快速入门:使用 Gemini Embeddings 和 Elasticsearch 进行向量搜索

2024年1月21日   |   by mebius

Gemini 是 Google DeepMind 开发的多模态大语言模型家族,作为tgcode LaMDA 和 PaLM 2 的后继者。由 Gemini Ultra、Gemini Pro 和 Gemini Nano 组成,于 2023 年 12 月 6 日发布,定位为 OpenAI 的竞争者 GPT-4。

%title插图%num

本教程演示如何使用 Gemini API 创建嵌入并将其存储在 Elasticsearch 中。 Elasticsearch 将使我们能够执行向量搜索 (Knn) 来查找相似的文档。

准备

Elasticsearch 及 Kibana

如果你还没有安装好自己的 Elasticsearch 及 Kibana 的话,请参阅如下的文章来进行安装:

在安装的时候,请参照 Elastic Stack 8.x 的文章来进行安装。

%title插图%num

Gemini 开发者 key

你可以参考文章来申请一个免费的 key 供下面的开发。你也可以直接去地址进行申请。

设置环境变量

我tgcode们在 termnial 中打入如下的命令来设置环境变量:

export ES_USER=elastic
export ES_PASSWORD=-M3aD_m3MHCZNYyJi_V2
export GOOGLE_API_KEY=YourGoogleAPIkey

拷贝 Elasticsearch 证书

我们把 Elasticsearch 的证书拷贝到当前的目录下:

$ pwd
/Users/liuxg/python/elser
$ cp ~/elastic/elasticsearch-8.12.0/config/certs/http_ca.crt .

安装 Python 依赖包tgcode

pip3 install -q -U google-generativeai elasticsearch

应用设计

我们在当前的工作目录下打入命令:

jupyter notebook

导入包及环境变量

import google.generativeai as genai
import google.ai.generativelanguage as glm
from elasticsearch import Elasticsearch, helpers
from dotenv import load_dotenv
import os

load_dotenv()

GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
ES_USER = os.getenv("ES_USER")
ES_PASSWORD = os.getenv("ES_PASSWORD")
elastic_index_name='gemini-demo'

连接到 Elasticsearch

url = f"https://{ES_USER}:{ES_PASSWORD}@192.168.0.3:9200"

es = Elasticsearch(
        hosts=[url], 
        ca_certs = "./http_ca.crt", 
        verify_certs = True
)
print(es.info())

%title插图%num

上面显示我们的 es 连接是成功的。

删除索引

if(es.indices.exists(index=elastic_index_name)):
    print("The index has already existed, going to remove it")
    es.options(ignore_status=404).indices.delete(index=elastic_index_name)

使用 Elasticsearch 索引文档

生成一个 title 为 “Beijing” 文档:

genai.configure(api_key=GOOGLE_API_KEY)

title = "Beijing"
sample_text = ("Beijing is the capital of China and the center of Chinese politics, culture, and economy. This city has a long history with many ancient buildings and cultural heritage. Beijing is renowned as a cultural city in China, boasting numerous museums, art galleries, and historical landmarks. Additionally, as a modern metropolis, Beijing is a thriving business center with modern architecture and advanced transportation systems. It serves as the seat of the Chinese government, where significant decisions and events often take place. Overall, Beijing holds a crucial position in China, serving as both a preserver of traditional culture and a representative of modern development.")

model = 'models/embedding-001'
embedding = genai.embed_content(model=model,
                                content=sample_text,
                                task_type="retrieval_document",
                                title=title)

doc = {
    'text' : sample_text,
    'text_embedding' : embedding['embedding'] 
}

resp = es.index(index=elastic_index_name, document=doc)

print(resp)

生成一个 title 为 “Shanghai” 的文档:

title = "Shanghai"
sample_text = ("Shanghai is one of China's largest cities and a significant hub for economy, finance, and trade. This modern city is located in the eastern part of China and serves as an international metropolis. The bustling streets, skyscrapers, and modern architecture in Shanghai showcase the city's prosperity and development. As one of China's economic engines, Shanghai is home to the headquarters of many international companies and various financial institutions. It is also a crucial trading port, connecting with destinations worldwide. Additionally, Shanghai boasts a rich cultural scene, including art galleries, theaters, and historical landmarks. In summary, Shanghai is a vibrant, modern city with international influence.")

model = 'models/embedding-001'
embedding = genai.embed_content(model=model,
                                content=sample_text,
                                task_type="retrieval_document",
                                title=title)

doc = {
    'text' : sample_text,
    'text_embedding' : embedding['embedding'] 
}

resp = es.index(index=elastic_index_name, document=doc)

print(resp)

我们可以在 Kibana 中进行查看:

%title插图%num

使用 Elasticsearch 来搜索文档

def search(question):
    print("nnQuestion: ", question)
    embedding = genai.embed_content(model=model,
                                    content=question,
                                    task_type="retrieval_query")

    resp = es.search(
    index = elastic_index_name,
    knn={
        "field": "text_embedding",
        "query_vector":  embedding['embedding'],
        "k": 10,
        "num_candidates": 100
        }
    )

    for result in resp['hits']['hits']:
        pretty_output = (f"nnID: {result['_id']}nnText: {result['_source']['text']}")
        print(pretty_output)
search("How do you describe Beijing?")

%title插图%num

search("What is Shanghai like?")

%title插图%num

从上面的输出中,我们可以看出来,当搜索的句子和文章更为接近时,相关的文档就会排在第一的位置。紧接着的是次之相关的文档。

search("which city is the capital of China?")

%title插图%num

search("the economy engine in China")

%title插图%num

最后,源码在位置可以进行下载:https://github.com/liu-xiao-guo/semantic_search_es/blob/main/vector-search-using-gemini-elastic.ipynb

文章来源于互联网:快速入门:使用 Gemini Embeddings 和 Elasticsearch 进行向量搜索

相关推荐: Elasticsearch:在不停机的情况下优化 Elasticsearch Reindex

实现零停机、高效率和成功迁移更新的指南。更多阅读:Elasticsearch:如何轻松安全地对实时 Elasticsearch 索引 reindex 你的数据。 在使用 Elasticsearch 的时候,总会有需要修改索引映射的时候,遇到这种情况,我们只能做…