Core#

core.ExactMatchEvaluation#

core.cache_all#

core.first#

core.get_data_manager#

Generate SSDataManager (with cache_base, vector_base, max_size, clean_size and eviction params),

or MAPDataManager (with data_path, max_size and get_data_container params) to manager the data.

param cache_base

a CacheBase object, or the name of the cache storage, it is support ‘sqlite’, ‘postgresql’, ‘mysql’, ‘mariadb’, ‘sqlserver’ and ‘oracle’ now.

type cache_base

CacheBase or str

param vector_base

a VectorBase object, or the name of the vector storage, it is support ‘milvus’, ‘faiss’ and ‘chromadb’ now.

type vector_base

VectorBase or str

param object_base

a object storage, supports local path and s3.

type object_base

ObjectBase or str

param max_size

the max size for the cache, defaults to 1000.

type max_size

int

param clean_size

the size to clean up, defaults to max_size * 0.2.

type clean_size

int

param eviction

the eviction policy, it is support “LRU” and “FIFO” now, and defaults to “LRU”.

type eviction

str

param data_path

the path to save the map data, defaults to ‘data_map.txt’.

type data_path

str

param get_data_container

a Callable to get the data container, defaults to None.

type get_data_container

Callable

return

SSDataManager or MapDataManager.

Example

from gptcache.manager import get_data_manager, CacheBase, VectorBase

data_manager = get_data_manager(CacheBase('sqlite'), VectorBase('faiss', dimension=128))

core.last_content#

core.string_embedding#