참고소스 수정본

참고/neo4j-graphrag-python-main/examples/build_graph/automatic_schema_extraction/simple_kg_builder_schema_from_pdf.py

@@ -0,0 +1,87 @@
+"""This example demonstrates how to use SimpleKGPipeline with automatic schema extraction
+from a PDF file. When no schema is provided to SimpleKGPipeline, automatic schema extraction
+is performed using the LLM.
+
+Note: This example requires an OpenAI API key to be set in the .env file.
+"""
+
+import asyncio
+import logging
+import os
+from pathlib import Path
+from dotenv import load_dotenv
+import neo4j
+
+from neo4j_graphrag.experimental.pipeline.kg_builder import SimpleKGPipeline
+from neo4j_graphrag.llm import OpenAILLM
+from neo4j_graphrag.embeddings import OpenAIEmbeddings
+
+# Load environment variables from .env file
+load_dotenv()
+
+# Configure logging
+logging.basicConfig()
+logging.getLogger("neo4j_graphrag").setLevel(logging.INFO)
+
+# PDF file path
+root_dir = Path(__file__).parents[2]
+PDF_FILE = str(
+    root_dir / "data" / "Harry Potter and the Chamber of Secrets Summary.pdf"
+)
+
+
+async def run_kg_pipeline_with_auto_schema() -> None:
+    """Run the SimpleKGPipeline with automatic schema extraction from a PDF file."""
+
+    # Define Neo4j connection
+    uri = os.getenv("NEO4J_URI", "neo4j://localhost:7687")
+    user = os.getenv("NEO4J_USER", "neo4j")
+    password = os.getenv("NEO4J_PASSWORD", "password")
+
+    # Initialize the Neo4j driver
+    driver = neo4j.GraphDatabase.driver(uri, auth=(user, password))
+
+    # Create the LLM instance
+    llm = OpenAILLM(model_name="gpt-5")
+
+    # Create the embedder instance
+    embedder = OpenAIEmbeddings()
+
+    try:
+        # Create a SimpleKGPipeline instance without providing a schema
+        # This will trigger automatic schema extraction
+        kg_builder = SimpleKGPipeline(
+            llm=llm,
+            driver=driver,
+            embedder=embedder,
+            from_file=True,
+        )
+
+        print(f"Processing PDF file: {PDF_FILE}")
+        # Run the pipeline on the PDF file
+        await kg_builder.run_async(file_path=PDF_FILE)
+
+    finally:
+        # Close connections
+        await llm.aclose()
+        driver.close()
+
+
+async def main() -> None:
+    """Run the example."""
+    # Create data directory if it doesn't exist
+    data_dir = root_dir / "data"
+    data_dir.mkdir(exist_ok=True)
+
+    # Check if the PDF file exists
+    if not Path(PDF_FILE).exists():
+        print(f"Warning: PDF file not found at {PDF_FILE}")
+        print("Please replace with a valid PDF file path.")
+        return
+
+    # Run the pipeline
+    await run_kg_pipeline_with_auto_schema()
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

참고/neo4j-graphrag-python-main/examples/build_graph/automatic_schema_extraction/simple_kg_builder_schema_from_text.py

@@ -0,0 +1,94 @@
+"""This example demonstrates how to use SimpleKGPipeline with automatic schema extraction
+from a text input. When no schema is provided to SimpleKGPipeline, automatic schema extraction
+is performed using the LLM.
+
+Note: This example requires an OpenAI API key to be set in the .env file.
+"""
+
+import asyncio
+import logging
+import os
+from dotenv import load_dotenv
+import neo4j
+
+from neo4j_graphrag.experimental.pipeline.kg_builder import SimpleKGPipeline
+from neo4j_graphrag.llm import OpenAILLM
+from neo4j_graphrag.embeddings import OpenAIEmbeddings
+
+# Load environment variables from .env file
+load_dotenv()
+
+# Configure logging
+logging.basicConfig()
+logging.getLogger("neo4j_graphrag").setLevel(logging.DEBUG)
+
+# Sample text to build a knowledge graph from
+TEXT = """
+Acme Corporation was founded in 1985 by John Smith in New York City. 
+The company specializes in manufacturing high-quality widgets and gadgets 
+for the consumer electronics industry.
+
+Sarah Johnson joined Acme in 2010 as a Senior Engineer and was promoted to 
+Engineering Director in 2015. She oversees a team of 12 engineers working on 
+next-generation products. Sarah holds a PhD in Electrical Engineering from MIT 
+and has filed 5 patents during her time at Acme.
+
+The company expanded to international markets in 2012, opening offices in London, 
+Tokyo, and Berlin. Each office is managed by a regional director who reports 
+directly to the CEO, Michael Brown, who took over leadership in 2008.
+
+Acme's most successful product, the SuperWidget X1, was launched in 2018 and 
+has sold over 2 million units worldwide. The product was developed by a team led 
+by Robert Chen, who joined the company in 2016 after working at TechGiant for 8 years.
+
+The company currently employs 250 people across its 4 locations and had a revenue 
+of $75 million in the last fiscal year. Acme is planning to go public in 2024 
+with an estimated valuation of $500 million.
+"""
+
+
+async def run_kg_pipeline_with_auto_schema() -> None:
+    """Run the SimpleKGPipeline with automatic schema extraction from text input."""
+
+    # Define Neo4j connection
+    uri = os.getenv("NEO4J_URI", "neo4j://localhost:7687")
+    user = os.getenv("NEO4J_USER", "neo4j")
+    password = os.getenv("NEO4J_PASSWORD", "password")
+
+    # Initialize the Neo4j driver
+    driver = neo4j.GraphDatabase.driver(uri, auth=(user, password))
+
+    # Create the LLM instance
+    llm = OpenAILLM(
+        model_name="gpt-5",
+    )
+
+    # Create the embedder instance
+    embedder = OpenAIEmbeddings()
+
+    try:
+        # Create a SimpleKGPipeline instance without providing a schema
+        # This will trigger automatic schema extraction
+        kg_builder = SimpleKGPipeline(
+            llm=llm,
+            driver=driver,
+            embedder=embedder,
+            from_file=False,  # Using raw text input, not PDF
+        )
+
+        # Run the pipeline on the text
+        await kg_builder.run_async(text=TEXT)
+
+    finally:
+        # Close connections
+        await llm.aclose()
+        driver.close()
+
+
+async def main() -> None:
+    """Run the example."""
+    await run_kg_pipeline_with_auto_schema()
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

참고/neo4j-graphrag-python-main/examples/build_graph/from_config_files/simple_kg_pipeline_config.json

@@ -0,0 +1,109 @@
+{
+    "version_": "1",
+    "template_": "SimpleKGPipeline",
+    "neo4j_config": {
+        "params_": {
+            "uri": {
+                "resolver_": "ENV",
+                "var_": "NEO4J_URI"
+            },
+            "user": {
+                "resolver_": "ENV",
+                "var_": "NEO4J_USER"
+            },
+            "password": {
+                "resolver_": "ENV",
+                "var_": "NEO4J_PASSWORD"
+            }
+        }
+    },
+    "llm_config": {
+        "class_": "OpenAILLM",
+        "params_": {
+            "api_key": {
+                "resolver_": "ENV",
+                "var_": "OPENAI_API_KEY"
+            },
+            "model_name": "gpt-5"
+        }
+    },
+    "embedder_config": {
+        "class_": "OpenAIEmbeddings",
+        "params_": {
+            "api_key": {
+                "resolver_": "ENV",
+                "var_": "OPENAI_API_KEY"
+            }
+        }
+    },
+    "from_file": false,
+    "schema": {
+        "node_types": [
+            "Person",
+            {
+                "label": "House",
+                "description": "Family the person belongs to",
+                "properties": [
+                    {
+                        "name": "name",
+                        "type": "STRING"
+                    }
+                ]
+            },
+            {
+                "label": "Planet",
+                "properties": [
+                    {
+                        "name": "name",
+                        "type": "STRING"
+                    },
+                    {
+                        "name": "weather",
+                        "type": "STRING"
+                    }
+                ]
+            }
+        ],
+        "relationship_types": [
+            "PARENT_OF",
+            {
+                "label": "HEIR_OF",
+                "description": "Used for inheritor relationship between father and sons"
+            },
+            {
+                "label": "RULES",
+                "properties": [
+                    {
+                        "name": "fromYear",
+                        "type": "INTEGER"
+                    }
+                ]
+            }
+        ],
+        "patterns": [
+            [
+                "Person",
+                "PARENT_OF",
+                "Person"
+            ],
+            [
+                "Person",
+                "HEIR_OF",
+                "House"
+            ],
+            [
+                "House",
+                "RULES",
+                "Planet"
+            ]
+        ]
+    },
+    "text_splitter": {
+        "class_": "text_splitters.fixed_size_splitter.FixedSizeSplitter",
+        "params_": {
+            "chunk_size": 100,
+            "chunk_overlap": 10
+        }
+    },
+    "perform_entity_resolution": true
+}

참고/neo4j-graphrag-python-main/examples/build_graph/from_config_files/simple_kg_pipeline_config.yaml

@@ -0,0 +1,59 @@
+version_: "1"
+template_: SimpleKGPipeline
+neo4j_config:
+  params_:
+    uri:
+      resolver_: ENV
+      var_: NEO4J_URI
+    user:
+      resolver_: ENV
+      var_: NEO4J_USER
+    password:
+      resolver_: ENV
+      var_: NEO4J_PASSWORD
+llm_config:
+  class_: OpenAILLM
+  params_:
+    api_key:
+      resolver_: ENV
+      var_: OPENAI_API_KEY
+    model_name: gpt-5
+embedder_config:
+  class_: OpenAIEmbeddings
+  params_:
+    api_key:
+      resolver_: ENV
+      var_: OPENAI_API_KEY
+from_file: false
+schema:
+  node_types:
+    - label: Person
+    - label: House
+      description: Family the person belongs to
+      properties:
+        - name: name
+          type: STRING
+    - label: Planet
+      properties:
+        - name: name
+          type: STRING
+        - name: weather
+          type: STRING
+  relationship_types:
+    - label: PARENT_OF
+    - label: HEIR_OF
+      description: Used for inheritor relationship between father and sons
+    - label: RULES
+      properties:
+        - name: fromYear
+          type: INTEGER
+  patterns:
+    - ["Person", "PARENT_OF", "Person"]
+    - ["Person", "HEIR_OF", "House"]
+    - ["House", "RULES", "Planet"]
+text_splitter:
+  class_: text_splitters.fixed_size_splitter.FixedSizeSplitter
+  params_:
+    chunk_size: 100
+    chunk_overlap: 10
+perform_entity_resolution: true

참고/neo4j-graphrag-python-main/examples/build_graph/from_config_files/simple_kg_pipeline_config_url.json

@@ -0,0 +1,115 @@
+{
+    "version_": "1",
+    "template_": "SimpleKGPipeline",
+    "neo4j_config": {
+        "params_": {
+            "uri": {
+                "resolver_": "ENV",
+                "var_": "NEO4J_URI"
+            },
+            "user": {
+                "resolver_": "ENV",
+                "var_": "NEO4J_USER"
+            },
+            "password": {
+                "resolver_": "ENV",
+                "var_": "NEO4J_PASSWORD"
+            }
+        }
+    },
+    "llm_config": {
+        "class_": "OpenAILLM",
+        "params_": {
+            "api_key": {
+                "resolver_": "ENV",
+                "var_": "OPENAI_API_KEY"
+            },
+            "model_name": "gpt-5"
+        }
+    },
+    "embedder_config": {
+        "class_": "OpenAIEmbeddings",
+        "params_": {
+            "api_key": {
+                "resolver_": "ENV",
+                "var_": "OPENAI_API_KEY"
+            }
+        }
+    },
+    "from_file": true,
+    "schema": {
+        "node_types": [
+            "Person",
+            {
+                "label": "House",
+                "description": "Family the person belongs to",
+                "properties": [
+                    {
+                        "name": "name",
+                        "type": "STRING"
+                    }
+                ]
+            },
+            {
+                "label": "Planet",
+                "properties": [
+                    {
+                        "name": "name",
+                        "type": "STRING"
+                    },
+                    {
+                        "name": "weather",
+                        "type": "STRING"
+                    }
+                ]
+            }
+        ],
+        "relationship_types": [
+            "PARENT_OF",
+            {
+                "label": "HEIR_OF",
+                "description": "Used for inheritor relationship between father and sons"
+            },
+            {
+                "label": "RULES",
+                "properties": [
+                    {
+                        "name": "fromYear",
+                        "type": "INTEGER"
+                    }
+                ]
+            }
+        ],
+        "patterns": [
+            [
+                "Person",
+                "PARENT_OF",
+                "Person"
+            ],
+            [
+                "Person",
+                "HEIR_OF",
+                "House"
+            ],
+            [
+                "House",
+                "RULES",
+                "Planet"
+            ]
+        ]
+    },
+    "text_splitter": {
+        "class_": "text_splitters.fixed_size_splitter.FixedSizeSplitter",
+        "params_": {
+            "chunk_size": 100,
+            "chunk_overlap": 10
+        }
+    },
+    "file_loader": {
+        "class_": "data_loader.PdfLoader",
+        "run_params_": {
+            "fs": "http"
+        }
+    },
+    "perform_entity_resolution": true
+}

참고/neo4j-graphrag-python-main/examples/build_graph/from_config_files/simple_kg_pipeline_from_config_file.py

@@ -0,0 +1,47 @@
+"""In this example, the pipeline is defined in a JSON ('simple_kg_pipeline_config.json')
+or YAML ('simple_kg_pipeline_config.yaml') file.
+
+According to the configuration file, some parameters will be read from the env vars
+(Neo4j credentials and the OpenAI API key).
+"""
+
+import asyncio
+import logging
+
+## If env vars are in a .env file, uncomment:
+## (requires pip install python-dotenv)
+# from dotenv import load_dotenv
+# load_dotenv()
+# env vars manually set for testing:
+import os
+from pathlib import Path
+
+from neo4j_graphrag.experimental.pipeline.config.runner import PipelineRunner
+from neo4j_graphrag.experimental.pipeline.pipeline import PipelineResult
+
+logging.basicConfig()
+logging.getLogger("neo4j_graphrag").setLevel(logging.DEBUG)
+
+os.environ["NEO4J_URI"] = "bolt://localhost:7687"
+os.environ["NEO4J_USER"] = "neo4j"
+os.environ["NEO4J_PASSWORD"] = "password"
+# os.environ["OPENAI_API_KEY"] = "sk-..."
+
+
+root_dir = Path(__file__).parent
+file_path = root_dir / "simple_kg_pipeline_config.yaml"
+# file_path = root_dir / "simple_kg_pipeline_config.json"
+
+
+# Text to process
+TEXT = """The son of Duke Leto Atreides and the Lady Jessica, Paul is the heir of House Atreides,
+an aristocratic family that rules the planet Caladan, the rainy planet, since 10191."""
+
+
+async def main() -> PipelineResult:
+    pipeline = PipelineRunner.from_config_file(file_path)
+    return await pipeline.run({"text": TEXT})
+
+
+if __name__ == "__main__":
+    print(asyncio.run(main()))

참고/neo4j-graphrag-python-main/examples/build_graph/from_config_files/simple_kg_pipeline_from_config_file_with_url.py

@@ -0,0 +1,45 @@
+"""In this example, the pipeline is defined in a JSON ('simple_kg_pipeline_config.json')
+or YAML ('simple_kg_pipeline_config.yaml') file.
+
+According to the configuration file, some parameters will be read from the env vars
+(Neo4j credentials and the OpenAI API key).
+"""
+
+import asyncio
+import logging
+
+## If env vars are in a .env file, uncomment:
+## (requires pip install python-dotenv)
+# from dotenv import load_dotenv
+# load_dotenv()
+# env vars manually set for testing:
+import os
+from pathlib import Path
+
+from neo4j_graphrag.experimental.pipeline.config.runner import PipelineRunner
+from neo4j_graphrag.experimental.pipeline.pipeline import PipelineResult
+
+logging.basicConfig()
+logging.getLogger("neo4j_graphrag").setLevel(logging.DEBUG)
+
+os.environ["NEO4J_URI"] = "bolt://localhost:7687"
+os.environ["NEO4J_USER"] = "neo4j"
+os.environ["NEO4J_PASSWORD"] = "password"
+# os.environ["OPENAI_API_KEY"] = "sk-..."
+
+
+root_dir = Path(__file__).parent
+file_path = root_dir / "simple_kg_pipeline_config_url.json"
+
+
+# File to process
+URL = "https://raw.githubusercontent.com/neo4j/neo4j-graphrag-python/c166afc4d5abc56a5686f3da46a97ed7c07da19d/examples/data/Harry%20Potter%20and%20the%20Chamber%20of%20Secrets%20Summary.pdf"
+
+
+async def main() -> PipelineResult:
+    pipeline = PipelineRunner.from_config_file(file_path)
+    return await pipeline.run({"file_path": URL})
+
+
+if __name__ == "__main__":
+    print(asyncio.run(main()))

참고/neo4j-graphrag-python-main/examples/build_graph/simple_kg_builder_from_pdf.py

@@ -0,0 +1,74 @@
+"""This example illustrates how to get started easily with the SimpleKGPipeline
+and ingest PDF into a Neo4j Knowledge Graph.
+
+This example assumes a Neo4j db is up and running. Update the credentials below
+if needed.
+
+OPENAI_API_KEY needs to be in the env vars.
+"""
+
+import asyncio
+from pathlib import Path
+
+import neo4j
+from neo4j_graphrag.embeddings import OpenAIEmbeddings
+from neo4j_graphrag.experimental.pipeline.kg_builder import SimpleKGPipeline
+from neo4j_graphrag.experimental.pipeline.pipeline import PipelineResult
+from neo4j_graphrag.llm import LLMInterface
+from neo4j_graphrag.llm import OpenAILLM
+
+# Neo4j db infos
+URI = "neo4j://localhost:7687"
+AUTH = ("neo4j", "password")
+DATABASE = "neo4j"
+
+
+root_dir = Path(__file__).parents[1]
+file_path = root_dir / "data" / "Harry Potter and the Chamber of Secrets Summary.pdf"
+
+
+# Instantiate NodeType and RelationshipType objects. This defines the
+# entities and relations the LLM will be looking for in the text.
+NODE_TYPES = ["Person", "Organization", "Location"]
+RELATIONSHIP_TYPES = ["SITUATED_AT", "INTERACTS", "LED_BY"]
+PATTERNS = [
+    ("Person", "SITUATED_AT", "Location"),
+    ("Person", "INTERACTS", "Person"),
+    ("Organization", "LED_BY", "Person"),
+]
+
+
+async def define_and_run_pipeline(
+    neo4j_driver: neo4j.Driver,
+    llm: LLMInterface,
+) -> PipelineResult:
+    # Create an instance of the SimpleKGPipeline
+    kg_builder = SimpleKGPipeline(
+        llm=llm,
+        driver=neo4j_driver,
+        embedder=OpenAIEmbeddings(),
+        schema={
+            "node_types": NODE_TYPES,
+            "relationship_types": RELATIONSHIP_TYPES,
+            "patterns": PATTERNS,
+        },
+        neo4j_database=DATABASE,
+    )
+    return await kg_builder.run_async(
+        file_path=str(file_path),
+        # optional, add document metadata, each item will
+        # be saved as a property of the Document node
+        # document_metadata={"author": "J. K. Rowling"},
+    )
+
+
+async def main() -> PipelineResult:
+    with neo4j.GraphDatabase.driver(URI, auth=AUTH) as driver:
+        async with OpenAILLM(model_name="gpt-5") as llm:
+            res = await define_and_run_pipeline(driver, llm)
+    return res
+
+
+if __name__ == "__main__":
+    res = asyncio.run(main())
+    print(res)

참고/neo4j-graphrag-python-main/examples/build_graph/simple_kg_builder_from_text.py

@@ -0,0 +1,105 @@
+"""This example illustrates how to get started easily with the SimpleKGPipeline
+and ingest text into a Neo4j Knowledge Graph.
+
+This example assumes a Neo4j db is up and running. Update the credentials below
+if needed.
+
+NB: when building a KG from text, no 'Document' node is created in the Knowledge Graph.
+"""
+
+import asyncio
+import logging
+
+import neo4j
+from neo4j_graphrag.embeddings import OpenAIEmbeddings
+from neo4j_graphrag.experimental.pipeline.kg_builder import SimpleKGPipeline
+from neo4j_graphrag.experimental.pipeline.pipeline import PipelineResult
+from neo4j_graphrag.experimental.pipeline.types.schema import (
+    EntityInputType,
+    RelationInputType,
+)
+from neo4j_graphrag.llm import LLMInterface
+from neo4j_graphrag.llm import OpenAILLM
+
+logging.basicConfig()
+logging.getLogger("neo4j_graphrag").setLevel(logging.DEBUG)
+# logging.getLogger("neo4j_graphrag").setLevel(logging.INFO)
+
+# Neo4j db infos
+URI = "neo4j://localhost:7687"
+AUTH = ("neo4j", "password")
+DATABASE = "neo4j"
+
+# Text to process
+TEXT = """The son of Duke Leto Atreides and the Lady Jessica, Paul is the heir of House Atreides,
+an aristocratic family that rules the planet Caladan, the rainy planet, since 10191."""
+
+# Instantiate Entity and Relation objects. This defines the
+# entities and relations the LLM will be looking for in the text.
+NODE_TYPES: list[EntityInputType] = [
+    # entities can be defined with a simple label...
+    "Person",
+    # ... or with a dict if more details are needed,
+    # such as a description:
+    {
+        "label": "House",
+        "description": "Family the person belongs to",
+        "properties": [{"name": "name", "type": "STRING"}],
+    },
+    # or a list of properties the LLM will try to attach to the entity:
+    {"label": "Planet", "properties": [{"name": "weather", "type": "STRING"}]},
+]
+# same thing for relationships:
+RELATIONSHIP_TYPES: list[RelationInputType] = [
+    "PARENT_OF",
+    {
+        "label": "HEIR_OF",
+        "description": "Used for inheritor relationship between father and sons",
+    },
+    {"label": "RULES", "properties": [{"name": "fromYear", "type": "INTEGER"}]},
+]
+PATTERNS = [
+    ("Person", "PARENT_OF", "Person"),
+    ("Person", "HEIR_OF", "House"),
+    ("House", "RULES", "Planet"),
+]
+
+
+async def define_and_run_pipeline(
+    neo4j_driver: neo4j.Driver,
+    llm: LLMInterface,
+) -> PipelineResult:
+    # Create an instance of the SimpleKGPipeline
+    kg_builder = SimpleKGPipeline(
+        llm=llm,
+        driver=neo4j_driver,
+        embedder=OpenAIEmbeddings(),
+        schema={
+            "node_types": NODE_TYPES,
+            "relationship_types": RELATIONSHIP_TYPES,
+            "patterns": PATTERNS,
+        },
+        from_file=False,
+        neo4j_database=DATABASE,
+    )
+    return await kg_builder.run_async(
+        text=TEXT,
+        # optional, specify file path for the Document node
+        # if not, a random name will be generated
+        # file_path="my_document.txt"
+        # optional, add document metadata, each item will
+        # be saved as a property of the Document node
+        # document_metadata={"author": "Frank Herbert"},
+    )
+
+
+async def main() -> PipelineResult:
+    with neo4j.GraphDatabase.driver(URI, auth=AUTH) as driver:
+        async with OpenAILLM(model_name="gpt-5") as llm:
+            res = await define_and_run_pipeline(driver, llm)
+    return res
+
+
+if __name__ == "__main__":
+    res = asyncio.run(main())
+    print(res)