mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-11 22:51:28 +00:00
16db51e2cf
Semantic cache keys omit the prompt, so every end user behind one virtual key shares a bucket and can be served another user's semantically similar response. Add an opt-in cache_params.semantic_cache_scope (key | end_user) that appends the authenticated end-user id to the tenant scope, read from metadata and litellm_metadata so /v1/chat/completions, /v1/responses and /v1/messages are all covered, falling back to the key scope when no end-user id is present. Expose the setting in the cache settings API and the Admin UI cache settings form Co-authored-by: yassin <yassin@berri.ai> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| test_azure_blob_cache.py | ||
| test_caching.py | ||
| test_caching_handler.py | ||
| test_check_and_fix_namespace_none_guard.py | ||
| test_disk_cache.py | ||
| test_dual_cache.py | ||
| test_embedding_router.py | ||
| test_evicted_client_closer.py | ||
| test_gcs_cache.py | ||
| test_in_memory_cache.py | ||
| test_llm_caching_handler.py | ||
| test_llm_client_cache_e2e.py | ||
| test_qdrant_semantic_cache.py | ||
| test_redis_cache.py | ||
| test_redis_cluster_cache.py | ||
| test_redis_cluster_node_isolation.py | ||
| test_redis_connection_pool.py | ||
| test_redis_semantic_cache.py | ||
| test_s3_cache.py | ||
| test_valkey_semantic_cache.py | ||