Add LangCache wrapper (LLM cache extension) with configurable distance scale (#408)

## Summary
Add a LangCache wrapper to RedisVL LLM cache extensions so users can
leverage LangCache for semantic caching via the familiar `BaseLLMCache`
interface. Also make the wrapper’s distance threshold semantics explicit
and configurable so users can swap it out for an existing
`SemanticCache` instance easily.

## Motivation
- Use LangCache while keeping RedisVL’s developer experience
- Avoid surprises by making threshold scale explicit

## What’s included
- New `LangCacheWrapper` implementing `BaseLLMCache` (sync + async) that
talks to the LangCache service:
- Exact + semantic search toggles, TTL, and standard `store`/`check`
APIs
- Consistent result shape (including `vector_distance`) compatible with
existing callers
- Lazily imports LangCache and gives a friendly error if it's not
installed
- Configurable distance threshold scale via `distance_scale`:
- `"normalized"`: interpret `distance_threshold` as 0–1 semantic
distance; converts to/from similarity (`1 - d`)
- `"redis"`: interpret `distance_threshold` as native COSINE [0–2];
converts using `norm_cosine_distance` / `denorm_cosine_distance`

## Usage
```python
from redisvl.extensions.cache.llm.langcache import LangCacheWrapper

cache = LangCacheWrapper(
    name="langcache",
    cache_id="<id>",
    api_key="<key>",
    distance_scale="normalized"  # or "redis" for COSINE [0–2]
)

cache.store(prompt="Hello?", response="Hi\!")

hits = cache.check(
    prompt="Hello\!",
    distance_threshold=0.15,  # interpreted per distance_scale
)
```

Author: abrookins

pyproject.toml

@@ -3,7 +3,7 @@ name = "redisvl"
 version = "0.11.0"
 description = "Python client library and CLI for using Redis as a vector database"
 authors = [{ name = "Redis Inc.", email = "applied.ai@redis.com" }]
-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",
@@ -76,6 +77,7 @@ dev = [
     "testcontainers>=4.3.1,<5",
     "cryptography>=44.0.1 ; python_version > '3.9.1'",
     "codespell>=2.4.1,<3",
+    "langcache>=0.9.0",
 ]
 docs = [
     "sphinx>=4.4.0",

redisvl/cli/index.py

@@ -8,7 +8,6 @@
 from redisvl.redis.utils import convert_bytes, make_dict
 from redisvl.schema.schema import IndexSchema
 from redisvl.utils.log import get_logger
-from redisvl.utils.utils import lazy_import
 
 logger = get_logger("[RedisVL]")
 

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",
+]