/query

Description

Query store with natural language RAG

Argument

prompt --store name

Prompt Preview

Query a Gemini File Search store with natural language using RAG (Retrieval-Augmented Generation).

## Usage



## Arguments

- `PROMPT`: Natural language query (required, positional)
- `--store NAME`: Store to query (required)
- `--query-model {flash|pro}`: Query model (default: flash)
- `--query-grounding-metadata`: Include source citations
- `--show-cost`: Show token usage and cost
- `-v/-vv/-vvv`: Verbosity levels

## Examples



## Output

Returns JSON with response_text, usage_metadata, grounding_metadata (if requested), and estimated_cost (if requested).

Other plugins with /query

llm-research

Query research memory history

research-memory

Query research memory history

pinecone

Query a user's index with Pinecone MCP. Accept an index name, input query, and optionally a top-k value

gemini-google-maps-tool

Query Gemini with Google Maps location data

sensei

Query sensei for accurate documentation and guidance