feat: Add LangCache integration with full feature support

- Implement LangCacheWrapper as BaseLLMCache extension
- Support semantic and exact search strategies
- Add distance_threshold support (converts to similarity_threshold)
- Add attributes filtering for metadata-based searches
- Fix SDK integration issues:
  - Use correct response model attributes (entry_id, data)
  - Remove incorrect context manager usage
  - Convert similarity to distance (1.0 - similarity)
  - Handle optional attributes in store operations
- Add comprehensive unit tests (16 tests)
- All 444 unit tests passing
- Type checking, formatting, and linting passing

Author: abrookins

pyproject.toml

@@ -3,7 +3,7 @@ name = "redisvl"
 version = "0.9.1"
 description = "Python client library and CLI for using Redis as a vector database"
 authors = [{ name = "Redis Inc.", email = "[email protected]" }]
-requires-python = ">=3.9,<3.14"
+requires-python = ">=3.9.2,<3.14"
 readme = "README.md"
 license = "MIT"
 keywords = [
@@ -39,6 +39,7 @@ nltk = ["nltk>=3.8.1,<4"]
 cohere = ["cohere>=4.44"]
 voyageai = ["voyageai>=0.2.2"]
 sentence-transformers = ["sentence-transformers>=3.4.0,<4"]
+langcache = ["langcache>=0.9.0"]
 vertexai = [
     "google-cloud-aiplatform>=1.26,<2.0.0",
     "protobuf>=5.28.0,<6.0.0",

redisvl/extensions/cache/llm/__init__.py

@@ -4,11 +4,18 @@
 This module provides LLM cache implementations for RedisVL.
 """
 
+from redisvl.extensions.cache.llm.langcache import LangCacheWrapper
 from redisvl.extensions.cache.llm.schema import (
     CacheEntry,
     CacheHit,
     SemanticCacheIndexSchema,
 )
 from redisvl.extensions.cache.llm.semantic import SemanticCache
 
-__all__ = ["SemanticCache", "CacheEntry", "CacheHit", "SemanticCacheIndexSchema"]
+__all__ = [
+    "SemanticCache",
+    "LangCacheWrapper",
+    "CacheEntry",
+    "CacheHit",
+    "SemanticCacheIndexSchema",
+]