根据搜索提示查找电影

一旦电影节点拥有对其标题和情节进行编码的嵌入，并且数据库中存在针对这些嵌入的向量索引，您就可以检索匹配模糊描述（即搜索提示）的电影，这有点类似于在搜索引擎中输入几个关键词来查找相关网页。

本页的示例展示了如何检索与提示 a criminal is changed through love 相关的电影。可以想象成去电影院并询问：“你会向我推荐哪些电影？今天我想看那些因爱情而改变的罪犯的电影。”主要区别在于，电影院的对话使用自然语言，而在数据库中搜索时，提示首先会被转换为嵌入。随后向量索引使用该提示嵌入检索出嵌入与搜索提示最相似的节点。

始终使用相同的模型生成嵌入：选择一个模型，并用它为数据集和搜索提示生成嵌入。尝试混合不同向量维度的模型会导致错误。维度相同的模型可以工作，但由于训练方式不同，通常也不会很好地协同工作。在创建向量索引时提供维度，这能确保只索引该尺寸的向量，并在查询时明确因维度不匹配而失败。

使用开源库生成的嵌入的相似度

本示例使用 SentenceTransformers 检索与描述 a criminal is changed through love 相关的节点。

from sentence_transformers import SentenceTransformer
import neo4j


URI = '<database-uri>'
AUTH = ('<username>', '<password>')
DB_NAME = '<database-name>'  # examples: 'recommendations-5.26', 'neo4j'

model = SentenceTransformer('all-MiniLM-L6-v2')  (1)

query_prompt = 'a criminal is changed through love'  (2)
query_embedding = model.encode(query_prompt)

with neo4j.GraphDatabase.driver(URI, auth=AUTH) as driver:
    driver.verify_connectivity()
    related_movies, _, _ = driver.execute_query('''
        MATCH (movie:Movie)
          SEARCH movie IN ( (3)
            VECTOR INDEX moviePlots
            FOR $queryEmbedding
            LIMIT 5
          ) SCORE AS similarityScore
        RETURN movie.title AS title, movie.plot AS plot, similarityScore
        ''', queryEmbedding=query_embedding,
        database_=DB_NAME)
    print(f'Movies whose plot and title relate to `{query_prompt}`:')
    for record in related_movies:
        print(record)
1 为搜索提示生成嵌入时必须使用与生成被搜索嵌入相同的模型。本教程使用 all-MiniLM-L6-V2 生成嵌入，这里也复用了该模型。
2 查询提示包含一个模糊的电影检索描述。随后它被编码为嵌入，以便用于查询相似的节点。
3 要查询向量索引，请使用 Cypher 子句 SEARCH。数据库返回向量索引 moviePlots 中与 queryVector 最相似的 5 个节点，并附带它们与查询嵌入匹配程度的 score。 
Movies whose plot and title relate to `a criminal is changed through love`:
<Record title='I Love You Phillip Morris' plot="A cop turns con man once he comes out of the closet. Once imprisoned, he meets the second love of his life, whom he'll stop at nothing to be with." score=0.792834997177124>
<Record title='Laura' plot='A police detective falls in love with the woman whose murder he is investigating.' score=0.7741715908050537>
<Record title='Despicable Me' plot='When a criminal mastermind uses a trio of orphan girls as pawns for a grand scheme, he finds their love is profoundly changing him for the better.' score=0.772994875907898>
<Record title='Laws of Attraction' plot='Amidst a sea of litigation, two New York City divorce lawyers find love.' score=0.7727792263031006>
<Record title='Love the Hard Way' plot='The story of a petty thief who meets an innocent young woman and brings her into his world of crime while she teaches him the lessons of enjoying life and being loved.' score=0.7681001424789429>

使用 OpenAI 和其他云服务生成的嵌入的相似度

本示例使用 OpenAI 检索与描述 a criminal is changed through love 相关的节点。

import neo4j


URI = '<database-uri>'
AUTH = ('<username>', '<password>')
DB_NAME = '<database-name>'  # examples: 'recommendations-5.26', 'neo4j'

openAI_token = '<OpenAI API token>'  (1)

search_prompt = 'a criminal is changed through love'  (2)

with neo4j.GraphDatabase.driver(URI, auth=AUTH) as driver:
    driver.verify_connectivity()
    records, summary, _ = driver.execute_query('''
        WITH ai.text.embed($searchPrompt, 'OpenAI', {
          token: $token, model: 'text-embedding-3-small'
        }) AS queryVector  (3)
        MATCH (movie:Movie)
          SEARCH movie IN ( (4)
            VECTOR INDEX moviePlots
            FOR queryVector
            LIMIT 5
          ) SCORE AS similarityScore
        RETURN movie.title AS title, movie.plot AS plot, similarityScore
        ''', searchPrompt=search_prompt, token=openAI_token,
        database_=DB_NAME)
    print(f'Movies whose plot and title relate to `{search_prompt}`:')
    for record in records:
        print(record)
1 您的 OpenAI API 令牌，例如 sk-proj-XXXX。
2 查询提示包含一个模糊的电影检索描述。
3 查询提示通过 Cypher 函数 ai.text.embed() 编码为嵌入，以便用于查询相似节点。
4 要查询向量索引，请使用 Cypher 子句 SEARCH。数据库返回向量索引 moviePlots 中与 queryVector 最相似的 5 个节点，并附带它们与查询嵌入匹配程度的 score。 
Movies whose plot and title relate to `a criminal is changed through love`:
<Record title='I Love You Phillip Morris' node.plot="A cop turns con man once he comes out of the closet. Once imprisoned, he meets the second love of his life, whom he'll stop at nothing to be with." score=0.9272396564483643>
<Record title='Love the Hard Way' node.plot='The story of a petty thief who meets an innocent young woman and brings her into his world of crime while she teaches him the lessons of enjoying life and being loved.' score=0.9221653938293457>
<Record title='Laura' node.plot='A police detective falls in love with the woman whose murder he is investigating.' score=0.9215129017829895>
<Record title='Despicable Me' node.plot='When a criminal mastermind uses a trio of orphan girls as pawns for a grand scheme, he finds their love is profoundly changing him for the better.' score=0.9206478595733643>
<Record title='Cook the Thief His Wife & Her Lover, The' node.plot='The wife of an abusive criminal finds solace in the arms of a kind regular guest in her husbands restaurant.' score=0.9205931425094604>

匹配质量

匹配质量完全取决于嵌入模型和数据集，而非 Neo4j 向量索引。 嵌入始终在 Neo4j 外部 生成；数据库仅 存储 它们为属性。

考虑使用 SentenceTransformers（OpenAI 的结果类似）时，使用搜索提示 a criminal is changed through love 检索到的节点

Movies whose plot and title relate to `a criminal is changed through love`:
<Record title='I Love You Phillip Morris' plot="A cop turns con man once he comes out of the closet. Once imprisoned, he meets the second love of his life, whom he'll stop at nothing to be with." score=0.792834997177124>
<Record title='Laura' plot='A police detective falls in love with the woman whose murder he is investigating.' score=0.7741715908050537>
<Record title='Despicable Me' plot='When a criminal mastermind uses a trio of orphan girls as pawns for a grand scheme, he finds their love is profoundly changing him for the better.' score=0.772994875907898>
<Record title='Laws of Attraction' plot='Amidst a sea of litigation, two New York City divorce lawyers find love.' score=0.7727792263031006>
<Record title='Love the Hard Way' plot='The story of a petty thief who meets an innocent young woman and brings her into his world of crime while she teaches him the lessons of enjoying life and being loved.' score=0.7681001424789429>

本示例表明嵌入符合预期：Despicable Me 排名第三，相关性得分为 77%。同时，它也展示了 嵌入模型的局限性，因为检索到的电影实际上并未真正与提示相关。

  • Laura 并没有“犯罪因爱情而改变”，但其中有一位警探（常与criminals合作），在一起谋杀案件的情境中坠入love（同样与criminals相关）。

  • Laws of Attraction 完全没有criminals，但包含：attraction（与love相关），litigation（通常在法庭上进行，法庭与criminals有关），lawyers（常与criminals关联），以及love，尽管是在律师之间。

  • Love the Hard Way 则几乎相反：一名无辜的学生爱上了一个较低层次的criminal（petty thief），随后陷入了跌宕的恶性循环。

即使这些电影几乎与搜索提示无关，数据库是正确的：它们是根据嵌入最相关的结果。嵌入为何未能以人们期望的方式编码意义，这不是向量索引的问题，而是外部 AI 模型本身的问题。如果您的搜索提示返回的结果不佳，应检查使用的嵌入模型及其所应用的数据集，而不是仅仅调整 Neo4j 的设置。