feat: centralize default memory path logic & add path validation tests

Co-Authored-By: Joe Moura <joao@crewai.com>

docs/how-to/Portkey-Observability-and-Guardrails.md

@@ -0,0 +1,211 @@
+# Portkey Integration with CrewAI
+<img src="https://raw.githubusercontent.com/siddharthsambharia-portkey/Portkey-Product-Images/main/Portkey-CrewAI.png" alt="Portkey CrewAI Header Image" width="70%" />
+
+
+[Portkey](https://portkey.ai/?utm_source=crewai&utm_medium=crewai&utm_campaign=crewai) is a 2-line upgrade to make your CrewAI agents reliable, cost-efficient, and fast.
+
+Portkey adds 4 core production capabilities to any CrewAI agent:
+1. Routing to **200+ LLMs**
+2. Making each LLM call more robust
+3. Full-stack tracing & cost, performance analytics
+4. Real-time guardrails to enforce behavior
+
+
+
+
+
+## Getting Started
+
+1. **Install Required Packages:**
+
+```bash
+pip install -qU crewai portkey-ai
+```
+
+2. **Configure the LLM Client:**
+
+To build CrewAI Agents with Portkey, you'll need two keys:
+- **Portkey API Key**: Sign up on the [Portkey app](https://app.portkey.ai/?utm_source=crewai&utm_medium=crewai&utm_campaign=crewai) and copy your API key
+- **Virtual Key**: Virtual Keys securely manage your LLM API keys in one place. Store your LLM provider API keys securely in Portkey's vault
+
+```python
+from crewai import LLM
+from portkey_ai import createHeaders, PORTKEY_GATEWAY_URL
+
+gpt_llm = LLM(
+    model="gpt-4",
+    base_url=PORTKEY_GATEWAY_URL,
+    api_key="dummy", # We are using Virtual key
+    extra_headers=createHeaders(
+        api_key="YOUR_PORTKEY_API_KEY",
+        virtual_key="YOUR_VIRTUAL_KEY", # Enter your Virtual key from Portkey
+    )
+)
+```
+
+3. **Create and Run Your First Agent:**
+
+```python
+from crewai import Agent, Task, Crew
+
+# Define your agents with roles and goals
+coder = Agent(
+    role='Software developer',
+    goal='Write clear, concise code on demand',
+    backstory='An expert coder with a keen eye for software trends.',
+    llm=gpt_llm
+)
+
+# Create tasks for your agents
+task1 = Task(
+    description="Define the HTML for making a simple website with heading- Hello World! Portkey is working!",
+    expected_output="A clear and concise HTML code",
+    agent=coder
+)
+
+# Instantiate your crew
+crew = Crew(
+    agents=[coder],
+    tasks=[task1],
+)
+
+result = crew.kickoff()
+print(result)
+```
+
+
+## Key Features
+
+| Feature | Description |
+|---------|-------------|
+| 🌐 Multi-LLM Support | Access OpenAI, Anthropic, Gemini, Azure, and 250+ providers through a unified interface |
+| 🛡️ Production Reliability | Implement retries, timeouts, load balancing, and fallbacks |
+| 📊 Advanced Observability | Track 40+ metrics including costs, tokens, latency, and custom metadata |
+| 🔍 Comprehensive Logging | Debug with detailed execution traces and function call logs |
+| 🚧 Security Controls | Set budget limits and implement role-based access control |
+| 🔄 Performance Analytics | Capture and analyze feedback for continuous improvement |
+| 💾 Intelligent Caching | Reduce costs and latency with semantic or simple caching |
+
+
+## Production Features with Portkey Configs
+
+All features mentioned below are through Portkey's Config system. Portkey's Config system allows you to define routing strategies using simple JSON objects in your LLM API calls. You can create and manage Configs directly in your code or through the Portkey Dashboard. Each Config has a unique ID for easy reference.
+
+<Frame>
+    <img src="https://raw.githubusercontent.com/Portkey-AI/docs-core/refs/heads/main/images/libraries/libraries-3.avif"/>
+</Frame>
+
+
+### 1. Use 250+ LLMs
+Access various LLMs like Anthropic, Gemini, Mistral, Azure OpenAI, and more with minimal code changes. Switch between providers or use them together seamlessly. [Learn more about Universal API](https://portkey.ai/docs/product/ai-gateway/universal-api)
+
+
+Easily switch between different LLM providers:
+
+```python
+# Anthropic Configuration
+anthropic_llm = LLM(
+    model="claude-3-5-sonnet-latest",
+    base_url=PORTKEY_GATEWAY_URL,
+    api_key="dummy",
+    extra_headers=createHeaders(
+        api_key="YOUR_PORTKEY_API_KEY",
+        virtual_key="YOUR_ANTHROPIC_VIRTUAL_KEY", #You don't need provider when using Virtual keys
+        trace_id="anthropic_agent"
+    )
+)
+
+# Azure OpenAI Configuration
+azure_llm = LLM(
+    model="gpt-4",
+    base_url=PORTKEY_GATEWAY_URL,
+    api_key="dummy",
+    extra_headers=createHeaders(
+        api_key="YOUR_PORTKEY_API_KEY",
+        virtual_key="YOUR_AZURE_VIRTUAL_KEY", #You don't need provider when using Virtual keys
+        trace_id="azure_agent"
+    )
+)
+```
+
+
+### 2. Caching
+Improve response times and reduce costs with two powerful caching modes:
+- **Simple Cache**: Perfect for exact matches
+- **Semantic Cache**: Matches responses for requests that are semantically similar
+[Learn more about Caching](https://portkey.ai/docs/product/ai-gateway/cache-simple-and-semantic)
+
+```py
+config = {
+    "cache": {
+        "mode": "semantic",  # or "simple" for exact matching
+    }
+}
+```
+
+### 3. Production Reliability
+Portkey provides comprehensive reliability features:
+- **Automatic Retries**: Handle temporary failures gracefully
+- **Request Timeouts**: Prevent hanging operations
+- **Conditional Routing**: Route requests based on specific conditions
+- **Fallbacks**: Set up automatic provider failovers
+- **Load Balancing**: Distribute requests efficiently
+
+[Learn more about Reliability Features](https://portkey.ai/docs/product/ai-gateway/)
+
+
+
+### 4. Metrics
+
+Agent runs are complex. Portkey automatically logs **40+ comprehensive metrics** for your AI agents, including cost, tokens used, latency, etc. Whether you need a broad overview or granular insights into your agent runs, Portkey's customizable filters provide the metrics you need.
+
+
+- Cost per agent interaction
+- Response times and latency
+- Token usage and efficiency
+- Success/failure rates
+- Cache hit rates
+
+<img src="https://github.com/siddharthsambharia-portkey/Portkey-Product-Images/blob/main/Portkey-Dashboard.png?raw=true" width="70%" alt="Portkey Dashboard" />
+
+### 5. Detailed Logging
+Logs are essential for understanding agent behavior, diagnosing issues, and improving performance. They provide a detailed record of agent activities and tool use, which is crucial for debugging and optimizing processes.
+
+
+Access a dedicated section to view records of agent executions, including parameters, outcomes, function calls, and errors. Filter logs based on multiple parameters such as trace ID, model, tokens used, and metadata.
+
+<details>
+  <summary><b>Traces</b></summary>
+  <img src="https://raw.githubusercontent.com/siddharthsambharia-portkey/Portkey-Product-Images/main/Portkey-Traces.png" alt="Portkey Traces" width="70%" />
+</details>
+
+<details>
+  <summary><b>Logs</b></summary>
+  <img src="https://raw.githubusercontent.com/siddharthsambharia-portkey/Portkey-Product-Images/main/Portkey-Logs.png" alt="Portkey Logs" width="70%" />
+</details>
+
+### 6. Enterprise Security Features
+- Set budget limit and rate limts per Virtual Key (disposable API keys)
+- Implement role-based access control
+- Track system changes with audit logs
+- Configure data retention policies
+
+
+
+For detailed information on creating and managing Configs, visit the [Portkey documentation](https://docs.portkey.ai/product/ai-gateway/configs).
+
+## Resources
+
+- [📘 Portkey Documentation](https://docs.portkey.ai)
+- [📊 Portkey Dashboard](https://app.portkey.ai/?utm_source=crewai&utm_medium=crewai&utm_campaign=crewai)
+- [🐦 Twitter](https://twitter.com/portkeyai)
+- [💬 Discord Community](https://discord.gg/DD7vgKK299)
+
+
+
+
+
+
+
+
+

docs/how-to/multimodal-agents.mdx

@@ -0,0 +1,138 @@
+---
+title: Using Multimodal Agents
+description: Learn how to enable and use multimodal capabilities in your agents for processing images and other non-text content within the CrewAI framework.
+icon: image
+---
+
+# Using Multimodal Agents
+
+CrewAI supports multimodal agents that can process both text and non-text content like images. This guide will show you how to enable and use multimodal capabilities in your agents.
+
+## Enabling Multimodal Capabilities
+
+To create a multimodal agent, simply set the `multimodal` parameter to `True` when initializing your agent:
+
+```python
+from crewai import Agent
+
+agent = Agent(
+    role="Image Analyst",
+    goal="Analyze and extract insights from images",
+    backstory="An expert in visual content interpretation with years of experience in image analysis",
+    multimodal=True  # This enables multimodal capabilities
+)
+```
+
+When you set `multimodal=True`, the agent is automatically configured with the necessary tools for handling non-text content, including the `AddImageTool`.
+
+## Working with Images
+
+The multimodal agent comes pre-configured with the `AddImageTool`, which allows it to process images. You don't need to manually add this tool - it's automatically included when you enable multimodal capabilities.
+
+Here's a complete example showing how to use a multimodal agent to analyze an image:
+
+```python
+from crewai import Agent, Task, Crew
+
+# Create a multimodal agent
+image_analyst = Agent(
+    role="Product Analyst",
+    goal="Analyze product images and provide detailed descriptions",
+    backstory="Expert in visual product analysis with deep knowledge of design and features",
+    multimodal=True
+)
+
+# Create a task for image analysis
+task = Task(
+    description="Analyze the product image at https://example.com/product.jpg and provide a detailed description",
+    agent=image_analyst
+)
+
+# Create and run the crew
+crew = Crew(
+    agents=[image_analyst],
+    tasks=[task]
+)
+
+result = crew.kickoff()
+```
+
+### Advanced Usage with Context
+
+You can provide additional context or specific questions about the image when creating tasks for multimodal agents. The task description can include specific aspects you want the agent to focus on:
+
+```python
+from crewai import Agent, Task, Crew
+
+# Create a multimodal agent for detailed analysis
+expert_analyst = Agent(
+    role="Visual Quality Inspector",
+    goal="Perform detailed quality analysis of product images",
+    backstory="Senior quality control expert with expertise in visual inspection",
+    multimodal=True  # AddImageTool is automatically included
+)
+
+# Create a task with specific analysis requirements
+inspection_task = Task(
+    description="""
+    Analyze the product image at https://example.com/product.jpg with focus on:
+    1. Quality of materials
+    2. Manufacturing defects
+    3. Compliance with standards
+    Provide a detailed report highlighting any issues found.
+    """,
+    agent=expert_analyst
+)
+
+# Create and run the crew
+crew = Crew(
+    agents=[expert_analyst],
+    tasks=[inspection_task]
+)
+
+result = crew.kickoff()
+```
+
+### Tool Details
+
+When working with multimodal agents, the `AddImageTool` is automatically configured with the following schema:
+
+```python
+class AddImageToolSchema:
+    image_url: str  # Required: The URL or path of the image to process
+    action: Optional[str] = None  # Optional: Additional context or specific questions about the image
+```
+
+The multimodal agent will automatically handle the image processing through its built-in tools, allowing it to:
+- Access images via URLs or local file paths
+- Process image content with optional context or specific questions
+- Provide analysis and insights based on the visual information and task requirements
+
+## Best Practices
+
+When working with multimodal agents, keep these best practices in mind:
+
+1. **Image Access**
+   - Ensure your images are accessible via URLs that the agent can reach
+   - For local images, consider hosting them temporarily or using absolute file paths
+   - Verify that image URLs are valid and accessible before running tasks
+
+2. **Task Description**
+   - Be specific about what aspects of the image you want the agent to analyze
+   - Include clear questions or requirements in the task description
+   - Consider using the optional `action` parameter for focused analysis
+
+3. **Resource Management**
+   - Image processing may require more computational resources than text-only tasks
+   - Some language models may require base64 encoding for image data
+   - Consider batch processing for multiple images to optimize performance
+
+4. **Environment Setup**
+   - Verify that your environment has the necessary dependencies for image processing
+   - Ensure your language model supports multimodal capabilities
+   - Test with small images first to validate your setup
+
+5. **Error Handling**
+   - Implement proper error handling for image loading failures
+   - Have fallback strategies for when image processing fails
+   - Monitor and log image processing operations for debugging

pyproject.toml

@@ -67,7 +67,6 @@ dev-dependencies = [
     "mkdocs-material-extensions>=1.3.1",
     "pillow>=10.2.0",
     "cairosvg>=2.7.1",
-    "crewai-tools>=0.17.0",
     "pytest>=8.0.0",
     "pytest-vcr>=1.0.2",
     "python-dotenv>=1.0.0",

src/crewai/agent.py

@@ -294,14 +294,7 @@ class Agent(BaseAgent):
             )
 
         if self.crew and self.crew.memory:
-            contextual_memory = ContextualMemory(
-                self.crew.memory_config,
-                self.crew._short_term_memory,
-                self.crew._long_term_memory,
-                self.crew._entity_memory,
-                self.crew._user_memory,
-            )
-            memory = contextual_memory.build_context_for_task(task, context)
+            memory = self.crew.contextual_memory.build_context_for_task(task, context)
             if memory.strip() != "":
                 task_prompt += self.i18n.slice("memory").format(memory=memory)
 

src/crewai/agents/crew_agent_executor.py

@@ -358,9 +358,9 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
             if self.crew is not None and hasattr(self.crew, "_train_iteration"):
                 train_iteration = self.crew._train_iteration
                 if agent_id in training_data and isinstance(train_iteration, int):
-                    training_data[agent_id][train_iteration][
-                        "improved_output"
-                    ] = result.output
+                    training_data[agent_id][train_iteration]["improved_output"] = (
+                        result.output
+                    )
                     training_handler.save(training_data)
                 else:
                     self._printer.print(

src/crewai/cli/tools/main.py

@@ -153,8 +153,12 @@ class ToolCommand(BaseCommand, PlusAPIMixin):
         login_response_json = login_response.json()
 
         settings = Settings()
-        settings.tool_repository_username = login_response_json["credential"]["username"]
-        settings.tool_repository_password = login_response_json["credential"]["password"]
+        settings.tool_repository_username = login_response_json["credential"][
+            "username"
+        ]
+        settings.tool_repository_password = login_response_json["credential"][
+            "password"
+        ]
         settings.dump()
 
         console.print(
@@ -179,7 +183,7 @@ class ToolCommand(BaseCommand, PlusAPIMixin):
             capture_output=False,
             env=self._build_env_with_credentials(repository_handle),
             text=True,
-            check=True
+            check=True,
         )
 
         if add_package_result.stderr:
@@ -204,7 +208,11 @@ class ToolCommand(BaseCommand, PlusAPIMixin):
         settings = Settings()
 
         env = os.environ.copy()
-        env[f"UV_INDEX_{repository_handle}_USERNAME"] = str(settings.tool_repository_username or "")
-        env[f"UV_INDEX_{repository_handle}_PASSWORD"] = str(settings.tool_repository_password or "")
+        env[f"UV_INDEX_{repository_handle}_USERNAME"] = str(
+            settings.tool_repository_username or ""
+        )
+        env[f"UV_INDEX_{repository_handle}_PASSWORD"] = str(
+            settings.tool_repository_password or ""
+        )
 
         return env

src/crewai/crew.py

@@ -25,6 +25,7 @@ from crewai.crews.crew_output import CrewOutput
 from crewai.knowledge.knowledge import Knowledge
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
 from crewai.llm import LLM
+from crewai.memory.contextual.contextual_memory import ContextualMemory
 from crewai.memory.entity.entity_memory import EntityMemory
 from crewai.memory.long_term.long_term_memory import LongTermMemory
 from crewai.memory.short_term.short_term_memory import ShortTermMemory
@@ -278,6 +279,13 @@ class Crew(BaseModel):
                 )
             else:
                 self._user_memory = None
+            self.contextual_memory = ContextualMemory(
+                memory_config=self.memory_config,
+                stm=self._short_term_memory,
+                ltm=self._long_term_memory,
+                em=self._entity_memory,
+                um=self._user_memory,
+            )
         return self
 
     @model_validator(mode="after")

src/crewai/knowledge/knowledge.py

@@ -14,13 +14,13 @@ class Knowledge(BaseModel):
     Knowledge is a collection of sources and setup for the vector store to save and query relevant context.
     Args:
         sources: List[BaseKnowledgeSource] = Field(default_factory=list)
-        storage: KnowledgeStorage = Field(default_factory=KnowledgeStorage)
+        storage: Optional[KnowledgeStorage] = Field(default=None)
         embedder_config: Optional[Dict[str, Any]] = None
     """
 
     sources: List[BaseKnowledgeSource] = Field(default_factory=list)
     model_config = ConfigDict(arbitrary_types_allowed=True)
-    storage: KnowledgeStorage = Field(default_factory=KnowledgeStorage)
+    storage: Optional[KnowledgeStorage] = Field(default=None)
     embedder_config: Optional[Dict[str, Any]] = None
     collection_name: Optional[str] = None
 
@@ -49,8 +49,13 @@ class Knowledge(BaseModel):
         """
         Query across all knowledge sources to find the most relevant information.
         Returns the top_k most relevant chunks.
+        
+        Raises:
+            ValueError: If storage is not initialized.
         """
-
+        if self.storage is None:
+            raise ValueError("Storage is not initialized.")
+            
         results = self.storage.search(
             query,
             limit,

src/crewai/knowledge/source/base_file_knowledge_source.py

@@ -22,7 +22,7 @@ class BaseFileKnowledgeSource(BaseKnowledgeSource, ABC):
         default_factory=list, description="The path to the file"
     )
     content: Dict[Path, str] = Field(init=False, default_factory=dict)
-    storage: KnowledgeStorage = Field(default_factory=KnowledgeStorage)
+    storage: Optional[KnowledgeStorage] = Field(default=None)
     safe_file_paths: List[Path] = Field(default_factory=list)
 
     @field_validator("file_path", "file_paths", mode="before")
@@ -62,7 +62,10 @@ class BaseFileKnowledgeSource(BaseKnowledgeSource, ABC):
 
     def _save_documents(self):
         """Save the documents to the storage."""
-        self.storage.save(self.chunks)
+        if self.storage:
+            self.storage.save(self.chunks)
+        else:
+            raise ValueError("No storage found to save documents.")
 
     def convert_to_path(self, path: Union[Path, str]) -> Path:
         """Convert a path to a Path object."""

src/crewai/knowledge/source/base_knowledge_source.py

@@ -16,7 +16,7 @@ class BaseKnowledgeSource(BaseModel, ABC):
     chunk_embeddings: List[np.ndarray] = Field(default_factory=list)
 
     model_config = ConfigDict(arbitrary_types_allowed=True)
-    storage: KnowledgeStorage = Field(default_factory=KnowledgeStorage)
+    storage: Optional[KnowledgeStorage] = Field(default=None)
     metadata: Dict[str, Any] = Field(default_factory=dict)  # Currently unused
     collection_name: Optional[str] = Field(default=None)
 
@@ -46,4 +46,7 @@ class BaseKnowledgeSource(BaseModel, ABC):
         Save the documents to the storage.
         This method should be called after the chunks and embeddings are generated.
         """
-        self.storage.save(self.chunks)
+        if self.storage:
+            self.storage.save(self.chunks)
+        else:
+            raise ValueError("No storage found to save documents.")

src/crewai/memory/contextual/contextual_memory.py

@@ -1,4 +1,5 @@
 from typing import Any, Dict, Optional
+from crewai.task import Task
 
 from crewai.memory import EntityMemory, LongTermMemory, ShortTermMemory, UserMemory
 
@@ -10,7 +11,7 @@ class ContextualMemory:
         stm: ShortTermMemory,
         ltm: LongTermMemory,
         em: EntityMemory,
-        um: UserMemory,
+        um: Optional[UserMemory],
     ):
         if memory_config is not None:
             self.memory_provider = memory_config.get("provider")
@@ -21,7 +22,7 @@ class ContextualMemory:
         self.em = em
         self.um = um
 
-    def build_context_for_task(self, task, context) -> str:
+    def build_context_for_task(self, task: Task, context: str) -> str:
         """
         Automatically builds a minimal, highly relevant set of contextual information
         for a given task.
@@ -39,7 +40,7 @@ class ContextualMemory:
             context.append(self._fetch_user_context(query))
         return "\n".join(filter(None, context))
 
-    def _fetch_stm_context(self, query) -> str:
+    def _fetch_stm_context(self, query: str) -> str:
         """
         Fetches recent relevant insights from STM related to the task's description and expected_output,
         formatted as bullet points.
@@ -53,7 +54,7 @@ class ContextualMemory:
         )
         return f"Recent Insights:\n{formatted_results}" if stm_results else ""
 
-    def _fetch_ltm_context(self, task) -> Optional[str]:
+    def _fetch_ltm_context(self, task: str) -> Optional[str]:
         """
         Fetches historical data or insights from LTM that are relevant to the task's description and expected_output,
         formatted as bullet points.
@@ -72,7 +73,7 @@ class ContextualMemory:
 
         return f"Historical Data:\n{formatted_results}" if ltm_results else ""
 
-    def _fetch_entity_context(self, query) -> str:
+    def _fetch_entity_context(self, query: str) -> str:
         """
         Fetches relevant entity information from Entity Memory related to the task's description and expected_output,
         formatted as bullet points.
@@ -94,6 +95,8 @@ class ContextualMemory:
         Returns:
             str: Formatted user memories as bullet points, or an empty string if none found.
         """
+        if not self.um:
+            return ""
         user_memories = self.um.search(query)
         if not user_memories:
             return ""

src/crewai/memory/entity/entity_memory.py

@@ -11,7 +11,7 @@ class EntityMemory(Memory):
     """
 
     def __init__(self, crew=None, embedder_config=None, storage=None, path=None):
-        if hasattr(crew, "memory_config") and crew.memory_config is not None:
+        if crew and hasattr(crew, "memory_config") and crew.memory_config is not None:
             self.memory_provider = crew.memory_config.get("provider")
         else:
             self.memory_provider = None

src/crewai/memory/long_term/long_term_memory.py

@@ -15,8 +15,17 @@ class LongTermMemory(Memory):
     """
 
     def __init__(self, storage=None, path=None):
+        """Initialize long term memory.
+
+        Args:
+            storage: Optional custom storage instance
+            path: Optional custom path for storage location
+
+        Note:
+            If both storage and path are provided, storage takes precedence
+        """
         if not storage:
-            storage = LTMSQLiteStorage(db_path=path) if path else LTMSQLiteStorage()
+            storage = LTMSQLiteStorage(storage_path=path) if path else LTMSQLiteStorage()
         super().__init__(storage)
 
     def save(self, item: LongTermMemoryItem) -> None:  # type: ignore # BUG?: Signature of "save" incompatible with supertype "Memory"

src/crewai/memory/short_term/short_term_memory.py

@@ -15,7 +15,7 @@ class ShortTermMemory(Memory):
     """
 
     def __init__(self, crew=None, embedder_config=None, storage=None, path=None):
-        if hasattr(crew, "memory_config") and crew.memory_config is not None:
+        if crew and hasattr(crew, "memory_config") and crew.memory_config is not None:
             self.memory_provider = crew.memory_config.get("provider")
         else:
             self.memory_provider = None

src/crewai/memory/storage/base_rag_storage.py

@@ -1,5 +1,11 @@
 from abc import ABC, abstractmethod
-from typing import Any, Dict, List, Optional
+from pathlib import Path
+import os
+from typing import Any, Dict, List, Optional, TypeVar
+from abc import ABC, abstractmethod
+from pathlib import Path
+
+from crewai.utilities.paths import get_default_storage_path
 
 
 class BaseRAGStorage(ABC):
@@ -12,17 +18,46 @@ class BaseRAGStorage(ABC):
     def __init__(
         self,
         type: str,
+        storage_path: Optional[Path] = None,
         allow_reset: bool = True,
         embedder_config: Optional[Any] = None,
         crew: Any = None,
-    ):
+    ) -> None:
+        """Initialize the BaseRAGStorage.
+
+        Args:
+            type: Type of storage being used
+            storage_path: Optional custom path for storage location
+            allow_reset: Whether storage can be reset
+            embedder_config: Optional configuration for the embedder
+            crew: Optional crew instance this storage belongs to
+        
+        Raises:
+            PermissionError: If storage path is not writable
+            OSError: If storage path cannot be created
+        """
         self.type = type
+        self.storage_path = storage_path if storage_path else get_default_storage_path('rag')
+        
+        # Validate storage path
+        try:
+            self.storage_path.parent.mkdir(parents=True, exist_ok=True)
+            if not os.access(self.storage_path.parent, os.W_OK):
+                raise PermissionError(f"No write permission for storage path: {self.storage_path}")
+        except OSError as e:
+            raise OSError(f"Failed to initialize storage path: {str(e)}")
+            
         self.allow_reset = allow_reset
         self.embedder_config = embedder_config
         self.crew = crew
         self.agents = self._initialize_agents()
 
     def _initialize_agents(self) -> str:
+        """Initialize agent identifiers for storage.
+        
+        Returns:
+            str: Underscore-joined string of sanitized agent role names
+        """
         if self.crew:
             return "_".join(
                 [self._sanitize_role(agent.role) for agent in self.crew.agents]
@@ -31,12 +66,27 @@ class BaseRAGStorage(ABC):
 
     @abstractmethod
     def _sanitize_role(self, role: str) -> str:
-        """Sanitizes agent roles to ensure valid directory names."""
+        """Sanitizes agent roles to ensure valid directory names.
+        
+        Args:
+            role: The agent role name to sanitize
+            
+        Returns:
+            str: Sanitized role name safe for use in paths
+        """
         pass
 
     @abstractmethod
     def save(self, value: Any, metadata: Dict[str, Any]) -> None:
-        """Save a value with metadata to the storage."""
+        """Save a value with metadata to the storage.
+        
+        Args:
+            value: The value to store
+            metadata: Additional metadata to store with the value
+            
+        Raises:
+            OSError: If there is an error writing to storage
+        """
         pass
 
     @abstractmethod
@@ -46,25 +96,55 @@ class BaseRAGStorage(ABC):
         limit: int = 3,
         filter: Optional[dict] = None,
         score_threshold: float = 0.35,
-    ) -> List[Any]:
-        """Search for entries in the storage."""
+    ) -> List[Dict[str, Any]]:
+        """Search for entries in the storage.
+        
+        Args:
+            query: The search query string
+            limit: Maximum number of results to return
+            filter: Optional filter criteria
+            score_threshold: Minimum similarity score threshold
+            
+        Returns:
+            List[Dict[str, Any]]: List of matching entries with their metadata
+        """
         pass
 
     @abstractmethod
     def reset(self) -> None:
-        """Reset the storage."""
+        """Reset the storage.
+        
+        Raises:
+            OSError: If there is an error clearing storage
+            PermissionError: If reset is not allowed
+        """
         pass
 
     @abstractmethod
     def _generate_embedding(
         self, text: str, metadata: Optional[Dict[str, Any]] = None
-    ) -> Any:
-        """Generate an embedding for the given text and metadata."""
+    ) -> List[float]:
+        """Generate an embedding for the given text and metadata.
+        
+        Args:
+            text: Text to generate embedding for
+            metadata: Optional metadata to include in embedding
+            
+        Returns:
+            List[float]: Vector embedding of the text
+            
+        Raises:
+            ValueError: If text is empty or invalid
+        """
         pass
 
     @abstractmethod
-    def _initialize_app(self):
-        """Initialize the vector db."""
+    def _initialize_app(self) -> None:
+        """Initialize the vector db.
+        
+        Raises:
+            OSError: If vector db initialization fails
+        """
         pass
 
     def setup_config(self, config: Dict[str, Any]):

src/crewai/memory/storage/kickoff_task_outputs_storage.py

@@ -1,11 +1,13 @@
 import json
+import os
 import sqlite3
+from pathlib import Path
 from typing import Any, Dict, List, Optional
 
 from crewai.task import Task
 from crewai.utilities import Printer
 from crewai.utilities.crew_json_encoder import CrewJSONEncoder
-from crewai.utilities.paths import db_storage_path
+from crewai.utilities.paths import get_default_storage_path
 
 
 class KickoffTaskOutputsSQLiteStorage:
@@ -13,10 +15,26 @@ class KickoffTaskOutputsSQLiteStorage:
     An updated SQLite storage class for kickoff task outputs storage.
     """
 
-    def __init__(
-        self, db_path: str = f"{db_storage_path()}/latest_kickoff_task_outputs.db"
-    ) -> None:
-        self.db_path = db_path
+    def __init__(self, storage_path: Optional[Path] = None) -> None:
+        """Initialize kickoff task outputs storage.
+        
+        Args:
+            storage_path: Optional custom path for storage location
+            
+        Raises:
+            PermissionError: If storage path is not writable
+            OSError: If storage path cannot be created
+        """
+        self.storage_path = storage_path if storage_path else get_default_storage_path('kickoff')
+        
+        # Validate storage path
+        try:
+            self.storage_path.parent.mkdir(parents=True, exist_ok=True)
+            if not os.access(self.storage_path.parent, os.W_OK):
+                raise PermissionError(f"No write permission for storage path: {self.storage_path}")
+        except OSError as e:
+            raise OSError(f"Failed to initialize storage path: {str(e)}")
+            
         self._printer: Printer = Printer()
         self._initialize_db()
 
@@ -25,7 +43,7 @@ class KickoffTaskOutputsSQLiteStorage:
         Initializes the SQLite database and creates LTM table
         """
         try:
-            with sqlite3.connect(self.db_path) as conn:
+            with sqlite3.connect(str(self.storage_path)) as conn:
                 cursor = conn.cursor()
                 cursor.execute(
                     """
@@ -55,9 +73,21 @@ class KickoffTaskOutputsSQLiteStorage:
         task_index: int,
         was_replayed: bool = False,
         inputs: Dict[str, Any] = {},
-    ):
+    ) -> None:
+        """Add a task output to storage.
+        
+        Args:
+            task: The task whose output is being stored
+            output: The output data from the task
+            task_index: Index of this task in the sequence
+            was_replayed: Whether this was from a replay
+            inputs: Optional input data that led to this output
+            
+        Raises:
+            sqlite3.Error: If there is an error saving to database
+        """
         try:
-            with sqlite3.connect(self.db_path) as conn:
+            with sqlite3.connect(str(self.storage_path)) as conn:
                 cursor = conn.cursor()
                 cursor.execute(
                     """
@@ -90,7 +120,7 @@ class KickoffTaskOutputsSQLiteStorage:
         Updates an existing row in the latest_kickoff_task_outputs table based on task_index.
         """
         try:
-            with sqlite3.connect(self.db_path) as conn:
+            with sqlite3.connect(str(self.storage_path)) as conn:
                 cursor = conn.cursor()
 
                 fields = []
@@ -119,7 +149,7 @@ class KickoffTaskOutputsSQLiteStorage:
 
     def load(self) -> Optional[List[Dict[str, Any]]]:
         try:
-            with sqlite3.connect(self.db_path) as conn:
+            with sqlite3.connect(str(self.storage_path)) as conn:
                 cursor = conn.cursor()
                 cursor.execute("""
                 SELECT *
@@ -155,7 +185,7 @@ class KickoffTaskOutputsSQLiteStorage:
         Deletes all rows from the latest_kickoff_task_outputs table.
         """
         try:
-            with sqlite3.connect(self.db_path) as conn:
+            with sqlite3.connect(str(self.storage_path)) as conn:
                 cursor = conn.cursor()
                 cursor.execute("DELETE FROM latest_kickoff_task_outputs")
                 conn.commit()

src/crewai/memory/storage/ltm_sqlite_storage.py

@@ -1,9 +1,11 @@
 import json
+import os
 import sqlite3
+from pathlib import Path
 from typing import Any, Dict, List, Optional, Union
 
 from crewai.utilities import Printer
-from crewai.utilities.paths import db_storage_path
+from crewai.utilities.paths import get_default_storage_path
 
 
 class LTMSQLiteStorage:
@@ -11,10 +13,26 @@ class LTMSQLiteStorage:
     An updated SQLite storage class for LTM data storage.
     """
 
-    def __init__(
-        self, db_path: str = f"{db_storage_path()}/long_term_memory_storage.db"
-    ) -> None:
-        self.db_path = db_path
+    def __init__(self, storage_path: Optional[Path] = None) -> None:
+        """Initialize LTM SQLite storage.
+        
+        Args:
+            storage_path: Optional custom path for storage location
+            
+        Raises:
+            PermissionError: If storage path is not writable
+            OSError: If storage path cannot be created
+        """
+        self.storage_path = storage_path if storage_path else get_default_storage_path('ltm')
+        
+        # Validate storage path
+        try:
+            self.storage_path.parent.mkdir(parents=True, exist_ok=True)
+            if not os.access(self.storage_path.parent, os.W_OK):
+                raise PermissionError(f"No write permission for storage path: {self.storage_path}")
+        except OSError as e:
+            raise OSError(f"Failed to initialize storage path: {str(e)}")
+            
         self._printer: Printer = Printer()
         self._initialize_db()
 
@@ -23,7 +41,7 @@ class LTMSQLiteStorage:
         Initializes the SQLite database and creates LTM table
         """
         try:
-            with sqlite3.connect(self.db_path) as conn:
+            with sqlite3.connect(str(self.storage_path)) as conn:
                 cursor = conn.cursor()
                 cursor.execute(
                     """
@@ -51,9 +69,20 @@ class LTMSQLiteStorage:
         datetime: str,
         score: Union[int, float],
     ) -> None:
+        """Save a memory entry to long-term memory.
+        
+        Args:
+            task_description: Description of the task this memory relates to
+            metadata: Additional data to store with the memory
+            datetime: Timestamp for when this memory was created
+            score: Relevance score for this memory (higher is more relevant)
+            
+        Raises:
+            sqlite3.Error: If there is an error saving to the database
+        """
         """Saves data to the LTM table with error handling."""
         try:
-            with sqlite3.connect(self.db_path) as conn:
+            with sqlite3.connect(str(self.storage_path)) as conn:
                 cursor = conn.cursor()
                 cursor.execute(
                     """
@@ -74,7 +103,7 @@ class LTMSQLiteStorage:
     ) -> Optional[List[Dict[str, Any]]]:
         """Queries the LTM table by task description with error handling."""
         try:
-            with sqlite3.connect(self.db_path) as conn:
+            with sqlite3.connect(str(self.storage_path)) as conn:
                 cursor = conn.cursor()
                 cursor.execute(
                     f"""
@@ -109,7 +138,7 @@ class LTMSQLiteStorage:
     ) -> None:
         """Resets the LTM table with error handling."""
         try:
-            with sqlite3.connect(self.db_path) as conn:
+            with sqlite3.connect(str(self.storage_path)) as conn:
                 cursor = conn.cursor()
                 cursor.execute("DELETE FROM long_term_memories")
                 conn.commit()

src/crewai/memory/storage/mem0_storage.py

@@ -19,7 +19,7 @@ class Mem0Storage(Storage):
 
         self.memory_type = type
         self.crew = crew
-        self.memory_config = crew.memory_config
+        self.memory_config = crew.memory_config if crew else None
 
         # User ID is required for user memory type "user" since it's used as a unique identifier for the user.
         user_id = self._get_user_id()
@@ -27,9 +27,10 @@ class Mem0Storage(Storage):
             raise ValueError("User ID is required for user memory type")
 
         # API key in memory config overrides the environment variable
-        mem0_api_key = self.memory_config.get("config", {}).get("api_key") or os.getenv(
-            "MEM0_API_KEY"
-        )
+        if self.memory_config and self.memory_config.get("config"):
+            mem0_api_key = self.memory_config.get("config").get("api_key")
+        else:
+            mem0_api_key = os.getenv("MEM0_API_KEY")
         self.memory = MemoryClient(api_key=mem0_api_key)
 
     def _sanitize_role(self, role: str) -> str:

src/crewai/memory/storage/rag_storage.py

@@ -11,7 +11,6 @@ from chromadb.api import ClientAPI
 from crewai.memory.storage.base_rag_storage import BaseRAGStorage
 from crewai.utilities import EmbeddingConfigurator
 from crewai.utilities.constants import MAX_FILE_NAME_LENGTH
-from crewai.utilities.paths import db_storage_path
 
 
 @contextlib.contextmanager
@@ -40,9 +39,15 @@ class RAGStorage(BaseRAGStorage):
     app: ClientAPI | None = None
 
     def __init__(
-        self, type, allow_reset=True, embedder_config=None, crew=None, path=None
+        self,
+        type,
+        storage_path=None,
+        allow_reset=True,
+        embedder_config=None,
+        crew=None,
+        path=None,
     ):
-        super().__init__(type, allow_reset, embedder_config, crew)
+        super().__init__(type, storage_path, allow_reset, embedder_config, crew)
         agents = crew.agents if crew else []
         agents = [self._sanitize_role(agent.role) for agent in agents]
         agents = "_".join(agents)
@@ -90,7 +95,7 @@ class RAGStorage(BaseRAGStorage):
         """
         Ensures file name does not exceed max allowed by OS
         """
-        base_path = f"{db_storage_path()}/{type}"
+        base_path = f"{self.storage_path}/{type}"
 
         if len(file_name) > MAX_FILE_NAME_LENGTH:
             logging.warning(
@@ -152,7 +157,7 @@ class RAGStorage(BaseRAGStorage):
         try:
             if self.app:
                 self.app.reset()
-                shutil.rmtree(f"{db_storage_path()}/{self.type}")
+                shutil.rmtree(f"{self.storage_path}/{self.type}")
                 self.app = None
                 self.collection = None
         except Exception as e:

src/crewai/project/annotations.py

@@ -66,7 +66,6 @@ def cache_handler(func):
 
 
 def crew(func) -> Callable[..., Crew]:
-
     @wraps(func)
     def wrapper(self, *args, **kwargs) -> Crew:
         instantiated_tasks = []

src/crewai/project/crew_base.py

@@ -216,5 +216,5 @@ def CrewBase(cls: T) -> T:
     # Include base class (qual)name in the wrapper class (qual)name.
     WrappedClass.__name__ = CrewBase.__name__ + "(" + cls.__name__ + ")"
     WrappedClass.__qualname__ = CrewBase.__qualname__ + "(" + cls.__name__ + ")"
-  
+
     return cast(T, WrappedClass)

src/crewai/task.py

@@ -373,7 +373,9 @@ class Task(BaseModel):
             content = (
                 json_output
                 if json_output
-                else pydantic_output.model_dump_json() if pydantic_output else result
+                else pydantic_output.model_dump_json()
+                if pydantic_output
+                else result
             )
             self._save_file(content)
 

src/crewai/utilities/embedding_configurator.py

@@ -27,7 +27,7 @@ class EmbeddingConfigurator:
         if embedder_config is None:
             return self._create_default_embedding_function()
 
-        provider = embedder_config.get("provider")
+        provider = embedder_config.get("provider", "")
         config = embedder_config.get("config", {})
         model_name = config.get("model")
 
@@ -38,12 +38,13 @@ class EmbeddingConfigurator:
             except Exception as e:
                 raise ValueError(f"Invalid custom embedding function: {str(e)}")
 
-        if provider not in self.embedding_functions:
+        embedding_function = self.embedding_functions.get(provider, None)
+        if not embedding_function:
             raise Exception(
                 f"Unsupported embedding provider: {provider}, supported providers: {list(self.embedding_functions.keys())}"
             )
 
-        return self.embedding_functions[provider](config, model_name)
+        return embedding_function(config, model_name)
 
     @staticmethod
     def _create_default_embedding_function():

src/crewai/utilities/paths.py

@@ -22,3 +22,26 @@ def get_project_directory_name():
         cwd = Path.cwd()
         project_directory_name = cwd.name
         return project_directory_name
+
+def get_default_storage_path(storage_type: str) -> Path:
+    """Returns the default storage path for a given storage type.
+    
+    Args:
+        storage_type: Type of storage ('ltm', 'kickoff', 'rag')
+        
+    Returns:
+        Path: Default storage path for the specified type
+        
+    Raises:
+        ValueError: If storage_type is not recognized
+    """
+    base_path = db_storage_path()
+    
+    if storage_type == 'ltm':
+        return base_path / 'latest_long_term_memories.db'
+    elif storage_type == 'kickoff':
+        return base_path / 'latest_kickoff_task_outputs.db'
+    elif storage_type == 'rag':
+        return base_path
+    else:
+        raise ValueError(f"Unknown storage type: {storage_type}")

tests/cli/tools/test_main.py

@@ -28,9 +28,10 @@ def test_create_success(mock_subprocess):
     with in_temp_dir():
         tool_command = ToolCommand()
 
-        with patch.object(tool_command, "login") as mock_login, patch(
-            "sys.stdout", new=StringIO()
-        ) as fake_out:
+        with (
+            patch.object(tool_command, "login") as mock_login,
+            patch("sys.stdout", new=StringIO()) as fake_out,
+        ):
             tool_command.create("test-tool")
             output = fake_out.getvalue()
 
@@ -82,7 +83,7 @@ def test_install_success(mock_get, mock_subprocess_run):
         capture_output=False,
         text=True,
         check=True,
-        env=unittest.mock.ANY
+        env=unittest.mock.ANY,
     )
 
     assert "Successfully installed sample-tool" in output

tests/memory/test_storage_paths.py

@@ -0,0 +1,83 @@
+import os
+import tempfile
+from pathlib import Path
+import pytest
+from unittest.mock import patch
+
+from crewai.memory.storage.ltm_sqlite_storage import LTMSQLiteStorage
+from crewai.memory.storage.kickoff_task_outputs_storage import KickoffTaskOutputsSQLiteStorage
+from crewai.memory.storage.base_rag_storage import BaseRAGStorage
+from crewai.utilities.paths import get_default_storage_path
+
+class MockRAGStorage(BaseRAGStorage):
+    """Mock implementation of BaseRAGStorage for testing."""
+    def _sanitize_role(self, role: str) -> str:
+        return role.lower()
+    
+    def save(self, value, metadata):
+        pass
+    
+    def search(self, query, limit=3, filter=None, score_threshold=0.35):
+        return []
+    
+    def reset(self):
+        pass
+    
+    def _generate_embedding(self, text, metadata=None):
+        return []
+    
+    def _initialize_app(self):
+        pass
+
+def test_default_storage_paths():
+    """Test that default storage paths are created correctly."""
+    ltm_path = get_default_storage_path('ltm')
+    kickoff_path = get_default_storage_path('kickoff')
+    rag_path = get_default_storage_path('rag')
+    
+    assert str(ltm_path).endswith('latest_long_term_memories.db')
+    assert str(kickoff_path).endswith('latest_kickoff_task_outputs.db')
+    assert isinstance(rag_path, Path)
+
+def test_custom_storage_paths():
+    """Test that custom storage paths are respected."""
+    with tempfile.TemporaryDirectory() as temp_dir:
+        custom_path = Path(temp_dir) / 'custom.db'
+        
+        ltm = LTMSQLiteStorage(storage_path=custom_path)
+        assert ltm.storage_path == custom_path
+        
+        kickoff = KickoffTaskOutputsSQLiteStorage(storage_path=custom_path)
+        assert kickoff.storage_path == custom_path
+        
+        rag = MockRAGStorage('test', storage_path=custom_path)
+        assert rag.storage_path == custom_path
+
+def test_directory_creation():
+    """Test that storage directories are created automatically."""
+    with tempfile.TemporaryDirectory() as temp_dir:
+        test_dir = Path(temp_dir) / 'test_storage'
+        storage_path = test_dir / 'test.db'
+        
+        assert not test_dir.exists()
+        LTMSQLiteStorage(storage_path=storage_path)
+        assert test_dir.exists()
+
+def test_permission_error():
+    """Test that permission errors are handled correctly."""
+    with tempfile.TemporaryDirectory() as temp_dir:
+        test_dir = Path(temp_dir) / 'readonly'
+        test_dir.mkdir()
+        os.chmod(test_dir, 0o444)  # Read-only
+        
+        storage_path = test_dir / 'test.db'
+        with pytest.raises((PermissionError, OSError)) as exc_info:
+            LTMSQLiteStorage(storage_path=storage_path)
+        # Verify that the error message mentions permission
+        assert "permission" in str(exc_info.value).lower()
+
+def test_invalid_path():
+    """Test that invalid paths raise appropriate errors."""
+    with pytest.raises(OSError):
+        # Try to create storage in a non-existent root directory
+        LTMSQLiteStorage(storage_path=Path('/nonexistent/dir/test.db'))

uv.lock

@@ -1,10 +1,18 @@
 version = 1
 requires-python = ">=3.10, <3.13"
 resolution-markers = [
-    "python_full_version < '3.11'",
-    "python_full_version == '3.11.*'",
-    "python_full_version >= '3.12' and python_full_version < '3.12.4'",
-    "python_full_version >= '3.12.4'",
+    "python_full_version < '3.11' and sys_platform == 'darwin'",
+    "python_full_version < '3.11' and platform_machine == 'aarch64' and sys_platform == 'linux'",
+    "(python_full_version < '3.11' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version < '3.11' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "python_full_version == '3.11.*' and sys_platform == 'darwin'",
+    "python_full_version == '3.11.*' and platform_machine == 'aarch64' and sys_platform == 'linux'",
+    "(python_full_version == '3.11.*' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version == '3.11.*' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "python_full_version >= '3.12' and python_full_version < '3.12.4' and sys_platform == 'darwin'",
+    "python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine == 'aarch64' and sys_platform == 'linux'",
+    "(python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version >= '3.12' and python_full_version < '3.12.4' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "python_full_version >= '3.12.4' and sys_platform == 'darwin'",
+    "python_full_version >= '3.12.4' and platform_machine == 'aarch64' and sys_platform == 'linux'",
+    "(python_full_version >= '3.12.4' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version >= '3.12.4' and sys_platform != 'darwin' and sys_platform != 'linux')",
 ]
 
 [[package]]
@@ -300,7 +308,7 @@ name = "build"
 version = "1.2.2.post1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "colorama", marker = "os_name == 'nt'" },
+    { name = "colorama", marker = "(os_name == 'nt' and platform_machine != 'aarch64' and sys_platform == 'linux') or (os_name == 'nt' and sys_platform != 'darwin' and sys_platform != 'linux')" },
     { name = "importlib-metadata", marker = "python_full_version < '3.10.2'" },
     { name = "packaging" },
     { name = "pyproject-hooks" },
@@ -535,7 +543,7 @@ name = "click"
 version = "8.1.7"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "colorama", marker = "platform_system == 'Windows'" },
+    { name = "colorama", marker = "sys_platform == 'win32'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/96/d3/f04c7bfcf5c1862a2a5b845c6b2b360488cf47af55dfa79c98f6a6bf98b5/click-8.1.7.tar.gz", hash = "sha256:ca9853ad459e787e2192211578cc907e7594e294c7ccc834310722b41b9ca6de", size = 336121 }
 wheels = [
@@ -642,7 +650,6 @@ tools = [
 [package.dev-dependencies]
 dev = [
     { name = "cairosvg" },
-    { name = "crewai-tools" },
     { name = "mkdocs" },
     { name = "mkdocs-material" },
     { name = "mkdocs-material-extensions" },
@@ -696,7 +703,6 @@ requires-dist = [
 [package.metadata.requires-dev]
 dev = [
     { name = "cairosvg", specifier = ">=2.7.1" },
-    { name = "crewai-tools", specifier = ">=0.17.0" },
     { name = "mkdocs", specifier = ">=1.4.3" },
     { name = "mkdocs-material", specifier = ">=9.5.7" },
     { name = "mkdocs-material-extensions", specifier = ">=1.3.1" },
@@ -2462,7 +2468,7 @@ version = "1.6.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "click" },
-    { name = "colorama", marker = "platform_system == 'Windows'" },
+    { name = "colorama", marker = "sys_platform == 'win32'" },
     { name = "ghp-import" },
     { name = "jinja2" },
     { name = "markdown" },
@@ -2643,7 +2649,7 @@ version = "2.10.2"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "pygments" },
-    { name = "pywin32", marker = "platform_system == 'Windows'" },
+    { name = "pywin32", marker = "sys_platform == 'win32'" },
     { name = "tqdm" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/3a/93/80ac75c20ce54c785648b4ed363c88f148bf22637e10c9863db4fbe73e74/mpire-2.10.2.tar.gz", hash = "sha256:f66a321e93fadff34585a4bfa05e95bd946cf714b442f51c529038eb45773d97", size = 271270 }
@@ -2890,7 +2896,7 @@ name = "nvidia-cudnn-cu12"
 version = "9.1.0.70"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux')" },
+    { name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/9f/fd/713452cd72343f682b1c7b9321e23829f00b842ceaedcda96e742ea0b0b3/nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl", hash = "sha256:165764f44ef8c61fcdfdfdbe769d687e06374059fbb388b6c89ecb0e28793a6f", size = 664752741 },
@@ -2917,9 +2923,9 @@ name = "nvidia-cusolver-cu12"
 version = "11.4.5.107"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux')" },
-    { name = "nvidia-cusparse-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux')" },
-    { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux')" },
+    { name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "nvidia-cusparse-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/bc/1d/8de1e5c67099015c834315e333911273a8c6aaba78923dd1d1e25fc5f217/nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl", hash = "sha256:8a7ec542f0412294b15072fa7dab71d31334014a69f953004ea7a118206fe0dd", size = 124161928 },
@@ -2930,7 +2936,7 @@ name = "nvidia-cusparse-cu12"
 version = "12.1.0.106"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux')" },
+    { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/65/5b/cfaeebf25cd9fdec14338ccb16f6b2c4c7fa9163aefcf057d86b9cc248bb/nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl", hash = "sha256:f3b50f42cf363f86ab21f720998517a659a48131e8d538dc02f8768237bd884c", size = 195958278 },
@@ -3480,7 +3486,7 @@ name = "portalocker"
 version = "2.10.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "pywin32", marker = "platform_system == 'Windows'" },
+    { name = "pywin32", marker = "sys_platform == 'win32'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/ed/d3/c6c64067759e87af98cc668c1cc75171347d0f1577fab7ca3749134e3cd4/portalocker-2.10.1.tar.gz", hash = "sha256:ef1bf844e878ab08aee7e40184156e1151f228f103aa5c6bd0724cc330960f8f", size = 40891 }
 wheels = [
@@ -5022,19 +5028,19 @@ dependencies = [
     { name = "fsspec" },
     { name = "jinja2" },
     { name = "networkx" },
-    { name = "nvidia-cublas-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
-    { name = "nvidia-cuda-cupti-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
-    { name = "nvidia-cuda-nvrtc-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
-    { name = "nvidia-cuda-runtime-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
-    { name = "nvidia-cudnn-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
-    { name = "nvidia-cufft-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
-    { name = "nvidia-curand-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
-    { name = "nvidia-cusolver-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
-    { name = "nvidia-cusparse-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
-    { name = "nvidia-nccl-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
-    { name = "nvidia-nvtx-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
+    { name = "nvidia-cublas-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cuda-cupti-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cuda-nvrtc-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cuda-runtime-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cudnn-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cufft-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-curand-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cusolver-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cusparse-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-nccl-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-nvtx-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
     { name = "sympy" },
-    { name = "triton", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
+    { name = "triton", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
     { name = "typing-extensions" },
 ]
 wheels = [
@@ -5081,7 +5087,7 @@ name = "tqdm"
 version = "4.66.5"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "colorama", marker = "platform_system == 'Windows'" },
+    { name = "colorama", marker = "sys_platform == 'win32'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/58/83/6ba9844a41128c62e810fddddd72473201f3eacde02046066142a2d96cc5/tqdm-4.66.5.tar.gz", hash = "sha256:e1020aef2e5096702d8a025ac7d16b1577279c9d63f8375b63083e9a5f0fcbad", size = 169504 }
 wheels = [
@@ -5124,7 +5130,7 @@ version = "0.27.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "attrs" },
-    { name = "cffi", marker = "implementation_name != 'pypy' and os_name == 'nt'" },
+    { name = "cffi", marker = "(implementation_name != 'pypy' and os_name == 'nt' and platform_machine != 'aarch64' and sys_platform == 'linux') or (implementation_name != 'pypy' and os_name == 'nt' and sys_platform != 'darwin' and sys_platform != 'linux')" },
     { name = "exceptiongroup", marker = "python_full_version < '3.11'" },
     { name = "idna" },
     { name = "outcome" },
@@ -5155,7 +5161,7 @@ name = "triton"
 version = "3.0.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "filelock", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux')" },
+    { name = "filelock", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/45/27/14cc3101409b9b4b9241d2ba7deaa93535a217a211c86c4cc7151fb12181/triton-3.0.0-1-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:e1efef76935b2febc365bfadf74bcb65a6f959a9872e5bddf44cc9e0adce1e1a", size = 209376304 },