Searching structured data has always meant knowing the exact words it was tagged with. Search for “servers with thermal issues” and you’ll miss every record tagged “CPU throttling” or “fan degradation.” Search for “customers upset about billing” and you’ll miss “subscription surcharge dispute.”
Starting today, every dynamic schema in Omnismith understands intent, not just keywords. Native semantic search — powered by Google’s gemini-embedding-2 model — is built directly into the platform, alongside the exact-match search you already rely on.
What This Unlocks
- Ask in plain English. Describe a problem, a symptom, or a concept, and Omnismith finds the records that match the meaning — even when the wording is completely different.
- No separate vector database. Semantic search lives inside your existing project data. There’s nothing extra to stand up, sync, or keep consistent, and every result still respects the same project and field-level permissions your team already has.
- Built for your AI assistant, not just the UI. Claude, Cursor, or any MCP-connected assistant chooses semantic search automatically for conceptual requests, and falls back to exact search when you give it precise criteria.
- Ready for more than text.
gemini-embedding-2understands text, images, audio, and documents in one shared space. As Omnismith expands to index file attachments and scanned documents, they’ll search the same way — no migration required.
In Practice
Imagine an infrastructure project tracking hundreds of servers and incident logs. A record might read: “Fan RPM degraded; CPU temperature peaked at 98°C causing frequency drops.”
Ask your AI assistant to “find servers showing signs of overheating or thermal instability,” and that record surfaces at the top — even though it never uses the words “overheating” or “thermal.” Omnismith understood what you meant.
Try It Today
Semantic search is live now across every project — no configuration, no re-indexing, and no change to how your data is structured. Just start asking.
- See how your AI assistant already turns plain language into structured queries in AI Tool-Calling: Translating Business Requirements to Database Schemas.
- Learn more about how Omnismith keeps your schema flexible in the Headless Backend Guide.