ractogateway.redis.exact_cache

Redis-backed exact-match cache — distributed drop-in for ExactMatchCache.

Stores LLM responses in Redis so the cache is shared across every process and server in a fleet. The public API is byte-for-byte identical to ExactMatchCache, which means you can substitute RedisExactCache wherever ExactMatchCache is accepted (including all developer-kit exact_cache= parameters) without changing any other code.

Thread-safety

Stats counters are guarded by threading.Lock (same pattern as the in-process cache). The Redis operations themselves are atomic at the command level; no additional locking is required across processes.

Cache key

"{key_prefix}:{sha256_hex}" where the SHA-256 digest is computed from (user_message, system_prompt, model, temperature, max_tokens) — identical hashing logic to _make_key().

Example:

from ractogateway.redis import RedisExactCache
from ractogateway import openai_developer_kit as gpt

cache = RedisExactCache(
    url="redis://localhost:6379/0",
    ttl_seconds=3600,
)
kit = gpt.OpenAIDeveloperKit(model="gpt-4o", exact_cache=cache)

class ractogateway.redis.exact_cache.RedisExactCache(*, url='redis://localhost:6379/0', client=None, ttl_seconds=None, key_prefix='ractogateway:exact')

Bases: object

Distributed exact-match LRU cache backed by Redis.

Parameters:

• url (str) – Redis connection URL (e.g. "redis://localhost:6379/0"). Ignored when client is provided.

• client (Any | None) – Pre-built redis.Redis (or compatible) client. Useful when you manage the connection pool yourself or use a mock in tests.

• ttl_seconds (float | None) – Optional TTL for each entry. Passed directly to Redis SET EX. None means entries never expire (Redis default).

• key_prefix (str) – Namespace for all Redis keys managed by this instance.

get(user_message, system_prompt, model, temperature, max_tokens)

Return a cached response or None on a miss.

O(1) Redis GET.

Return type:

LLMResponse | None

put(user_message, system_prompt, model, temperature, max_tokens, response)

Store a response in Redis.

O(1) Redis SET [EX ttl].

Return type:

None

invalidate(user_message, system_prompt, model, temperature, max_tokens)

Remove a specific entry. Returns True if it was present.

Return type:

bool

clear()

Delete all entries matching this instance’s key prefix.

Uses SCAN to iterate safely (no KEYS * in production). Also resets in-memory stats counters.

Return type:

None

property stats: CacheStats

Return a snapshot of hit/miss counters plus current Redis key count.