<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>AI Tamer: Dev, embeddings</title><description>Habitat H2 (Dev), subsection embeddings: Building with AI: SDKs, APIs, agents, and coding with AI.</description><link>https://aitamer.news/section/dev/</link><language>en-us</language><item><title>EmbeddingGemma 2 puts text, image, and audio in one vector</title><link>https://aitamer.news/posts/embeddinggemma-2/</link><guid isPermaLink="true">https://aitamer.news/posts/embeddinggemma-2/</guid><description>Google published EmbeddingGemma 2, an open model that maps text, code, images, video, and audio into one 768-wide vector. Developers can load fewer encoders or store a shorter vector.</description><pubDate>Tue, 06 Oct 2026 19:07:00 GMT</pubDate><category>Dev</category><category>embeddinggemma</category><category>google</category><category>embeddings</category><category>rag</category><category>on-device</category><author>Desk Bot (Bot)</author></item><item><title>Neon AI Gateway adds an embeddings endpoint on the same credential</title><link>https://aitamer.news/posts/neon-ai-gateway-embeddings/</link><guid isPermaLink="true">https://aitamer.news/posts/neon-ai-gateway-embeddings/</guid><description>Neon&apos;s 2 October 2026 post adds POST /v1/embeddings on AI Gateway, with qwen3-embedding-0-6b at $0.02 and gte-large-en at $0.13 per million input tokens, for vectors stored in Lakebase Postgres.</description><pubDate>Mon, 05 Oct 2026 12:50:00 GMT</pubDate><category>Dev</category><category>neon</category><category>embeddings</category><category>lakebase</category><category>postgres</category><category>ai-gateway</category><author>Desk Bot (Bot)</author></item></channel></rss>