Knowledge graphs: Chat with your data

concept Person extends GraphNode {
  @label("ACTED_IN")
  --> Movie[] actedIn optional
  @label("DIRECTED")
  --> Movie[] directed optional
}

concept Actor extends Person {
}

concept Director extends Person {
}

concept User extends Person {
  o ContactDetails contactDetails
  o AddressBook addressBook
  @label("RATED")
  --> Movie[] ratedMovies optional
}

concept Genre extends GraphNode {
}

concept Movie extends GraphNode {
  o Double[] embedding optional
  @vector_index("embedding", 1536, "COSINE")
  @fulltext_index
  o String summary optional
  @label("IN_GENRE")
  --> Genre[] genres optional
}

const options:GraphModelOptions = {
    NEO4J_USER: process.env.NEO4J_USER,
    NEO4J_PASS: process.env.NEO4J_PASS,
    NEO4J_URL: process.env.NEO4J_URL,
    logger: console,
    logQueries: false,
    embeddingFunction: process.env.OPENAI_API_KEY ? getOpenAiEmbedding : undefined
  }
  const graphModel = new GraphModel([MODEL], options);  
  await graphModel.connect();
  await graphModel.deleteGraph();
  await graphModel.dropIndexes();
  await graphModel.createConstraints();
  await graphModel.createVectorIndexes();
  await graphModel.createFullTextIndexes();

await graphModel.mergeNode(transaction, 'Movie', {
   identifier: 'Fear and Loathing in Las Vegas', 
   summary: 'Duke, under the influence of mescaline, complains of a swarm of 
   giant bats, and inventories their drug stash. They pick up a young 
   hitchhiker and explain their mission: Duke has been assigned by a 
   magazine to cover the Mint 400 motorcycle race in Las Vegas. They bought 
   excessive drugs for the trip, and rented a red Chevrolet Impala 
   convertible.'} 
);

 const fullTextSearch = 'bats';
  console.log(`Full text search for movies with: '${fullTextSearch}'`);
  const fullTextResults = await graphModel.fullTextQuery('Movie', fullTextSearch, 2);

[
  {
    summary: 'Duke, under the influence of mescaline, complains of a swarm of giant bats, and inventories their drug stash. They pick up a young hitchhiker and explain their mission: Duke has been assigned by a magazine to cover the Mint 400 motorcycle race in Las Vegas. They bought excessive drugs for the trip, and rented a red Chevrolet Impala convertible.',
    score: 0.4010826349258423,
    identifier: 'Fear and Loathing in Las Vegas'
  }
]

const search = 'working in a boring job and looking for love.';
    console.log(`Searching for movies related to: '${search}'`);
    const results = await graphModel.similarityQuery('Movie', 'summary', search, 3);
    console.log(results);

[
  {
    identifier: 'Brazil',
    content: 'The film centres on Sam Lowry, a low-ranking bureaucrat trying 
    to find a woman who appears in his dreams while he is working in a mind-
    numbing job and living in a small apartment, set in a dystopian world 
    in which there is an over-reliance on poorly maintained (and rather 
    whimsical) machines', score: 0.7013247609138489
  },
  {
    identifier: 'Fear and Loathing in Las Vegas',
    content: 'Duke, under the influence of mescaline, complains of a swarm of 
    giant bats, and inventories their drug stash. They pick up a young 
    hitchhiker and explain their mission: Duke has been assigned by a magazine 
    to cover the Mint 400 motorcycle race in Las Vegas. They bought excessive 
    drugs for the trip, and rented a red Chevrolet Impala convertible.', 
    score: 0.5629135966300964
  },
  {
    identifier: 'The Man Who Killed Don Quixote',
    content: `Instead of a literal adaptation, Gilliam's film was about "an 
    old, retired, and slightly kooky nobleman named Alonso Quixano".`,
    score: 0.5493587255477905
  }
]

const chat = 'Which director has directed both Johnny Depp and Jonathan Pryce, 
but not necessarily in the same movie?';
const chatResult = await graphModel.chatWithData(chat);
    
Chat with data: Which director has directed both Johnny Depp and Jonathan Pryce, 
but not necessarily in the same movie?
Converted to Cypher query: MATCH (d:Director)-[:DIRECTED]->(m:Movie)(m2:Movie)

<p>Finally, our coup de grâce! Let’s create a natural language query that has to exploit <strong>both</strong> the structured data in the graph and the unstructured text data that we’ve indexed using vector embeddings:</p>

<code data-uuid="syynPXt3">const search = 'working in a boring job and looking for love.';
const chat2 = `Which director has directed a movie that is about the concepts of 
${search}? Return a single movie.`;
const chatResult2 = await graphModel.chatWithData(chat2);

Calling tool: get_embeddings
Tool replacing embeddings: MATCH (d:Director)-[:DIRECTED]->(m:Movie)
CALL db.index.vector.queryNodes('movie_summary', 1, <embeddings>)
YIELD node AS similar, score
MATCH (similar)

<p>In the output trace we can see a couple of steps:</p>

<ol><li>Open AI determining that, to satisfy this query, it needs vector embeddings for the string <em>‘working in a boring job and looking for love.’</em> via an Open AI tool configuration.</li>
	<li>Generation of a Cypher query with a placeholder set of embeddings <code><embeddings></embeddings></code>;. If you are curious to see how this works, you can find the prompt we use for Open AI on <a href="https://github.com/accordproject/lab-concerto-graph/blob/0bf4f8dedc6aea04543181f9dc179312211e503e/src/graphmodel.ts#L70">GitHub</a>. It combines the Concerto domain model with the natural language query and some information about index naming to create (mostly) valid Cypher queries.</li>
	<li>Generation of the embeddings using the Open AI embedding model.</li>
	<li>Execution of the Cypher query, which correctly returns Terry Gilliam as the only (most likely) director of a movie about the concepts of <em>‘working in a boring job and looking for love.’</em></li>
</ol><p>Voilà! We are <strong>chatting with our data</strong> — and we’ve not written any application-specific code; we’ve just defined our data model and called some framework APIs. For a full-fledged movie database example, please refer to my <a href="https://github.com/dselman/movie-graph">movie-graph demo</a>.</p>

<p>To give you a hint of how powerful this can be, take a look at this transcript:</p>

<code data-uuid="vetnZMvA">Which actor famously starred in a film conceptually about journalism, hitchhiking and drugs in Las Vegas?
Calling tool: get_embeddings
Converting query with embeddings to Cypher...
Tool replacing embeddings: MATCH (m:Movie)
    CALL db.index.vector.queryNodes('movie_summary', 3, <embeddings> )
    YIELD node AS similar, score
    MATCH (similar)

<p>Have fun!</p></embeddings></code></embeddings></code>