Skip to content

Fix: Redis semantic cache v2 with CacheEmbedding support #17495

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
fcenedes wants to merge 6 commits into
base: main
Choose a base branch
from
Open

Fix: Redis semantic cache v2 with CacheEmbedding support #17495

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
1be0e0c
Cache Embeddings support for redis-semantic cache
fcenedes Dec 2, 2025
333c18e
Merge branch 'BerriAI:main' into redis_semantic_cache_v2
fcenedes Dec 4, 2025
c2a7453
minor fix
fcenedes Dec 4, 2025
71501d5
Merge branch 'redis_semantic_cache_v2' of https://github.com/fcenedes…
fcenedes Dec 4, 2025
d4ae129
Update caching.md
fcenedes Dec 4, 2025
72d723c
fix tests
fcenedes Dec 10, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
minor fix 
- bump redisvl version
- default embedding cache namespace
  • Loading branch information
@fcenedes
fcenedes committed Dec 4, 2025
commit c2a7453cda5bbc7189874c1cfe16dcdbdba63a7f
8 changes: 7 additions & 1 deletion docs/my-website/docs/caching/all_caches.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -211,7 +211,7 @@ response2 = completion(

Install redisvl client
```shell
pip install redisvl==0.4.1
pip install redisvl==0.12.1
```

For the hosted version you can setup your own Redis DB here: https://redis.io/try-free/
Expand All @@ -234,6 +234,9 @@ litellm.cache = Cache(
similarity_threshold=0.8, # similarity threshold for cache hits, 0 == no similarity, 1 = exact matches, 0.5 == 50% similarity
ttl=120,
redis_semantic_cache_embedding_model="text-embedding-ada-002", # this model is passed to litellm.embedding(), any litellm.embedding() model is supported here
embedding_cache_enabled=True, # enable caching of embeddings
embedding_cache_ttl=120, # ttl for embeddings cache
embedding_cache_name="litellm-embeddings-cache", # name for embeddings cache default is litellm_redis_semantic_embeddings_cache
)
response1 = completion(
model="gpt-3.5-turbo",
Expand Down Expand Up @@ -603,6 +606,9 @@ def __init__(
similarity_threshold: Optional[float] = None,
redis_semantic_cache_embedding_model: str = "text-embedding-ada-002",
redis_semantic_cache_index_name: Optional[str] = None,
embedding_cache_enabled: bool = False,
embedding_cache_ttl: Optional[int] = None,
embedding_cache_name: Optional[str] = None,

# s3 Bucket, boto3 configuration
s3_bucket_name: Optional[str] = None,
Expand Down
6 changes: 3 additions & 3 deletions litellm/caching/redis_semantic_cache.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,6 +35,7 @@ class RedisSemanticCache(BaseCache):
"""

DEFAULT_REDIS_INDEX_NAME: str = "litellm_semantic_cache_index"
DEFAULT_REDIS_EMBEDDINGS_CACHE_NAME: str = "litellm_redis_semantic_embeddings_cache"

def __init__(
self,
Expand Down Expand Up @@ -98,9 +99,8 @@ def __init__(
# Embeddings cache configuration
self.embedding_cache_enabled: bool = embedding_cache_enabled
self.embedding_cache_ttl: Optional[int] = embedding_cache_ttl
self.embedding_cache_name: str = (
embedding_cache_name or "litellm_redis_semantic_embeddings_cache"
)
if embedding_cache_name is None:
self.embedding_cache_name = self.DEFAULT_REDIS_EMBEDDINGS_CACHE_NAME
self._embeddings_cache: Optional[EmbeddingsCache] = None

# Set up Redis connection
Expand Down