Dnvriend Gemini File Search Tool
dnvriend-gemini-file-search-tool is a Claude Code plugin for the Build phase that manages Gemini File Search stores and Q&A via CLI and Python.
by dnvriend · github.com/dnvriend/gemini-file-search-tool
Create and query Gemini File Search stores from CLI or Python so your agent can run managed RAG over product docs, specs, and support PDFs.
Add it to Claude Code
Install the plugin in Claude Code. One command, paste-ready.
/plugin install dnvriend-gemini-file-search-tool@dnvriend/gemini-file-search-toolBuilt to be called by your agent
Skillselion is itself an MCP server. Your agent can pull this entry and a paste-ready install config straight from the API - no copy-paste.
Retrieve this entry with skillselion.get_details("plugin:dnvriend/gemini-file-search-tool") and the paste-ready config with skillselion.get_install_config("plugin:dnvriend/gemini-file-search-tool").
What it does
dnvriend-gemini-file-search-tool brings Google’s Gemini File Search API to the terminal and Python so Claude Code can administer corpora and ask grounded questions without you wiring vector databases by hand. Indie builders shipping doc assistants, internal copilots, or support bots frequently stall on ingest pipelines and store versioning; this plugin centers on the managed RAG surface—file upload, store management, and query—described in the catalog as production-ready. It sits in Build agent-tooling as phase-specific infrastructure you adopt while composing retrieval features, with natural spillover into Validate when you prototype whether uploaded specs answer real user questions. Advanced complexity reflects Google Cloud or Gemini API setup, permissions on document buckets, and designing chunk-friendly source material. It is an integration plugin, not a turnkey customer-facing chat UI—you still own auth, prompts, and evaluation.
Highlights
- Production-ready CLI and Python library for Google Gemini File Search API
- Fully managed RAG pattern: upload documents, manage stores, run queries
- Catalog keywords include file, gemini, manage, query, search, and stores
- Single Claude Code plugin in the bundle (pluginCount: 1)
- Fits solo builders standing up doc Q&A without self-hosting embeddings infra
Why builders use it
Rolling your own RAG stack for document Q&A is heavy when you only need managed ingest, search stores, and API-driven answers over PDFs and specs.
After registration, Claude Code can create stores, load files, and query Gemini File Search so your agent or app returns grounded answers from your corpus.
At a glance
- Type - Plugin in LLM Integration.
- Adoption - 0 installs, 0 stars, 0 votes.
FAQ
Who is dnvriend-gemini-file-search-tool for?
Builders using Claude Code who need managed document search and Q&A on Google Gemini File Search without maintaining their own embedding pipeline.
When should I use dnvriend-gemini-file-search-tool?
Use it during Build agent-tooling when you are uploading specs, wiring store management, and validating retrieval quality before shipping a doc-aware assistant.
How do I add dnvriend-gemini-file-search-tool to my agent?
Install the dnvriend/gemini-file-search-tool Claude Code plugin, configure Gemini API credentials per the repo, install the CLI or Python package, then expose tool calls for store and query commands.
Comments
Share how you use dnvriend-gemini-file-search-tool, gotchas, or tips for other indie builders.
No comments yet - be the first to share how you use it.