GEMINI LABJP
PRICE — Gemini 3.6 Flash consumes about 17% fewer output tokens and costs less at $1.50 per 1M input and $7.50 per 1M output, against $9 output for 3.5 FlashLITE — Gemini 3.5 Flash-Lite targets high-throughput work at $0.3 per million input tokensCYBER — Gemini 3.5 Flash Cyber powers vulnerability detection and patching inside Google's CodeMender agentGEMINI4 — Google says it has already begun its most ambitious pre-training run yet, for Gemini 4, even as 3.5 Pro slipsSUNSET — The Imagen 4 and Gemini 3 Image generation models shut down on August 17, 2026, so integrations need moving to newer stable or preview endpointsSTUDIO — Gemini Omni Flash is available in Google AI Studio for the first time, putting cost-efficient video generation and conversational editing within reachPRICE — Gemini 3.6 Flash consumes about 17% fewer output tokens and costs less at $1.50 per 1M input and $7.50 per 1M output, against $9 output for 3.5 FlashLITE — Gemini 3.5 Flash-Lite targets high-throughput work at $0.3 per million input tokensCYBER — Gemini 3.5 Flash Cyber powers vulnerability detection and patching inside Google's CodeMender agentGEMINI4 — Google says it has already begun its most ambitious pre-training run yet, for Gemini 4, even as 3.5 Pro slipsSUNSET — The Imagen 4 and Gemini 3 Image generation models shut down on August 17, 2026, so integrations need moving to newer stable or preview endpointsSTUDIO — Gemini Omni Flash is available in Google AI Studio for the first time, putting cost-efficient video generation and conversational editing within reach
TAG

gemini-embedding-2

7 articles
Back to all tags
Related:
Gemini API4Image Classification2Indie Development2Cost Optimization2gemini2rag2multilingual1vector search1evaluation1Structured Output1Taxonomy1file-search1
Gemini Advanced/2026-07-17Advanced

A Japanese query won't surface its English twin — when embeddings notice language before meaning

Embed a translation pair with gemini-embedding-2 and the two halves won't be nearest neighbours, because language itself inflates similarity. Here is how I measured cross-lingual recall using translation pairs as ground truth, and what happened when I subtracted the language centroid.

Gemini Advanced/2026-07-15Advanced

A near-miss label won't fix itself on retry — a normalization layer for closed-vocabulary classification

When responseSchema enum returns an out-of-set label, retrying tends to return the same near-miss. From a wallpaper app's 30-category batch, here is the distribution of how labels miss, plus a normalization layer built on an alias table and gemini-embedding-2 nearest-neighbor, with measured results.

Gemini Advanced/2026-07-10Advanced

The Day We Went From 30 Categories to 34 — Reclassifying 1,180 Assets Instead of 8,142

Adding categories to a taxonomy does not require reclassifying everything. Here is how embeddings and confidence margins narrowed a backfill from 8,142 assets to 1,180, with the numbers.

Gemini API/2026-06-23Advanced

Your File Search Store Goes Stale in Production — Catalog Sync and Drift Detection That Actually Hold

Load a catalog into File Search once and forget it, and within weeks it starts confidently pointing users at assets you already pulled. Here is the sync pipeline I run: hash-based incremental import, a blue/green rebuild that swallows deletions, and a nightly drift audit.

Gemini API/2026-06-19Advanced

Catch Near-Duplicate Images Before You Publish with gemini-embedding-2

This is about removing near-duplicates, not image search. Use gemini-embedding-2 multimodal embeddings to vectorize images, cluster them, and build a pre-publish gate — with working code and threshold guidance.

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/2026-06-13Advanced

Rebuilding a Three-Layer RAG Cache After Migrating to Gemini 3.5 Flash

When Gemini 2.0 Flash was retired, I rebuilt my RAG caching stack around 3.5 Flash. Here are the working implementations for response, semantic, and embedding caches, measured hit rates from production, and how self-managed caching divides the work with the API's Context Caching.