gmakstutis/cognee
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

feat: removing invalidValueErrors

Browse source
This commit is contained in:
hajdul88 2025-08-13 14:42:57 +02:00
parent 38329da0e8
commit 544e08930b
19 changed files with 62 additions and 69 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
cognee-mcp/src/server.py
View file

@ -221,14 +221,6 @@ async def cognify(data: str, graph_model_file: str = None, graph_model_name: str
- The actual cognify process may take significant time depending on text length
- Use the cognify_status tool to check the progress of the operation
Raises
------
InvalidValueError
If LLM_API_KEY is not set
ValueError
If chunks exceed max token limits (reduce chunk_size)
DatabaseNotCreatedError
If databases are not properly initialized
"""
async def cognify_task(
@ -512,14 +504,6 @@ async def search(search_query: str, search_type: str) -> list:
- Different search types produce different output formats
- The function handles the conversion between Cognee's internal result format and MCP's output format
Raises
------
InvalidValueError
If LLM_API_KEY is not set (for LLM-based search types)
ValueError
If query_text is empty or search parameters are invalid
NoDataError
If no relevant data found for the search query
"""
async def search_task(search_query: str, search_type: str) -> str:

5
cognee/api/v1/add/add.py
View file

@ -133,11 +133,6 @@ async def add(
- VECTOR_DB_PROVIDER: "lancedb" (default), "chromadb", "qdrant", "weaviate"
- GRAPH_DATABASE_PROVIDER: "kuzu" (default), "neo4j", "networkx"
Raises:
FileNotFoundError: If specified file paths don't exist
PermissionError: If user lacks access to files or dataset
UnsupportedFileTypeError: If file format cannot be processed
InvalidValueError: If LLM_API_KEY is not set or invalid
"""
tasks = [
Task(resolve_data_directories, include_subdirectories=True),

8
cognee/api/v1/cognify/cognify.py
View file

@ -177,14 +177,6 @@ async def cognify(
- LLM_PROVIDER, LLM_MODEL, VECTOR_DB_PROVIDER, GRAPH_DATABASE_PROVIDER
- LLM_RATE_LIMIT_ENABLED: Enable rate limiting (default: False)
- LLM_RATE_LIMIT_REQUESTS: Max requests per interval (default: 60)
Raises:
DatasetNotFoundError: If specified datasets don't exist
PermissionError: If user lacks processing rights
InvalidValueError: If LLM_API_KEY is not set
OntologyParsingError: If ontology file is malformed
ValueError: If chunks exceed max token limits (reduce chunk_size)
DatabaseNotCreatedError: If databases are not properly initialized
"""
tasks = await get_default_tasks(user, graph_model, chunker, chunk_size, ontology_file_path)

7
cognee/api/v1/search/search.py
View file

@ -158,13 +158,6 @@ async def search(
- VECTOR_DB_PROVIDER: Must match what was used during cognify
- GRAPH_DATABASE_PROVIDER: Must match what was used during cognify
Raises:
DatasetNotFoundError: If specified datasets don't exist or aren't accessible
PermissionDeniedError: If user lacks read access to requested datasets
NoDataError: If no relevant data found for the search query
InvalidValueError: If LLM_API_KEY is not set (for LLM-based search types)
ValueError: If query_text is empty or search parameters are invalid
CollectionNotFoundError: If vector collection not found (data not processed)
"""
# We use lists from now on for datasets
if isinstance(datasets, UUID) or isinstance(datasets, str):

2
cognee/infrastructure/data/utils/extract_keywords.py
View file

@ -8,7 +8,7 @@ def extract_keywords(text: str) -> list[str]:
"""
Extract keywords from the provided text string.
This function raises an InvalidValueError if the input text is empty. It processes the
This function raises an KeyWordExtractionError if the input text is empty. It processes the
text to extract parts of speech, focusing on nouns, and uses TF-IDF to identify the most
relevant keywords based on their frequency. The function returns a list of up to 15
keywords, each having more than 3 characters.

2
cognee/infrastructure/databases/exceptions/__init__.py
View file

@ -9,4 +9,6 @@ from .exceptions import (
EntityAlreadyExistsError,
DatabaseNotCreatedError,
EmbeddingException,
MissingQueryParameterError,
MutuallyExclusiveQueryParametersError
)

28
cognee/infrastructure/databases/exceptions/exceptions.py
View file

@ -102,3 +102,31 @@ class EmbeddingException(CogneeConfigurationError):
status_code=status.HTTP_422_UNPROCESSABLE_ENTITY,
):
super().__init__(message, name, status_code)
class MissingQueryParameterError(CogneeValidationError):
"""
Raised when neither 'query_text' nor 'query_vector' is provided,
and at least one is required to perform the operation.
"""
def __init__(
self,
name: str = "MissingQueryParameterError",
status_code: int = status.HTTP_400_BAD_REQUEST,
):
message = "One of query_text or query_vector must be provided!"
super().__init__(message, name, status_code)
class MutuallyExclusiveQueryParametersError(CogneeValidationError):
"""
Raised when both 'text' and 'embedding' are provided to the search function,
but only one type of input is allowed at a time.
"""
def __init__(
self,
name: str = "MutuallyExclusiveQueryParametersError",
status_code: int = status.HTTP_400_BAD_REQUEST,
):
message = (
"The search function accepts either text or embedding as input, but not both."
)
super().__init__(message, name, status_code)

4
cognee/infrastructure/databases/hybrid/falkordb/FalkorDBAdapter.py
View file

@ -9,7 +9,7 @@ from typing import List, Dict, Any, Optional, Tuple, Type, Union
from falkordb import FalkorDB
from cognee.exceptions import InvalidValueError
from cognee.infrastructure.databases.exceptions import MissingQueryParameterError
from cognee.infrastructure.databases.graph.graph_db_interface import (
GraphDBInterface,
record_graph_changes,
@ -721,7 +721,7 @@ class FalkorDBAdapter(VectorDBInterface, GraphDBInterface):
Returns the search results as a result set from the graph database.
"""
if query_text is None and query_vector is None:
raise InvalidValueError(message="One of query_text or query_vector must be provided!")
raise MissingQueryParameterError()
if query_text and not query_vector:
query_vector = (await self.embed_data([query_text]))[0]

9
cognee/infrastructure/databases/hybrid/neptune_analytics/NeptuneAnalyticsAdapter.py
View file

@ -5,7 +5,8 @@ import json
from typing import List, Optional, Any, Dict, Type, Tuple
from uuid import UUID
from cognee.exceptions import InvalidValueError
from cognee.infrastructure.databases.exceptions import MissingQueryParameterError
from cognee.infrastructure.databases.exceptions import MutuallyExclusiveQueryParametersError
from cognee.infrastructure.databases.graph.neptune_driver.adapter import NeptuneGraphDB
from cognee.infrastructure.databases.vector.vector_db_interface import VectorDBInterface
from cognee.infrastructure.engine import DataPoint
@ -274,11 +275,9 @@ class NeptuneAnalyticsAdapter(NeptuneGraphDB, VectorDBInterface):
limit = self._TOPK_UPPER_BOUND
if query_vector and query_text:
raise InvalidValueError(
message="The search function accepts either text or embedding as input, but not both."
)
raise MutuallyExclusiveQueryParametersError()
elif query_text is None and query_vector is None:
raise InvalidValueError(message="One of query_text or query_vector must be provided!")
raise MissingQueryParameterError()
elif query_vector:
embedding = query_vector
else:

4
cognee/infrastructure/databases/vector/chromadb/ChromaDBAdapter.py
View file

@ -3,13 +3,13 @@ from uuid import UUID
from typing import List, Optional
from chromadb import AsyncHttpClient, Settings
from cognee.exceptions import InvalidValueError
from cognee.shared.logging_utils import get_logger
from cognee.modules.storage.utils import get_own_properties
from cognee.infrastructure.engine import DataPoint
from cognee.infrastructure.engine.utils import parse_id
from cognee.infrastructure.databases.vector.exceptions import CollectionNotFoundError
from cognee.infrastructure.databases.vector.models.ScoredResult import ScoredResult
from cognee.infrastructure.databases.exceptions import MissingQueryParameterError
from ..embeddings.EmbeddingEngine import EmbeddingEngine
from ..vector_db_interface import VectorDBInterface
@ -373,7 +373,7 @@ class ChromaDBAdapter(VectorDBInterface):
Returns a list of ScoredResult instances representing the search results.
"""
if query_text is None and query_vector is None:
raise InvalidValueError(message="One of query_text or query_vector must be provided!")
raise MissingQueryParameterError()
if query_text and not query_vector:
query_vector = (await self.embedding_engine.embed_text([query_text]))[0]

4
cognee/infrastructure/databases/vector/lancedb/LanceDBAdapter.py
View file

@ -5,7 +5,7 @@ from pydantic import BaseModel
from lancedb.pydantic import LanceModel, Vector
from typing import Generic, List, Optional, TypeVar, Union, get_args, get_origin, get_type_hints
from cognee.exceptions import InvalidValueError
from cognee.infrastructure.databases.exceptions import MissingQueryParameterError
from cognee.infrastructure.engine import DataPoint
from cognee.infrastructure.engine.utils import parse_id
from cognee.infrastructure.files.storage import get_file_storage
@ -228,7 +228,7 @@ class LanceDBAdapter(VectorDBInterface):
normalized: bool = True,
):
if query_text is None and query_vector is None:
raise InvalidValueError(message="One of query_text or query_vector must be provided!")
raise MissingQueryParameterError()
if query_text and not query_vector:
query_vector = (await self.embedding_engine.embed_text([query_text]))[0]

3
cognee/infrastructure/databases/vector/pgvector/PGVectorAdapter.py
View file

@ -17,6 +17,7 @@ from cognee.infrastructure.databases.relational import get_relational_engine
from distributed.utils import override_distributed
from distributed.tasks.queued_add_data_points import queued_add_data_points
from cognee.infrastructure.databases.exceptions import MissingQueryParameterError
from ...relational.ModelBase import Base
from ...relational.sqlalchemy.SqlAlchemyAdapter import SQLAlchemyAdapter
@ -302,7 +303,7 @@ class PGVectorAdapter(SQLAlchemyAdapter, VectorDBInterface):
with_vector: bool = False,
) -> List[ScoredResult]:
if query_text is None and query_vector is None:
raise InvalidValueError(message="One of query_text or query_vector must be provided!")
raise MissingQueryParameterError()
if query_text and not query_vector:
query_vector = (await self.embedding_engine.embed_text([query_text]))[0]

6
cognee/infrastructure/databases/vector/qdrant/QDrantAdapter.py
View file

@ -4,7 +4,7 @@ from qdrant_client import AsyncQdrantClient, models
from cognee.shared.logging_utils import get_logger
from cognee.infrastructure.engine.utils import parse_id
from cognee.exceptions import InvalidValueError
from cognee.infrastructure.databases.exceptions import MissingQueryParameterError
from cognee.infrastructure.engine import DataPoint
from cognee.infrastructure.databases.vector.exceptions import CollectionNotFoundError
from cognee.infrastructure.databases.vector.models.ScoredResult import ScoredResult
@ -363,7 +363,7 @@ class QDrantAdapter(VectorDBInterface):
Search for data points in a collection based on either a textual query or a vector
query.
Raises InvalidValueError if both query_text and query_vector are None.
Raises MissingQueryParameterError if both query_text and query_vector are None.
Returns a list of scored results that match the search criteria.
@ -388,7 +388,7 @@ class QDrantAdapter(VectorDBInterface):
from qdrant_client.http.exceptions import UnexpectedResponse
if query_text is None and query_vector is None:
raise InvalidValueError(message="One of query_text or query_vector must be provided!")
raise MissingQueryParameterError()
if not await self.has_collection(collection_name):
return []

6
cognee/infrastructure/databases/vector/weaviate_db/WeaviateAdapter.py
View file

@ -3,7 +3,7 @@ from typing import List, Optional
from tenacity import retry, retry_if_exception, stop_after_attempt, wait_exponential
from cognee.shared.logging_utils import get_logger
from cognee.exceptions import InvalidValueError
from cognee.infrastructure.databases.exceptions import MissingQueryParameterError
from cognee.infrastructure.engine import DataPoint
from cognee.infrastructure.engine.utils import parse_id
from cognee.infrastructure.databases.vector.exceptions import CollectionNotFoundError
@ -390,7 +390,7 @@ class WeaviateAdapter(VectorDBInterface):
"""
Perform a search on a collection using either a text query or a vector query.
Return scored results based on the search criteria provided. Raise InvalidValueError if
Return scored results based on the search criteria provided. Raise MissingQueryParameterError if
no query is provided.
Parameters:
@ -413,7 +413,7 @@ class WeaviateAdapter(VectorDBInterface):
import weaviate.exceptions
if query_text is None and query_vector is None:
raise InvalidValueError(message="One of query_text or query_vector must be provided!")
raise MissingQueryParameterError()
if query_vector is None:
query_vector = (await self.embed_data([query_text]))[0]

4
cognee/infrastructure/llm/structured_output_framework/litellm_instructor/llm/anthropic/adapter.py
View file

@ -2,7 +2,7 @@ from typing import Type
from pydantic import BaseModel
import instructor
from cognee.exceptions import InvalidValueError
from cognee.infrastructure.llm.exceptions import MissingSystemPromptPathError
from cognee.infrastructure.llm.structured_output_framework.litellm_instructor.llm.llm_interface import (
LLMInterface,
)
@ -89,7 +89,7 @@ class AnthropicAdapter(LLMInterface):
if not text_input:
text_input = "No user input provided."
if not system_prompt:
raise InvalidValueError(message="No system prompt path provided.")
raise MissingSystemPromptPathError()
system_prompt = LLMGateway.read_query_prompt(system_prompt)

6
cognee/infrastructure/llm/structured_output_framework/litellm_instructor/llm/gemini/adapter.py
View file

@ -5,7 +5,7 @@ from litellm import acompletion, JSONSchemaValidationError
from cognee.shared.logging_utils import get_logger
from cognee.modules.observability.get_observe import get_observe
from cognee.exceptions import InvalidValueError
from cognee.infrastructure.llm.exceptions import MissingSystemPromptPathError
from cognee.infrastructure.llm.structured_output_framework.litellm_instructor.llm.llm_interface import (
LLMInterface,
)
@ -118,7 +118,7 @@ class GeminiAdapter(LLMInterface):
"""
Format and display the prompt for a user query.
Raises an InvalidValueError if no system prompt is provided.
Raises an MissingQueryParameterError if no system prompt is provided.
Parameters:
-----------
@ -135,7 +135,7 @@ class GeminiAdapter(LLMInterface):
if not text_input:
text_input = "No user input provided."
if not system_prompt:
raise InvalidValueError(message="No system prompt path provided.")
raise MissingSystemPromptPathError()
system_prompt = LLMGateway.read_query_prompt(system_prompt)
formatted_prompt = (

4
cognee/infrastructure/llm/structured_output_framework/litellm_instructor/llm/get_llm_client.py
View file

@ -38,7 +38,7 @@ def get_llm_client():
This function retrieves the configuration for the LLM provider and model, and
initializes the appropriate LLM client adapter accordingly. It raises an
InvalidValueError if the LLM API key is not set for certain providers or if the provider
LLMAPIKeyNotSetError if the LLM API key is not set for certain providers or if the provider
is unsupported.
Returns:
@ -62,7 +62,7 @@ def get_llm_client():
if provider == LLMProvider.OPENAI:
if llm_config.llm_api_key is None:
raise InvalidValueError(message="LLM API key is not set.")
raise LLMAPIKeyNotSetError()
from cognee.infrastructure.llm.structured_output_framework.litellm_instructor.llm.openai.adapter import (
OpenAIAdapter,

2
cognee/infrastructure/llm/structured_output_framework/litellm_instructor/llm/openai/adapter.py
View file

@ -307,7 +307,7 @@ class OpenAIAdapter(LLMInterface):
Format and display the prompt for a user query.
This method formats the prompt using the provided user input and system prompt,
returning a string representation. Raises InvalidValueError if the system prompt is not
returning a string representation. Raises MissingSystemPromptPathError if the system prompt is not
provided.
Parameters:

11
cognee/tests/unit/modules/graph/cognee_graph_elements_test.py
View file

@ -1,9 +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():
"""Test that a Node is initialized correctly."""
@ -16,7 +15,7 @@ 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, match="Dimensions must be a positive integers"):
Node("node1", dimension=0)
@ -69,7 +68,7 @@ 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, match="Dimension 1 is out of range"):
node.is_node_alive_in_dimension(1)
@ -106,7 +105,7 @@ 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(DimensionOutOfRangeError, match="Dimensions must be a positive integer."):
Edge(node1, node2, dimension=0)
@ -125,7 +124,7 @@ 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, match="Dimension 1 is out of range"):
edge.is_edge_alive_in_dimension(1)