Add neo4j vector index docs

docs/extras/modules/data_connection/vectorstores/integrations/neo4jvector.mdx

@@ -0,0 +1,52 @@
+# Neo4j Vector Index
+
+Neo4j is an open-source graph database with integrated support for vector similarity search.
+It supports:
+
+- approximate nearest neighbor search
+- Euclidean similarity and cosine similarity
+- Hybrid search combining vector and keyword searches
+
+## Setup
+
+To work with Neo4j Vector Index, you need to install the `neo4j-driver` package:
+
+```bash npm2yarn
+npm install neo4j-driver
+```
+
+### Setup a `Neo4j` self hosted instance with `docker-compose`
+
+`Neo4j` provides a prebuilt Docker image that can be used to quickly setup a self-hosted Neo4j database instance.
+Create a file below named `docker-compose.yml`:
+
+import CodeBlock from "@theme/CodeBlock";
+import DockerExample from "@examples/indexes/vector_stores/neo4j_vector/docker-compose.example.yml";
+
+<CodeBlock language="yml" name="docker-compose.yml">
+  {DockerExample}
+</CodeBlock>
+
+And then in the same directory, run `docker compose up` to start the container.
+
+You can find more information on how to setup `Neo4j` on their [website](https://neo4j.com/docs/operations-manual/current/installation/).
+
+## Usage
+
+import Example from "@examples/indexes/vector_stores/neo4j_vector/neo4j_vector.ts";
+
+One complete example of using `Neo4jVectorIndex` is the following:
+
+<CodeBlock language="typescript">{Example}</CodeBlock>
+
+### Use retrievalQuery parameter to customize responses
+
+import RetrievalExample from "@examples/indexes/vector_stores/neo4j_vector/neo4j_vector_retrieval.ts";
+
+<CodeBlock language="typescript">{RetrievalExample}</CodeBlock>
+
+### Instantiate Neo4jVectorIndex from existing graph
+
+import ExistingGraphExample from "@examples/indexes/vector_stores/neo4j_vector/neo4j_vector_existinggraph.ts";
+
+<CodeBlock language="typescript">{ExistingGraphExample}</CodeBlock>

examples/src/indexes/vector_stores/neo4j_vector/docker-compose.example.yml

@@ -0,0 +1,8 @@
+services:
+  database:
+    image: neo4j
+    ports:
+      - 7687:7687
+      - 7474:7474
+    environment:
+      - NEO4J_AUTH=neo4j/pleaseletmein

examples/src/indexes/vector_stores/neo4j_vector/neo4j_vector.ts

@@ -0,0 +1,36 @@
+import { OpenAIEmbeddings } from "langchain/embeddings/openai";
+import { Neo4jVectorIndex } from "langchain/vectorstores/neo4j_vector";
+
+// Configuration object for Neo4j connection and other related settings
+const config = {
+  url: "bolt://localhost:7687", // URL for the Neo4j instance
+  username: "neo4j", // Username for Neo4j authentication
+  password: "pleaseletmein", // Password for Neo4j authentication
+  indexName: "vector", // Name of the vector index
+  keywordIndexName: "keyword", // Name of the keyword index if using hybrid search
+  searchType: "vector", // Type of search (e.g., vector, hybrid)
+  nodeLabel: "Chunk", // Label for the nodes in the graph
+  textNodeProperty: "text", // Property of the node containing text
+  embeddingNodeProperty: "embedding", // Property of the node containing embedding
+};
+
+const documents = [
+  { pageContent: "what's this", metadata: { a: 2 } },
+  { pageContent: "Cat drinks milk", metadata: { a: 1 } },
+];
+
+const neo4jVectorIndex = await Neo4jVectorIndex.fromDocuments(
+  documents,
+  new OpenAIEmbeddings(),
+  config
+);
+
+const results = await neo4jVectorIndex.similaritySearch("water", 1);
+
+console.log(results);
+
+/*
+  [ Document { pageContent: 'Cat drinks milk', metadata: { a: 1 } } ]
+*/
+
+await Neo4jVectorIndex.close();

examples/src/indexes/vector_stores/neo4j_vector/neo4j_vector_existinggraph.ts

@@ -0,0 +1,35 @@
+import { OpenAIEmbeddings } from "langchain/embeddings/openai";
+import { Neo4jVectorIndex } from "langchain/vectorstores/neo4j_vector";
+
+/**
+ * `fromExistingGraph` Method:
+ *
+ * Description:
+ * This method initializes a `Neo4jVectorStore` instance using an existing graph in the Neo4j database.
+ * It's designed to work with nodes that already have textual properties but might not have embeddings.
+ * The method will compute and store embeddings for nodes that lack them.
+ *
+ * Note:
+ * This method is particularly useful when you have a pre-existing graph with textual data and you want
+ * to enhance it with vector embeddings for similarity searches without altering the original data structure.
+ */
+
+// Configuration object for Neo4j connection and other related settings
+const config = {
+  url: "bolt://localhost:7687", // URL for the Neo4j instance
+  username: "neo4j", // Username for Neo4j authentication
+  password: "pleaseletmein", // Password for Neo4j authentication
+  indexName: "wikipedia",
+  nodeLabel: "Wikipedia",
+  textNodeProperties: ["title", "description"],
+  embeddingNodeProperty: "embedding",
+  searchType: "hybrid",
+};
+
+// You should have a populated Neo4j database to use this method
+const neo4jVectorIndex = await Neo4jVectorIndex.fromExistingGraph(
+  new OpenAIEmbeddings(),
+  config
+);
+
+await Neo4jVectorIndex.close();

examples/src/indexes/vector_stores/neo4j_vector/neo4j_vector_retrieval.ts

@@ -0,0 +1,59 @@
+import { OpenAIEmbeddings } from "langchain/embeddings/openai";
+import { Neo4jVectorIndex } from "langchain/vectorstores/neo4j_vector";
+
+/*
+ * The retrievalQuery is a customizable Cypher query fragment used in the Neo4jVectorStore class to define how
+ * search results should be retrieved and presented from the Neo4j database. It allows developers to specify
+ * the format and structure of the data returned after a similarity search.
+ * Mandatory columns for `retrievalQuery`:
+ *
+ * 1. text:
+ *    - Description: Represents the textual content of the node.
+ *    - Type: String
+ *
+ * 2. score:
+ *    - Description: Represents the similarity score of the node in relation to the search query. A
+ *      higher score indicates a closer match.
+ *    - Type: Float (ranging between 0 and 1, where 1 is a perfect match)
+ *
+ * 3. metadata:
+ *    - Description: Contains additional properties and information about the node. This can include
+ *      any other attributes of the node that might be relevant to the application.
+ *    - Type: Object (key-value pairs)
+ *    - Example: { "id": "12345", "category": "Books", "author": "John Doe" }
+ *
+ * Note: While you can customize the `retrievalQuery` to fetch additional columns or perform
+ * transformations, never omit the mandatory columns. The names of these columns (`text`, `score`,
+ * and `metadata`) should remain consistent. Renaming them might lead to errors or unexpected behavior.
+ */
+
+// Configuration object for Neo4j connection and other related settings
+const config = {
+  url: "bolt://localhost:7687", // URL for the Neo4j instance
+  username: "neo4j", // Username for Neo4j authentication
+  password: "pleaseletmein", // Password for Neo4j authentication
+  retrievalQuery: `
+    RETURN node.text AS text, score, {a: node.a * 2} AS metadata
+  `,
+};
+
+const documents = [
+  { pageContent: "what's this", metadata: { a: 2 } },
+  { pageContent: "Cat drinks milk", metadata: { a: 1 } },
+];
+
+const neo4jVectorIndex = await Neo4jVectorIndex.fromDocuments(
+  documents,
+  new OpenAIEmbeddings(),
+  config
+);
+
+const results = await neo4jVectorIndex.similaritySearch("water", 1);
+
+console.log(results);
+
+/*
+  [ Document { pageContent: 'Cat drinks milk', metadata: { a: 2 } } ]
+*/
+
+await Neo4jVectorIndex.close();