GEMINI LABJP
VIDS — Gemini Omni is now built directly into Google Vids, so a text prompt can change style, color grading, or strip background noiseHOME — The Gemini for Home conversation memory window stretched to 15 minutes, so follow-ups no longer need the full context repeatedLIVE — Gemini Live reached the first-generation Google Home Mini and Nest Hub, and the July Nest Cam update is rolling out alongside itDOCS — Gemini-powered document creation and editing in Google Docs added 11 more languages, with context drawn from your Workspace dataLOGS — Since July 6, developer logs for supported Interactions API calls are viewable right in the AI Studio dashboardSAATHI — ATL Saathi, a Gemini-powered web app for educators, is piloting across 100 schools in IndiaVIDS — Gemini Omni is now built directly into Google Vids, so a text prompt can change style, color grading, or strip background noiseHOME — The Gemini for Home conversation memory window stretched to 15 minutes, so follow-ups no longer need the full context repeatedLIVE — Gemini Live reached the first-generation Google Home Mini and Nest Hub, and the July Nest Cam update is rolling out alongside itDOCS — Gemini-powered document creation and editing in Google Docs added 11 more languages, with context drawn from your Workspace dataLOGS — Since July 6, developer logs for supported Interactions API calls are viewable right in the AI Studio dashboardSAATHI — ATL Saathi, a Gemini-powered web app for educators, is piloting across 100 schools in India
TAG

File Search

6 articles
Back to all tags
Related:
Gemini API5RAG3indie development2multimodal2Managed Agents1Architecture1customMetadata1Embeddings1Data Lifecycle1Operations1Gemini1Deep Research1
Gemini Advanced/2026-07-08Advanced

When Your Knowledge Base Shifts Mid-Run: Pinning File Search to an Execution Epoch for Consistent Agent Grounding

When a File Search store is updated while a Managed Agent is running, a single execution can mix old and new grounding. Borrowing MVCC ideas, pinning an execution epoch keeps one agent run's evidence consistent. Here is the design and implementation.

Gemini Advanced/2026-07-08Advanced

One File Search Store for Many Apps: Splitting Retrieval With customMetadata and Chunk Config

Put several apps' FAQs in a single Gemini File Search store and metadataFilter can silently return empty grounding, or answers get split across chunk boundaries. Here is the customMetadata design, the AIP-160 filter-syntax trap, and measured chunkingConfig tuning.

Gemini Dev/2026-07-02Advanced

Deleting the Source Isn't Enough — A Ledger Design for Propagating Deletes Through Gemini-Derived Data

When a user deletes their data, the embeddings, caches, and File Search documents you generated from it live on. A provenance ledger written at generation time, per-sink propagation workers, and a verification sweep make deletion actually reach your derived data.

Gemini Advanced/2026-06-27Advanced

Don't Ingest Gemini Deep Research Reports Blindly — A Citation-Verification Acceptance Gate for MCP-Grounded Research

Now that Deep Research connects to MCP servers and File Search, you can ground research on your own data. This builds an acceptance gate that verifies, before any automated ingest, whether each citation resolves to a trusted source — with an allowlist, a grounding-coverage ratio, and categorized reject reasons, all in working code.

Gemini API/2026-06-15Intermediate

Put Help Docs and Screenshots in One File Search Store and Return Answers That Cite the Image Too

Your text help docs and your screenshots live in separate stores, so a single question can never return both the steps and the matching screen. With gemini-embedding-2 going multimodal in File Search, here is how I merged them and returned the cited screenshot alongside the answer.

Gemini API/2026-06-12Intermediate

Letting File Search's Multimodal Mode Find Wallpapers I Couldn't: A Field Report

I tested whether File Search's new multimodal retrieval (gemini-embedding-2) could replace category tags for finding one wallpaper among thousands. A 300-image trial, the walls I hit, and where semantic search actually fits — with working code.