llm elasticsearch cache下载llm elasticsearch cache源代码下载

llm elasticsearch cache

Ai源码

1.0.0

下载

重要的

该图书馆现在是Langchain的一部分，请按照官方文档（例如LLM CACHE）进行官方文档

llm-elasticsearch-cache

LLMS的缓存层，可利用与Langchain Caching完全兼容的Elasticsearch，无论是用于聊天还是嵌入模型。

安装

pip install llm-elasticsearch-cache

聊天缓存使用情况

Langchain高速缓存可以与其他缓存集成类似。

基本示例

 from langchain . globals import set_llm_cache
from llmescache . langchain import ElasticsearchCache
from elasticsearch import Elasticsearch

es_client = Elasticsearch ( hosts = "http://localhost:9200" )
set_llm_cache (
    ElasticsearchCache (
        es_client = es_client , 
        es_index = "llm-chat-cache" , 
        metadata = { "project" : "my_chatgpt_project" }
    )
)

es_index参数也可以采用别名。这允许使用ILM：管理我们建议考虑用于管理保留和控制缓存增长的索引生命周期。

查看所有参数的类docstring。

索引生成的文本

默认情况下，缓存数据无法搜索。开发人员可以自定义Elasticsearch文档的构建，以添加索引的文本字段，例如，在何处使用LLM生成的文本。

这可以通过子类末端覆盖方法来完成。新的缓存类也可以应用于预先存在的缓存索引：

 from llmescache . langchain import ElasticsearchCache
from elasticsearch import Elasticsearch
from langchain_core . caches import RETURN_VAL_TYPE
from typing import Any , Dict , List
from langchain . globals import set_llm_cache
import json


class SearchableElasticsearchCache ( ElasticsearchCache ):

    @ property
    def mapping ( self ) -> Dict [ str , Any ]:
        mapping = super (). mapping
        mapping [ "mappings" ][ "properties" ][ "parsed_llm_output" ] = { "type" : "text" , "analyzer" : "english" }
        return mapping
    
    def build_document ( self , prompt : str , llm_string : str , return_val : RETURN_VAL_TYPE ) -> Dict [ str , Any ]:
        body = super (). build_document ( prompt , llm_string , return_val )
        body [ "parsed_llm_output" ] = self . _parse_output ( body [ "llm_output" ])
        return body

    @ staticmethod
    def _parse_output ( data : List [ str ]) -> List [ str ]:
        return [ json . loads ( output )[ "kwargs" ][ "message" ][ "kwargs" ][ "content" ] for output in data ]


es_client = Elasticsearch ( hosts = "http://localhost:9200" )
set_llm_cache ( SearchableElasticsearchCache ( es_client = es_client , es_index = "llm-chat-cache" ))

嵌入式缓存使用情况

通过使用Cachebackedembeddings以与官方文档略有不同的方式获得缓存嵌入。

 from llmescache . langchain import ElasticsearchStore
from elasticsearch import Elasticsearch
from langchain . embeddings import CacheBackedEmbeddings
from langchain_openai import OpenAIEmbeddings

es_client = Elasticsearch ( hosts = "http://localhost:9200" )

underlying_embeddings = OpenAIEmbeddings ( model = "text-embedding-3-small" )
store = ElasticsearchStore (
    es_client = es_client , 
    es_index = "llm-embeddings-cache" ,
    namespace = underlying_embeddings . model ,
    metadata = { "project" : "my_llm_project" }
)
cached_embeddings = CacheBackedEmbeddings (
    underlying_embeddings , 
    store
)

与聊天缓存类似，可以为搜索索引向量索引ElasticsearchStore 。

 from llmescache . langchain import ElasticsearchStore
from typing import Any , Dict , List

class SearchableElasticsearchStore ( ElasticsearchStore ):

    @ property
    def mapping ( self ) -> Dict [ str , Any ]:
        mapping = super (). mapping
        mapping [ "mappings" ][ "properties" ][ "vector" ] = { "type" : "dense_vector" , "dims" : 1536 , "index" : True , "similarity" : "dot_product" }
        return mapping
    
    def build_document ( self , llm_input : str , vector : List [ float ]) -> Dict [ str , Any ]:
        body = super (). build_document ( llm_input , vector )
        body [ "vector" ] = vector
        return body