cognee 0.2.3.dev0__py3-none-any.whl → 0.2.3.dev1__py3-none-any.whl

cognee/tasks/documents/classify_documents.py

@@ -10,6 +10,7 @@ from cognee.modules.data.processing.document_types import (
 )
 from cognee.modules.engine.models.node_set import NodeSet
 from cognee.modules.engine.utils.generate_node_id import generate_node_id
+from cognee.tasks.documents.exceptions import WrongDataDocumentInputError
 
 EXTENSION_TO_DOCUMENT_CLASS = {
     "pdf": PdfDocument,  # Text documents
@@ -111,6 +112,9 @@ async def classify_documents(data_documents: list[Data]) -> list[Document]:
         - list[Document]: A list of Document objects created based on the classified data
           documents.
     """
+    if not isinstance(data_documents, list):
+        raise WrongDataDocumentInputError("data_documents")
+
     documents = []
     for data_item in data_documents:
         document = EXTENSION_TO_DOCUMENT_CLASS[data_item.extension](

cognee/tasks/documents/exceptions/__init__.py

@@ -0,0 +1,11 @@
+"""
+Custom exceptions for the Cognee API.
+
+This module defines a set of exceptions for handling various data errors
+"""
+
+from .exceptions import (
+    WrongDataDocumentInputError,
+    InvalidChunkSizeError,
+    InvalidChunkerError,
+)

cognee/tasks/documents/exceptions/exceptions.py

@@ -0,0 +1,36 @@
+from cognee.exceptions import (
+    CogneeValidationError,
+    CogneeConfigurationError,
+)
+from fastapi import status
+
+
+class WrongDataDocumentInputError(CogneeValidationError):
+    """Raised when a wrong data document is provided."""
+
+    def __init__(
+        self,
+        field: str,
+        name: str = "WrongDataDocumentInputError",
+        status_code: int = status.HTTP_422_UNPROCESSABLE_ENTITY,
+    ):
+        message = f"Missing of invalid parameter: '{field}'."
+        super().__init__(message, name, status_code)
+
+
+class InvalidChunkSizeError(CogneeValidationError):
+    def __init__(self, value):
+        super().__init__(
+            message=f"max_chunk_size must be a positive integer (got {value}).",
+            name="InvalidChunkSizeError",
+            status_code=status.HTTP_400_BAD_REQUEST,
+        )
+
+
+class InvalidChunkerError(CogneeValidationError):
+    def __init__(self):
+        super().__init__(
+            message="chunker must be a valid Chunker class.",
+            name="InvalidChunkerError",
+            status_code=status.HTTP_400_BAD_REQUEST,
+        )

cognee/tasks/documents/extract_chunks_from_documents.py

@@ -8,6 +8,7 @@ from cognee.modules.data.models import Data
 from cognee.infrastructure.databases.relational import get_relational_engine
 from cognee.modules.chunking.TextChunker import TextChunker
 from cognee.modules.chunking.Chunker import Chunker
+from cognee.tasks.documents.exceptions import InvalidChunkSizeError, InvalidChunkerError
 
 
 async def update_document_token_count(document_id: UUID, token_count: int) -> None:
@@ -37,6 +38,13 @@ async def extract_chunks_from_documents(
         - The `read` method of the `Document` class must be implemented to support the chunking operation.
         - The `chunker` parameter determines the chunking logic and should align with the document type.
     """
+    if not isinstance(max_chunk_size, int) or max_chunk_size <= 0:
+        raise InvalidChunkSizeError(max_chunk_size)
+    if not isinstance(chunker, type):
+        raise InvalidChunkerError()
+    if not hasattr(chunker, "read"):
+        raise InvalidChunkerError()
+
     for document in documents:
         document_token_count = 0
 
@@ -48,5 +56,3 @@ async def extract_chunks_from_documents(
             yield document_chunk
 
         await update_document_token_count(document.id, document_token_count)
-
-        # todo rita

cognee/tasks/graph/exceptions/__init__.py

@@ -0,0 +1,12 @@
+"""
+Custom exceptions for the Cognee API.
+
+This module defines a set of exceptions for handling various data errors
+"""
+
+from .exceptions import (
+    InvalidDataChunksError,
+    InvalidGraphModelError,
+    InvalidOntologyAdapterError,
+    InvalidChunkGraphInputError,
+)

cognee/tasks/graph/exceptions/exceptions.py

@@ -0,0 +1,41 @@
+from cognee.exceptions import (
+    CogneeValidationError,
+    CogneeConfigurationError,
+)
+from fastapi import status
+
+
+class InvalidDataChunksError(CogneeValidationError):
+    def __init__(self, detail: str):
+        super().__init__(
+            message=f"Invalid data_chunks: {detail}",
+            name="InvalidDataChunksError",
+            status_code=status.HTTP_400_BAD_REQUEST,
+        )
+
+
+class InvalidGraphModelError(CogneeValidationError):
+    def __init__(self, got):
+        super().__init__(
+            message=f"graph_model must be a subclass of BaseModel (got {got}).",
+            name="InvalidGraphModelError",
+            status_code=status.HTTP_400_BAD_REQUEST,
+        )
+
+
+class InvalidOntologyAdapterError(CogneeConfigurationError):
+    def __init__(self, got):
+        super().__init__(
+            message=f"ontology_adapter lacks required interface (got {got}).",
+            name="InvalidOntologyAdapterError",
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+        )
+
+
+class InvalidChunkGraphInputError(CogneeValidationError):
+    def __init__(self, detail: str):
+        super().__init__(
+            message=f"Invalid chunk inputs or LLM Chunkgraphs: {detail}",
+            name="InvalidChunkGraphInputError",
+            status_code=status.HTTP_400_BAD_REQUEST,
+        )

cognee/tasks/graph/extract_graph_from_data.py

@@ -12,6 +12,12 @@ from cognee.modules.graph.utils import (
 )
 from cognee.shared.data_models import KnowledgeGraph
 from cognee.infrastructure.llm.LLMGateway import LLMGateway
+from cognee.tasks.graph.exceptions import (
+    InvalidGraphModelError,
+    InvalidDataChunksError,
+    InvalidChunkGraphInputError,
+    InvalidOntologyAdapterError,
+)
 
 
 async def integrate_chunk_graphs(
@@ -21,6 +27,20 @@ async def integrate_chunk_graphs(
     ontology_adapter: OntologyResolver,
 ) -> List[DocumentChunk]:
     """Updates DocumentChunk objects, integrates data points and edges into databases."""
+
+    if not isinstance(data_chunks, list) or not isinstance(chunk_graphs, list):
+        raise InvalidChunkGraphInputError("data_chunks and chunk_graphs must be lists.")
+    if len(data_chunks) != len(chunk_graphs):
+        raise InvalidChunkGraphInputError(
+            f"length mismatch: {len(data_chunks)} chunks vs {len(chunk_graphs)} graphs."
+        )
+    if not isinstance(graph_model, type) or not issubclass(graph_model, BaseModel):
+        raise InvalidGraphModelError(graph_model)
+    if ontology_adapter is None or not hasattr(ontology_adapter, "get_subgraph"):
+        raise InvalidOntologyAdapterError(
+            type(ontology_adapter).__name__ if ontology_adapter else "None"
+        )
+
     graph_engine = await get_graph_engine()
 
     if graph_model is not KnowledgeGraph:
@@ -55,6 +75,14 @@ async def extract_graph_from_data(
     """
     Extracts and integrates a knowledge graph from the text content of document chunks using a specified graph model.
     """
+
+    if not isinstance(data_chunks, list) or not data_chunks:
+        raise InvalidDataChunksError("must be a non-empty list of DocumentChunk.")
+    if not all(hasattr(c, "text") for c in data_chunks):
+        raise InvalidDataChunksError("each chunk must have a 'text' attribute")
+    if not isinstance(graph_model, type) or not issubclass(graph_model, BaseModel):
+        raise InvalidGraphModelError(graph_model)
+
     chunk_graphs = await asyncio.gather(
         *[LLMGateway.extract_content_graph(chunk.text, graph_model) for chunk in data_chunks]
     )

cognee/tasks/ingestion/exceptions/__init__.py

@@ -0,0 +1,8 @@
+"""
+Custom exceptions for the Cognee API.
+
+This module defines a set of exceptions for handling various application errors,
+such as System, Validation, Configuration or TransientErrors
+"""
+
+from .exceptions import S3FileSystemNotFoundError

cognee/tasks/ingestion/exceptions/exceptions.py

@@ -0,0 +1,12 @@
+from cognee.exceptions import CogneeSystemError
+from fastapi import status
+
+
+class S3FileSystemNotFoundError(CogneeSystemError):
+    def __init__(
+        self,
+        name: str = "S3FileSystemNotFoundError",
+        status_code: int = status.HTTP_500_INTERNAL_SERVER_ERROR,
+    ):
+        message = "Could not find S3FileSystem."
+        super().__init__(message, name, status_code)

cognee/tasks/ingestion/resolve_data_directories.py

@@ -1,6 +1,9 @@
 import os
 from urllib.parse import urlparse
 from typing import List, Union, BinaryIO
+
+from cognee.tasks.ingestion.exceptions import S3FileSystemNotFoundError
+from cognee.exceptions import CogneeSystemError
 from cognee.infrastructure.files.storage.s3_config import get_s3_config
 
 
@@ -54,6 +57,8 @@ async def resolve_data_directories(
                             else:
                                 s3_files.append(key)
                     resolved_data.extend(s3_files)
+                else:
+                    raise S3FileSystemNotFoundError()
 
             elif os.path.isdir(item):  # If it's a directory
                 if include_subdirectories:

cognee/tasks/storage/add_data_points.py

@@ -5,9 +5,17 @@ from cognee.infrastructure.databases.graph import get_graph_engine
 from cognee.modules.graph.utils import deduplicate_nodes_and_edges, get_graph_from_model
 from .index_data_points import index_data_points
 from .index_graph_edges import index_graph_edges
+from cognee.tasks.storage.exceptions import (
+    InvalidDataPointsInAddDataPointsError,
+)
 
 
 async def add_data_points(data_points: List[DataPoint]) -> List[DataPoint]:
+    if not isinstance(data_points, list):
+        raise InvalidDataPointsInAddDataPointsError("data_points must be a list.")
+    if not all(isinstance(dp, DataPoint) for dp in data_points):
+        raise InvalidDataPointsInAddDataPointsError("data_points: each item must be a DataPoint.")
+
     nodes = []
     edges = []
 

cognee/tasks/storage/exceptions/__init__.py

@@ -0,0 +1,9 @@
+"""
+Custom exceptions for the Cognee API.
+
+This module defines a set of exceptions for handling various data errors
+"""
+
+from .exceptions import (
+    InvalidDataPointsInAddDataPointsError,
+)

cognee/tasks/storage/exceptions/exceptions.py

@@ -0,0 +1,13 @@
+from cognee.exceptions import (
+    CogneeValidationError,
+)
+from fastapi import status
+
+
+class InvalidDataPointsInAddDataPointsError(CogneeValidationError):
+    def __init__(self, detail: str):
+        super().__init__(
+            message=f"Invalid data_points: {detail}",
+            name="InvalidDataPointsInAddDataPointsError",
+            status_code=status.HTTP_400_BAD_REQUEST,
+        )

cognee/tasks/storage/index_data_points.py

@@ -1,6 +1,6 @@
 from cognee.shared.logging_utils import get_logger
 
-from cognee.infrastructure.databases.exceptions.EmbeddingException import EmbeddingException
+from cognee.infrastructure.databases.exceptions import EmbeddingException
 from cognee.infrastructure.databases.vector import get_vector_engine
 from cognee.infrastructure.engine import DataPoint
 

cognee/tasks/summarization/exceptions/__init__.py

@@ -0,0 +1,9 @@
+"""
+Custom exceptions for the Cognee API.
+
+This module defines a set of exceptions for handling various data errors
+"""
+
+from .exceptions import (
+    InvalidSummaryInputsError,
+)

cognee/tasks/summarization/exceptions/exceptions.py

@@ -0,0 +1,14 @@
+from cognee.exceptions import (
+    CogneeValidationError,
+    CogneeConfigurationError,
+)
+from fastapi import status
+
+
+class InvalidSummaryInputsError(CogneeValidationError):
+    def __init__(self, detail: str):
+        super().__init__(
+            message=f"Invalid summarize_text inputs: {detail}",
+            name="InvalidSummaryInputsError",
+            status_code=status.HTTP_400_BAD_REQUEST,
+        )

cognee/tasks/summarization/summarize_text.py

@@ -3,10 +3,11 @@ from typing import Type
 from uuid import uuid5
 from pydantic import BaseModel
 
+from cognee.tasks.summarization.exceptions import InvalidSummaryInputsError
 from cognee.modules.chunking.models.DocumentChunk import DocumentChunk
 from cognee.infrastructure.llm.LLMGateway import LLMGateway
 from cognee.modules.cognify.config import get_cognify_config
-from .models import TextSummary
+from cognee.tasks.summarization.models import TextSummary
 
 
 async def summarize_text(
@@ -35,6 +36,12 @@ async def summarize_text(
         A list of TextSummary objects, each containing the summary of a corresponding
         DocumentChunk.
     """
+
+    if not isinstance(data_chunks, list):
+        raise InvalidSummaryInputsError("data_chunks must be a list.")
+    if not all(hasattr(c, "text") for c in data_chunks):
+        raise InvalidSummaryInputsError("each DocumentChunk must have a 'text' attribute.")
+
     if len(data_chunks) == 0:
         return data_chunks
 

cognee/tests/test_delete_by_id.py

@@ -7,7 +7,7 @@ from cognee.shared.logging_utils import get_logger
 from cognee.modules.users.methods import get_default_user, create_user
 from cognee.modules.users.permissions.methods import authorized_give_permission_on_datasets
 from cognee.modules.data.methods import get_dataset_data, get_datasets_by_name
-from cognee.api.v1.delete.exceptions import DocumentNotFoundError, DatasetNotFoundError
+from cognee.api.v1.exceptions import DocumentNotFoundError, DatasetNotFoundError
 
 logger = get_logger()
 

cognee/tests/unit/modules/graph/cognee_graph_elements_test.py

@@ -1,8 +1,8 @@
 import numpy as np
 import pytest
 
-from cognee.exceptions import InvalidValueError
 from cognee.modules.graph.cognee_graph.CogneeGraphElements import Edge, Node
+from cognee.modules.graph.exceptions import InvalidDimensionsError, DimensionOutOfRangeError
 
 
 def test_node_initialization():
@@ -16,7 +16,7 @@ def test_node_initialization():
 
 def test_node_invalid_dimension():
     """Test that initializing a Node with a non-positive dimension raises an error."""
-    with pytest.raises(InvalidValueError, match="Dimension must be a positive integer"):
+    with pytest.raises(InvalidDimensionsError):
         Node("node1", dimension=0)
 
 
@@ -69,7 +69,7 @@ def test_is_node_alive_in_dimension():
 def test_node_alive_invalid_dimension():
     """Test that checking alive status with an invalid dimension raises an error."""
     node = Node("node1", dimension=1)
-    with pytest.raises(InvalidValueError, match="Dimension 1 is out of range"):
+    with pytest.raises(DimensionOutOfRangeError):
         node.is_node_alive_in_dimension(1)
 
 
@@ -106,7 +106,7 @@ def test_edge_invalid_dimension():
     """Test that initializing an Edge with a non-positive dimension raises an error."""
     node1 = Node("node1")
     node2 = Node("node2")
-    with pytest.raises(InvalidValueError, match="Dimensions must be a positive integer."):
+    with pytest.raises(InvalidDimensionsError):
         Edge(node1, node2, dimension=0)
 
 
@@ -125,7 +125,7 @@ def test_edge_alive_invalid_dimension():
     node1 = Node("node1")
     node2 = Node("node2")
     edge = Edge(node1, node2, dimension=1)
-    with pytest.raises(InvalidValueError, match="Dimension 1 is out of range"):
+    with pytest.raises(DimensionOutOfRangeError):
         edge.is_edge_alive_in_dimension(1)
 
 

cognee/tests/unit/modules/search/search_methods_test.py

@@ -5,7 +5,7 @@ from unittest.mock import AsyncMock, MagicMock, patch
 import pytest
 from pylint.checkers.utils import node_type
 
-from cognee.exceptions import InvalidValueError
+from cognee.modules.search.exceptions import UnsupportedSearchTypeError
 from cognee.modules.search.methods.search import search, specific_search
 from cognee.modules.search.types import SearchType
 from cognee.modules.users.models import User
@@ -217,7 +217,7 @@ async def test_specific_search_invalid_type(mock_user):
     query_type = "INVALID_TYPE"  # Not a valid SearchType
 
     # Execute and verify
-    with pytest.raises(InvalidValueError) as excinfo:
+    with pytest.raises(UnsupportedSearchTypeError) as excinfo:
         await specific_search(query_type, query, mock_user)
 
     assert "Unsupported search type" in str(excinfo.value)

{cognee-0.2.3.dev0.dist-info → cognee-0.2.3.dev1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cognee
-Version: 0.2.3.dev0
+Version: 0.2.3.dev1
 Summary: Cognee - is a library for enriching LLM context with a semantic layer for better understanding and reasoning.
 Project-URL: Homepage, https://www.cognee.ai
 Project-URL: Repository, https://github.com/topoteretes/cognee