如何通过提示提升结果

在本指南中，我们将介绍一些提示策略，以改进图数据库查询的生成。我们主要关注将相关的数据库特定信息包含在提示中的方法。

danger

本指南中使用的 GraphCypherQAChain 将对提供的数据库执行 Cypher 语句。在生产环境中，请确保数据库连接使用的凭据范围严格限定为仅包含必要权限。

如果不这样做，可能会导致数据损坏或丢失，因为调用的代码可能会执行删除、修改数据的命令，或者在数据库中存在敏感数据的情况下读取敏感数据。

安装配置

安装依赖

npm
yarn
pnpm

npm i langchain @langchain/community @langchain/openai @langchain/core neo4j-driver

yarn add langchain @langchain/community @langchain/openai @langchain/core neo4j-driver

pnpm add langchain @langchain/community @langchain/openai @langchain/core neo4j-driver

设置环境变量

本示例中我们将使用 OpenAI:

OPENAI_API_KEY=your-api-key

# 可选，使用 LangSmith 实现最佳观测能力
LANGSMITH_API_KEY=your-api-key
LANGSMITH_TRACING=true

# 如果你不在无服务器环境中运行，可以减少追踪延迟
# LANGCHAIN_CALLBACKS_BACKGROUND=true

接下来，我们需要定义 Neo4j 凭据。请按照这些安装步骤来设置 Neo4j 数据库。

NEO4J_URI="bolt://localhost:7687"
NEO4J_USERNAME="neo4j"
NEO4J_PASSWORD="password"

以下示例将创建一个与 Neo4j 数据库的连接，并使用有关电影及其演员的示例数据填充该数据库。

const url = process.env.NEO4J_URI;
const username = process.env.NEO4J_USER;
const password = process.env.NEO4J_PASSWORD;

import "neo4j-driver";
import { Neo4jGraph } from "@langchain/community/graphs/neo4j_graph";

const graph = await Neo4jGraph.initialize({ url, username, password });

// Import movie information
const moviesQuery = `LOAD CSV WITH HEADERS FROM 
'https://raw.githubusercontent.com/tomasonjo/blog-datasets/main/movies/movies_small.csv'
AS row
MERGE (m:Movie {id:row.movieId})
SET m.released = date(row.released),
    m.title = row.title,
    m.imdbRating = toFloat(row.imdbRating)
FOREACH (director in split(row.director, '|') | 
    MERGE (p:Person {name:trim(director)})
    MERGE (p)-[:DIRECTED]->(m))
FOREACH (actor in split(row.actors, '|') | 
    MERGE (p:Person {name:trim(actor)})
    MERGE (p)-[:ACTED_IN]->(m))
FOREACH (genre in split(row.genres, '|') | 
    MERGE (g:Genre {name:trim(genre)})
    MERGE (m)-[:IN_GENRE]->(g))`;

await graph.query(moviesQuery);

Schema refreshed successfully.

[]

过滤图模式

有时，在生成 Cypher 语句时，您可能需要专注于图模式的特定子集。假设我们处理的是以下图模式：

await graph.refreshSchema();
console.log(graph.getSchema());

Node properties are the following:
Movie {imdbRating: FLOAT, id: STRING, released: DATE, title: STRING}, Person {name: STRING}, Genre {name: STRING}, Chunk {embedding: LIST, id: STRING, text: STRING}
Relationship properties are the following:

The relationships are the following:
(:Movie)-[:IN_GENRE]->(:Genre), (:Person)-[:DIRECTED]->(:Movie), (:Person)-[:ACTED_IN]->(:Movie)

少样本示例

在提示中包含自然语言问题转换为针对我们数据库的有效 Cypher 查询的示例，通常会提高模型性能，尤其是对于复杂查询。

假设我们有以下示例：

const examples = [
  {
    question: "How many artists are there?",
    query: "MATCH (a:Person)-[:ACTED_IN]->(:Movie) RETURN count(DISTINCT a)",
  },
  {
    question: "Which actors played in the movie Casino?",
    query: "MATCH (m:Movie {{title: 'Casino'}})<-[:ACTED_IN]-(a) RETURN a.name",
  },
  {
    question: "How many movies has Tom Hanks acted in?",
    query:
      "MATCH (a:Person {{name: 'Tom Hanks'}})-[:ACTED_IN]->(m:Movie) RETURN count(m)",
  },
  {
    question: "List all the genres of the movie Schindler's List",
    query:
      "MATCH (m:Movie {{title: 'Schindler\\'s List'}})-[:IN_GENRE]->(g:Genre) RETURN g.name",
  },
  {
    question:
      "Which actors have worked in movies from both the comedy and action genres?",
    query:
      "MATCH (a:Person)-[:ACTED_IN]->(:Movie)-[:IN_GENRE]->(g1:Genre), (a)-[:ACTED_IN]->(:Movie)-[:IN_GENRE]->(g2:Genre) WHERE g1.name = 'Comedy' AND g2.name = 'Action' RETURN DISTINCT a.name",
  },
  {
    question:
      "Which directors have made movies with at least three different actors named 'John'?",
    query:
      "MATCH (d:Person)-[:DIRECTED]->(m:Movie)<-[:ACTED_IN]-(a:Person) WHERE a.name STARTS WITH 'John' WITH d, COUNT(DISTINCT a) AS JohnsCount WHERE JohnsCount >= 3 RETURN d.name",
  },
  {
    question: "Identify movies where directors also played a role in the film.",
    query:
      "MATCH (p:Person)-[:DIRECTED]->(m:Movie), (p)-[:ACTED_IN]->(m) RETURN m.title, p.name",
  },
  {
    question:
      "Find the actor with the highest number of movies in the database.",
    query:
      "MATCH (a:Actor)-[:ACTED_IN]->(m:Movie) RETURN a.name, COUNT(m) AS movieCount ORDER BY movieCount DESC LIMIT 1",
  },
];

我们可以用它们创建一个少样本提示，如下所示：

import { FewShotPromptTemplate, PromptTemplate } from "@langchain/core/prompts";

const examplePrompt = PromptTemplate.fromTemplate(
  "User input: {question}\nCypher query: {query}"
);
const prompt = new FewShotPromptTemplate({
  examples: examples.slice(0, 5),
  examplePrompt,
  prefix:
    "You are a Neo4j expert. Given an input question, create a syntactically correct Cypher query to run.\n\nHere is the schema information\n{schema}.\n\nBelow are a number of examples of questions and their corresponding Cypher queries.",
  suffix: "User input: {question}\nCypher query: ",
  inputVariables: ["question", "schema"],
});

console.log(
  await prompt.format({
    question: "How many artists are there?",
    schema: "foo",
  })
);

You are a Neo4j expert. Given an input question, create a syntactically correct Cypher query to run.

Here is the schema information
foo.

Below are a number of examples of questions and their corresponding Cypher queries.

User input: How many artists are there?
Cypher query: MATCH (a:Person)-[:ACTED_IN]->(:Movie) RETURN count(DISTINCT a)

User input: Which actors played in the movie Casino?
Cypher query: MATCH (m:Movie {title: 'Casino'})<-[:ACTED_IN]-(a) RETURN a.name

User input: How many movies has Tom Hanks acted in?
Cypher query: MATCH (a:Person {name: 'Tom Hanks'})-[:ACTED_IN]->(m:Movie) RETURN count(m)

User input: List all the genres of the movie Schindler's List
Cypher query: MATCH (m:Movie {title: 'Schindler\'s List'})-[:IN_GENRE]->(g:Genre) RETURN g.name

User input: Which actors have worked in movies from both the comedy and action genres?
Cypher query: MATCH (a:Person)-[:ACTED_IN]->(:Movie)-[:IN_GENRE]->(g1:Genre), (a)-[:ACTED_IN]->(:Movie)-[:IN_GENRE]->(g2:Genre) WHERE g1.name = 'Comedy' AND g2.name = 'Action' RETURN DISTINCT a.name

User input: How many artists are there?
Cypher query:

动态少样本示例

如果我们有足够多的示例，可能希望仅在提示中包含最相关的那些示例，这要么是因为示例无法全部放入模型的上下文窗口中，要么是因为过多的示例会使模型分心。具体来说，对于任何输入，我们希望包含与该输入最相关的示例。

我们可以使用 ExampleSelector 来实现这一点。在这种情况下，我们将使用 SemanticSimilarityExampleSelector，它会将示例存储在我们选择的向量数据库中。在运行时，它将在输入与我们的示例之间执行相似性搜索，并返回语义上最相似的示例：

import { OpenAIEmbeddings } from "@langchain/openai";
import { SemanticSimilarityExampleSelector } from "@langchain/core/example_selectors";
import { Neo4jVectorStore } from "@langchain/community/vectorstores/neo4j_vector";

const exampleSelector = await SemanticSimilarityExampleSelector.fromExamples(
  examples,
  new OpenAIEmbeddings(),
  Neo4jVectorStore,
  {
    k: 5,
    inputKeys: ["question"],
    preDeleteCollection: true,
    url,
    username,
    password,
  }
);

await exampleSelector.selectExamples({
  question: "how many artists are there?",
});

[
  {
    query: "MATCH (a:Person)-[:ACTED_IN]->(:Movie) RETURN count(DISTINCT a)",
    question: "How many artists are there?"
  },
  {
    query: "MATCH (a:Person {{name: 'Tom Hanks'}})-[:ACTED_IN]->(m:Movie) RETURN count(m)",
    question: "How many movies has Tom Hanks acted in?"
  },
  {
    query: "MATCH (a:Person)-[:ACTED_IN]->(:Movie)-[:IN_GENRE]->(g1:Genre), (a)-[:ACTED_IN]->(:Movie)-[:IN_GENRE"... 84 more characters,
    question: "Which actors have worked in movies from both the comedy and action genres?"
  },
  {
    query: "MATCH (d:Person)-[:DIRECTED]->(m:Movie)<-[:ACTED_IN]-(a:Person) WHERE a.name STARTS WITH 'John' WITH"... 71 more characters,
    question: "Which directors have made movies with at least three different actors named 'John'?"
  },
  {
    query: "MATCH (a:Actor)-[:ACTED_IN]->(m:Movie) RETURN a.name, COUNT(m) AS movieCount ORDER BY movieCount DES"... 9 more characters,
    question: "Find the actor with the highest number of movies in the database."
  }
]

使用它时，我们可以将 ExampleSelector 直接传递给我们的 FewShotPromptTemplate：

const promptWithExampleSelector = new FewShotPromptTemplate({
  exampleSelector,
  examplePrompt,
  prefix:
    "You are a Neo4j expert. Given an input question, create a syntactically correct Cypher query to run.\n\nHere is the schema information\n{schema}.\n\nBelow are a number of examples of questions and their corresponding Cypher queries.",
  suffix: "User input: {question}\nCypher query: ",
  inputVariables: ["question", "schema"],
});

console.log(
  await promptWithExampleSelector.format({
    question: "how many artists are there?",
    schema: "foo",
  })
);

You are a Neo4j expert. Given an input question, create a syntactically correct Cypher query to run.

Here is the schema information
foo.

Below are a number of examples of questions and their corresponding Cypher queries.

User input: How many artists are there?
Cypher query: MATCH (a:Person)-[:ACTED_IN]->(:Movie) RETURN count(DISTINCT a)

User input: How many movies has Tom Hanks acted in?
Cypher query: MATCH (a:Person {name: 'Tom Hanks'})-[:ACTED_IN]->(m:Movie) RETURN count(m)

User input: Which actors have worked in movies from both the comedy and action genres?
Cypher query: MATCH (a:Person)-[:ACTED_IN]->(:Movie)-[:IN_GENRE]->(g1:Genre), (a)-[:ACTED_IN]->(:Movie)-[:IN_GENRE]->(g2:Genre) WHERE g1.name = 'Comedy' AND g2.name = 'Action' RETURN DISTINCT a.name

User input: Which directors have made movies with at least three different actors named 'John'?
Cypher query: MATCH (d:Person)-[:DIRECTED]->(m:Movie)<-[:ACTED_IN]-(a:Person) WHERE a.name STARTS WITH 'John' WITH d, COUNT(DISTINCT a) AS JohnsCount WHERE JohnsCount >= 3 RETURN d.name

User input: Find the actor with the highest number of movies in the database.
Cypher query: MATCH (a:Actor)-[:ACTED_IN]->(m:Movie) RETURN a.name, COUNT(m) AS movieCount ORDER BY movieCount DESC LIMIT 1

User input: how many artists are there?
Cypher query:

import { ChatOpenAI } from "@langchain/openai";
import { GraphCypherQAChain } from "langchain/chains/graph_qa/cypher";

const llm = new ChatOpenAI({
  model: "gpt-3.5-turbo",
  temperature: 0,
});
const chain = GraphCypherQAChain.fromLLM({
  graph,
  llm,
  cypherPrompt: promptWithExampleSelector,
});

await chain.invoke({
  query: "How many actors are in the graph?",
});

{ result: "There are 967 actors in the graph." }

如何通过提示提升结果

安装配置

安装依赖

设置环境变量

过滤图模式

少样本示例

动态少样本示例

Was this page helpful?

You can also leave detailed feedback on GitHub.

安装配置​

安装依赖​

设置环境变量​

过滤图模式

少样本示例​

动态少样本示例​

Was this page helpful?

You can also leave detailed feedback on GitHub.

安装配置

安装依赖

设置环境变量

少样本示例

动态少样本示例