import pyarrow as pa
from lance_graph import CypherQuery, GraphConfig

cfg = (
    GraphConfig.builder()
    .with_node_label("Person", "id")
    .with_node_label("City", "id")
    .with_relationship("lives_in", "src", "dst")
    .build()
)

datasets = {
    "Person": pa.table({"id": [1, 2], "name": ["Alice", "Bob"]}),
    "City": pa.table({"id": [10, 20], "name": ["London", "Sydney"]}),
    "lives_in": pa.table({"src": [1, 2], "dst": [10, 20]}),
}

query = """
    MATCH (p:Person)-[:lives_in]->(c:City)
    RETURN p.name, c.name
"""

result = CypherQuery(query).with_config(cfg).execute(datasets)
print(result.to_pylist())

[{'p.name': 'Alice', 'c.name': 'London'}, {'p.name': 'Bob', 'c.name': 'Sydney'}]

import pyarrow as pa
from lance_graph import CypherEngine, GraphConfig

cfg = (
    GraphConfig.builder()
    .with_node_label("Person", "id")
    .with_node_label("City", "id")
    .with_relationship("lives_in", "src", "dst")
    .build()
)

datasets = {
    "Person": pa.table({"id": [1, 2], "name": ["Alice", "Bob"], "age": [30, 25]}),
    "City": pa.table({"id": [10, 20], "name": ["London", "Sydney"]}),
    "lives_in": pa.table({"src": [1, 2], "dst": [10, 20]}),
}

# Create engine once - builds catalog
engine = CypherEngine(cfg, datasets)

# Execute multiple queries efficiently - catalog is reused
result1 = engine.execute("MATCH (p:Person) WHERE p.age > 25 RETURN p.name")
result2 = engine.execute("MATCH (p:Person)-[:lives_in]->(c:City) RETURN p.name, c.name")
result3 = engine.execute("MATCH (p:Person) RETURN count(*) as total")

print(result1.to_pylist())
# [{'p.name': 'Alice'}]

import pyarrow as pa
from lance_graph import SqlQuery, SqlEngine

person = pa.table({
    "id": [1, 2, 3],
    "name": ["Alice", "Bob", "Carol"],
    "age": [28, 34, 29],
})
knows = pa.table({"src_id": [1, 1, 2], "dst_id": [2, 3, 3]})
datasets = {"person": person, "knows": knows}

# One-off query
result = SqlQuery(
    "SELECT p.name, p.age FROM person p WHERE p.age > 30"
).execute(datasets)
print(result.to_pylist())
# [{'name': 'Bob', 'age': 34}]

# Multi-query with cached context
engine = SqlEngine(datasets)
r1 = engine.execute("SELECT COUNT(*) AS cnt FROM person")
r2 = engine.execute(
    "SELECT p1.name AS person, p2.name AS friend "
    "FROM person p1 "
    "JOIN knows k ON p1.id = k.src_id "
    "JOIN person p2 ON p2.id = k.dst_id"
)

from lance_graph import UnityCatalog

# Connect to Unity Catalog
uc = UnityCatalog("http://localhost:8080/api/2.1/unity-catalog")

# Browse catalog hierarchy
catalogs = uc.list_catalogs()
schemas = uc.list_schemas("unity")
tables = uc.list_tables("unity", "default")

# Inspect table metadata
table = uc.get_table("unity", "default", "marksheet")
print(table.data_source_format)  # "Delta"
print(table.columns())           # [{"name": "id", "type_name": "INT", ...}, ...]

# Auto-register all tables and query via SQL
engine = uc.create_sql_engine("unity", "default")
result = engine.execute("SELECT * FROM marksheet WHERE mark > 80")
print(result.to_pandas())

uc = UnityCatalog(
    "http://localhost:8080/api/2.1/unity-catalog",
    storage_options={
        "azure_storage_account_name": "myaccount",
        "azure_storage_account_key": "...",
    }
)
engine = uc.create_sql_engine("unity", "default")

from pathlib import Path
from knowledge_graph import (
    KnowledgeGraphConfig,
    LanceKnowledgeGraph,
    LanceGraphStore,
    get_extractor,
)
from knowledge_graph.cli.ingest import extract_and_add

# Initialize knowledge graph
config = KnowledgeGraphConfig.from_root(Path("./my_graph"))
config.ensure_directories()

# Create schema
schema_path = config.resolved_schema_path()
if not schema_path.exists():
    schema_content = """
nodes:
  Entity:
    id_field: entity_id

relationships:
  RELATIONSHIP:
    source: source_entity_id
    target: target_entity_id
"""
    schema_path.write_text(schema_content, encoding="utf-8")

store = LanceGraphStore(config)
store.ensure_layout()

graph_config = config.load_graph_config()
kg = LanceKnowledgeGraph(graph_config, storage=store)
kg.ensure_initialized()

# Extract and add entities/relationships from text
# Using heuristic extractor for testing without API key
extractor = get_extractor("heuristic")
# or using LLM extractor (requires API key)
# extractor = get_extractor("llm", llm_model="gpt-4o-mini")
text = """
Albert Einstein developed the theory of relativity at Princeton.
Marie Curie discovered radioactivity in Paris.
"""

extract_and_add(text, kg, extractor, embedding_generator=None)

# Query the graph
result = kg.query("""
    MATCH (e:Entity)
    RETURN e.name, e.entity_type
    LIMIT 10
""")
print(result.to_pylist())

from knowledge_graph.llm.qa import ask_question

# Ask questions in natural language
answer = ask_question(
    "Who discovered radioactivity?",
    kg,
    llm_model="gpt-4o-mini"
)
print(answer)
# Output: Marie Curie discovered radioactivity.