EdgeDB 5: Introducing ext::ai
Blog post from Gel Data
In EdgeDB 5.0, the ext::ai extension enables semantic similarity search and indexing of content using embeddings, allowing developers to easily perform searches without manual embedding creation. The new deferred index mechanism allows for asynchronous index creation, avoiding blocking object mutation during slow operations. The ext::ai extension also supports calling into OpenAI, Mistral, and Anthropic model APIs out of the box, enabling RAG (Reinforcement Algorithm for Generation) with database data as context. A JavaScript package provides a convenient wrapper for the ext::ai HTTP API, allowing developers to build AI-enabled apps in minutes.
| Trend | Post Mentions | Total Month Mentions | Posts | Companies | MoM |
|---|---|---|---|---|---|
| RAG | 5 | 1,795 | 223 | 72 | +55% |
| Vector Search | 3 | 2,613 | 257 | 91 | +44% |
| LLM | 2 | 3,398 | 379 | 136 | +44% |
| Real-time | 1 | 2,334 | 631 | 194 | -8% |
Use this post, company, and trend context to find content marketing opportunities, perform competitive analysis, or address product feature gaps via the Plushcap MCP server or the Plushcap API.