add codes from guides to a separate folder

guides/custom_data_models.py

@@ -0,0 +1,38 @@
+import asyncio
+from typing import Any
+from pydantic import SkipValidation
+
+import cognee
+from cognee.infrastructure.engine import DataPoint
+from cognee.infrastructure.engine.models.Edge import Edge
+from cognee.tasks.storage import add_data_points
+
+
+class Person(DataPoint):
+    name: str
+    # Keep it simple for forward refs / mixed values
+    knows: SkipValidation[Any] = None  # single Person or list[Person]
+    # Recommended: specify which fields to index for search
+    metadata: dict = {"index_fields": ["name"]}
+
+
+async def main():
+    # Start clean (optional in your app)
+    await cognee.prune.prune_data()
+    await cognee.prune.prune_system(metadata=True)
+
+    alice = Person(name="Alice")
+    bob = Person(name="Bob")
+    charlie = Person(name="Charlie")
+
+    # Create relationships - field name becomes edge label
+    alice.knows = bob
+    # You can also do lists: alice.knows = [bob, charlie]
+
+    # Optional: add weights and custom relationship types
+    bob.knows = (Edge(weight=0.9, relationship_type="friend_of"), charlie)
+
+    await add_data_points([alice, bob, charlie])
+
+
+asyncio.run(main())

guides/custom_prompts.py

@@ -0,0 +1,30 @@
+import asyncio
+import cognee
+from cognee.api.v1.search import SearchType
+
+custom_prompt = """
+Extract only people and cities as entities.
+Connect people to cities with the relationship "lives_in".
+Ignore all other entities.
+"""
+
+
+async def main():
+    await cognee.add(
+        [
+            "Alice moved to Paris in 2010, while Bob has always lived in New York.",
+            "Andreas was born in Venice, but later settled in Lisbon.",
+            "Diana and Tom were born and raised in Helsingy. Diana currently resides in Berlin, while Tom never moved.",
+        ]
+    )
+    await cognee.cognify(custom_prompt=custom_prompt)
+
+    res = await cognee.search(
+        query_type=SearchType.GRAPH_COMPLETION,
+        query_text="Where does Alice live?",
+    )
+    print(res)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

guides/custom_tasks_and_pipelines.py

@@ -0,0 +1,53 @@
+import asyncio
+from typing import Any, Dict, List
+from pydantic import BaseModel, SkipValidation
+
+import cognee
+from cognee.modules.engine.operations.setup import setup
+from cognee.infrastructure.llm.LLMGateway import LLMGateway
+from cognee.infrastructure.engine import DataPoint
+from cognee.tasks.storage import add_data_points
+from cognee.modules.pipelines import Task, run_pipeline
+
+
+class Person(DataPoint):
+    name: str
+    # Optional relationships (we'll let the LLM populate this)
+    knows: List["Person"] = []
+    # Make names searchable in the vector store
+    metadata: Dict[str, Any] = {"index_fields": ["name"]}
+
+
+class People(BaseModel):
+    persons: List[Person]
+
+
+async def extract_people(text: str) -> List[Person]:
+    system_prompt = (
+        "Extract people mentioned in the text. "
+        "Return as `persons: Person[]` with each Person having `name` and optional `knows` relations. "
+        "If the text says someone knows someone set `knows` accordingly. "
+        "Only include facts explicitly stated."
+    )
+    people = await LLMGateway.acreate_structured_output(text, system_prompt, People)
+    return people.persons
+
+
+async def main():
+    await cognee.prune.prune_data()
+    await cognee.prune.prune_system(metadata=True)
+    await setup()
+
+    text = "Alice knows Bob."
+
+    tasks = [
+        Task(extract_people),  # input: text -> output: list[Person]
+        Task(add_data_points),  # input: list[Person] -> output: list[Person]
+    ]
+
+    async for _ in run_pipeline(tasks=tasks, data=text, datasets=["people_demo"]):
+        pass
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

guides/graph_visualization.py

@@ -0,0 +1,13 @@
+import asyncio
+import cognee
+from cognee.api.v1.visualize.visualize import visualize_graph
+
+
+async def main():
+    await cognee.add(["Alice knows Bob.", "NLP is a subfield of CS."])
+    await cognee.cognify()
+
+    await visualize_graph("./graph_after_cognify.html")
+
+
+asyncio.run(main())

guides/low_level_llm.py

@@ -0,0 +1,31 @@
+import asyncio
+
+from pydantic import BaseModel
+from typing import List
+from cognee.infrastructure.llm.LLMGateway import LLMGateway
+
+
+class MiniEntity(BaseModel):
+    name: str
+    type: str
+
+
+class MiniGraph(BaseModel):
+    nodes: List[MiniEntity]
+
+
+async def main():
+    system_prompt = (
+        "Extract entities as nodes with name and type. "
+        "Use concise, literal values present in the text."
+    )
+
+    text = "Apple develops iPhone; Audi produces the R8."
+
+    result = await LLMGateway.acreate_structured_output(text, system_prompt, MiniGraph)
+    print(result)
+    # MiniGraph(nodes=[MiniEntity(name='Apple', type='Organization'), ...])
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

guides/memify_quickstart.py

@@ -0,0 +1,29 @@
+import asyncio
+import cognee
+from cognee import SearchType
+
+
+async def main():
+    # 1) Add two short chats and build a graph
+    await cognee.add(
+        [
+            "We follow PEP8. Add type hints and docstrings.",
+            "Releases should not be on Friday. Susan must review PRs.",
+        ],
+        dataset_name="rules_demo",
+    )
+    await cognee.cognify(datasets=["rules_demo"])  # builds graph
+
+    # 2) Enrich the graph (uses default memify tasks)
+    await cognee.memify(dataset="rules_demo")
+
+    # 3) Query the new coding rules
+    rules = await cognee.search(
+        query_type=SearchType.CODING_RULES,
+        query_text="List coding rules",
+        node_name=["coding_agent_rules"],
+    )
+    print("Rules:", rules)
+
+
+asyncio.run(main())

guides/ontology_quickstart.py

@@ -0,0 +1,30 @@
+import asyncio
+import cognee
+
+
+async def main():
+    texts = ["Audi produces the R8 and e-tron.", "Apple develops iPhone and MacBook."]
+
+    await cognee.add(texts)
+    # or: await cognee.add("/path/to/folder/of/files")
+
+    import os
+    from cognee.modules.ontology.ontology_config import Config
+    from cognee.modules.ontology.rdf_xml.RDFLibOntologyResolver import RDFLibOntologyResolver
+
+    ontology_path = os.path.join(
+        os.path.dirname(os.path.abspath(__file__)), "ontology_input_example/basic_ontology.owl"
+    )
+
+    # Create full config structure manually
+    config: Config = {
+        "ontology_config": {
+            "ontology_resolver": RDFLibOntologyResolver(ontology_file=ontology_path)
+        }
+    }
+
+    await cognee.cognify(config=config)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

guides/s3_storage.py

@@ -0,0 +1,25 @@
+import asyncio
+import cognee
+
+
+async def main():
+    # Single file
+    await cognee.add("s3://cognee-s3-small-test/Natural_language_processing.txt")
+
+    # Folder/prefix (recursively expands)
+    await cognee.add("s3://cognee-s3-small-test")
+
+    # Mixed list
+    await cognee.add(
+        [
+            "s3://cognee-s3-small-test/Natural_language_processing.txt",
+            "Some inline text to ingest",
+        ]
+    )
+
+    # Process the data
+    await cognee.cognify()
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

guides/search_basics.py

@@ -0,0 +1,58 @@
+import asyncio
+import cognee
+
+from cognee.modules.search.types import SearchType, CombinedSearchResult
+
+
+async def main():
+    await cognee.prune.prune_data()
+    await cognee.prune.prune_system(metadata=True)
+
+    text = """
+        Natural language processing (NLP) is an interdisciplinary
+        subfield of computer science and information retrieval.
+        First rule of coding: Do not talk about coding.
+        """
+
+    text2 = """
+    Sandwiches are best served toasted with cheese, ham, mayo,
+    lettuce, mustard, and salt & pepper.
+    """
+
+    await cognee.add(text, dataset_name="NLP_coding")
+    await cognee.add(text2, dataset_name="Sandwiches")
+    await cognee.add(text2)
+
+    await cognee.cognify()
+
+    # Make sure you've already run cognee.cognify(...) so the graph has content
+    answers = await cognee.search(query_text="What are the main themes in my data?")
+    assert len(answers) > 0
+
+    answers = await cognee.search(
+        query_text="List coding guidelines",
+        query_type=SearchType.CODING_RULES,
+    )
+    assert len(answers) > 0
+
+    answers = await cognee.search(
+        query_text="Give me a confident answer: What is NLP?",
+        system_prompt="Answer succinctly and state confidence at the end.",
+    )
+    assert len(answers) > 0
+
+    answers = await cognee.search(
+        query_text="Tell me about NLP",
+        only_context=True,
+    )
+    assert len(answers) > 0
+
+    answers = await cognee.search(
+        query_text="Quarterly financial highlights",
+        datasets=["NLP_coding", "Sandwiches"],
+        use_combined_context=True,
+    )
+    assert isinstance(answers, CombinedSearchResult)
+
+
+asyncio.run(main())

guides/sessions.py

@@ -0,0 +1,46 @@
+import asyncio
+import cognee
+from cognee import SearchType
+from cognee.modules.users.methods import get_default_user
+from cognee.context_global_variables import set_session_user_context_variable
+
+async def main():
+    # Prepare knowledge base
+    await cognee.add([
+        "Alice moved to Paris in 2010. She works as a software engineer.",
+        "Bob lives in New York. He is a data scientist.",
+        "Alice and Bob met at a conference in 2015."
+    ])
+    await cognee.cognify()
+
+    # Set user context (required for sessions)
+    user = await get_default_user()
+    await set_session_user_context_variable(user)
+
+    # First search - starts a new session
+    result1 = await cognee.search(
+        query_type=SearchType.GRAPH_COMPLETION,
+        query_text="Where does Alice live?",
+        session_id="conversation_1"
+    )
+    print("First answer:", result1[0])
+
+    # Follow-up search - uses conversation history
+    result2 = await cognee.search(
+        query_type=SearchType.GRAPH_COMPLETION,
+        query_text="What does she do for work?",
+        session_id="conversation_1"  # Same session
+    )
+    print("Follow-up answer:", result2[0])
+    # The LLM knows "she" refers to Alice from previous context
+
+    # Different session - no memory of previous conversation
+    result3 = await cognee.search(
+        query_type=SearchType.GRAPH_COMPLETION,
+        query_text="What does she do for work?",
+        session_id="conversation_2"  # New session
+    )
+    print("New session answer:", result3[0])
+    # This won't know who "she" refers to
+
+asyncio.run(main())

guides/temporal_cognify.py

@@ -0,0 +1,57 @@
+import asyncio
+import cognee
+
+
+async def main():
+    text = """
+    In 1998 the project launched. In 2001 version 1.0 shipped. In 2004 the team merged
+    with another group. In 2010 support for v1 ended.
+    """
+
+    await cognee.add(text, dataset_name="timeline_demo")
+
+    await cognee.cognify(datasets=["timeline_demo"], temporal_cognify=True)
+
+    from cognee.api.v1.search import SearchType
+
+    # Before / after queries
+    result = await cognee.search(
+        query_type=SearchType.TEMPORAL, query_text="What happened before 2000?", top_k=10
+    )
+
+    assert result != []
+
+    result = await cognee.search(
+        query_type=SearchType.TEMPORAL, query_text="What happened after 2010?", top_k=10
+    )
+
+    assert result != []
+
+    # Between queries
+    result = await cognee.search(
+        query_type=SearchType.TEMPORAL, query_text="Events between 2001 and 2004", top_k=10
+    )
+
+    assert result != []
+
+    # Scoped descriptions
+    result = await cognee.search(
+        query_type=SearchType.TEMPORAL,
+        query_text="Key project milestones between 1998 and 2010",
+        top_k=10,
+    )
+
+    assert result != []
+
+    result = await cognee.search(
+        query_type=SearchType.TEMPORAL,
+        query_text="What happened after 2004?",
+        datasets=["timeline_demo"],
+        top_k=10,
+    )
+
+    assert result != []
+
+
+if __name__ == "__main__":
+    asyncio.run(main())