝗮𝗻𝗱-𝗳𝗼𝗿𝗴𝗲𝘁 𝗺𝗲𝗺𝗼𝗿𝘆  07/22 23:01 ♡
34. A slow search query doesn't 𝘁𝗲𝗹𝗹 𝘆𝗼𝘂 𝘄𝗵𝗮𝘁 𝘁𝗼 𝗼𝗽𝘁𝗶𝗺𝗶𝘇𝗲. The latency could be co... A slow search query doesn't 𝘁𝗲𝗹𝗹 𝘆𝗼𝘂 𝘄𝗵𝗮𝘁 𝘁𝗼 𝗼𝗽𝘁 07/22 00:00 ♡
35. 𝗠𝗮𝗻𝗮𝗴𝗲𝗱 𝗪𝗲𝗮𝘃𝗶𝗮𝘁𝗲 𝗶𝘀 𝗻𝗼𝘄 𝗮𝘃𝗮𝗶𝗹𝗮𝗯𝗹𝗲 𝗼𝗻 𝗗𝗶𝗴𝗶𝘁𝗮𝗹𝗢𝗰𝗲𝗮𝗻 𝗶𝗻 ... 𝗠𝗮𝗻𝗮𝗴𝗲𝗱 𝗪𝗲𝗮𝘃𝗶𝗮𝘁𝗲 𝗶𝘀 𝗻𝗼ǖ 07/16 22:00 ♡
36. M Most AI agents get 𝗱𝘂𝗺𝗯𝗲𝗿 as they learn more. (There's a better way) We just released a demo... Most AI agents get 𝗱𝘂𝗺𝗯𝗲𝗿 as they learn more. (There's a better way) We just released a demo of 𝗘𝗻𝗴 07/14 23:00 ♡
37. Y You've typed the perfect search query and gotten completely useless results. Here's what modern pro... You've typed the perfect search query and gotten completely useless results. Here's what modern product discovery looks like when it actually works. The Weaviate Playground 07/09 21:50 ♡
38. M Most developers pick the wrong search method. We built a demo so you can see exactly why. Our keyw... Most developers pick the wrong search method. We built a demo so you can see exactly why. Our keyword vs vector search demo in the Weaviate Playground lets you explore and compare 07/08 21:50 ♡
39. Most vector database demos show you search. This one shows you how information organizes itself. T... Most vector database demos show you search. This one shows you how information organizes itself. This newspaper-themed demo in Weaviate Playground showcases vector clustering in ac 07/07 21:36 ♡
40. F Fraud detection used to be slow, rigid, and blind to novel patterns. Here's what conversational dat... Fraud detection used to be slow, rigid, and blind to novel patterns. Here's what conversational data exploration looks like instead. Powered by the 𝗪𝗲𝗮& 07/02 23:00 ♡
