redis-semantic-cache

Redis Semantic Cache

Semantic caching for LLM responses with Redis Cloud's LangCache service. Stores prompts as embeddings; subsequent semantically-similar prompts return the cached response without re-calling the model.

LangCache is currently in preview on Redis Cloud. Features and behavior may change.

When to apply

• Wrapping an LLM call (OpenAI, Anthropic, etc.) with a cache layer to cut cost and latency.
• Caching RAG answers, classification outputs, or any deterministic LLM workload.
• Tuning the precision/hit-rate trade-off for a semantic cache.
• Splitting one application's LLM workloads across multiple cache instances.

1. The cache-aside flow

LangCache fits in front of any LLM call as a standard cache-aside pattern:

1. Send the user's prompt to LangCache's search.
2. Cache hit — return the stored response directly.
3. Cache miss — call the LLM, then set the response so future similar prompts hit.

from langcache import LangCache
import os
 
lang_cache = LangCache(
    server_url=f"https://{os.getenv('HOST')}",
    cache_id

The same operations are available via REST (POST /v1/caches/{cacheId}/entries/search and POST /v1/caches/{cacheId}/entries) when an SDK isn't an option.

See references/langcache-usage.md for full SDK + REST samples and attribute-based storage.

2. Tune the similarity threshold

The threshold controls how close (in embedding cosine distance) a new prompt must be to a cached one to count as a hit. Higher = stricter match, fewer false positives. Lower = more hits, more risk of returning an off-topic answer.

Adjust by watching the actual cache-hit rate and spot-checking that returned answers are still relevant.

See references/best-practices.md.

3. Separate caches per task type

Different LLM workloads should not share one cache — a "code question" prompt is semantically close to other code questions but has nothing to do with a password-reset support query, and crossing them returns garbage.

Create distinct cache IDs in Redis Cloud per task, and route each call to the right one. As a finer-grained alternative, store and search with custom attributes (e.g. {"category": "database"}) to keep tasks in the same cache but isolated by attribute filter — useful when the same prompt format spans subtopics.

References

• LangCache documentation