Adds GenAI client object (#1)

* Adds GenAIClient class and examples

.gitignore

@@ -1 +1,4 @@
 dist/
+**/__pycache__/*
+*.py[cod]
+.mypy_cache/

.pre-commit-config.yaml

@@ -0,0 +1,6 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.5.0  # Use the ref you want to point at
+    hooks:
+    - id: trailing-whitespace
+    # -   id: ...

README.md

@@ -0,0 +1,3 @@
+# Neo4j GenAI package for Python
+
+This repository contains the official Neo4j GenAI features for Python.

examples/similarity_search_for_text.py

@@ -0,0 +1,54 @@
+from typing import List
+from neo4j import GraphDatabase
+from neo4j.exceptions import DatabaseError
+from neo4j_genai.client import GenAIClient
+
+from random import random
+from neo4j_genai.embeddings import Embeddings
+
+URI = "neo4j://localhost:7687"
+AUTH = ("neo4j", "password")
+
+INDEX_NAME = "embedding-name"
+DIMENSION = 1536
+
+# Connect to Neo4j database
+driver = GraphDatabase.driver(URI, auth=AUTH)
+
+
+# Create Embeddings object
+class CustomEmbeddings(Embeddings):
+    def embed_query(self, text: str) -> List[float]:
+        return [random() for _ in range(DIMENSION)]
+
+
+embeddings = CustomEmbeddings()
+
+# Initialize the client
+client = GenAIClient(driver, embeddings)
+
+# Creating the index
+client.create_index(
+    INDEX_NAME,
+    label="Document",
+    property="propertyKey",
+    dimensions=DIMENSION,
+    similarity_fn="euclidean",
+)
+
+# Upsert the query
+vector = [random() for _ in range(DIMENSION)]
+insert_query = (
+    "MERGE (n:Document)"
+    "WITH n "
+    "CALL db.create.setNodeVectorProperty(n, 'propertyKey', $vector)"
+    "RETURN n"
+)
+parameters = {
+    "vector": vector,
+}
+client.database_query(insert_query, params=parameters)
+
+# Perform the similarity search for a text query
+query_text = "hello world"
+print(client.similarity_search(INDEX_NAME, query_text=query_text, top_k=5))

examples/similarity_search_for_vector.py

@@ -0,0 +1,42 @@
+from neo4j import GraphDatabase
+from neo4j_genai.client import GenAIClient
+
+from random import random
+
+URI = "neo4j://localhost:7687"
+AUTH = ("neo4j", "password")
+
+INDEX_NAME = "embedding-name"
+DIMENSION = 1536
+
+# Connect to Neo4j database
+driver = GraphDatabase.driver(URI, auth=AUTH)
+
+# Initialize the client
+client = GenAIClient(driver)
+
+# Creating the index
+client.create_index(
+    INDEX_NAME,
+    label="Document",
+    property="propertyKey",
+    dimensions=DIMENSION,
+    similarity_fn="euclidean",
+)
+
+# Upsert the vector
+vector = [random() for _ in range(DIMENSION)]
+insert_query = (
+    "MERGE (n:Document)"
+    "WITH n "
+    "CALL db.create.setNodeVectorProperty(n, 'propertyKey', $vector)"
+    "RETURN n"
+)
+parameters = {
+    "vector": vector,
+}
+client.database_query(insert_query, params=parameters)
+
+# Perform the similarity search for a vector query
+query_vector = [random() for _ in range(DIMENSION)]
+print(client.similarity_search(INDEX_NAME, query_vector=query_vector, top_k=5))