Fix path handling consistency (#1327)

<!-- .github/pull_request_template.md -->

## Description
Fix path handling consistency by Gneeraj2001

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.

README.md

@@ -79,7 +79,9 @@ More on [use-cases](https://docs.cognee.ai/use-cases) and [evals](https://github
 
 ## Get Started
 
-Get started quickly with a Google Colab  <a href="https://colab.research.google.com/drive/1jHbWVypDgCLwjE71GSXhRL3YxYhCZzG1?usp=sharing">notebook</a> , <a href="https://deepnote.com/workspace/cognee-382213d0-0444-4c89-8265-13770e333c02/project/cognee-demo-78ffacb9-5832-4611-bb1a-560386068b30/notebook/Notebook-1-75b24cda566d4c24ab348f7150792601?utm_source=share-modal&utm_medium=product-shared-content&utm_campaign=notebook&utm_content=78ffacb9-5832-4611-bb1a-560386068b30">Deepnote notebook</a> or  <a href="https://github.com/topoteretes/cognee-starter">starter repo</a>
+Get started quickly with a Google Colab  <a href="https://colab.research.google.com/drive/1jHbWVypDgCLwjE71GSXhRL3YxYhCZzG1?usp=sharing">notebook</a> , <a href="https://deepnote.com/workspace/cognee-382213d0-0444-4c89-8265-13770e333c02/project/cognee-demo-78ffacb9-5832-4611-bb1a-560386068b30/notebook/Notebook-1-75b24cda566d4c24ab348f7150792601?utm_source=share-modal&utm_medium=product-shared-content&utm_campaign=notebook&utm_content=78ffacb9-5832-4611-bb1a-560386068b30">Deepnote notebook</a> or  <a href="https://github.com/topoteretes/cognee/tree/main/cognee-starter-kit">starter repo</a>
+
+
 
 
 ## Contributing

cognee/base_config.py

@@ -1,15 +1,24 @@
 import os
 from typing import Optional
 from functools import lru_cache
-from cognee.root_dir import get_absolute_path
+from cognee.root_dir import get_absolute_path, ensure_absolute_path
 from cognee.modules.observability.observers import Observer
 from pydantic_settings import BaseSettings, SettingsConfigDict
+import pydantic
 
 
 class BaseConfig(BaseSettings):
     data_root_directory: str = get_absolute_path(".data_storage")
     system_root_directory: str = get_absolute_path(".cognee_system")
     monitoring_tool: object = Observer.LANGFUSE
+
+    @pydantic.model_validator(mode="after")
+    def validate_paths(self):
+        # Require absolute paths for root directories
+        self.data_root_directory = ensure_absolute_path(self.data_root_directory)
+        self.system_root_directory = ensure_absolute_path(self.system_root_directory)
+        return self
+
     langfuse_public_key: Optional[str] = os.getenv("LANGFUSE_PUBLIC_KEY")
     langfuse_secret_key: Optional[str] = os.getenv("LANGFUSE_SECRET_KEY")
     langfuse_host: Optional[str] = os.getenv("LANGFUSE_HOST")

cognee/infrastructure/databases/graph/config.py

@@ -6,6 +6,7 @@ from pydantic_settings import BaseSettings, SettingsConfigDict
 import pydantic
 from pydantic import Field
 from cognee.base_config import get_base_config
+from cognee.root_dir import ensure_absolute_path
 from cognee.shared.data_models import KnowledgeGraph
 
 
@@ -51,15 +52,20 @@ class GraphConfig(BaseSettings):
     @pydantic.model_validator(mode="after")
     def fill_derived(cls, values):
         provider = values.graph_database_provider.lower()
+        base_config = get_base_config()
 
         # Set default filename if no filename is provided
         if not values.graph_filename:
             values.graph_filename = f"cognee_graph_{provider}"
 
-        # Set file path based on graph database provider if no file path is provided
-        if not values.graph_file_path:
-            base_config = get_base_config()
-
+        # Handle graph file path
+        if values.graph_file_path:
+            # Check if absolute path is provided
+            values.graph_file_path = ensure_absolute_path(
+                os.path.join(values.graph_file_path, values.graph_filename)
+            )
+        else:
+            # Default path
             databases_directory_path = os.path.join(base_config.system_root_directory, "databases")
             values.graph_file_path = os.path.join(databases_directory_path, values.graph_filename)
 

cognee/infrastructure/databases/vector/config.py

@@ -1,9 +1,11 @@
 import os
 import pydantic
+from pathlib import Path
 from functools import lru_cache
 from pydantic_settings import BaseSettings, SettingsConfigDict
 
 from cognee.base_config import get_base_config
+from cognee.root_dir import ensure_absolute_path
 
 
 class VectorConfig(BaseSettings):
@@ -11,11 +13,9 @@ class VectorConfig(BaseSettings):
     Manage the configuration settings for the vector database.
 
     Public methods:
-
     - to_dict: Convert the configuration to a dictionary.
 
     Instance variables:
-
     - vector_db_url: The URL of the vector database.
     - vector_db_port: The port for the vector database.
     - vector_db_key: The key for accessing the vector database.
@@ -30,10 +30,17 @@ class VectorConfig(BaseSettings):
     model_config = SettingsConfigDict(env_file=".env", extra="allow")
 
     @pydantic.model_validator(mode="after")
-    def fill_derived(cls, values):
-        # Set file path based on graph database provider if no file path is provided
-        if not values.vector_db_url:
-            base_config = get_base_config()
+    def validate_paths(cls, values):
+        base_config = get_base_config()
+
+        # If vector_db_url is provided and is not a path skip checking if path is absolute (as it can also be a url)
+        if values.vector_db_url and Path(values.vector_db_url).exists():
+            # Relative path to absolute
+            values.vector_db_url = ensure_absolute_path(
+                values.vector_db_url,
+            )
+        else:
+            # Default path
             databases_directory_path = os.path.join(base_config.system_root_directory, "databases")
             values.vector_db_url = os.path.join(databases_directory_path, "cognee.lancedb")
 

cognee/root_dir.py

@@ -1,4 +1,5 @@
 from pathlib import Path
+from typing import Optional
 
 ROOT_DIR = Path(__file__).resolve().parent
 
@@ -6,3 +7,21 @@ ROOT_DIR = Path(__file__).resolve().parent
 def get_absolute_path(path_from_root: str) -> str:
     absolute_path = ROOT_DIR / path_from_root
     return str(absolute_path.resolve())
+
+
+def ensure_absolute_path(path: str) -> str:
+    """Ensures a path is absolute.
+
+    Args:
+        path: The path to validate.
+
+    Returns:
+        Absolute path as string
+    """
+    if path is None:
+        raise ValueError("Path cannot be None")
+    path_obj = Path(path).expanduser()
+    if path_obj.is_absolute():
+        return str(path_obj.resolve())
+
+    raise ValueError(f"Path must be absolute. Got relative path: {path}")

cognee/tests/unit/processing/utils/utils_test.py

@@ -4,8 +4,9 @@ import pytest
 from unittest.mock import patch, mock_open
 from io import BytesIO
 from uuid import uuid4
+from pathlib import Path
 
-
+from cognee.root_dir import ensure_absolute_path
 from cognee.infrastructure.files.utils.get_file_content_hash import get_file_content_hash
 from cognee.shared.utils import get_anonymous_id
 
@@ -52,3 +53,21 @@ async def test_get_file_content_hash_stream():
     expected_hash = hashlib.md5(b"test_data").hexdigest()
     result = await get_file_content_hash(stream)
     assert result == expected_hash
+
+
+@pytest.mark.asyncio
+async def test_root_dir_absolute_paths():
+    """Test absolute path handling in root_dir.py"""
+    # Test with absolute path
+    abs_path = "C:/absolute/path" if os.name == "nt" else "/absolute/path"
+    result = ensure_absolute_path(abs_path)
+    assert result == str(Path(abs_path).resolve())
+
+    # Test with relative path (should fail)
+    rel_path = "relative/path"
+    with pytest.raises(ValueError, match="must be absolute"):
+        ensure_absolute_path(rel_path)
+
+    # Test with None path
+    with pytest.raises(ValueError, match="cannot be None"):
+        ensure_absolute_path(None)