169 cosmetics improvements

CHANGELOG.md

@@ -5,6 +5,16 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [1.4.5] - 2026-02-02
+
+### Added
+- **Inferencer**: Row count estimates and row samples
+- **Discard disconnected vertices**: Option to discard disconnected vertices during graph operations
+
+### Changed
+- **clean_start**: Refactored into `recreate_schema` and `clear_data` for clearer separation of schema and data reset
+- **output_config**: Renamed to `target_db_config`
+
 ## [1.4.3] - 2026-01-25
 
 ### Added

README.md

@@ -129,27 +129,27 @@ from graflo.hq import GraphEngine
 # Option 1: Use GraphEngine for schema definition and ingestion (recommended)
 engine = GraphEngine()
 ingestion_params = IngestionParams(
-    clean_start=False,  # Set to True to wipe existing database
+    recreate_schema=False,  # Set to True to drop and redefine schema (script halts if schema exists)
     # max_items=1000,  # Optional: limit number of items to process
     # batch_size=10000,  # Optional: customize batch size
 )
 
 engine.define_and_ingest(
     schema=schema,
-    output_config=conn_conf,  # Target database config
+    target_db_config=conn_conf,  # Target database config
     patterns=patterns,  # Source data patterns
     ingestion_params=ingestion_params,
-    clean_start=False,  # Set to True to wipe existing database
+    recreate_schema=False,  # Set to True to drop and redefine schema (script halts if schema exists)
 )
 
 # Option 2: Use Caster directly (schema must be defined separately)
 # from graflo.hq import GraphEngine
 # engine = GraphEngine()
-# engine.define_schema(schema=schema, output_config=conn_conf, clean_start=False)
+# engine.define_schema(schema=schema, target_db_config=conn_conf, recreate_schema=False)
 # 
 # caster = Caster(schema)
 # caster.ingest(
-#     output_config=conn_conf,
+#     target_db_config=conn_conf,
 #     patterns=patterns,
 #     ingestion_params=ingestion_params,
 # )
@@ -178,8 +178,8 @@ schema = engine.infer_schema(
 target_config = ArangoConfig.from_docker_env()
 engine.define_schema(
     schema=schema,
-    output_config=target_config,
-    clean_start=False,
+    target_db_config=target_config,
+    recreate_schema=False,
 )
 
 # Use the inferred schema with Caster for ingestion

docs/examples/example-1.md

@@ -121,12 +121,12 @@ from graflo.hq.caster import IngestionParams
 caster = Caster(schema)
 
 ingestion_params = IngestionParams(
-    clean_start=False,  # Set to True to wipe existing database
+    recreate_schema=False,  # Set to True to drop and redefine schema (script halts if schema exists)
     # max_items=1000,  # Optional: limit number of items to process
 )
 
 caster.ingest(
-    output_config=conn_conf,  # Target database config
+    target_db_config=conn_conf,  # Target database config
     patterns=patterns,  # Source data patterns
     ingestion_params=ingestion_params,
 )

docs/examples/example-2.md

@@ -132,11 +132,11 @@ patterns.add_file_pattern(
 from graflo.hq.caster import IngestionParams
 
 ingestion_params = IngestionParams(
-    clean_start=True,  # Wipe existing database before ingestion
+    recreate_schema=True,  # Wipe existing schema before defining and ingesting
 )
 
 caster.ingest(
-    output_config=conn_conf,  # Target database config
+    target_db_config=conn_conf,  # Target database config
     patterns=patterns,  # Source data patterns
     ingestion_params=ingestion_params,
 )

docs/examples/example-3.md

@@ -120,11 +120,11 @@ from graflo.hq.caster import IngestionParams
 caster = Caster(schema)
 
 ingestion_params = IngestionParams(
-    clean_start=True,  # Wipe existing database before ingestion
+    recreate_schema=True,  # Wipe existing schema before defining and ingesting
 )
 
 caster.ingest(
-    output_config=conn_conf,  # Target database config
+    target_db_config=conn_conf,  # Target database config
     patterns=patterns,  # Source data patterns
     ingestion_params=ingestion_params,
 )

docs/examples/example-4.md

@@ -214,11 +214,11 @@ from graflo.hq.caster import IngestionParams
 caster = Caster(schema)
 
 ingestion_params = IngestionParams(
-    clean_start=True,  # Wipe existing database before ingestion
+    recreate_schema=True,  # Wipe existing schema before defining and ingesting
 )
 
 caster.ingest(
-    output_config=conn_conf,  # Target database config
+    target_db_config=conn_conf,  # Target database config
     patterns=patterns,  # Source data patterns
     ingestion_params=ingestion_params,
 )

docs/examples/example-5.md

@@ -373,15 +373,15 @@ from graflo.hq.caster import IngestionParams
 # Use GraphEngine for schema definition and ingestion
 engine = GraphEngine()
 ingestion_params = IngestionParams(
-    clean_start=True,  # Clear existing data first
+    recreate_schema=True,  # Drop existing schema and define new one before ingesting
 )
 
 engine.define_and_ingest(
     schema=schema,
-    output_config=target_config,  # Target graph database config
+    target_db_config=target_config,  # Target graph database config
     patterns=patterns,  # PostgreSQL table patterns
     ingestion_params=ingestion_params,
-    clean_start=True,  # Clear existing data first
+    recreate_schema=True,  # Drop existing schema and define new one before ingesting
 )
 ```
 
@@ -436,16 +436,16 @@ patterns = engine.create_patterns(postgres_conf, schema_name="public")
 
 # Step 7: Define schema and ingest data
 ingestion_params = IngestionParams(
-    clean_start=True,  # Clear existing data first
+    recreate_schema=True,  # Drop existing schema and define new one before ingesting
 )
 
 # Use GraphEngine to define schema and ingest data
 engine.define_and_ingest(
     schema=schema,
-    output_config=target_config,
+    target_db_config=target_config,
     patterns=patterns,
     ingestion_params=ingestion_params,
-    clean_start=True,  # Clear existing data first
+    recreate_schema=True,  # Drop existing schema and define new one before ingesting
 )
 
 print("\n" + "=" * 80)

docs/getting_started/quickstart.md

@@ -82,24 +82,24 @@ from graflo.hq import GraphEngine
 # Option 1: Use GraphEngine for schema definition and ingestion (recommended)
 engine = GraphEngine()
 ingestion_params = IngestionParams(
-    clean_start=False,  # Set to True to wipe existing database
+    recreate_schema=False,  # Set to True to drop and redefine schema (script halts if schema exists)
 )
 
 engine.define_and_ingest(
     schema=schema,
-    output_config=conn_conf,  # Target database config
+    target_db_config=conn_conf,  # Target database config
     patterns=patterns,  # Source data patterns
     ingestion_params=ingestion_params,
-    clean_start=False,  # Set to True to wipe existing database
+    recreate_schema=False,  # Set to True to drop and redefine schema (script halts if schema exists)
 )
 
 # Option 2: Use Caster directly (schema must be defined separately)
 # engine = GraphEngine()
-# engine.define_schema(schema=schema, output_config=conn_conf, clean_start=False)
+# engine.define_schema(schema=schema, target_db_config=conn_conf, recreate_schema=False)
 # 
 # caster = Caster(schema)
 # caster.ingest(
-#     output_config=conn_conf,
+#     target_db_config=conn_conf,
 #     patterns=patterns,
 #     ingestion_params=ingestion_params,
 # )
@@ -112,7 +112,7 @@ The `Patterns` class maps resource names (from `Schema`) to their physical data
 - **TablePattern**: For PostgreSQL table resources with connection configuration
 
 The `ingest()` method takes:
-- `output_config`: Target graph database configuration (where to write the graph)
+- `target_db_config`: Target graph database configuration (where to write the graph)
 - `patterns`: Source data patterns (where to read data from - files or database tables)
 
 ## 🚀 Using PostgreSQL Tables as Data Sources
@@ -161,15 +161,15 @@ arango_config = ArangoConfig.from_docker_env()  # Target graph database
 # Use GraphEngine for schema definition and ingestion
 engine = GraphEngine()
 ingestion_params = IngestionParams(
-    clean_start=False,  # Set to True to wipe existing database
+    recreate_schema=False,  # Set to True to drop and redefine schema (script halts if schema exists)
 )
 
 engine.define_and_ingest(
     schema=schema,
-    output_config=arango_config,  # Target graph database
+    target_db_config=arango_config,  # Target graph database
     patterns=patterns,  # Source PostgreSQL tables
     ingestion_params=ingestion_params,
-    clean_start=False,  # Set to True to wipe existing database
+    recreate_schema=False,  # Set to True to drop and redefine schema (script halts if schema exists)
 )
 ```
 
@@ -211,8 +211,8 @@ from graflo.hq import GraphEngine
 engine = GraphEngine()
 engine.define_schema(
     schema=schema,
-    output_config=conn_conf,
-    clean_start=False,
+    target_db_config=conn_conf,
+    recreate_schema=False,
 )
 
 # Then ingest using Caster

docs/reference/data_source/index.md

@@ -170,7 +170,7 @@ caster = Caster(schema)
 
 ingestion_params = IngestionParams(
     batch_size=1000,  # Process 1000 items per batch
-    clean_start=False,  # Set to True to wipe existing database
+    recreate_schema=False,  # Set to True to drop and redefine schema
 )
 
 caster.ingest_data_sources(

examples/1-ingest-csv/ingest.py

@@ -51,10 +51,10 @@
 
 # Create GraphEngine and define schema + ingest in one operation
 engine = GraphEngine(target_db_flavor=db_type)
-ingestion_params = IngestionParams(clean_start=True)
+ingestion_params = IngestionParams(clear_data=True)
 engine.define_and_ingest(
     schema=schema,
-    output_config=conn_conf,
+    target_db_config=conn_conf,
     patterns=patterns,
     ingestion_params=ingestion_params,
 )

examples/2-ingest-self-references/ingest.py

@@ -42,10 +42,10 @@
 
 # Create GraphEngine and define schema + ingest in one operation
 engine = GraphEngine(target_db_flavor=db_type)
-ingestion_params = IngestionParams(clean_start=True)
+ingestion_params = IngestionParams(clear_data=True)
 engine.define_and_ingest(
     schema=schema,
-    output_config=conn_conf,
+    target_db_config=conn_conf,
     patterns=patterns,
     ingestion_params=ingestion_params,
 )

examples/3-ingest-csv-edge-weights/ingest.py

@@ -50,10 +50,10 @@
 
 # Create GraphEngine and define schema + ingest in one operation
 engine = GraphEngine(target_db_flavor=db_type)
-ingestion_params = IngestionParams(clean_start=True)
+ingestion_params = IngestionParams(clear_data=True)
 engine.define_and_ingest(
     schema=schema,
-    output_config=conn_conf,
+    target_db_config=conn_conf,
     patterns=patterns,
     ingestion_params=ingestion_params,
 )

examples/4-ingest-neo4j/ingest.py

@@ -56,12 +56,12 @@
 # Create GraphEngine and define schema + ingest in one operation
 engine = GraphEngine(target_db_flavor=db_type)
 ingestion_params = IngestionParams(
-    clean_start=True,
     # max_items=5,
 )
 engine.define_and_ingest(
     schema=schema,
-    output_config=conn_conf,  # Target database config
+    target_db_config=conn_conf,  # Target database config
     patterns=patterns,  # Source data patterns
     ingestion_params=ingestion_params,
+    recreate_schema=True,  # Wipe existing schema before defining and ingesting
 )

examples/5-ingest-postgres/ingest.py

@@ -115,12 +115,10 @@
 # Note: ingestion will create its own PostgreSQL connections per table internally
 engine.define_and_ingest(
     schema=schema,
-    output_config=conn_conf,
+    target_db_config=conn_conf,
     patterns=patterns,
-    ingestion_params=IngestionParams(
-        clean_start=False
-    ),  # clean_start handled by define_and_ingest
-    clean_start=True,  # Clean existing data before defining schema
+    ingestion_params=IngestionParams(clear_data=False),
+    recreate_schema=True,  # Drop existing schema and define new one before ingesting
 )
 
 print("\n" + "=" * 80)

graflo/__init__.py

@@ -15,7 +15,7 @@
 Example:
     >>> from graflo.db.manager import ConnectionManager
     >>> with ConnectionManager(config) as conn:
-    ...     conn.init_db(schema, clean_start=True)
+    ...     conn.init_db(schema, recreate_schema=True)
     ...     conn.upsert_docs_batch(docs, "users")
 """