cognee 0.4.1__py3-none-any.whl → 0.5.0.dev0__py3-none-any.whl

cognee/infrastructure/llm/structured_output_framework/litellm_instructor/llm/ollama/adapter.py

@@ -42,8 +42,16 @@ class OllamaAPIAdapter(LLMInterface):
     - aclient
     """
 
+    default_instructor_mode = "json_mode"
+
     def __init__(
-        self, endpoint: str, api_key: str, model: str, name: str, max_completion_tokens: int
+        self,
+        endpoint: str,
+        api_key: str,
+        model: str,
+        name: str,
+        max_completion_tokens: int,
+        instructor_mode: str = None,
     ):
         self.name = name
         self.model = model
@@ -51,8 +59,11 @@ class OllamaAPIAdapter(LLMInterface):
         self.endpoint = endpoint
         self.max_completion_tokens = max_completion_tokens
 
+        self.instructor_mode = instructor_mode if instructor_mode else self.default_instructor_mode
+
         self.aclient = instructor.from_openai(
-            OpenAI(base_url=self.endpoint, api_key=self.api_key), mode=instructor.Mode.JSON
+            OpenAI(base_url=self.endpoint, api_key=self.api_key),
+            mode=instructor.Mode(self.instructor_mode),
         )
 
     @retry(

cognee/infrastructure/llm/structured_output_framework/litellm_instructor/llm/openai/adapter.py

@@ -56,6 +56,7 @@ class OpenAIAdapter(LLMInterface):
     model: str
     api_key: str
     api_version: str
+    default_instructor_mode = "json_schema_mode"
 
     MAX_RETRIES = 5
 
@@ -69,19 +70,21 @@ class OpenAIAdapter(LLMInterface):
         model: str,
         transcription_model: str,
         max_completion_tokens: int,
+        instructor_mode: str = None,
         streaming: bool = False,
         fallback_model: str = None,
         fallback_api_key: str = None,
         fallback_endpoint: str = None,
     ):
+        self.instructor_mode = instructor_mode if instructor_mode else self.default_instructor_mode
         # TODO: With gpt5 series models OpenAI expects JSON_SCHEMA as a mode for structured outputs.
         #       Make sure all new gpt models will work with this mode as well.
         if "gpt-5" in model:
             self.aclient = instructor.from_litellm(
-                litellm.acompletion, mode=instructor.Mode.JSON_SCHEMA
+                litellm.acompletion, mode=instructor.Mode(self.instructor_mode)
             )
             self.client = instructor.from_litellm(
-                litellm.completion, mode=instructor.Mode.JSON_SCHEMA
+                litellm.completion, mode=instructor.Mode(self.instructor_mode)
             )
         else:
             self.aclient = instructor.from_litellm(litellm.acompletion)

cognee/infrastructure/loaders/LoaderEngine.py

@@ -31,6 +31,7 @@ class LoaderEngine:
             "pypdf_loader",
             "image_loader",
             "audio_loader",
+            "csv_loader",
             "unstructured_loader",
             "advanced_pdf_loader",
         ]

cognee/infrastructure/loaders/core/__init__.py

@@ -3,5 +3,6 @@
 from .text_loader import TextLoader
 from .audio_loader import AudioLoader
 from .image_loader import ImageLoader
+from .csv_loader import CsvLoader
 
-__all__ = ["TextLoader", "AudioLoader", "ImageLoader"]
+__all__ = ["TextLoader", "AudioLoader", "ImageLoader", "CsvLoader"]

cognee/infrastructure/loaders/core/csv_loader.py

@@ -0,0 +1,93 @@
+import os
+from typing import List
+import csv
+from cognee.infrastructure.loaders.LoaderInterface import LoaderInterface
+from cognee.infrastructure.files.storage import get_file_storage, get_storage_config
+from cognee.infrastructure.files.utils.get_file_metadata import get_file_metadata
+
+
+class CsvLoader(LoaderInterface):
+    """
+    Core CSV file loader that handles basic CSV file formats.
+    """
+
+    @property
+    def supported_extensions(self) -> List[str]:
+        """Supported text file extensions."""
+        return [
+            "csv",
+        ]
+
+    @property
+    def supported_mime_types(self) -> List[str]:
+        """Supported MIME types for text content."""
+        return [
+            "text/csv",
+        ]
+
+    @property
+    def loader_name(self) -> str:
+        """Unique identifier for this loader."""
+        return "csv_loader"
+
+    def can_handle(self, extension: str, mime_type: str) -> bool:
+        """
+        Check if this loader can handle the given file.
+
+        Args:
+            extension: File extension
+            mime_type: Optional MIME type
+
+        Returns:
+            True if file can be handled, False otherwise
+        """
+        if extension in self.supported_extensions and mime_type in self.supported_mime_types:
+            return True
+
+        return False
+
+    async def load(self, file_path: str, encoding: str = "utf-8", **kwargs):
+        """
+        Load and process the csv file.
+
+        Args:
+            file_path: Path to the file to load
+            encoding: Text encoding to use (default: utf-8)
+            **kwargs: Additional configuration (unused)
+
+        Returns:
+            LoaderResult containing the file content and metadata
+
+        Raises:
+            FileNotFoundError: If file doesn't exist
+            UnicodeDecodeError: If file cannot be decoded with specified encoding
+            OSError: If file cannot be read
+        """
+        if not os.path.exists(file_path):
+            raise FileNotFoundError(f"File not found: {file_path}")
+
+        with open(file_path, "rb") as f:
+            file_metadata = await get_file_metadata(f)
+        # Name ingested file of current loader based on original file content hash
+        storage_file_name = "text_" + file_metadata["content_hash"] + ".txt"
+
+        row_texts = []
+        row_index = 1
+
+        with open(file_path, "r", encoding=encoding, newline="") as file:
+            reader = csv.DictReader(file)
+            for row in reader:
+                pairs = [f"{str(k)}: {str(v)}" for k, v in row.items()]
+                row_text = ", ".join(pairs)
+                row_texts.append(f"Row {row_index}:\n{row_text}\n")
+                row_index += 1
+
+        content = "\n".join(row_texts)
+
+        storage_config = get_storage_config()
+        data_root_directory = storage_config["data_root_directory"]
+        storage = get_file_storage(data_root_directory)
+
+        full_file_path = await storage.store(storage_file_name, content)
+
+        return full_file_path

cognee/infrastructure/loaders/core/text_loader.py

@@ -16,7 +16,7 @@ class TextLoader(LoaderInterface):
     @property
     def supported_extensions(self) -> List[str]:
         """Supported text file extensions."""
-        return ["txt", "md", "csv", "json", "xml", "yaml", "yml", "log"]
+        return ["txt", "md", "json", "xml", "yaml", "yml", "log"]
 
     @property
     def supported_mime_types(self) -> List[str]:
@@ -24,7 +24,6 @@ class TextLoader(LoaderInterface):
         return [
             "text/plain",
             "text/markdown",
-            "text/csv",
             "application/json",
             "text/xml",
             "application/xml",

cognee/infrastructure/loaders/external/advanced_pdf_loader.py

@@ -227,12 +227,3 @@ class AdvancedPdfLoader(LoaderInterface):
         if value is None:
             return ""
         return str(value).replace("\xa0", " ").strip()
-
-
-if __name__ == "__main__":
-    loader = AdvancedPdfLoader()
-    asyncio.run(
-        loader.load(
-            "/Users/xiaotao/work/cognee/cognee/infrastructure/loaders/external/attention_is_all_you_need.pdf"
-        )
-    )

cognee/infrastructure/loaders/supported_loaders.py

@@ -1,5 +1,5 @@
 from cognee.infrastructure.loaders.external import PyPdfLoader
-from cognee.infrastructure.loaders.core import TextLoader, AudioLoader, ImageLoader
+from cognee.infrastructure.loaders.core import TextLoader, AudioLoader, ImageLoader, CsvLoader
 
 # Registry for loader implementations
 supported_loaders = {
@@ -7,6 +7,7 @@ supported_loaders = {
     TextLoader.loader_name: TextLoader,
     ImageLoader.loader_name: ImageLoader,
     AudioLoader.loader_name: AudioLoader,
+    CsvLoader.loader_name: CsvLoader,
 }
 
 # Try adding optional loaders

cognee/memify_pipelines/persist_sessions_in_knowledge_graph.py

@@ -0,0 +1,55 @@
+from typing import Optional, List
+
+from cognee import memify
+from cognee.context_global_variables import (
+    set_database_global_context_variables,
+    set_session_user_context_variable,
+)
+from cognee.exceptions import CogneeValidationError
+from cognee.modules.data.methods import get_authorized_existing_datasets
+from cognee.shared.logging_utils import get_logger
+from cognee.modules.pipelines.tasks.task import Task
+from cognee.modules.users.models import User
+from cognee.tasks.memify import extract_user_sessions, cognify_session
+
+
+logger = get_logger("persist_sessions_in_knowledge_graph")
+
+
+async def persist_sessions_in_knowledge_graph_pipeline(
+    user: User,
+    session_ids: Optional[List[str]] = None,
+    dataset: str = "main_dataset",
+    run_in_background: bool = False,
+):
+    await set_session_user_context_variable(user)
+    dataset_to_write = await get_authorized_existing_datasets(
+        user=user, datasets=[dataset], permission_type="write"
+    )
+
+    if not dataset_to_write:
+        raise CogneeValidationError(
+            message=f"User (id: {str(user.id)}) does not have write access to dataset: {dataset}",
+            log=False,
+        )
+
+    await set_database_global_context_variables(
+        dataset_to_write[0].id, dataset_to_write[0].owner_id
+    )
+
+    extraction_tasks = [Task(extract_user_sessions, session_ids=session_ids)]
+
+    enrichment_tasks = [
+        Task(cognify_session, dataset_id=dataset_to_write[0].id),
+    ]
+
+    result = await memify(
+        extraction_tasks=extraction_tasks,
+        enrichment_tasks=enrichment_tasks,
+        dataset=dataset_to_write[0].id,
+        data=[{}],
+        run_in_background=run_in_background,
+    )
+
+    logger.info("Session persistence pipeline completed")
+    return result

cognee/modules/chunking/CsvChunker.py

@@ -0,0 +1,35 @@
+from cognee.shared.logging_utils import get_logger
+
+
+from cognee.tasks.chunks import chunk_by_row
+from cognee.modules.chunking.Chunker import Chunker
+from .models.DocumentChunk import DocumentChunk
+
+logger = get_logger()
+
+
+class CsvChunker(Chunker):
+    async def read(self):
+        async for content_text in self.get_text():
+            if content_text is None:
+                continue
+
+            for chunk_data in chunk_by_row(content_text, self.max_chunk_size):
+                if chunk_data["chunk_size"] <= self.max_chunk_size:
+                    yield DocumentChunk(
+                        id=chunk_data["chunk_id"],
+                        text=chunk_data["text"],
+                        chunk_size=chunk_data["chunk_size"],
+                        is_part_of=self.document,
+                        chunk_index=self.chunk_index,
+                        cut_type=chunk_data["cut_type"],
+                        contains=[],
+                        metadata={
+                            "index_fields": ["text"],
+                        },
+                    )
+                    self.chunk_index += 1
+                else:
+                    raise ValueError(
+                        f"Chunk size is larger than the maximum chunk size {self.max_chunk_size}"
+                    )

cognee/modules/chunking/models/DocumentChunk.py

@@ -1,6 +1,7 @@
 from typing import List, Union
 
 from cognee.infrastructure.engine import DataPoint
+from cognee.infrastructure.engine.models.Edge import Edge
 from cognee.modules.data.processing.document_types import Document
 from cognee.modules.engine.models import Entity
 from cognee.tasks.temporal_graph.models import Event
@@ -31,6 +32,6 @@ class DocumentChunk(DataPoint):
     chunk_index: int
     cut_type: str
     is_part_of: Document
-    contains: List[Union[Entity, Event]] = None
+    contains: List[Union[Entity, Event, tuple[Edge, Entity]]] = None
 
     metadata: dict = {"index_fields": ["text"]}

cognee/modules/chunking/text_chunker_with_overlap.py

@@ -0,0 +1,124 @@
+from cognee.shared.logging_utils import get_logger
+from uuid import NAMESPACE_OID, uuid5
+
+from cognee.tasks.chunks import chunk_by_paragraph
+from cognee.modules.chunking.Chunker import Chunker
+from .models.DocumentChunk import DocumentChunk
+
+logger = get_logger()
+
+
+class TextChunkerWithOverlap(Chunker):
+    def __init__(
+        self,
+        document,
+        get_text: callable,
+        max_chunk_size: int,
+        chunk_overlap_ratio: float = 0.0,
+        get_chunk_data: callable = None,
+    ):
+        super().__init__(document, get_text, max_chunk_size)
+        self._accumulated_chunk_data = []
+        self._accumulated_size = 0
+        self.chunk_overlap_ratio = chunk_overlap_ratio
+        self.chunk_overlap = int(max_chunk_size * chunk_overlap_ratio)
+
+        if get_chunk_data is not None:
+            self.get_chunk_data = get_chunk_data
+        elif chunk_overlap_ratio > 0:
+            paragraph_max_size = int(0.5 * chunk_overlap_ratio * max_chunk_size)
+            self.get_chunk_data = lambda text: chunk_by_paragraph(
+                text, paragraph_max_size, batch_paragraphs=True
+            )
+        else:
+            self.get_chunk_data = lambda text: chunk_by_paragraph(
+                text, self.max_chunk_size, batch_paragraphs=True
+            )
+
+    def _accumulation_overflows(self, chunk_data):
+        """Check if adding chunk_data would exceed max_chunk_size."""
+        return self._accumulated_size + chunk_data["chunk_size"] > self.max_chunk_size
+
+    def _accumulate_chunk_data(self, chunk_data):
+        """Add chunk_data to the current accumulation."""
+        self._accumulated_chunk_data.append(chunk_data)
+        self._accumulated_size += chunk_data["chunk_size"]
+
+    def _clear_accumulation(self):
+        """Reset accumulation, keeping overlap chunk_data based on chunk_overlap_ratio."""
+        if self.chunk_overlap == 0:
+            self._accumulated_chunk_data = []
+            self._accumulated_size = 0
+            return
+
+        # Keep chunk_data from the end that fit in overlap
+        overlap_chunk_data = []
+        overlap_size = 0
+
+        for chunk_data in reversed(self._accumulated_chunk_data):
+            if overlap_size + chunk_data["chunk_size"] <= self.chunk_overlap:
+                overlap_chunk_data.insert(0, chunk_data)
+                overlap_size += chunk_data["chunk_size"]
+            else:
+                break
+
+        self._accumulated_chunk_data = overlap_chunk_data
+        self._accumulated_size = overlap_size
+
+    def _create_chunk(self, text, size, cut_type, chunk_id=None):
+        """Create a DocumentChunk with standard metadata."""
+        try:
+            return DocumentChunk(
+                id=chunk_id or uuid5(NAMESPACE_OID, f"{str(self.document.id)}-{self.chunk_index}"),
+                text=text,
+                chunk_size=size,
+                is_part_of=self.document,
+                chunk_index=self.chunk_index,
+                cut_type=cut_type,
+                contains=[],
+                metadata={"index_fields": ["text"]},
+            )
+        except Exception as e:
+            logger.error(e)
+            raise e
+
+    def _create_chunk_from_accumulation(self):
+        """Create a DocumentChunk from current accumulated chunk_data."""
+        chunk_text = " ".join(chunk["text"] for chunk in self._accumulated_chunk_data)
+        return self._create_chunk(
+            text=chunk_text,
+            size=self._accumulated_size,
+            cut_type=self._accumulated_chunk_data[-1]["cut_type"],
+        )
+
+    def _emit_chunk(self, chunk_data):
+        """Emit a chunk when accumulation overflows."""
+        if len(self._accumulated_chunk_data) > 0:
+            chunk = self._create_chunk_from_accumulation()
+            self._clear_accumulation()
+            self._accumulate_chunk_data(chunk_data)
+        else:
+            # Handle single chunk_data exceeding max_chunk_size
+            chunk = self._create_chunk(
+                text=chunk_data["text"],
+                size=chunk_data["chunk_size"],
+                cut_type=chunk_data["cut_type"],
+                chunk_id=chunk_data["chunk_id"],
+            )
+
+        self.chunk_index += 1
+        return chunk
+
+    async def read(self):
+        async for content_text in self.get_text():
+            for chunk_data in self.get_chunk_data(content_text):
+                if not self._accumulation_overflows(chunk_data):
+                    self._accumulate_chunk_data(chunk_data)
+                    continue
+
+                yield self._emit_chunk(chunk_data)
+
+        if len(self._accumulated_chunk_data) == 0:
+            return
+
+        yield self._create_chunk_from_accumulation()

cognee/modules/data/methods/__init__.py

@@ -10,6 +10,7 @@ from .get_authorized_dataset import get_authorized_dataset
 from .get_authorized_dataset_by_name import get_authorized_dataset_by_name
 from .get_data import get_data
 from .get_unique_dataset_id import get_unique_dataset_id
+from .get_unique_data_id import get_unique_data_id
 from .get_authorized_existing_datasets import get_authorized_existing_datasets
 from .get_dataset_ids import get_dataset_ids
 

cognee/modules/data/methods/create_dataset.py

@@ -16,14 +16,16 @@ async def create_dataset(dataset_name: str, user: User, session: AsyncSession) -
             .options(joinedload(Dataset.data))
             .filter(Dataset.name == dataset_name)
             .filter(Dataset.owner_id == owner_id)
+            .filter(Dataset.tenant_id == user.tenant_id)
         )
     ).first()
 
     if dataset is None:
         # Dataset id should be generated based on dataset_name and owner_id/user so multiple users can use the same dataset_name
         dataset_id = await get_unique_dataset_id(dataset_name=dataset_name, user=user)
-        dataset = Dataset(id=dataset_id, name=dataset_name, data=[])
-        dataset.owner_id = owner_id
+        dataset = Dataset(
+            id=dataset_id, name=dataset_name, data=[], owner_id=owner_id, tenant_id=user.tenant_id
+        )
 
         session.add(dataset)
 

cognee/modules/data/methods/get_dataset_ids.py

@@ -27,7 +27,11 @@ async def get_dataset_ids(datasets: Union[list[str], list[UUID]], user):
             # Get all user owned dataset objects (If a user wants to write to a dataset he is not the owner of it must be provided through UUID.)
             user_datasets = await get_datasets(user.id)
             # Filter out non name mentioned datasets
-            dataset_ids = [dataset.id for dataset in user_datasets if dataset.name in datasets]
+            dataset_ids = [dataset for dataset in user_datasets if dataset.name in datasets]
+            # Filter out non current tenant datasets
+            dataset_ids = [
+                dataset.id for dataset in dataset_ids if dataset.tenant_id == user.tenant_id
+            ]
         else:
             raise DatasetTypeError(
                 f"One or more of the provided dataset types is not handled: f{datasets}"

cognee/modules/data/methods/get_unique_data_id.py

@@ -0,0 +1,68 @@
+from uuid import uuid5, NAMESPACE_OID, UUID
+from sqlalchemy import select
+
+from cognee.modules.data.models.Data import Data
+from cognee.infrastructure.databases.relational import get_relational_engine
+from cognee.modules.users.models import User
+
+
+async def get_unique_data_id(data_identifier: str, user: User) -> UUID:
+    """
+    Function returns a unique UUID for data based on data identifier, user id and tenant id.
+    If data with legacy ID exists, return that ID to maintain compatibility.
+
+    Args:
+        data_identifier: A way to uniquely identify data (e.g. file hash, data name, etc.)
+        user: User object adding the data
+        tenant_id: UUID of the tenant for which data is being added
+
+    Returns:
+        UUID: Unique identifier for the data
+    """
+
+    def _get_deprecated_unique_data_id(data_identifier: str, user: User) -> UUID:
+        """
+        Deprecated function, returns a unique UUID for data based on data identifier and user id.
+        Needed to support legacy data without tenant information.
+        Args:
+            data_identifier: A way to uniquely identify data (e.g. file hash, data name, etc.)
+            user: User object adding the data
+
+        Returns:
+            UUID: Unique identifier for the data
+        """
+        # return UUID hash of file contents + owner id + tenant_id
+        return uuid5(NAMESPACE_OID, f"{data_identifier}{str(user.id)}")
+
+    def _get_modern_unique_data_id(data_identifier: str, user: User) -> UUID:
+        """
+        Function returns a unique UUID for data based on data identifier, user id and tenant id.
+        Args:
+            data_identifier: A way to uniquely identify data (e.g. file hash, data name, etc.)
+            user: User object adding the data
+            tenant_id: UUID of the tenant for which data is being added
+
+        Returns:
+            UUID: Unique identifier for the data
+        """
+        # return UUID hash of file contents + owner id + tenant_id
+        return uuid5(NAMESPACE_OID, f"{data_identifier}{str(user.id)}{str(user.tenant_id)}")
+
+    # Get all possible data_id values
+    data_id = {
+        "modern_data_id": _get_modern_unique_data_id(data_identifier=data_identifier, user=user),
+        "legacy_data_id": _get_deprecated_unique_data_id(
+            data_identifier=data_identifier, user=user
+        ),
+    }
+
+    # Check if data item with legacy_data_id exists, if so use that one, else use modern_data_id
+    db_engine = get_relational_engine()
+    async with db_engine.get_async_session() as session:
+        legacy_data_point = (
+            await session.execute(select(Data).filter(Data.id == data_id["legacy_data_id"]))
+        ).scalar_one_or_none()
+
+        if not legacy_data_point:
+            return data_id["modern_data_id"]
+        return data_id["legacy_data_id"]

cognee/modules/data/methods/get_unique_dataset_id.py

@@ -1,9 +1,71 @@
 from uuid import UUID, uuid5, NAMESPACE_OID
-from cognee.modules.users.models import User
 from typing import Union
+from sqlalchemy import select
+
+from cognee.modules.data.models.Dataset import Dataset
+from cognee.modules.users.models import User
+from cognee.infrastructure.databases.relational import get_relational_engine
 
 
 async def get_unique_dataset_id(dataset_name: Union[str, UUID], user: User) -> UUID:
-    if isinstance(dataset_name, UUID):
-        return dataset_name
-    return uuid5(NAMESPACE_OID, f"{dataset_name}{str(user.id)}")
+    """
+    Function returns a unique UUID for dataset based on dataset name, user id and tenant id.
+    If dataset with legacy ID exists, return that ID to maintain compatibility.
+
+    Args:
+        dataset_name: string representing the dataset name
+        user: User object adding the dataset
+        tenant_id: UUID of the tenant for which dataset is being added
+
+    Returns:
+        UUID: Unique identifier for the dataset
+    """
+
+    def _get_legacy_unique_dataset_id(dataset_name: Union[str, UUID], user: User) -> UUID:
+        """
+        Legacy function, returns a unique UUID for dataset based on dataset name and user id.
+        Needed to support legacy datasets without tenant information.
+        Args:
+            dataset_name: string representing the dataset name
+            user: Current User object adding the dataset
+
+        Returns:
+            UUID: Unique identifier for the dataset
+        """
+        if isinstance(dataset_name, UUID):
+            return dataset_name
+        return uuid5(NAMESPACE_OID, f"{dataset_name}{str(user.id)}")
+
+    def _get_modern_unique_dataset_id(dataset_name: Union[str, UUID], user: User) -> UUID:
+        """
+        Returns a unique UUID for dataset based on dataset name, user id and tenant_id.
+        Args:
+            dataset_name: string representing the dataset name
+            user: Current User object adding the dataset
+            tenant_id: UUID of the tenant for which dataset is being added
+
+        Returns:
+            UUID: Unique identifier for the dataset
+        """
+        if isinstance(dataset_name, UUID):
+            return dataset_name
+        return uuid5(NAMESPACE_OID, f"{dataset_name}{str(user.id)}{str(user.tenant_id)}")
+
+    # Get all possible dataset_id values
+    dataset_id = {
+        "modern_dataset_id": _get_modern_unique_dataset_id(dataset_name=dataset_name, user=user),
+        "legacy_dataset_id": _get_legacy_unique_dataset_id(dataset_name=dataset_name, user=user),
+    }
+
+    # Check if dataset with legacy_dataset_id exists, if so use that one, else use modern_dataset_id
+    db_engine = get_relational_engine()
+    async with db_engine.get_async_session() as session:
+        legacy_dataset = (
+            await session.execute(
+                select(Dataset).filter(Dataset.id == dataset_id["legacy_dataset_id"])
+            )
+        ).scalar_one_or_none()
+
+        if not legacy_dataset:
+            return dataset_id["modern_dataset_id"]
+        return dataset_id["legacy_dataset_id"]

cognee/modules/data/models/Dataset.py

@@ -18,6 +18,7 @@ class Dataset(Base):
     updated_at = Column(DateTime(timezone=True), onupdate=lambda: datetime.now(timezone.utc))
 
     owner_id = Column(UUID, index=True)
+    tenant_id = Column(UUID, index=True, nullable=True)
 
     acls = relationship("ACL", back_populates="dataset", cascade="all, delete-orphan")
 
@@ -36,5 +37,6 @@ class Dataset(Base):
             "createdAt": self.created_at.isoformat(),
             "updatedAt": self.updated_at.isoformat() if self.updated_at else None,
             "ownerId": str(self.owner_id),
+            "tenantId": str(self.tenant_id),
             "data": [data.to_json() for data in self.data],
         }