feat: adds errors to classify, and chunking top level

cognee/tasks/documents/classify_documents.py

@@ -117,7 +117,6 @@ async def classify_documents(data_documents: list[Data]) -> list[Document]:
 
     documents = []
     for data_item in data_documents:
-
         document = EXTENSION_TO_DOCUMENT_CLASS[data_item.extension](
             id=data_item.id,
             title=f"{data_item.name}.{data_item.extension}",

cognee/tasks/documents/exceptions/__init__.py

@@ -6,4 +6,6 @@ This module defines a set of exceptions for handling various data errors
 
 from .exceptions import (
     WrongDataDocumentInputError,
+    InvalidChunkSizeError,
+    InvalidChunkerError,
 )

cognee/tasks/documents/exceptions/exceptions.py

@@ -7,6 +7,7 @@ from fastapi import status
 
 class WrongDataDocumentInputError(CogneeValidationError):
     """Raised when a wrong data document is provided."""
+
     def __init__(
         self,
         field: str,
@@ -14,4 +15,22 @@ class WrongDataDocumentInputError(CogneeValidationError):
         status_code: int = status.HTTP_422_UNPROCESSABLE_ENTITY,
     ):
         message = f"Missing of invalid parameter: '{field}'."
-        super().__init__(message, name, status_code)
+        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=f"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