Google GeminiAI and LLM Providers
Gemini Reads Your Library and Shows Its Sources
Google serves the Gemini model family and embedding models over a hosted API. Connected to AI Intelligence Hub, Gemini can embed your content for retrieval by meaning. It can also write the answer to a question from the passages retrieved for it, with a citation to each. The inspection videos, recordings and documents stay in Nexus under your access rules. Google receives text: what to embed, the question, and the passages behind the answer.
What you can do together
- Ask AI Intelligence Hub a question across inspection video, call recordings and procedure documents and get one answer with a citation card for each source.
- Find footage by what it shows, because visual descriptions are embedded alongside transcripts, OCR text and document text.
- Run one agent on Gemini for the shared procedures library and another on a self-hosted model for material that must stay on your own network.
- Attach a photo or a document in the conversation for analysis and keep asking in the same context.
- Build a workflow with a Gemini node in it and a human approval step before the result is published.
How it connects
AI Intelligence Hub calls Google's REST API with your organization's own account and key. The language model is configuration, set per deployment or per agent, so different agents can run different models. The embedding provider is configured separately and can be Google as well.
Two things flow. At indexing time, the text of transcripts, OCR output, visual descriptions and documents goes to the embedding endpoint and vectors come back to the index. At question time, the question and the passages retrieved for the asking user go to Gemini and the answer returns, cited to the passages it drew on.
Retrieval runs under the asking user's own identity, with their access list applied before the vector search. Media files never go to Google, only text, and the library stays where it is.
Google GeminiAI and LLM Providers
A scenario
- SetupIT enters the utility's Google key in AI Intelligence Hub and selects a Google embedding model for the index. Gemini becomes the model for the Field Operations agent, scoped to the inspections and procedures folders.
- NightlyThe day's inspection videos are transcribed and described on ingest, and the descriptions, transcripts and updated procedures are embedded through Google. The vectors join the index; the video stays in Nexus.
- 07:15A maintenance planner asks, "Which substation inspections this quarter noted corrosion on transformer bushings?" The agent retrieves passages from the descriptions and inspection reports he is permitted to open and sends them to Gemini with the question.
- Seconds laterThe answer lists four inspections, each cited to the moment in its video. He opens a card and the video plays from that frame.
- 07:25He asks what the procedure requires after a corrosion finding. The conversation carries the context, and the answer cites the procedure page.
- Same dayA contractor account that can open only its own crews' videos asks the same question and gets only those. Prompts and text went to Google; no video left the utility's deployment.
What stays where
Google keeps serving the models
The account, the key, the usage and the choice of model per agent are yours.
AI Intelligence Hub sends text, not media
Text to embed goes out and vectors come back; a question and its retrieved passages go out and an answer comes back. Nothing else travels.
Nothing is replaced
Changing the model behind an agent is a configuration change, and the workflows behind it stay as they are.
Where processing runs
Google processes prompts and embeddings in its hosted service. The platform runs as SaaS, in your own cloud subscription, on your own servers, or air-gapped. An air-gapped deployment cannot reach a hosted API and runs its models through Ollama or vLLM instead.
Products and solutions
Next step
See it on your own Google Gemini instance.
We will show the connection made, the data moving and the output, then size it for your deployment.
Contact VIDIZMO
sales@vidizmo.ai
+1 571-969-2180
vidizmo.ai