llm elasticsearch cache下載llm elasticsearch cache源代碼下載

llm elasticsearch cache

Ai源碼

1.0.0

下載

重要的

該圖書館現在是Langchain的一部分，請按照官方文檔（例如LLM CACHE）進行官方文檔

llm-elasticsearch-cache

LLMS的緩存層，可利用與Langchain Caching完全兼容的Elasticsearch，無論是用於聊天還是嵌入模型。

安裝

pip install llm-elasticsearch-cache

聊天緩存使用情況

Langchain高速緩存可以與其他緩存集成類似。

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參數也可以採用別名。這允許使用ILM：管理我們建議考慮用於管理保留和控制緩存增長的索引生命週期。

查看所有參數的類docstring。

索引生成的文本

默認情況下，緩存數據無法搜索。開發人員可以自定義Elasticsearch文檔的構建，以添加索引的文本字段，例如，在何處使用LLM生成的文本。

這可以通過子類末端覆蓋方法來完成。新的緩存類也可以應用於預先存在的緩存索引：

 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" ))

嵌入式緩存使用情況

通過使用Cachebackedembeddings以與官方文檔略有不同的方式獲得緩存嵌入。

 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
)

與聊天緩存類似，可以為搜索索引向量索引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