Redis Semantic Cache
Wire Redis LangCache so LLM calls use semantic cache-aside with tuned thresholds and separate caches per task.
Overview
redis-semantic-cache is an agent skill for the Build phase that configures Redis LangCache similarity thresholds and per-task caches for LLM responses.
Install
npx skills add https://github.com/redis/agent-skills --skill redis-semantic-cacheWhat is this skill?
- Documents cache-aside flow for LLM responses via Redis LangCache (preview)
- Tunable similarity thresholds (e.g. 0.95 strict vs 0.8 higher hit rate)
- Separate cache IDs per task (support vs code generation)
- Python LangCache client examples with server URL, cache_id, and API key env vars
- Similarity threshold examples: 0.95 (stricter) and 0.8 (looser) documented in SKILL.md
- Recommends separate cache IDs for distinct LLM tasks (e.g. support vs code)
Adoption & trust: 1 installs on skills.sh; 70 GitHub stars; trending (+100% hot-view momentum).
What problem does it solve?
Your agent app repeats similar LLM prompts and burns tokens because every request hits the model with no semantic reuse.
Who is it for?
Builders on Redis Cloud preview LangCache who want Python-ready cache-aside patterns for distinct LLM workloads.
Skip if: Projects without Redis LangCache, or teams that need exact string match caching only with no embedding similarity.
When should I use this skill?
When adding or tuning Redis LangCache for LLM cache-aside with similarity search and per-use-case cache separation.
What do I get? / Deliverables
LangCache searches run with task-appropriate thresholds and isolated cache IDs before falling back to live generation.
- Configured LangCache client calls with thresholds
- Per-task cache_id separation pattern
Recommended Skills
Journey fit
Semantic caching is implemented while integrating the LLM stack into your product backend. LangCache client setup, thresholds, and multi-cache IDs are integration work against Redis Cloud—not generic prompt tuning alone.
How it compares
Integration skill for managed semantic cache—not a substitute for application-level prompt versioning or eval harnesses.
Common Questions / FAQ
Who is redis-semantic-cache for?
Solo and indie developers integrating LLM APIs who already use or plan Redis LangCache on Redis Cloud.
When should I use redis-semantic-cache?
During Build integrations when you wire production LLM routes and need threshold and multi-cache tuning before Ship load testing.
Is redis-semantic-cache safe to install?
Treat API keys and cache IDs as secrets; confirm preview-service terms and review Security Audits on this Prism page before install.
SKILL.md
READMESKILL.md - Redis Semantic Cache
{ "name": "redis-semantic-cache", "version": "1.0.0", "description": "Redis LangCache — cache-aside flow for LLM responses, similarity threshold tuning, per-task cache separation.", "author": { "name": "Redis", "email": "support@redis.com" }, "homepage": "https://redis.io", "repository": "https://github.com/redis/agent-skills", "license": "MIT", "keywords": ["redis", "semantic-cache", "langcache", "llm", "ai"] } # Configure Semantic Cache Properly > **Note:** LangCache is currently in preview on Redis Cloud. Features and behavior may change. Tune similarity threshold and cache separation for optimal LangCache results. **Correct:** Tune similarity threshold for your use case. ```python from langcache import LangCache lang_cache = LangCache( server_url=f"https://{os.getenv('HOST')}", cache_id=os.getenv("CACHE_ID"), api_key=os.getenv("API_KEY") ) # Stricter matching - fewer false positives (0.95 = very similar) result = lang_cache.search( prompt="What is Redis?", similarity_threshold=0.95 ) # Looser matching - higher hit rate (0.8 = somewhat similar) result = lang_cache.search( prompt="What is Redis?", similarity_threshold=0.8 ) ``` **Correct:** Use separate caches for different use cases. ```python # Create different cache IDs in Redis Cloud for different LLM tasks support_cache = LangCache( server_url=server_url, cache_id="support-cache-id", api_key=api_key ) code_cache = LangCache( server_url=server_url, cache_id="code-cache-id", api_key=api_key ) ``` **Incorrect:** Using a single cache for all LLM tasks. ```python # All tasks share one cache - responses may not be relevant result = lang_cache.search(prompt="How do I reset my password?") # Could return a code snippet if someone asked a similar coding question ``` **Best practices:** - Start with threshold 0.9, adjust based on your use case - Use custom attributes to filter results within a single cache - Monitor cache hit rates to evaluate effectiveness - Use separate cache IDs for fundamentally different LLM tasks Reference: [LangCache Best Practices](https://redis.io/docs/latest/develop/ai/langcache/) # Use LangCache for LLM Response Caching > **Note:** LangCache is currently in preview on Redis Cloud. Features and behavior may change. LangCache is a fully-managed semantic caching service on Redis Cloud that reduces LLM costs and latency. **How it works:** 1. Your app sends a prompt to LangCache via `POST /v1/caches/{cacheId}/entries/search` 2. LangCache generates an embedding and searches for similar cached responses 3. If found (cache hit), returns the cached response instantly 4. If not found (cache miss), your app calls the LLM and stores the response **Correct:** Use the LangCache Python SDK. ```python from langcache import LangCache import os lang_cache = LangCache( server_url=f"https://{os.getenv('HOST')}", cache_id=os.getenv("CACHE_ID"), api_key=os.getenv("API_KEY") ) # Search for cached response result = lang_cache.search( prompt="What is Redis?", similarity_threshold=0.9 ) if result: response = result[0]["response"] else: response = llm.generate("What is Redis?") # Store for future queries lang_cache.set( prompt="What is Redis?", response=response ) ``` **LangCache REST API:** ```bash # Search cache curl -X POST "https://$HOST/v1/caches/$CACHE_ID/entries/search" \ -H "Authorization: Bearer $API_KEY" \ -H "Content-Type: application/json" \ -d '{"prompt": "What is Redis?"}' # Store a response curl -X POST "https://$HOST/v1/caches/$CACHE_ID/entries" \ -H "Authorization: Bearer $API_KEY" \ -H "Content-Type: application/json" \ -d '{"prompt": "What is Redis?", "response": "Redis is an in-memory database..."}' ``` **With custom attributes for filtering:** ```python # Store with attributes lang_cache.set( prompt="What is Redis?", response="Redis is an in-memory database...", attributes=