chore(release): @betterdb/semantic-cache v0.10.0 & betterdb-semantic-cache v0.8.0

Adds Google AI (Gemini) embedding provider to both packages (#160).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_018rezwnc5b5aaj9DwXHyrqi

Author: KIvanow

packages/semantic-cache-py/CHANGELOG.md

@@ -1,6 +1,10 @@
 # Changelog
 
-## [Unreleased]
+## [0.8.0] - 2026-07-09
+
+### Added
+
+- **Google AI (Gemini) embedding provider** — `create_google_embed()` in `embed/google.py` backs an `EmbedFn` with Google's `embedContent` REST API (default `text-embedding-004`, 768-dim). Configurable `task_type`, optional `title` and `output_dimensionality`, API key via `GOOGLE_API_KEY` or explicit config sent in the `x-goog-api-key` header. Uses `httpx` (via the `httpx` extra) with a `close()` helper to release the connection pool; no Google SDK dependency. Follows the existing Cohere/Voyage provider pattern.
 
 ### Changed
 

packages/semantic-cache-py/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "betterdb-semantic-cache"
-version = "0.7.0"
+version = "0.8.0"
 description = "Semantic cache for AI workloads backed by Valkey vector search. Embeddings-based similarity matching with OpenTelemetry and Prometheus instrumentation."
 keywords = ["valkey", "redis", "semantic-cache", "vector-search", "embeddings", "llm", "opentelemetry", "prometheus", "langchain", "langgraph"]
 license = { text = "MIT" }

packages/semantic-cache/CHANGELOG.md

@@ -5,6 +5,12 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.10.0] - 2026-07-09
+
+### Added
+
+- **Google AI (Gemini) embedding provider** — `createGoogleEmbed()` in `embed/google.ts` backs an `EmbedFn` with Google's `embedContent` REST API (default `text-embedding-004`, 768-dim). Configurable `taskType`, optional `title` and `outputDimensionality`, API key via `GOOGLE_API_KEY` or explicit config sent in the `x-goog-api-key` header. Native `fetch`, no SDK dependency; follows the existing Cohere/Voyage provider pattern.
+
 ## [0.6.0] - 2026-06-11
 
 ### Added

packages/semantic-cache/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@betterdb/semantic-cache",
-  "version": "0.9.0",
+  "version": "0.10.0",
   "description": "Valkey-native semantic cache for LLM applications with built-in OpenTelemetry and Prometheus instrumentation",
   "keywords": [
     "valkey",