preparing new version

Fix threading

.github/workflows/tests.yml

@@ -26,7 +26,7 @@ jobs:
         run: uv python install 3.11.9
 
       - name: Install the project
-        run: uv sync --dev
+        run: uv sync --dev --all-extras
 
       - name: Run tests
-        run: uv run pytest tests
+        run: uv run pytest tests -vv

README.md

@@ -100,7 +100,7 @@ You can now start developing your crew by editing the files in the `src/my_proje
 
 #### Example of a simple crew with a sequential process:
 
-Instatiate your crew:
+Instantiate your crew:
 
 ```shell
 crewai create crew latest-ai-development
@@ -399,7 +399,7 @@ Data collected includes:
 - Roles of agents in a crew
   - Understand high level use cases so we can build better tools, integrations and examples about it
 - Tools names available
-  - Understand out of the publically available tools, which ones are being used the most so we can improve them
+  - Understand out of the publicly available tools, which ones are being used the most so we can improve them
 
 Users can opt-in to Further Telemetry, sharing the complete telemetry data by setting the `share_crew` attribute to `True` on their Crews. Enabling `share_crew` results in the collection of detailed crew and task execution data, including `goal`, `backstory`, `context`, and `output` of tasks. This enables a deeper insight into usage patterns while respecting the user's choice to share.
 

docs/concepts/knowledge.mdx

@@ -0,0 +1,79 @@
+---
+title: Knowledge
+description: Understand what knowledge is in CrewAI and how to effectively use it.
+icon: book
+---
+
+# Using Knowledge in CrewAI
+
+## Introduction
+
+Knowledge in CrewAI serves as a foundational component for enriching AI agents with contextual and relevant information. It enables agents to access and utilize structured data sources during their execution processes, making them more intelligent and responsive.
+
+The Knowledge class in CrewAI provides a powerful way to manage and query knowledge sources for your AI agents. This guide will show you how to implement knowledge management in your CrewAI projects.
+
+## What is Knowledge?
+
+The `Knowledge` class in CrewAI manages various sources that store information, which can be queried and retrieved by AI agents. This modular approach allows you to integrate diverse data formats such as text, PDFs, spreadsheets, and more into your AI workflows.
+
+Additionally, we have specific tools for generate knowledge sources for strings, text files, PDF's, and Spreadsheets. You can expand on any source type by extending the `KnowledgeSource` class.
+
+## Basic Implementation
+
+Here's a simple example of how to use the Knowledge class:
+
+```python
+from crewai import Agent, Task, Crew, Process, LLM
+from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
+
+# Create a knowledge source
+content = "Users name is John. He is 30 years old and lives in San Francisco."
+string_source = StringKnowledgeSource(
+    content=content, metadata={"preference": "personal"}
+)
+
+# Create an agent with the knowledge store
+agent = Agent(
+    role="About User",
+    goal="You know everything about the user.",
+    backstory="""You are a master at understanding people and their preferences.""",
+    verbose=True
+)
+
+task = Task(
+    description="Answer the following questions about the user: {question}",
+    expected_output="An answer to the question.",
+    agent=agent,
+)
+
+crew = Crew(
+    agents=[agent],
+    tasks=[task],
+    verbose=True,
+    process=Process.sequential,
+    knowledge={"sources": [string_source], "metadata": {"preference": "personal"}}, # Enable knowledge by adding the sources here. You can also add more sources to the sources list.
+)
+
+result = crew.kickoff(inputs={"question": "What city does John live in and how old is he?"})
+```
+
+
+## Embedder Configuration
+
+You can also configure the embedder for the knowledge store. This is useful if you want to use a different embedder for the knowledge store than the one used for the agents.
+
+```python
+...
+string_source = StringKnowledgeSource(
+    content="Users name is John. He is 30 years old and lives in San Francisco.",
+    metadata={"preference": "personal"}
+)
+crew = Crew(
+    ...
+    knowledge={
+        "sources": [string_source],
+        "metadata": {"preference": "personal"},
+        "embedder_config": {"provider": "openai", "config": {"model": "text-embedding-3-small"}},
+    },
+)
+```

docs/concepts/llms.mdx

@@ -310,8 +310,8 @@ These are examples of how to configure LLMs for your agent.
     from crewai import LLM
 
     llm = LLM(
-        model="perplexity/mistral-7b-instruct",
-        base_url="https://api.perplexity.ai/v1",
+        model="llama-3.1-sonar-large-128k-online",
+        base_url="https://api.perplexity.ai/",
         api_key="your-api-key-here"
     )
     agent = Agent(llm=llm, ...)
@@ -400,4 +400,4 @@ This is particularly useful when working with OpenAI-compatible APIs or when you
 - **API Errors**: Check your API key, network connection, and rate limits.
 - **Unexpected Outputs**: Refine your prompts and adjust temperature or top_p.
 - **Performance Issues**: Consider using a more powerful model or optimizing your queries.
-- **Timeout Errors**: Increase the `timeout` parameter or optimize your input.
+- **Timeout Errors**: Increase the `timeout` parameter or optimize your input.

docs/how-to/before-and-after-kickoff-hooks.mdx

@@ -0,0 +1,59 @@
+---
+title: Before and After Kickoff Hooks
+description: Learn how to use before and after kickoff hooks in CrewAI
+---
+
+CrewAI provides hooks that allow you to execute code before and after a crew's kickoff. These hooks are useful for preprocessing inputs or post-processing results.
+
+## Before Kickoff Hook
+
+The before kickoff hook is executed before the crew starts its tasks. It receives the input dictionary and can modify it before passing it to the crew. You can use this hook to set up your environment, load necessary data, or preprocess your inputs. This is useful in scenarios where the input data might need enrichment or validation before being processed by the crew.
+
+Here's an example of defining a before kickoff function in your `crew.py`:
+
+```python
+from crewai import CrewBase, before_kickoff
+
+@CrewBase
+class MyCrew:
+    @before_kickoff
+    def prepare_data(self, inputs):
+        # Preprocess or modify inputs
+        inputs['processed'] = True
+        return inputs
+
+#...
+```
+
+In this example, the prepare_data function modifies the inputs by adding a new key-value pair indicating that the inputs have been processed.
+
+## After Kickoff Hook
+
+The after kickoff hook is executed after the crew has completed its tasks. It receives the result object, which contains the outputs of the crew's execution. This hook is ideal for post-processing results, such as logging, data transformation, or further analysis.
+
+Here's how you can define an after kickoff function in your `crew.py`:
+
+```python
+from crewai import CrewBase, after_kickoff
+
+@CrewBase
+class MyCrew:
+    @after_kickoff
+    def log_results(self, result):
+        # Log or modify the results
+        print("Crew execution completed with result:", result)
+        return result
+
+# ...
+```
+
+
+In the `log_results` function, the results of the crew execution are simply printed out. You can extend this to perform more complex operations such as sending notifications or integrating with other services.
+
+## Utilizing Both Hooks
+
+Both hooks can be used together to provide a comprehensive setup and teardown process for your crew's execution. They are particularly useful in maintaining clean code architecture by separating concerns and enhancing the modularity of your CrewAI implementations.
+
+## Conclusion
+
+Before and after kickoff hooks in CrewAI offer powerful ways to interact with the lifecycle of a crew's execution. By understanding and utilizing these hooks, you can greatly enhance the robustness and flexibility of your AI agents.

docs/quickstart.mdx

@@ -8,7 +8,7 @@ icon: rocket
 
 Let's create a simple crew that will help us `research` and `report` on the `latest AI developments` for a given topic or subject.
 
-Before we proceed, make sure you have `crewai` and `crewai-tools` installed. 
+Before we proceed, make sure you have `crewai` and `crewai-tools` installed.
 If you haven't installed them yet, you can do so by following the [installation guide](/installation).
 
 Follow the steps below to get crewing! 🚣‍♂️
@@ -23,7 +23,7 @@ Follow the steps below to get crewing! 🚣‍♂️
       ```
     </CodeGroup>
   </Step>
-  <Step title="Modify your `agents.yaml` file">  
+  <Step title="Modify your `agents.yaml` file">
   <Tip>
   You can also modify the agents as needed to fit your use case or copy and paste as is to your project.
   Any variable interpolated in your `agents.yaml` and `tasks.yaml` files like `{topic}` will be replaced by the value of the variable in the `main.py` file.
@@ -39,7 +39,7 @@ Follow the steps below to get crewing! 🚣‍♂️
         You're a seasoned researcher with a knack for uncovering the latest
         developments in {topic}. Known for your ability to find the most relevant
         information and present it in a clear and concise manner.
-          
+
     reporting_analyst:
       role: >
         {topic} Reporting Analyst
@@ -51,7 +51,7 @@ Follow the steps below to get crewing! 🚣‍♂️
         it easy for others to understand and act on the information you provide.
     ```
   </Step>
-  <Step title="Modify your `tasks.yaml` file">  
+  <Step title="Modify your `tasks.yaml` file">
     ```yaml tasks.yaml
     # src/latest_ai_development/config/tasks.yaml
     research_task:
@@ -73,8 +73,8 @@ Follow the steps below to get crewing! 🚣‍♂️
       agent: reporting_analyst
       output_file: report.md
     ```
-  </Step>   
-  <Step title="Modify your `crew.py` file">  
+  </Step>
+  <Step title="Modify your `crew.py` file">
     ```python crew.py
     # src/latest_ai_development/crew.py
     from crewai import Agent, Crew, Process, Task
@@ -121,10 +121,34 @@ Follow the steps below to get crewing! 🚣‍♂️
           tasks=self.tasks, # Automatically created by the @task decorator
           process=Process.sequential,
           verbose=True,
-        ) 
+        )
     ```
   </Step>
-  <Step title="Feel free to pass custom inputs to your crew"> 
+  <Step title="[Optional] Add before and after crew functions">
+    ```python crew.py
+    # src/latest_ai_development/crew.py
+    from crewai import Agent, Crew, Process, Task
+    from crewai.project import CrewBase, agent, crew, task, before_kickoff, after_kickoff
+    from crewai_tools import SerperDevTool
+
+    @CrewBase
+    class LatestAiDevelopmentCrew():
+      """LatestAiDevelopment crew"""
+
+      @before_kickoff
+      def before_kickoff_function(self, inputs):
+        print(f"Before kickoff function with inputs: {inputs}")
+        return inputs # You can return the inputs or modify them as needed
+
+      @after_kickoff
+      def after_kickoff_function(self, result):
+        print(f"After kickoff function with result: {result}")
+        return result # You can return the result or modify it as needed
+
+      # ... remaining code
+    ```
+  </Step>
+  <Step title="Feel free to pass custom inputs to your crew">
   For example, you can pass the `topic` input to your crew to customize the research and reporting.
     ```python main.py
     #!/usr/bin/env python
@@ -237,14 +261,14 @@ Follow the steps below to get crewing! 🚣‍♂️
 ### Note on Consistency in Naming
 
 The names you use in your YAML files (`agents.yaml` and `tasks.yaml`) should match the method names in your Python code.
-For example, you can reference the agent for specific tasks from `tasks.yaml` file. 
+For example, you can reference the agent for specific tasks from `tasks.yaml` file.
 This naming consistency allows CrewAI to automatically link your configurations with your code; otherwise, your task won't recognize the reference properly.
 
 #### Example References
 
 <Tip>
   Note how we use the same name for the agent in the `agents.yaml` (`email_summarizer`) file as the method name in the `crew.py` (`email_summarizer`) file.
-</Tip>  
+</Tip>
 
 ```yaml agents.yaml
 email_summarizer:
@@ -281,6 +305,8 @@ Use the annotations to properly reference the agent and task in the `crew.py` fi
 * `@task`
 * `@crew`
 * `@tool`
+* `@before_kickoff`
+* `@after_kickoff`
 * `@callback`
 * `@output_json`
 * `@output_pydantic`
@@ -304,7 +330,7 @@ def email_summarizer_task(self) -> Task:
 
 <Tip>
 In addition to the [sequential process](../how-to/sequential-process), you can use the [hierarchical process](../how-to/hierarchical-process),
-which automatically assigns a manager to the defined crew to properly coordinate the planning and execution of tasks through delegation and validation of results. 
+which automatically assigns a manager to the defined crew to properly coordinate the planning and execution of tasks through delegation and validation of results.
 You can learn more about the core concepts [here](/concepts).
 </Tip>
 

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "crewai"
-version = "0.80.0"
+version = "0.83.0"
 description = "Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks."
 readme = "README.md"
 requires-python = ">=3.10,<=3.13"
@@ -29,6 +29,8 @@ dependencies = [
     "tomli-w>=1.1.0",
     "tomli>=2.0.2",
     "chromadb>=0.5.18",
+    "pdfplumber>=0.11.4",
+    "openpyxl>=3.1.5",
 ]
 
 [project.urls]
@@ -39,6 +41,16 @@ Repository = "https://github.com/crewAIInc/crewAI"
 [project.optional-dependencies]
 tools = ["crewai-tools>=0.14.0"]
 agentops = ["agentops>=0.3.0"]
+fastembed = ["fastembed>=0.4.1"]
+pdfplumber = [
+    "pdfplumber>=0.11.4",
+]
+pandas = [
+    "pandas>=2.2.3",
+]
+openpyxl = [
+    "openpyxl>=3.1.5",
+]
 mem0 = ["mem0ai>=0.1.29"]
 
 [tool.uv]

src/crewai/__init__.py

@@ -1,7 +1,9 @@
 import warnings
+
 from crewai.agent import Agent
 from crewai.crew import Crew
 from crewai.flow.flow import Flow
+from crewai.knowledge.knowledge import Knowledge
 from crewai.llm import LLM
 from crewai.pipeline import Pipeline
 from crewai.process import Process
@@ -14,5 +16,15 @@ warnings.filterwarnings(
     category=UserWarning,
     module="pydantic.main",
 )
-__version__ = "0.80.0"
-__all__ = ["Agent", "Crew", "Process", "Task", "Pipeline", "Router", "LLM", "Flow"]
+__version__ = "0.83.0"
+__all__ = [
+    "Agent",
+    "Crew",
+    "Process",
+    "Task",
+    "Pipeline",
+    "Router",
+    "LLM",
+    "Flow",
+    "Knowledge",
+]

src/crewai/agent.py

@@ -11,8 +11,8 @@ from crewai.agents.crew_agent_executor import CrewAgentExecutor
 from crewai.cli.constants import ENV_VARS
 from crewai.llm import LLM
 from crewai.memory.contextual.contextual_memory import ContextualMemory
-from crewai.tools.agent_tools.agent_tools import AgentTools
 from crewai.tools import BaseTool
+from crewai.tools.agent_tools.agent_tools import AgentTools
 from crewai.utilities import Converter, Prompts
 from crewai.utilities.constants import TRAINED_AGENTS_DATA_FILE, TRAINING_DATA_FILE
 from crewai.utilities.token_counter_callback import TokenCalcHandler
@@ -52,6 +52,7 @@ class Agent(BaseAgent):
             role: The role of the agent.
             goal: The objective of the agent.
             backstory: The backstory of the agent.
+            knowledge: The knowledge base of the agent.
             config: Dict representation of agent configuration.
             llm: The language model that will run the agent.
             function_calling_llm: The language model that will handle the tool calling for this agent, it overrides the crew function_calling_llm.
@@ -272,6 +273,18 @@ class Agent(BaseAgent):
             if memory.strip() != "":
                 task_prompt += self.i18n.slice("memory").format(memory=memory)
 
+        # Integrate the knowledge base
+        if self.crew and self.crew.knowledge:
+            knowledge_snippets = self.crew.knowledge.query([task.prompt()])
+            valid_snippets = [
+                result["context"] 
+                for result in knowledge_snippets 
+                if result and result.get("context")
+            ]
+            if valid_snippets:
+                formatted_knowledge = "\n".join(valid_snippets)
+                task_prompt += f"\n\nAdditional Information:\n{formatted_knowledge}"
+
         tools = tools or self.tools or []
         self.create_agent_executor(tools=tools, task=task)
 

src/crewai/cli/cli.py

@@ -136,6 +136,7 @@ def log_tasks_outputs() -> None:
 @click.option("-l", "--long", is_flag=True, help="Reset LONG TERM memory")
 @click.option("-s", "--short", is_flag=True, help="Reset SHORT TERM memory")
 @click.option("-e", "--entities", is_flag=True, help="Reset ENTITIES memory")
+@click.option("-kn", "--knowledge", is_flag=True, help="Reset KNOWLEDGE storage")
 @click.option(
     "-k",
     "--kickoff-outputs",
@@ -143,17 +144,24 @@ def log_tasks_outputs() -> None:
     help="Reset LATEST KICKOFF TASK OUTPUTS",
 )
 @click.option("-a", "--all", is_flag=True, help="Reset ALL memories")
-def reset_memories(long, short, entities, kickoff_outputs, all):
+def reset_memories(
+    long: bool,
+    short: bool,
+    entities: bool,
+    knowledge: bool,
+    kickoff_outputs: bool,
+    all: bool,
+) -> None:
     """
     Reset the crew memories (long, short, entity, latest_crew_kickoff_ouputs). This will delete all the data saved.
     """
     try:
-        if not all and not (long or short or entities or kickoff_outputs):
+        if not all and not (long or short or entities or knowledge or kickoff_outputs):
             click.echo(
                 "Please specify at least one memory type to reset using the appropriate flags."
             )
             return
-        reset_memories_command(long, short, entities, kickoff_outputs, all)
+        reset_memories_command(long, short, entities, knowledge, kickoff_outputs, all)
     except Exception as e:
         click.echo(f"An error occurred while resetting memories: {e}", err=True)
 

src/crewai/cli/reset_memories_command.py

@@ -5,9 +5,17 @@ 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
 from crewai.utilities.task_output_storage_handler import TaskOutputStorageHandler
+from crewai.knowledge.storage.knowledge_storage import KnowledgeStorage
 
 
-def reset_memories_command(long, short, entity, kickoff_outputs, all) -> None:
+def reset_memories_command(
+    long,
+    short,
+    entity,
+    knowledge,
+    kickoff_outputs,
+    all,
+) -> None:
     """
     Reset the crew memories.
 
@@ -17,6 +25,7 @@ def reset_memories_command(long, short, entity, kickoff_outputs, all) -> None:
       entity (bool): Whether to reset the entity memory.
       kickoff_outputs (bool): Whether to reset the latest kickoff task outputs.
       all (bool): Whether to reset all memories.
+      knowledge (bool): Whether to reset the knowledge.
     """
 
     try:
@@ -25,6 +34,7 @@ def reset_memories_command(long, short, entity, kickoff_outputs, all) -> None:
             EntityMemory().reset()
             LongTermMemory().reset()
             TaskOutputStorageHandler().reset()
+            KnowledgeStorage().reset()
             click.echo("All memories have been reset.")
         else:
             if long:
@@ -40,6 +50,9 @@ def reset_memories_command(long, short, entity, kickoff_outputs, all) -> None:
             if kickoff_outputs:
                 TaskOutputStorageHandler().reset()
                 click.echo("Latest Kickoff outputs stored has been reset.")
+            if knowledge:
+                KnowledgeStorage().reset()
+                click.echo("Knowledge has been reset.")
 
     except subprocess.CalledProcessError as e:
         click.echo(f"An error occurred while resetting the memories: {e}", err=True)

src/crewai/cli/templates/crew/crew.py

@@ -1,5 +1,5 @@
 from crewai import Agent, Crew, Process, Task
-from crewai.project import CrewBase, agent, crew, task
+from crewai.project import CrewBase, agent, crew, task, before_kickoff, after_kickoff
 
 # Uncomment the following line to use an example of a custom tool
 # from {{folder_name}}.tools.custom_tool import MyCustomTool
@@ -14,6 +14,18 @@ class {{crew_name}}():
 	agents_config = 'config/agents.yaml'
 	tasks_config = 'config/tasks.yaml'
 
+	@before_kickoff # Optional hook to be executed before the crew starts
+	def pull_data_example(self, inputs):
+		# Example of pulling data from an external API, dynamically changing the inputs
+		inputs['extra_data'] = "This is extra data"
+		return inputs
+
+	@after_kickoff # Optional hook to be executed after the crew has finished
+	def log_results(self, output):
+		# Example of logging results, dynamically changing the output
+		print(f"Results: {output}")
+		return output
+
 	@agent
 	def researcher(self) -> Agent:
 		return Agent(

src/crewai/cli/templates/crew/pyproject.toml

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<=3.13"
 dependencies = [
-    "crewai[tools]>=0.80.0,<1.0.0"
+    "crewai[tools]>=0.83.0,<1.0.0"
 ]
 
 [project.scripts]

src/crewai/cli/templates/flow/pyproject.toml

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<=3.13"
 dependencies = [
-    "crewai[tools]>=0.80.0,<1.0.0",
+    "crewai[tools]>=0.83.0,<1.0.0",
 ]
 
 [project.scripts]

src/crewai/cli/templates/pipeline/pyproject.toml

@@ -6,7 +6,7 @@ authors = ["Your Name <you@example.com>"]
 
 [tool.poetry.dependencies]
 python = ">=3.10,<=3.13"
-crewai = { extras = ["tools"], version = ">=0.80.0,<1.0.0" }
+crewai = { extras = ["tools"], version = ">=0.83.0,<1.0.0" }
 asyncio = "*"
 
 [tool.poetry.scripts]

src/crewai/cli/templates/pipeline_router/pyproject.toml

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = ["Your Name <you@example.com>"]
 requires-python = ">=3.10,<=3.13"
 dependencies = [
-    "crewai[tools]>=0.80.0,<1.0.0"
+    "crewai[tools]>=0.83.0,<1.0.0"
 ]
 
 [project.scripts]

src/crewai/cli/templates/tool/pyproject.toml

@@ -5,6 +5,6 @@ description = "Power up your crews with {{folder_name}}"
 readme = "README.md"
 requires-python = ">=3.10,<=3.13"
 dependencies = [
-    "crewai[tools]>=0.80.0"
+    "crewai[tools]>=0.83.0"
 ]
 

src/crewai/crew.py

@@ -27,6 +27,7 @@ from crewai.llm import LLM
 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
+from crewai.knowledge.knowledge import Knowledge
 from crewai.memory.user.user_memory import UserMemory
 from crewai.process import Process
 from crewai.task import Task
@@ -201,6 +202,10 @@ class Crew(BaseModel):
         default=[],
         description="List of execution logs for tasks",
     )
+    knowledge: Optional[Dict[str, Any]] = Field(
+        default=None, description="Knowledge for the crew. Add knowledge sources to the knowledge object."
+    )
+
 
     @field_validator("id", mode="before")
     @classmethod
@@ -275,6 +280,15 @@ class Crew(BaseModel):
                 self._user_memory = None
         return self
 
+    @model_validator(mode="after")
+    def create_crew_knowledge(self) -> "Crew":
+        if self.knowledge:
+            try:
+                self.knowledge = Knowledge(**self.knowledge) if isinstance(self.knowledge, dict) else self.knowledge
+            except (TypeError, ValueError) as e:
+                raise ValueError(f"Invalid knowledge configuration: {str(e)}")
+        return self
+
     @model_validator(mode="after")
     def check_manager_llm(self):
         """Validates that the language model is set when using hierarchical process."""

src/crewai/knowledge/embedder/base_embedder.py

@@ -0,0 +1,55 @@
+from abc import ABC, abstractmethod
+from typing import List
+
+import numpy as np
+
+
+class BaseEmbedder(ABC):
+    """
+    Abstract base class for text embedding models
+    """
+
+    @abstractmethod
+    def embed_chunks(self, chunks: List[str]) -> np.ndarray:
+        """
+        Generate embeddings for a list of text chunks
+
+        Args:
+            chunks: List of text chunks to embed
+
+        Returns:
+            Array of embeddings
+        """
+        pass
+
+    @abstractmethod
+    def embed_texts(self, texts: List[str]) -> np.ndarray:
+        """
+        Generate embeddings for a list of texts
+
+        Args:
+            texts: List of texts to embed
+
+        Returns:
+            Array of embeddings
+        """
+        pass
+
+    @abstractmethod
+    def embed_text(self, text: str) -> np.ndarray:
+        """
+        Generate embedding for a single text
+
+        Args:
+            text: Text to embed
+
+        Returns:
+            Embedding array
+        """
+        pass
+
+    @property
+    @abstractmethod
+    def dimension(self) -> int:
+        """Get the dimension of the embeddings"""
+        pass

src/crewai/knowledge/embedder/fastembed.py

@@ -0,0 +1,93 @@
+from pathlib import Path
+from typing import List, Optional, Union
+
+import numpy as np
+
+from .base_embedder import BaseEmbedder
+
+try:
+    from fastembed_gpu import TextEmbedding  # type: ignore
+
+    FASTEMBED_AVAILABLE = True
+except ImportError:
+    try:
+        from fastembed import TextEmbedding
+
+        FASTEMBED_AVAILABLE = True
+    except ImportError:
+        FASTEMBED_AVAILABLE = False
+
+
+class FastEmbed(BaseEmbedder):
+    """
+    A wrapper class for text embedding models using FastEmbed
+    """
+
+    def __init__(
+        self,
+        model_name: str = "BAAI/bge-small-en-v1.5",
+        cache_dir: Optional[Union[str, Path]] = None,
+    ):
+        """
+        Initialize the embedding model
+
+        Args:
+            model_name: Name of the model to use
+            cache_dir: Directory to cache the model
+            gpu: Whether to use GPU acceleration
+        """
+        if not FASTEMBED_AVAILABLE:
+            raise ImportError(
+                "FastEmbed is not installed. Please install it with: "
+                "uv pip install fastembed or uv pip install fastembed-gpu for GPU support"
+            )
+
+        self.model = TextEmbedding(
+            model_name=model_name,
+            cache_dir=str(cache_dir) if cache_dir else None,
+        )
+
+    def embed_chunks(self, chunks: List[str]) -> List[np.ndarray]:
+        """
+        Generate embeddings for a list of text chunks
+
+        Args:
+            chunks: List of text chunks to embed
+
+        Returns:
+            List of embeddings
+        """
+        embeddings = list(self.model.embed(chunks))
+        return embeddings
+
+    def embed_texts(self, texts: List[str]) -> List[np.ndarray]:
+        """
+        Generate embeddings for a list of texts
+
+        Args:
+            texts: List of texts to embed
+
+        Returns:
+            List of embeddings
+        """
+        embeddings = list(self.model.embed(texts))
+        return embeddings
+
+    def embed_text(self, text: str) -> np.ndarray:
+        """
+        Generate embedding for a single text
+
+        Args:
+            text: Text to embed
+
+        Returns:
+            Embedding array
+        """
+        return self.embed_texts([text])[0]
+
+    @property
+    def dimension(self) -> int:
+        """Get the dimension of the embeddings"""
+        # Generate a test embedding to get dimensions
+        test_embed = self.embed_text("test")
+        return len(test_embed)

src/crewai/knowledge/knowledge.py

@@ -0,0 +1,54 @@
+import os
+
+from typing import List, Optional, Dict, Any
+from pydantic import BaseModel, ConfigDict, Field
+
+from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
+from crewai.knowledge.storage.knowledge_storage import KnowledgeStorage
+from crewai.utilities.logger import Logger
+from crewai.utilities.constants import DEFAULT_SCORE_THRESHOLD
+os.environ["TOKENIZERS_PARALLELISM"] = "false"  # removes logging from fastembed
+
+
+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)
+        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)
+    embedder_config: Optional[Dict[str, Any]] = None
+
+    def __init__(self, embedder_config: Optional[Dict[str, Any]] = None, **data):
+        super().__init__(**data)
+        self.storage = KnowledgeStorage(embedder_config=embedder_config or None)
+
+        try:
+            for source in self.sources:
+                source.add()
+        except Exception as e:
+            Logger(verbose=True).log(
+                "warning",
+                f"Failed to init knowledge: {e}",
+                color="yellow",
+            )
+
+    def query(
+        self, query: List[str], limit: int = 3, preference: Optional[str] = None
+    ) -> List[Dict[str, Any]]:
+        """
+        Query across all knowledge sources to find the most relevant information.
+        Returns the top_k most relevant chunks.
+        """
+
+        results = self.storage.search(
+            query,
+            limit,
+            filter={"preference": preference} if preference else None,
+            score_threshold=DEFAULT_SCORE_THRESHOLD,
+        )
+        return results

src/crewai/knowledge/source/base_file_knowledge_source.py

@@ -0,0 +1,36 @@
+from pathlib import Path
+from typing import Union, List
+
+from pydantic import Field
+
+from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
+from typing import Dict, Any
+from crewai.knowledge.storage.knowledge_storage import KnowledgeStorage
+
+
+class BaseFileKnowledgeSource(BaseKnowledgeSource):
+    """Base class for knowledge sources that load content from files."""
+
+    file_path: Union[Path, List[Path]] = Field(...)
+    content: Dict[Path, str] = Field(init=False, default_factory=dict)
+    storage: KnowledgeStorage = Field(default_factory=KnowledgeStorage)
+
+    def model_post_init(self, _):
+        """Post-initialization method to load content."""
+        self.content = self.load_content()
+
+    def load_content(self) -> Dict[Path, str]:
+        """Load and preprocess file content. Should be overridden by subclasses."""
+        paths = [self.file_path] if isinstance(self.file_path, Path) else self.file_path
+
+        for path in paths:
+            if not path.exists():
+                raise FileNotFoundError(f"File not found: {path}")
+            if not path.is_file():
+                raise ValueError(f"Path is not a file: {path}")
+        return {}
+
+    def save_documents(self, metadata: Dict[str, Any]):
+        """Save the documents to the storage."""
+        chunk_metadatas = [metadata.copy() for _ in self.chunks]
+        self.storage.save(self.chunks, chunk_metadatas)

src/crewai/knowledge/source/base_knowledge_source.py

@@ -0,0 +1,48 @@
+from abc import ABC, abstractmethod
+from typing import List, Dict, Any
+
+import numpy as np
+from pydantic import BaseModel, ConfigDict, Field
+
+from crewai.knowledge.storage.knowledge_storage import KnowledgeStorage
+
+
+class BaseKnowledgeSource(BaseModel, ABC):
+    """Abstract base class for knowledge sources."""
+
+    chunk_size: int = 4000
+    chunk_overlap: int = 200
+    chunks: List[str] = Field(default_factory=list)
+    chunk_embeddings: List[np.ndarray] = Field(default_factory=list)
+
+    model_config = ConfigDict(arbitrary_types_allowed=True)
+    storage: KnowledgeStorage = Field(default_factory=KnowledgeStorage)
+    metadata: Dict[str, Any] = Field(default_factory=dict)
+
+    @abstractmethod
+    def load_content(self) -> Dict[Any, str]:
+        """Load and preprocess content from the source."""
+        pass
+
+    @abstractmethod
+    def add(self) -> None:
+        """Process content, chunk it, compute embeddings, and save them."""
+        pass
+
+    def get_embeddings(self) -> List[np.ndarray]:
+        """Return the list of embeddings for the chunks."""
+        return self.chunk_embeddings
+
+    def _chunk_text(self, text: str) -> List[str]:
+        """Utility method to split text into chunks."""
+        return [
+            text[i : i + self.chunk_size]
+            for i in range(0, len(text), self.chunk_size - self.chunk_overlap)
+        ]
+
+    def save_documents(self, metadata: Dict[str, Any]):
+        """
+        Save the documents to the storage.
+        This method should be called after the chunks and embeddings are generated.
+        """
+        self.storage.save(self.chunks, metadata)

src/crewai/knowledge/source/csv_knowledge_source.py

@@ -0,0 +1,44 @@
+import csv
+from typing import Dict, List
+from pathlib import Path
+
+from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
+
+
+class CSVKnowledgeSource(BaseFileKnowledgeSource):
+    """A knowledge source that stores and queries CSV file content using embeddings."""
+
+    def load_content(self) -> Dict[Path, str]:
+        """Load and preprocess CSV file content."""
+        super().load_content()  # Validate the file path
+
+        file_path = (
+            self.file_path[0] if isinstance(self.file_path, list) else self.file_path
+        )
+        file_path = Path(file_path) if isinstance(file_path, str) else file_path
+
+        with open(file_path, "r", encoding="utf-8") as csvfile:
+            reader = csv.reader(csvfile)
+            content = ""
+            for row in reader:
+                content += " ".join(row) + "\n"
+        return {file_path: content}
+
+    def add(self) -> None:
+        """
+        Add CSV file content to the knowledge source, chunk it, compute embeddings,
+        and save the embeddings.
+        """
+        content_str = (
+            str(self.content) if isinstance(self.content, dict) else self.content
+        )
+        new_chunks = self._chunk_text(content_str)
+        self.chunks.extend(new_chunks)
+        self.save_documents(metadata=self.metadata)
+
+    def _chunk_text(self, text: str) -> List[str]:
+        """Utility method to split text into chunks."""
+        return [
+            text[i : i + self.chunk_size]
+            for i in range(0, len(text), self.chunk_size - self.chunk_overlap)
+        ]

src/crewai/knowledge/source/excel_knowledge_source.py

@@ -0,0 +1,56 @@
+from typing import Dict, List
+from pathlib import Path
+from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
+
+
+class ExcelKnowledgeSource(BaseFileKnowledgeSource):
+    """A knowledge source that stores and queries Excel file content using embeddings."""
+
+    def load_content(self) -> Dict[Path, str]:
+        """Load and preprocess Excel file content."""
+        super().load_content()  # Validate the file path
+        pd = self._import_dependencies()
+
+        if isinstance(self.file_path, list):
+            file_path = self.file_path[0]
+        else:
+            file_path = self.file_path
+
+        df = pd.read_excel(file_path)
+        content = df.to_csv(index=False)
+        return {file_path: content}
+
+    def _import_dependencies(self):
+        """Dynamically import dependencies."""
+        try:
+            import openpyxl  # noqa
+            import pandas as pd
+
+            return pd
+        except ImportError as e:
+            missing_package = str(e).split()[-1]
+            raise ImportError(
+                f"{missing_package} is not installed. Please install it with: pip install {missing_package}"
+            )
+
+    def add(self) -> None:
+        """
+        Add Excel file content to the knowledge source, chunk it, compute embeddings,
+        and save the embeddings.
+        """
+        # Convert dictionary values to a single string if content is a dictionary
+        if isinstance(self.content, dict):
+            content_str = "\n".join(str(value) for value in self.content.values())
+        else:
+            content_str = str(self.content)
+
+        new_chunks = self._chunk_text(content_str)
+        self.chunks.extend(new_chunks)
+        self.save_documents(metadata=self.metadata)
+
+    def _chunk_text(self, text: str) -> List[str]:
+        """Utility method to split text into chunks."""
+        return [
+            text[i : i + self.chunk_size]
+            for i in range(0, len(text), self.chunk_size - self.chunk_overlap)
+        ]

src/crewai/knowledge/source/json_knowledge_source.py

@@ -0,0 +1,54 @@
+import json
+from typing import Any, Dict, List
+from pathlib import Path
+
+from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
+
+
+class JSONKnowledgeSource(BaseFileKnowledgeSource):
+    """A knowledge source that stores and queries JSON file content using embeddings."""
+
+    def load_content(self) -> Dict[Path, str]:
+        """Load and preprocess JSON file content."""
+        super().load_content()  # Validate the file path
+        paths = [self.file_path] if isinstance(self.file_path, Path) else self.file_path
+
+        content: Dict[Path, str] = {}
+        for path in paths:
+            with open(path, "r", encoding="utf-8") as json_file:
+                data = json.load(json_file)
+            content[path] = self._json_to_text(data)
+        return content
+
+    def _json_to_text(self, data: Any, level: int = 0) -> str:
+        """Recursively convert JSON data to a text representation."""
+        text = ""
+        indent = "  " * level
+        if isinstance(data, dict):
+            for key, value in data.items():
+                text += f"{indent}{key}: {self._json_to_text(value, level + 1)}\n"
+        elif isinstance(data, list):
+            for item in data:
+                text += f"{indent}- {self._json_to_text(item, level + 1)}\n"
+        else:
+            text += f"{str(data)}"
+        return text
+
+    def add(self) -> None:
+        """
+        Add JSON file content to the knowledge source, chunk it, compute embeddings,
+        and save the embeddings.
+        """
+        content_str = (
+            str(self.content) if isinstance(self.content, dict) else self.content
+        )
+        new_chunks = self._chunk_text(content_str)
+        self.chunks.extend(new_chunks)
+        self.save_documents(metadata=self.metadata)
+
+    def _chunk_text(self, text: str) -> List[str]:
+        """Utility method to split text into chunks."""
+        return [
+            text[i : i + self.chunk_size]
+            for i in range(0, len(text), self.chunk_size - self.chunk_overlap)
+        ]

src/crewai/knowledge/source/pdf_knowledge_source.py

@@ -0,0 +1,54 @@
+from typing import List, Dict
+from pathlib import Path
+
+from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
+
+
+class PDFKnowledgeSource(BaseFileKnowledgeSource):
+    """A knowledge source that stores and queries PDF file content using embeddings."""
+
+    def load_content(self) -> Dict[Path, str]:
+        """Load and preprocess PDF file content."""
+        super().load_content()  # Validate the file paths
+        pdfplumber = self._import_pdfplumber()
+
+        paths = [self.file_path] if isinstance(self.file_path, Path) else self.file_path
+        content = {}
+
+        for path in paths:
+            text = ""
+            with pdfplumber.open(path) as pdf:
+                for page in pdf.pages:
+                    page_text = page.extract_text()
+                    if page_text:
+                        text += page_text + "\n"
+            content[path] = text
+        return content
+
+    def _import_pdfplumber(self):
+        """Dynamically import pdfplumber."""
+        try:
+            import pdfplumber
+
+            return pdfplumber
+        except ImportError:
+            raise ImportError(
+                "pdfplumber is not installed. Please install it with: pip install pdfplumber"
+            )
+
+    def add(self) -> None:
+        """
+        Add PDF file content to the knowledge source, chunk it, compute embeddings,
+        and save the embeddings.
+        """
+        for _, text in self.content.items():
+            new_chunks = self._chunk_text(text)
+            self.chunks.extend(new_chunks)
+        self.save_documents(metadata=self.metadata)
+
+    def _chunk_text(self, text: str) -> List[str]:
+        """Utility method to split text into chunks."""
+        return [
+            text[i : i + self.chunk_size]
+            for i in range(0, len(text), self.chunk_size - self.chunk_overlap)
+        ]

src/crewai/knowledge/source/string_knowledge_source.py

@@ -0,0 +1,33 @@
+from typing import List
+
+from pydantic import Field
+
+from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
+
+
+class StringKnowledgeSource(BaseKnowledgeSource):
+    """A knowledge source that stores and queries plain text content using embeddings."""
+
+    content: str = Field(...)
+
+    def model_post_init(self, _):
+        """Post-initialization method to validate content."""
+        self.load_content()
+
+    def load_content(self):
+        """Validate string content."""
+        if not isinstance(self.content, str):
+            raise ValueError("StringKnowledgeSource only accepts string content")
+
+    def add(self) -> None:
+        """Add string content to the knowledge source, chunk it, compute embeddings, and save them."""
+        new_chunks = self._chunk_text(self.content)
+        self.chunks.extend(new_chunks)
+        self.save_documents(metadata=self.metadata)
+
+    def _chunk_text(self, text: str) -> List[str]:
+        """Utility method to split text into chunks."""
+        return [
+            text[i : i + self.chunk_size]
+            for i in range(0, len(text), self.chunk_size - self.chunk_overlap)
+        ]

src/crewai/knowledge/source/text_file_knowledge_source.py

@@ -0,0 +1,35 @@
+from typing import Dict, List
+from pathlib import Path
+
+from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
+
+
+class TextFileKnowledgeSource(BaseFileKnowledgeSource):
+    """A knowledge source that stores and queries text file content using embeddings."""
+
+    def load_content(self) -> Dict[Path, str]:
+        """Load and preprocess text file content."""
+        super().load_content()
+        paths = [self.file_path] if isinstance(self.file_path, Path) else self.file_path
+        content = {}
+        for path in paths:
+            with path.open("r", encoding="utf-8") as f:
+                content[path] = f.read()  # type: ignore
+        return content
+
+    def add(self) -> None:
+        """
+        Add text file content to the knowledge source, chunk it, compute embeddings,
+        and save the embeddings.
+        """
+        for _, text in self.content.items():
+            new_chunks = self._chunk_text(text)
+            self.chunks.extend(new_chunks)
+        self.save_documents(metadata=self.metadata)
+
+    def _chunk_text(self, text: str) -> List[str]:
+        """Utility method to split text into chunks."""
+        return [
+            text[i : i + self.chunk_size]
+            for i in range(0, len(text), self.chunk_size - self.chunk_overlap)
+        ]

src/crewai/knowledge/storage/base_knowledge_storage.py

@@ -0,0 +1,29 @@
+from abc import ABC, abstractmethod
+from typing import Dict, Any, List, Optional
+
+
+class BaseKnowledgeStorage(ABC):
+    """Abstract base class for knowledge storage implementations."""
+
+    @abstractmethod
+    def search(
+        self,
+        query: List[str],
+        limit: int = 3,
+        filter: Optional[dict] = None,
+        score_threshold: float = 0.35,
+    ) -> List[Dict[str, Any]]:
+        """Search for documents in the knowledge base."""
+        pass
+
+    @abstractmethod
+    def save(
+        self, documents: List[str], metadata: Dict[str, Any] | List[Dict[str, Any]]
+    ) -> None:
+        """Save documents to the knowledge base."""
+        pass
+
+    @abstractmethod
+    def reset(self) -> None:
+        """Reset the knowledge base."""
+        pass

src/crewai/knowledge/storage/knowledge_storage.py

@@ -0,0 +1,132 @@
+import contextlib
+import io
+import logging
+import chromadb
+import os
+from crewai.utilities.paths import db_storage_path
+from typing import Optional, List
+from typing import Dict, Any
+from crewai.utilities import EmbeddingConfigurator
+from crewai.knowledge.storage.base_knowledge_storage import BaseKnowledgeStorage
+import hashlib
+
+
+@contextlib.contextmanager
+def suppress_logging(
+    logger_name="chromadb.segment.impl.vector.local_persistent_hnsw",
+    level=logging.ERROR,
+):
+    logger = logging.getLogger(logger_name)
+    original_level = logger.getEffectiveLevel()
+    logger.setLevel(level)
+    with (
+        contextlib.redirect_stdout(io.StringIO()),
+        contextlib.redirect_stderr(io.StringIO()),
+        contextlib.suppress(UserWarning),
+    ):
+        yield
+    logger.setLevel(original_level)
+
+
+class KnowledgeStorage(BaseKnowledgeStorage):
+    """
+    Extends Storage to handle embeddings for memory entries, improving
+    search efficiency.
+    """
+
+    collection: Optional[chromadb.Collection] = None
+
+    def __init__(self, embedder_config: Optional[Dict[str, Any]] = None):
+        self._initialize_app(embedder_config or {})
+
+    def search(
+        self,
+        query: List[str],
+        limit: int = 3,
+        filter: Optional[dict] = None,
+        score_threshold: float = 0.35,
+    ) -> List[Dict[str, Any]]:
+        with suppress_logging():
+            if self.collection:
+                fetched = self.collection.query(
+                    query_texts=query,
+                    n_results=limit,
+                    where=filter,
+                )
+                results = []
+                for i in range(len(fetched["ids"][0])):  # type: ignore
+                    result = {
+                        "id": fetched["ids"][0][i],  # type: ignore
+                        "metadata": fetched["metadatas"][0][i],  # type: ignore
+                        "context": fetched["documents"][0][i],  # type: ignore
+                        "score": fetched["distances"][0][i],  # type: ignore
+                    }
+                    if result["score"] >= score_threshold:  # type: ignore
+                        results.append(result)
+                return results
+            else:
+                raise Exception("Collection not initialized")
+
+    def _initialize_app(self, embedder_config: Optional[Dict[str, Any]] = None):
+        import chromadb
+        from chromadb.config import Settings
+
+        self._set_embedder_config(embedder_config)
+
+        chroma_client = chromadb.PersistentClient(
+            path=f"{db_storage_path()}/knowledge",
+            settings=Settings(allow_reset=True),
+        )
+
+        self.app = chroma_client
+
+        try:
+            self.collection = self.app.get_or_create_collection(name="knowledge")
+        except Exception:
+            raise Exception("Failed to create or get collection")
+
+    def reset(self):
+        if self.app:
+            self.app.reset()
+
+    def save(
+        self, documents: List[str], metadata: Dict[str, Any] | List[Dict[str, Any]]
+    ):
+        if self.collection:
+            metadatas = [metadata] if isinstance(metadata, dict) else metadata
+
+            ids = [
+                hashlib.sha256(doc.encode("utf-8")).hexdigest() for doc in documents
+            ]
+
+            self.collection.upsert(
+                documents=documents,
+                metadatas=metadatas,
+                ids=ids,
+            )
+        else:
+            raise Exception("Collection not initialized")
+
+    def _create_default_embedding_function(self):
+        from chromadb.utils.embedding_functions.openai_embedding_function import (
+            OpenAIEmbeddingFunction,
+        )
+
+        return OpenAIEmbeddingFunction(
+            api_key=os.getenv("OPENAI_API_KEY"), model_name="text-embedding-3-small"
+        )
+
+    def _set_embedder_config(
+        self, embedder_config: Optional[Dict[str, Any]] = None
+    ) -> None:
+        """Set the embedding configuration for the knowledge storage.
+
+        Args:
+            embedder_config (Optional[Dict[str, Any]]): Configuration dictionary for the embedder.
+                If None or empty, defaults to the default embedding function.
+        """
+        self.embedder_config = (
+            EmbeddingConfigurator().configure_embedder(embedder_config)
+            if embedder_config
+            else self._create_default_embedding_function()
+        )

src/crewai/llm.py

@@ -1,6 +1,6 @@
-import io
 import logging
 import sys
+import threading
 import warnings
 from contextlib import contextmanager
 from typing import Any, Dict, List, Optional, Union
@@ -13,16 +13,25 @@ from crewai.utilities.exceptions.context_window_exceeding_exception import (
 )
 
 
-class FilteredStream(io.StringIO):
-    def write(self, s):
-        if (
-            "Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new"
-            in s
-            or "LiteLLM.Info: If you need to debug this error, use `litellm.set_verbose=True`"
-            in s
-        ):
-            return
-        super().write(s)
+class FilteredStream:
+    def __init__(self, original_stream):
+        self._original_stream = original_stream
+        self._lock = threading.Lock()
+
+    def write(self, s) -> int:
+        with self._lock:
+            if (
+                "Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new"
+                in s
+                or "LiteLLM.Info: If you need to debug this error, use `litellm.set_verbose=True`"
+                in s
+            ):
+                return 0
+            return self._original_stream.write(s)
+
+    def flush(self):
+        with self._lock:
+            return self._original_stream.flush()
 
 
 LLM_CONTEXT_WINDOW_SIZES = {
@@ -60,8 +69,8 @@ def suppress_warnings():
         # Redirect stdout and stderr
         old_stdout = sys.stdout
         old_stderr = sys.stderr
-        sys.stdout = FilteredStream()
-        sys.stderr = FilteredStream()
+        sys.stdout = FilteredStream(old_stdout)
+        sys.stderr = FilteredStream(old_stderr)
 
         try:
             yield

src/crewai/memory/storage/rag_storage.py

@@ -4,13 +4,12 @@ import logging
 import os
 import shutil
 import uuid
-from typing import Any, Dict, List, Optional, cast
 
-from chromadb import Documents, EmbeddingFunction, Embeddings
+from typing import Any, Dict, List, Optional
 from chromadb.api import ClientAPI
-from chromadb.api.types import validate_embedding_function
 from crewai.memory.storage.base_rag_storage import BaseRAGStorage
 from crewai.utilities.paths import db_storage_path
+from crewai.utilities import EmbeddingConfigurator
 
 
 @contextlib.contextmanager
@@ -51,133 +50,8 @@ class RAGStorage(BaseRAGStorage):
         self._initialize_app()
 
     def _set_embedder_config(self):
-        if self.embedder_config is None:
-            self.embedder_config = self._create_default_embedding_function()
-
-        if isinstance(self.embedder_config, dict):
-            provider = self.embedder_config.get("provider")
-            config = self.embedder_config.get("config", {})
-            model_name = config.get("model")
-            if provider == "openai":
-                from chromadb.utils.embedding_functions.openai_embedding_function import (
-                    OpenAIEmbeddingFunction,
-                )
-
-                self.embedder_config = OpenAIEmbeddingFunction(
-                    api_key=config.get("api_key") or os.getenv("OPENAI_API_KEY"),
-                    model_name=model_name,
-                )
-            elif provider == "azure":
-                from chromadb.utils.embedding_functions.openai_embedding_function import (
-                    OpenAIEmbeddingFunction,
-                )
-
-                self.embedder_config = OpenAIEmbeddingFunction(
-                    api_key=config.get("api_key"),
-                    api_base=config.get("api_base"),
-                    api_type=config.get("api_type", "azure"),
-                    api_version=config.get("api_version"),
-                    model_name=model_name,
-                )
-            elif provider == "ollama":
-                from chromadb.utils.embedding_functions.ollama_embedding_function import (
-                    OllamaEmbeddingFunction,
-                )
-
-                self.embedder_config = OllamaEmbeddingFunction(
-                    url=config.get("url", "http://localhost:11434/api/embeddings"),
-                    model_name=model_name,
-                )
-            elif provider == "vertexai":
-                from chromadb.utils.embedding_functions.google_embedding_function import (
-                    GoogleVertexEmbeddingFunction,
-                )
-
-                self.embedder_config = GoogleVertexEmbeddingFunction(
-                    model_name=model_name,
-                    api_key=config.get("api_key"),
-                )
-            elif provider == "google":
-                from chromadb.utils.embedding_functions.google_embedding_function import (
-                    GoogleGenerativeAiEmbeddingFunction,
-                )
-
-                self.embedder_config = GoogleGenerativeAiEmbeddingFunction(
-                    model_name=model_name,
-                    api_key=config.get("api_key"),
-                )
-            elif provider == "cohere":
-                from chromadb.utils.embedding_functions.cohere_embedding_function import (
-                    CohereEmbeddingFunction,
-                )
-
-                self.embedder_config = CohereEmbeddingFunction(
-                    model_name=model_name,
-                    api_key=config.get("api_key"),
-                )
-            elif provider == "bedrock":
-                from chromadb.utils.embedding_functions.amazon_bedrock_embedding_function import (
-                    AmazonBedrockEmbeddingFunction,
-                )
-
-                self.embedder_config = AmazonBedrockEmbeddingFunction(
-                    session=config.get("session"),
-                )
-            elif provider == "huggingface":
-                from chromadb.utils.embedding_functions.huggingface_embedding_function import (
-                    HuggingFaceEmbeddingServer,
-                )
-
-                self.embedder_config = HuggingFaceEmbeddingServer(
-                    url=config.get("api_url"),
-                )
-            elif provider == "watson":
-                try:
-                    import ibm_watsonx_ai.foundation_models as watson_models
-                    from ibm_watsonx_ai import Credentials
-                    from ibm_watsonx_ai.metanames import (
-                        EmbedTextParamsMetaNames as EmbedParams,
-                    )
-                except ImportError as e:
-                    raise ImportError(
-                        "IBM Watson dependencies are not installed. Please install them to use Watson embedding."
-                    ) from e
-
-                class WatsonEmbeddingFunction(EmbeddingFunction):
-                    def __call__(self, input: Documents) -> Embeddings:
-                        if isinstance(input, str):
-                            input = [input]
-
-                        embed_params = {
-                            EmbedParams.TRUNCATE_INPUT_TOKENS: 3,
-                            EmbedParams.RETURN_OPTIONS: {"input_text": True},
-                        }
-
-                        embedding = watson_models.Embeddings(
-                            model_id=config.get("model"),
-                            params=embed_params,
-                            credentials=Credentials(
-                                api_key=config.get("api_key"), url=config.get("api_url")
-                            ),
-                            project_id=config.get("project_id"),
-                        )
-
-                        try:
-                            embeddings = embedding.embed_documents(input)
-                            return cast(Embeddings, embeddings)
-
-                        except Exception as e:
-                            print("Error during Watson embedding:", e)
-                            raise e
-
-                self.embedder_config = WatsonEmbeddingFunction()
-            else:
-                raise Exception(
-                    f"Unsupported embedding provider: {provider}, supported providers: [openai, azure, ollama, vertexai, google, cohere, huggingface, watson]"
-                )
-        else:
-            validate_embedding_function(self.embedder_config)
-            self.embedder_config = self.embedder_config
+        configurator = EmbeddingConfigurator()
+        self.embedder_config = configurator.configure_embedder(self.embedder_config)
 
     def _initialize_app(self):
         import chromadb

src/crewai/task.py

@@ -20,10 +20,10 @@ from pydantic import (
 from pydantic_core import PydanticCustomError
 
 from crewai.agents.agent_builder.base_agent import BaseAgent
-from crewai.tools.base_tool import BaseTool
 from crewai.tasks.output_format import OutputFormat
 from crewai.tasks.task_output import TaskOutput
 from crewai.telemetry.telemetry import Telemetry
+from crewai.tools.base_tool import BaseTool
 from crewai.utilities.config import process_config
 from crewai.utilities.converter import Converter, convert_to_model
 from crewai.utilities.i18n import I18N
@@ -208,7 +208,9 @@ class Task(BaseModel):
         """Execute the task asynchronously."""
         future: Future[TaskOutput] = Future()
         threading.Thread(
-            target=self._execute_task_async, args=(agent, context, tools, future)
+            daemon=True,
+            target=self._execute_task_async,
+            args=(agent, context, tools, future),
         ).start()
         return future
 
@@ -277,7 +279,9 @@ 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/__init__.py

@@ -10,6 +10,7 @@ from .rpm_controller import RPMController
 from .exceptions.context_window_exceeding_exception import (
     LLMContextLengthExceededException,
 )
+from .embedding_configurator import EmbeddingConfigurator
 
 __all__ = [
     "Converter",
@@ -23,4 +24,5 @@ __all__ = [
     "RPMController",
     "YamlParser",
     "LLMContextLengthExceededException",
+    "EmbeddingConfigurator",
 ]

src/crewai/utilities/constants.py

@@ -1,2 +1,3 @@
 TRAINING_DATA_FILE = "training_data.pkl"
 TRAINED_AGENTS_DATA_FILE = "trained_agents_data.pkl"
+DEFAULT_SCORE_THRESHOLD = 0.35

src/crewai/utilities/embedding_configurator.py

@@ -0,0 +1,183 @@
+import os
+from typing import Any, Dict, cast
+from chromadb import EmbeddingFunction, Documents, Embeddings
+from chromadb.api.types import validate_embedding_function
+
+
+class EmbeddingConfigurator:
+    def __init__(self):
+        self.embedding_functions = {
+            "openai": self._configure_openai,
+            "azure": self._configure_azure,
+            "ollama": self._configure_ollama,
+            "vertexai": self._configure_vertexai,
+            "google": self._configure_google,
+            "cohere": self._configure_cohere,
+            "bedrock": self._configure_bedrock,
+            "huggingface": self._configure_huggingface,
+            "watson": self._configure_watson,
+        }
+
+    def configure_embedder(
+        self,
+        embedder_config: Dict[str, Any] | None = None,
+    ) -> EmbeddingFunction:
+        """Configures and returns an embedding function based on the provided config."""
+        if embedder_config is None:
+            return self._create_default_embedding_function()
+
+        provider = embedder_config.get("provider")
+        config = embedder_config.get("config", {})
+        model_name = config.get("model")
+
+        if isinstance(provider, EmbeddingFunction):
+            try:
+                validate_embedding_function(provider)
+                return provider
+            except Exception as e:
+                raise ValueError(f"Invalid custom embedding function: {str(e)}")
+
+        if provider not in self.embedding_functions:
+            raise Exception(
+                f"Unsupported embedding provider: {provider}, supported providers: {list(self.embedding_functions.keys())}"
+            )
+
+        return self.embedding_functions[provider](config, model_name)
+
+    @staticmethod
+    def _create_default_embedding_function():
+        from chromadb.utils.embedding_functions.openai_embedding_function import (
+            OpenAIEmbeddingFunction,
+        )
+
+        return OpenAIEmbeddingFunction(
+            api_key=os.getenv("OPENAI_API_KEY"), model_name="text-embedding-3-small"
+        )
+
+    @staticmethod
+    def _configure_openai(config, model_name):
+        from chromadb.utils.embedding_functions.openai_embedding_function import (
+            OpenAIEmbeddingFunction,
+        )
+
+        return OpenAIEmbeddingFunction(
+            api_key=config.get("api_key") or os.getenv("OPENAI_API_KEY"),
+            model_name=model_name,
+        )
+
+    @staticmethod
+    def _configure_azure(config, model_name):
+        from chromadb.utils.embedding_functions.openai_embedding_function import (
+            OpenAIEmbeddingFunction,
+        )
+
+        return OpenAIEmbeddingFunction(
+            api_key=config.get("api_key"),
+            api_base=config.get("api_base"),
+            api_type=config.get("api_type", "azure"),
+            api_version=config.get("api_version"),
+            model_name=model_name,
+        )
+
+    @staticmethod
+    def _configure_ollama(config, model_name):
+        from chromadb.utils.embedding_functions.ollama_embedding_function import (
+            OllamaEmbeddingFunction,
+        )
+
+        return OllamaEmbeddingFunction(
+            url=config.get("url", "http://localhost:11434/api/embeddings"),
+            model_name=model_name,
+        )
+
+    @staticmethod
+    def _configure_vertexai(config, model_name):
+        from chromadb.utils.embedding_functions.google_embedding_function import (
+            GoogleVertexEmbeddingFunction,
+        )
+
+        return GoogleVertexEmbeddingFunction(
+            model_name=model_name,
+            api_key=config.get("api_key"),
+        )
+
+    @staticmethod
+    def _configure_google(config, model_name):
+        from chromadb.utils.embedding_functions.google_embedding_function import (
+            GoogleGenerativeAiEmbeddingFunction,
+        )
+
+        return GoogleGenerativeAiEmbeddingFunction(
+            model_name=model_name,
+            api_key=config.get("api_key"),
+        )
+
+    @staticmethod
+    def _configure_cohere(config, model_name):
+        from chromadb.utils.embedding_functions.cohere_embedding_function import (
+            CohereEmbeddingFunction,
+        )
+
+        return CohereEmbeddingFunction(
+            model_name=model_name,
+            api_key=config.get("api_key"),
+        )
+
+    @staticmethod
+    def _configure_bedrock(config, model_name):
+        from chromadb.utils.embedding_functions.amazon_bedrock_embedding_function import (
+            AmazonBedrockEmbeddingFunction,
+        )
+
+        return AmazonBedrockEmbeddingFunction(
+            session=config.get("session"),
+        )
+
+    @staticmethod
+    def _configure_huggingface(config, model_name):
+        from chromadb.utils.embedding_functions.huggingface_embedding_function import (
+            HuggingFaceEmbeddingServer,
+        )
+
+        return HuggingFaceEmbeddingServer(
+            url=config.get("api_url"),
+        )
+
+    @staticmethod
+    def _configure_watson(config, model_name):
+        try:
+            import ibm_watsonx_ai.foundation_models as watson_models
+            from ibm_watsonx_ai import Credentials
+            from ibm_watsonx_ai.metanames import EmbedTextParamsMetaNames as EmbedParams
+        except ImportError as e:
+            raise ImportError(
+                "IBM Watson dependencies are not installed. Please install them to use Watson embedding."
+            ) from e
+
+        class WatsonEmbeddingFunction(EmbeddingFunction):
+            def __call__(self, input: Documents) -> Embeddings:
+                if isinstance(input, str):
+                    input = [input]
+
+                embed_params = {
+                    EmbedParams.TRUNCATE_INPUT_TOKENS: 3,
+                    EmbedParams.RETURN_OPTIONS: {"input_text": True},
+                }
+
+                embedding = watson_models.Embeddings(
+                    model_id=config.get("model"),
+                    params=embed_params,
+                    credentials=Credentials(
+                        api_key=config.get("api_key"), url=config.get("api_url")
+                    ),
+                    project_id=config.get("project_id"),
+                )
+
+                try:
+                    embeddings = embedding.embed_documents(input)
+                    return cast(Embeddings, embeddings)
+                except Exception as e:
+                    print("Error during Watson embedding:", e)
+                    raise e
+
+        return WatsonEmbeddingFunction()

tests/agent_test.py

@@ -10,10 +10,11 @@ from crewai import Agent, Crew, Task
 from crewai.agents.cache import CacheHandler
 from crewai.agents.crew_agent_executor import CrewAgentExecutor
 from crewai.agents.parser import AgentAction, CrewAgentParser, OutputParserException
+from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
 from crewai.llm import LLM
+from crewai.tools import tool
 from crewai.tools.tool_calling import InstructorToolCalling
 from crewai.tools.tool_usage import ToolUsage
-from crewai.tools import tool
 from crewai.tools.tool_usage_events import ToolUsageFinished
 from crewai.utilities import RPMController
 from crewai.utilities.events import Emitter
@@ -1574,3 +1575,42 @@ def test_agent_execute_task_with_ollama():
     result = agent.execute_task(task)
     assert len(result.split(".")) == 2
     assert "AI" in result or "artificial intelligence" in result.lower()
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_agent_with_knowledge_sources():
+    # Create a knowledge source with some content
+    content = "Brandon's favorite color is blue and he likes Mexican food."
+    string_source = StringKnowledgeSource(
+        content=content, metadata={"preference": "personal"}
+    )
+    
+
+    with patch('crewai.knowledge.storage.knowledge_storage.KnowledgeStorage') as MockKnowledge:
+        mock_knowledge_instance = MockKnowledge.return_value
+        mock_knowledge_instance.sources = [string_source]
+        mock_knowledge_instance.query.return_value = [{
+            "content": content,
+            "metadata": {"preference": "personal"}
+        }]
+        
+        agent = Agent(
+            role="Information Agent",
+            goal="Provide information based on knowledge sources",
+            backstory="You have access to specific knowledge sources.",
+            llm=LLM(model="gpt-4o-mini"),
+        )
+
+        # Create a task that requires the agent to use the knowledge
+        task = Task(
+            description="What is Brandon's favorite color?",
+            expected_output="Brandon's favorite color.",
+            agent=agent,
+        )
+
+        crew = Crew(agents=[agent], tasks=[task])
+        result = crew.kickoff()
+
+        # Assert that the agent provides the correct information
+        assert "blue" in result.raw.lower()
+

tests/cassettes/test_agent_with_knowledge_sources.yaml

@@ -0,0 +1,115 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Information Agent.
+      You have access to specific knowledge sources.\nYour personal goal is: Provide
+      information based on knowledge sources\nTo give my best complete final answer
+      to the task use the exact following format:\n\nThought: I now can give a great
+      answer\nFinal Answer: Your final answer must be the great and the most complete
+      as possible, it must be outcome described.\n\nI MUST use these formats, my job
+      depends on it!"}, {"role": "user", "content": "\nCurrent Task: What is Brandon''s
+      favorite color?\n\nThis is the expect criteria for your final answer: Brandon''s
+      favorite color.\nyou MUST return the actual complete content as the final answer,
+      not a summary.\n\nBegin! This is VERY important to you, use the tools available
+      and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
+      "gpt-4o-mini", "stop": ["\nObservation:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '931'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA4xSQW7bMBC86xULXnqxAtmxI1e3FEWBtJekCXJpC4GmVhIdapcgqbhN4L8HlB1L
+        QVOgFwGa2RnOLPmcAAhdiQKEamVQnTXp5f3d9lsdbndh++C+757Or6/bm6uvn59WH/FGzKKCN1tU
+        4VV1prizBoNmOtDKoQwYXef5+SK7WK3ny4HouEITZY0N6ZLTTpNOF9limWZ5Ol8f1S1rhV4U8CMB
+        AHgevjEnVfhbFJDNXpEOvZcNiuI0BCAcm4gI6b32QVIQs5FUTAFpiH4FxDtQkqDRjwgSmhgbJPkd
+        OoCf9EWTNHA5/BfwyUmqmD54qOUjOx0QFBt2oD1sTI9n02Mc1r2XsSr1xhzx/Sm34cY63vgjf8Jr
+        Tdq3pUPpmWJGH9iKgd0nAL+G/fRvKgvruLOhDPyAFA3nF/nBT4zXMmHXRzJwkGaKr2bv+JUVBqmN
+        n2xYKKlarEbpeB2yrzRPiGTS+u8073kfmmtq/sd+JJRCG7AqrcNKq7eNxzGH8dX+a+y05SGw8H98
+        wK6sNTXorNOHN1PbMsuz1aZe5yoTyT55AQAA//8DAPaYLdRBAwAA
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8e54a2a7d81467f7-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 20 Nov 2024 01:23:34 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=DoHo1Z11nN9bxkwZmJGnaxRhyrWE0UfyimYuUVRU6A4-1732065814-1.0.1.1-JVRvFrIJLHEq9OaFQS0qcgYcawE7t2XQ4Tpqd58n2Yfx3mvEqD34MJmooi1LtvdvjB2J8x1Rs.rCdXD.msLlKw;
+        path=/; expires=Wed, 20-Nov-24 01:53:34 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=n3RrNhFMqC3HtJ7n3e3agyxnM1YOQ6eKESz_eeXLtZA-1732065814630-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '344'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999790'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_8f1622677c64913753a595f679596614
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cassettes/test_kickoff_for_each_error_handling.yaml

@@ -0,0 +1,232 @@
+interactions:
+- request:
+    body: !!binary |
+      Cv1YCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkS1FgKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRLADQoQ5TzgW9QzcBbzMl1hJozLcxIIl3adf7U81wwqDENyZXcgQ3JlYXRlZDABOaAJ
+      txhffgkYQfiVuRhffgkYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODAuMEoaCg5weXRob25fdmVy
+      c2lvbhIICgYzLjEyLjVKLgoIY3Jld19rZXkSIgogM2Y4ZDVjM2FiODgyZDY4NjlkOTNjYjgxZjBl
+      MmVkNGFKMQoHY3Jld19pZBImCiRjYjRiY2Q1Zi0xYWJkLTQyYmYtOGQ1OC02ZmEzMDU3ZDFjOTZK
+      HAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdf
+      bnVtYmVyX29mX3Rhc2tzEgIYA0obChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgCSpIFCgtjcmV3
+      X2FnZW50cxKCBQr/BFt7ImtleSI6ICI4YmQyMTM5YjU5NzUxODE1MDZlNDFmZDljNDU2M2Q3NSIs
+      ICJpZCI6ICI1ZThjNTM1MS1jNWVlLTRhZGUtODY5MC1kM2RhOWI1NzI5YzciLCAicm9sZSI6ICJS
+      ZXNlYXJjaGVyIiwgInZlcmJvc2U/IjogZmFsc2UsICJtYXhfaXRlciI6IDIwLCAibWF4X3JwbSI6
+      IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00by1taW5pIiwg
+      ImRlbGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZh
+      bHNlLCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjogW119LCB7ImtleSI6ICI5
+      YTUwMTVlZjQ4OTVkYzYyNzhkNTQ4MThiYTQ0NmFmNyIsICJpZCI6ICJhMTcwODczOC0yYWE2LTRk
+      ZmYtODFlNy00OGFkMDNjNWFjY2QiLCAicm9sZSI6ICJTZW5pb3IgV3JpdGVyIiwgInZlcmJvc2U/
+      IjogZmFsc2UsICJtYXhfaXRlciI6IDIwLCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxs
+      aW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00by1taW5pIiwgImRlbGVnYXRpb25fZW5hYmxlZD8i
+      OiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5X2xpbWl0
+      IjogMiwgInRvb2xzX25hbWVzIjogW119XUrbBQoKY3Jld190YXNrcxLMBQrJBVt7ImtleSI6ICI2
+      Nzg0OWZmNzE3ZGJhZGFiYTFiOTVkNWYyZGZjZWVhMSIsICJpZCI6ICIyNzkxNTMxMy0wNDBhLTRk
+      ZWItOTVkMy1mNWVmMzg2Mjk3NTEiLCAiYXN5bmNfZXhlY3V0aW9uPyI6IHRydWUsICJodW1hbl9p
+      bnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAiUmVzZWFyY2hlciIsICJhZ2VudF9rZXkiOiAi
+      OGJkMjEzOWI1OTc1MTgxNTA2ZTQxZmQ5YzQ1NjNkNzUiLCAidG9vbHNfbmFtZXMiOiBbXX0sIHsi
+      a2V5IjogImZjNTZkZWEzOGM5OTc0YjZmNTVhMmUyOGMxNDk5ODg2IiwgImlkIjogIjc3NzQ3MmVl
+      LWYzNzAtNDQyZS05NWMyLWVlMGVkYzZiMTgyZiIsICJhc3luY19leGVjdXRpb24/IjogZmFsc2Us
+      ICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAiUmVzZWFyY2hlciIsICJhZ2Vu
+      dF9rZXkiOiAiOGJkMjEzOWI1OTc1MTgxNTA2ZTQxZmQ5YzQ1NjNkNzUiLCAidG9vbHNfbmFtZXMi
+      OiBbXX0sIHsia2V5IjogIjk0YTgyNmMxOTMwNTU5Njg2YmFmYjQwOWVlODM4NzZmIiwgImlkIjog
+      ImM4OWEzODA2LTg5MDItNGQ2My1iYzA0LTdjMzRhZTJmM2UxNyIsICJhc3luY19leGVjdXRpb24/
+      IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAiU2VuaW9yIFdy
+      aXRlciIsICJhZ2VudF9rZXkiOiAiOWE1MDE1ZWY0ODk1ZGM2Mjc4ZDU0ODE4YmE0NDZhZjciLCAi
+      dG9vbHNfbmFtZXMiOiBbXX1degIYAYUBAAEAABKOAgoQSqupTllrk2mxgu2AqenZUhIIspWxig2+
+      1M0qDFRhc2sgQ3JlYXRlZDABOcCj1BhffgkYQfhq1RhffgkYSi4KCGNyZXdfa2V5EiIKIDNmOGQ1
+      YzNhYjg4MmQ2ODY5ZDkzY2I4MWYwZTJlZDRhSjEKB2NyZXdfaWQSJgokY2I0YmNkNWYtMWFiZC00
+      MmJmLThkNTgtNmZhMzA1N2QxYzk2Si4KCHRhc2tfa2V5EiIKIDY3ODQ5ZmY3MTdkYmFkYWJhMWI5
+      NWQ1ZjJkZmNlZWExSjEKB3Rhc2tfaWQSJgokMjc5MTUzMTMtMDQwYS00ZGViLTk1ZDMtZjVlZjM4
+      NjI5NzUxegIYAYUBAAEAABKOAgoQ3dJesXQA5ISCqVgmwvBMgRIIdrWBiVQuihcqDFRhc2sgQ3Jl
+      YXRlZDABOdjAch1ffgkYQVh8cx1ffgkYSi4KCGNyZXdfa2V5EiIKIDNmOGQ1YzNhYjg4MmQ2ODY5
+      ZDkzY2I4MWYwZTJlZDRhSjEKB2NyZXdfaWQSJgokY2I0YmNkNWYtMWFiZC00MmJmLThkNTgtNmZh
+      MzA1N2QxYzk2Si4KCHRhc2tfa2V5EiIKIGZjNTZkZWEzOGM5OTc0YjZmNTVhMmUyOGMxNDk5ODg2
+      SjEKB3Rhc2tfaWQSJgokNzc3NDcyZWUtZjM3MC00NDJlLTk1YzItZWUwZWRjNmIxODJmegIYAYUB
+      AAEAABKOAgoQCBmV+4VbArZNiL5MaefbahII1fRxaC46KKgqDFRhc2sgQ3JlYXRlZDABOaDs4SNf
+      fgkYQai74iNffgkYSi4KCGNyZXdfa2V5EiIKIDNmOGQ1YzNhYjg4MmQ2ODY5ZDkzY2I4MWYwZTJl
+      ZDRhSjEKB2NyZXdfaWQSJgokY2I0YmNkNWYtMWFiZC00MmJmLThkNTgtNmZhMzA1N2QxYzk2Si4K
+      CHRhc2tfa2V5EiIKIDk0YTgyNmMxOTMwNTU5Njg2YmFmYjQwOWVlODM4NzZmSjEKB3Rhc2tfaWQS
+      JgokYzg5YTM4MDYtODkwMi00ZDYzLWJjMDQtN2MzNGFlMmYzZTE3egIYAYUBAAEAABKiBwoQhITI
+      U8q3JLgneRv1MZQY8RIIF2CpEmiZsP4qDENyZXcgQ3JlYXRlZDABOZDBCytffgkYQTDFDStffgkY
+      ShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODAuMEoaCg5weXRob25fdmVyc2lvbhIICgYzLjEyLjVK
+      LgoIY3Jld19rZXkSIgogYTljYzVkNDMzOTViMjFiMTgxYzgwYmQ0MzUxY2NlYzhKMQoHY3Jld19p
+      ZBImCiQ2MTMwMWVmYS0yOGQ4LTQyNTItOWVjNi1iM2JmZDcyMWM0MzVKHAoMY3Jld19wcm9jZXNz
+      EgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tz
+      EgIYAUobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgBStECCgtjcmV3X2FnZW50cxLBAgq+Alt7
+      ImtleSI6ICI4YmQyMTM5YjU5NzUxODE1MDZlNDFmZDljNDU2M2Q3NSIsICJpZCI6ICI3NWRjOTUw
+      OS02MjQ4LTQ0YWQtYTExZC1iZjdlZWVhOWI0NTQiLCAicm9sZSI6ICJSZXNlYXJjaGVyIiwgInZl
+      cmJvc2U/IjogZmFsc2UsICJtYXhfaXRlciI6IDIwLCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlv
+      bl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00by1taW5pIiwgImRlbGVnYXRpb25fZW5h
+      YmxlZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5
+      X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjogW119XUr+AQoKY3Jld190YXNrcxLvAQrsAVt7Imtl
+      eSI6ICJlOWU2YjcyYWFjMzI2NDU5ZGQ3MDY4ZjBiMTcxN2MxYyIsICJpZCI6ICIxOTBlMGQ1Zi0y
+      NDg1LTQ3N2ItYWIxNC1kMTlmNDE5YTFlYjQiLCAiYXN5bmNfZXhlY3V0aW9uPyI6IHRydWUsICJo
+      dW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAiUmVzZWFyY2hlciIsICJhZ2VudF9r
+      ZXkiOiAiOGJkMjEzOWI1OTc1MTgxNTA2ZTQxZmQ5YzQ1NjNkNzUiLCAidG9vbHNfbmFtZXMiOiBb
+      XX1degIYAYUBAAEAABKOAgoQxgDNe1lQGKnixKPk3O1TDBIISyqKkjcA7OYqDFRhc2sgQ3JlYXRl
+      ZDABOfCYJCtffgkYQZAlJStffgkYSi4KCGNyZXdfa2V5EiIKIGE5Y2M1ZDQzMzk1YjIxYjE4MWM4
+      MGJkNDM1MWNjZWM4SjEKB2NyZXdfaWQSJgokNjEzMDFlZmEtMjhkOC00MjUyLTllYzYtYjNiZmQ3
+      MjFjNDM1Si4KCHRhc2tfa2V5EiIKIGU5ZTZiNzJhYWMzMjY0NTlkZDcwNjhmMGIxNzE3YzFjSjEK
+      B3Rhc2tfaWQSJgokMTkwZTBkNWYtMjQ4NS00NzdiLWFiMTQtZDE5ZjQxOWExZWI0egIYAYUBAAEA
+      ABK/DQoQwwR54Z8nOGgj2VSb63WRwhIIonLT+7Mwj00qDENyZXcgQ3JlYXRlZDABObDfvzhffgkY
+      QfBvwjhffgkYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODAuMEoaCg5weXRob25fdmVyc2lvbhII
+      CgYzLjEyLjVKLgoIY3Jld19rZXkSIgogNjZhOTYwZGM2OWZmZjU3OGIyNmM2MWQ0ZjdjNWE5ZmVK
+      MQoHY3Jld19pZBImCiQxNThhMTkzOS01OWUzLTRlODgtYTRkYi04M2IzN2U5MjgxZWVKHAoMY3Jl
+      d19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVy
+      X29mX3Rhc2tzEgIYA0obChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgCSpIFCgtjcmV3X2FnZW50
+      cxKCBQr/BFt7ImtleSI6ICI4YmQyMTM5YjU5NzUxODE1MDZlNDFmZDljNDU2M2Q3NSIsICJpZCI6
+      ICI1ZThjNTM1MS1jNWVlLTRhZGUtODY5MC1kM2RhOWI1NzI5YzciLCAicm9sZSI6ICJSZXNlYXJj
+      aGVyIiwgInZlcmJvc2U/IjogZmFsc2UsICJtYXhfaXRlciI6IDIwLCAibWF4X3JwbSI6IG51bGws
+      ICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00by1taW5pIiwgImRlbGVn
+      YXRpb25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZhbHNlLCAi
+      bWF4X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjogW119LCB7ImtleSI6ICI5YTUwMTVl
+      ZjQ4OTVkYzYyNzhkNTQ4MThiYTQ0NmFmNyIsICJpZCI6ICJhMTcwODczOC0yYWE2LTRkZmYtODFl
+      Ny00OGFkMDNjNWFjY2QiLCAicm9sZSI6ICJTZW5pb3IgV3JpdGVyIiwgInZlcmJvc2U/IjogZmFs
+      c2UsICJtYXhfaXRlciI6IDIwLCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xs
+      bSI6ICIiLCAibGxtIjogImdwdC00by1taW5pIiwgImRlbGVnYXRpb25fZW5hYmxlZD8iOiBmYWxz
+      ZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5X2xpbWl0IjogMiwg
+      InRvb2xzX25hbWVzIjogW119XUraBQoKY3Jld190YXNrcxLLBQrIBVt7ImtleSI6ICI5NDRhZWYw
+      YmFjODQwZjFjMjdiZDgzYTkzN2JjMzYxYiIsICJpZCI6ICIzN2FkNzI5MC04Yjg5LTRjNWEtYmNl
+      Zi03YzY0ZWJhMWM5NjciLCAiYXN5bmNfZXhlY3V0aW9uPyI6IHRydWUsICJodW1hbl9pbnB1dD8i
+      OiBmYWxzZSwgImFnZW50X3JvbGUiOiAiUmVzZWFyY2hlciIsICJhZ2VudF9rZXkiOiAiOGJkMjEz
+      OWI1OTc1MTgxNTA2ZTQxZmQ5YzQ1NjNkNzUiLCAidG9vbHNfbmFtZXMiOiBbXX0sIHsia2V5Ijog
+      ImZjNTZkZWEzOGM5OTc0YjZmNTVhMmUyOGMxNDk5ODg2IiwgImlkIjogIjZhMmViMGY2LTgwZTIt
+      NDkxOC05Zjk3LWVhNDY3OTNkMjI2YyIsICJhc3luY19leGVjdXRpb24/IjogdHJ1ZSwgImh1bWFu
+      X2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJSZXNlYXJjaGVyIiwgImFnZW50X2tleSI6
+      ICI4YmQyMTM5YjU5NzUxODE1MDZlNDFmZDljNDU2M2Q3NSIsICJ0b29sc19uYW1lcyI6IFtdfSwg
+      eyJrZXkiOiAiOTRhODI2YzE5MzA1NTk2ODZiYWZiNDA5ZWU4Mzg3NmYiLCAiaWQiOiAiZGQ2Yzkz
+      NzAtOGYwNC00ZDFmLThjODMtMmFiM2IyYzIwYWI3IiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxz
+      ZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJTZW5pb3IgV3JpdGVyIiwg
+      ImFnZW50X2tleSI6ICI5YTUwMTVlZjQ4OTVkYzYyNzhkNTQ4MThiYTQ0NmFmNyIsICJ0b29sc19u
+      YW1lcyI6IFtdfV16AhgBhQEAAQAAErMHChBV+1WNQzpVlY6l4C/mUgHzEgi3vWQXjOQJ5CoMQ3Jl
+      dyBDcmVhdGVkMAE5sH1kPF9+CRhBaH1mPF9+CRhKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC44MC4w
+      ShoKDnB5dGhvbl92ZXJzaW9uEggKBjMuMTIuNUouCghjcmV3X2tleRIiCiBlZTY3NDVkN2M4YWU4
+      MmUwMGRmOTRkZTBmN2Y4NzExOEoxCgdjcmV3X2lkEiYKJDAwOThmODNmLTdkNTAtNGI2Mi1hYmIy
+      LTJlNTc0N2ZlMWE4OUocCgxjcmV3X3Byb2Nlc3MSDAoKc2VxdWVudGlhbEoRCgtjcmV3X21lbW9y
+      eRICEABKGgoUY3Jld19udW1iZXJfb2ZfdGFza3MSAhgBShsKFWNyZXdfbnVtYmVyX29mX2FnZW50
+      cxICGAFK2QIKC2NyZXdfYWdlbnRzEskCCsYCW3sia2V5IjogImYzMzg2ZjZkOGRhNzVhYTQxNmE2
+      ZTMxMDA1M2Y3Njk4IiwgImlkIjogIjEzODI4ZDViLWIyOWMtNDllMy05NWVhLTkyOGQ2ZmZhY2I0
+      NSIsICJyb2xlIjogInt0b3BpY30gUmVzZWFyY2hlciIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4
+      X2l0ZXIiOiAyMCwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwg
+      ImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxv
+      d19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19u
+      YW1lcyI6IFtdfV1KhwIKCmNyZXdfdGFza3MS+AEK9QFbeyJrZXkiOiAiMDZhNzMyMjBmNDE0OGE0
+      YmJkNWJhY2IwZDBiNDRmY2UiLCAiaWQiOiAiNWM4MjM1ZmYtNWVjNy00NzFhLWI4NWEtNWFkZjk3
+      YzJkYzI3IiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNl
+      LCAiYWdlbnRfcm9sZSI6ICJ7dG9waWN9IFJlc2VhcmNoZXIiLCAiYWdlbnRfa2V5IjogImYzMzg2
+      ZjZkOGRhNzVhYTQxNmE2ZTMxMDA1M2Y3Njk4IiwgInRvb2xzX25hbWVzIjogW119XXoCGAGFAQAB
+      AAASjgIKEHOZ/a+LQwTLSkMO0sPwg9gSCL1SwQw1+0iKKgxUYXNrIENyZWF0ZWQwATl4kX48X34J
+      GEFIFn88X34JGEouCghjcmV3X2tleRIiCiBlZTY3NDVkN2M4YWU4MmUwMGRmOTRkZTBmN2Y4NzEx
+      OEoxCgdjcmV3X2lkEiYKJDAwOThmODNmLTdkNTAtNGI2Mi1hYmIyLTJlNTc0N2ZlMWE4OUouCgh0
+      YXNrX2tleRIiCiAwNmE3MzIyMGY0MTQ4YTRiYmQ1YmFjYjBkMGI0NGZjZUoxCgd0YXNrX2lkEiYK
+      JDVjODIzNWZmLTVlYzctNDcxYS1iODVhLTVhZGY5N2MyZGMyN3oCGAGFAQABAAASswcKEHZQCRd7
+      z4ZBCh4+06qs1r4SCNzrNsw+dn2zKgxDcmV3IENyZWF0ZWQwATlgWdtDX34JGEGIcN1DX34JGEoa
+      Cg5jcmV3YWlfdmVyc2lvbhIICgYwLjgwLjBKGgoOcHl0aG9uX3ZlcnNpb24SCAoGMy4xMi41Si4K
+      CGNyZXdfa2V5EiIKIGVlNjc0NWQ3YzhhZTgyZTAwZGY5NGRlMGY3Zjg3MTE4SjEKB2NyZXdfaWQS
+      JgokZTgzMTdjNzEtNmZiZS00MjI5LWE3MzctYTkxM2I0ZmU0ZTU0ShwKDGNyZXdfcHJvY2VzcxIM
+      CgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9vZl90YXNrcxIC
+      GAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUrZAgoLY3Jld19hZ2VudHMSyQIKxgJbeyJr
+      ZXkiOiAiZjMzODZmNmQ4ZGE3NWFhNDE2YTZlMzEwMDUzZjc2OTgiLCAiaWQiOiAiNjAwMzU5OTYt
+      ZWU1ZS00YmZhLThmODctMGM1ZTY0OTBlMmE4IiwgInJvbGUiOiAie3RvcGljfSBSZXNlYXJjaGVy
+      IiwgInZlcmJvc2U/IjogZmFsc2UsICJtYXhfaXRlciI6IDIwLCAibWF4X3JwbSI6IG51bGwsICJm
+      dW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00by1taW5pIiwgImRlbGVnYXRp
+      b25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZhbHNlLCAibWF4
+      X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjogW119XUqHAgoKY3Jld190YXNrcxL4AQr1
+      AVt7ImtleSI6ICIwNmE3MzIyMGY0MTQ4YTRiYmQ1YmFjYjBkMGI0NGZjZSIsICJpZCI6ICI4MDc3
+      MDhjNS0yN2RkLTQ4ZDEtYTU0ZC1lZTRkNTZmMzBiZTQiLCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZh
+      bHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogInt0b3BpY30gUmVzZWFy
+      Y2hlciIsICJhZ2VudF9rZXkiOiAiZjMzODZmNmQ4ZGE3NWFhNDE2YTZlMzEwMDUzZjc2OTgiLCAi
+      dG9vbHNfbmFtZXMiOiBbXX1degIYAYUBAAEAABKOAgoQtqHg5uy2kZsnJlJTYgmZoxIIlgUHkQ7m
+      LugqDFRhc2sgQ3JlYXRlZDABOTi470NffgkYQQg98ENffgkYSi4KCGNyZXdfa2V5EiIKIGVlNjc0
+      NWQ3YzhhZTgyZTAwZGY5NGRlMGY3Zjg3MTE4SjEKB2NyZXdfaWQSJgokZTgzMTdjNzEtNmZiZS00
+      MjI5LWE3MzctYTkxM2I0ZmU0ZTU0Si4KCHRhc2tfa2V5EiIKIDA2YTczMjIwZjQxNDhhNGJiZDVi
+      YWNiMGQwYjQ0ZmNlSjEKB3Rhc2tfaWQSJgokODA3NzA4YzUtMjdkZC00OGQxLWE1NGQtZWU0ZDU2
+      ZjMwYmU0egIYAYUBAAEAABKzBwoQpfKhpM9cCoiT5Mun1aoNQhII4HhX0QHHc/0qDENyZXcgQ3Jl
+      YXRlZDABORiH20lffgkYQcix3UlffgkYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODAuMEoaCg5w
+      eXRob25fdmVyc2lvbhIICgYzLjEyLjVKLgoIY3Jld19rZXkSIgogZWU2NzQ1ZDdjOGFlODJlMDBk
+      Zjk0ZGUwZjdmODcxMThKMQoHY3Jld19pZBImCiRmZDk2MmQwMi0wNGY0LTQ3NDUtODc5YS02NTFm
+      MzFmMmZhOTZKHAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAA
+      ShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgB
+      StkCCgtjcmV3X2FnZW50cxLJAgrGAlt7ImtleSI6ICJmMzM4NmY2ZDhkYTc1YWE0MTZhNmUzMTAw
+      NTNmNzY5OCIsICJpZCI6ICIzNmZhMTEyZS02ZDVlLTRhMzgtODk0Yy01M2M5YjAzNTI5ODUiLCAi
+      cm9sZSI6ICJ7dG9waWN9IFJlc2VhcmNoZXIiLCAidmVyYm9zZT8iOiBmYWxzZSwgIm1heF9pdGVy
+      IjogMjAsICJtYXhfcnBtIjogbnVsbCwgImZ1bmN0aW9uX2NhbGxpbmdfbGxtIjogIiIsICJsbG0i
+      OiAiZ3B0LTRvLW1pbmkiLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29k
+      ZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMi
+      OiBbXX1dSocCCgpjcmV3X3Rhc2tzEvgBCvUBW3sia2V5IjogIjA2YTczMjIwZjQxNDhhNGJiZDVi
+      YWNiMGQwYjQ0ZmNlIiwgImlkIjogIjY3NTE3ZjY1LThhYzMtNDIyZi1hMmJhLTM4NDcyZDRkYmZl
+      NSIsICJhc3luY19leGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFn
+      ZW50X3JvbGUiOiAie3RvcGljfSBSZXNlYXJjaGVyIiwgImFnZW50X2tleSI6ICJmMzM4NmY2ZDhk
+      YTc1YWE0MTZhNmUzMTAwNTNmNzY5OCIsICJ0b29sc19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEo4C
+      ChAzGUzQMDZOgJ090im3887lEgik7+/nVnqntioMVGFzayBDcmVhdGVkMAE5UO7rSV9+CRhBWEDs
+      SV9+CRhKLgoIY3Jld19rZXkSIgogZWU2NzQ1ZDdjOGFlODJlMDBkZjk0ZGUwZjdmODcxMThKMQoH
+      Y3Jld19pZBImCiRmZDk2MmQwMi0wNGY0LTQ3NDUtODc5YS02NTFmMzFmMmZhOTZKLgoIdGFza19r
+      ZXkSIgogMDZhNzMyMjBmNDE0OGE0YmJkNWJhY2IwZDBiNDRmY2VKMQoHdGFza19pZBImCiQ2NzUx
+      N2Y2NS04YWMzLTQyMmYtYTJiYS0zODQ3MmQ0ZGJmZTV6AhgBhQEAAQAAErMHChCB1TPvVbWX62DF
+      102NfOHLEghdZ/LjI40W8SoMQ3JldyBDcmVhdGVkMAE5sJDUT19+CRhBEHXWT19+CRhKGgoOY3Jl
+      d2FpX3ZlcnNpb24SCAoGMC44MC4wShoKDnB5dGhvbl92ZXJzaW9uEggKBjMuMTIuNUouCghjcmV3
+      X2tleRIiCiBlZTY3NDVkN2M4YWU4MmUwMGRmOTRkZTBmN2Y4NzExOEoxCgdjcmV3X2lkEiYKJDUx
+      YmI1NGQ0LWM4MTAtNDA0Yy04MTQzLWVmNTgwMTlhN2Q2OEocCgxjcmV3X3Byb2Nlc3MSDAoKc2Vx
+      dWVudGlhbEoRCgtjcmV3X21lbW9yeRICEABKGgoUY3Jld19udW1iZXJfb2ZfdGFza3MSAhgBShsK
+      FWNyZXdfbnVtYmVyX29mX2FnZW50cxICGAFK2QIKC2NyZXdfYWdlbnRzEskCCsYCW3sia2V5Ijog
+      ImYzMzg2ZjZkOGRhNzVhYTQxNmE2ZTMxMDA1M2Y3Njk4IiwgImlkIjogIjRlNTExYTRhLTM1Yzkt
+      NDA0NC1iMzBlLWM4OGZjZTJiMzc5YiIsICJyb2xlIjogInt0b3BpY30gUmVzZWFyY2hlciIsICJ2
+      ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyMCwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rp
+      b25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2Vu
+      YWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRy
+      eV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfV1KhwIKCmNyZXdfdGFza3MS+AEK9QFbeyJr
+      ZXkiOiAiMDZhNzMyMjBmNDE0OGE0YmJkNWJhY2IwZDBiNDRmY2UiLCAiaWQiOiAiOTIzMWJmZjIt
+      ODFmOS00MjU4LTgyMDktMjkzMjUyOWI1ZjlmIiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwg
+      Imh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJ7dG9waWN9IFJlc2VhcmNoZXIi
+      LCAiYWdlbnRfa2V5IjogImYzMzg2ZjZkOGRhNzVhYTQxNmE2ZTMxMDA1M2Y3Njk4IiwgInRvb2xz
+      X25hbWVzIjogW119XXoCGAGFAQABAAASjgIKECTO19lNFYzBivlrqiZfSxASCIAH8VhjiPfQKgxU
+      YXNrIENyZWF0ZWQwATnIr+NPX34JGEHQAeRPX34JGEouCghjcmV3X2tleRIiCiBlZTY3NDVkN2M4
+      YWU4MmUwMGRmOTRkZTBmN2Y4NzExOEoxCgdjcmV3X2lkEiYKJDUxYmI1NGQ0LWM4MTAtNDA0Yy04
+      MTQzLWVmNTgwMTlhN2Q2OEouCgh0YXNrX2tleRIiCiAwNmE3MzIyMGY0MTQ4YTRiYmQ1YmFjYjBk
+      MGI0NGZjZUoxCgd0YXNrX2lkEiYKJDkyMzFiZmYyLTgxZjktNDI1OC04MjA5LTI5MzI1MjliNWY5
+      ZnoCGAGFAQABAAASswcKEHGb7KITfOkYfQT7CRjWfUcSCIn6YlQJ1QVbKgxDcmV3IENyZWF0ZWQw
+      ATmYH/BYX34JGEEgJ/JYX34JGEoaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjgwLjBKGgoOcHl0aG9u
+      X3ZlcnNpb24SCAoGMy4xMi41Si4KCGNyZXdfa2V5EiIKIGVlNjc0NWQ3YzhhZTgyZTAwZGY5NGRl
+      MGY3Zjg3MTE4SjEKB2NyZXdfaWQSJgokZDc5Y2UyMWUtYmU1Ny00NTdiLWExMzEtNjZkMDFmZjQx
+      ZTI2ShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRj
+      cmV3X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUrZAgoL
+      Y3Jld19hZ2VudHMSyQIKxgJbeyJrZXkiOiAiZjMzODZmNmQ4ZGE3NWFhNDE2YTZlMzEwMDUzZjc2
+      OTgiLCAiaWQiOiAiNzRhNDUxNzgtNmExOS00N2RjLThlZjktZDdhZmQ5YzUwMDQ0IiwgInJvbGUi
+      OiAie3RvcGljfSBSZXNlYXJjaGVyIiwgInZlcmJvc2U/IjogZmFsc2UsICJtYXhfaXRlciI6IDIw
+      LCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdw
+      dC00by1taW5pIiwgImRlbGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhl
+      Y3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjogW119
+      XUqHAgoKY3Jld190YXNrcxL4AQr1AVt7ImtleSI6ICIwNmE3MzIyMGY0MTQ4YTRiYmQ1YmFjYjBk
+      MGI0NGZjZSIsICJpZCI6ICJjZWZiYjE1ZS01Y2M4LTQwZTctYTViMS03ODkzYjJlZGFkYmQiLCAi
+      YXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9y
+      b2xlIjogInt0b3BpY30gUmVzZWFyY2hlciIsICJhZ2VudF9rZXkiOiAiZjMzODZmNmQ4ZGE3NWFh
+      NDE2YTZlMzEwMDUzZjc2OTgiLCAidG9vbHNfbmFtZXMiOiBbXX1degIYAYUBAAEAAA==
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '11392'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.27.0
+    method: POST
+    uri: https://telemetry.crewai.com:4319/v1/traces
+  response:
+    body:
+      string: "\n\0"
+    headers:
+      Content-Length:
+      - '2'
+      Content-Type:
+      - application/x-protobuf
+      Date:
+      - Tue, 19 Nov 2024 22:14:39 GMT
+    status:
+      code: 200
+      message: OK
+version: 1

tests/knowledge/knowledge_test.py

@@ -0,0 +1,545 @@
+"""Test Knowledge creation and querying functionality."""
+
+from pathlib import Path
+from unittest.mock import patch
+
+from crewai.knowledge.source.csv_knowledge_source import CSVKnowledgeSource
+from crewai.knowledge.source.excel_knowledge_source import ExcelKnowledgeSource
+from crewai.knowledge.source.json_knowledge_source import JSONKnowledgeSource
+from crewai.knowledge.source.pdf_knowledge_source import PDFKnowledgeSource
+from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
+from crewai.knowledge.source.text_file_knowledge_source import TextFileKnowledgeSource
+
+import pytest
+
+
+@pytest.fixture(autouse=True)
+def mock_vector_db():
+    """Mock vector database operations."""
+    with patch("crewai.knowledge.storage.knowledge_storage.KnowledgeStorage") as mock:
+        # Mock the query method to return a predefined response
+        instance = mock.return_value
+        instance.query.return_value = [
+            {
+                "context": "Brandon's favorite color is blue and he likes Mexican food.",
+                "score": 0.9,
+            }
+        ]
+        instance.reset.return_value = None
+        yield instance
+
+
+@pytest.fixture(autouse=True)
+def reset_knowledge_storage(mock_vector_db):
+    """Fixture to reset knowledge storage before each test."""
+    yield
+
+
+def test_single_short_string(mock_vector_db):
+    # Create a knowledge base with a single short string
+    content = "Brandon's favorite color is blue and he likes Mexican food."
+    string_source = StringKnowledgeSource(
+        content=content, metadata={"preference": "personal"}
+    )
+    mock_vector_db.sources = [string_source]
+    mock_vector_db.query.return_value = [{"context": content, "score": 0.9}]
+    # Perform a query
+    query = "What is Brandon's favorite color?"
+    results = mock_vector_db.query(query)
+
+    # Assert that the results contain the expected information
+    assert any("blue" in result["context"].lower() for result in results)
+    # Verify the mock was called
+    mock_vector_db.query.assert_called_once()
+
+
+# @pytest.mark.vcr(filter_headers=["authorization"])
+def test_single_2k_character_string(mock_vector_db):
+    # Create a 2k character string with various facts about Brandon
+    content = (
+        "Brandon is a software engineer who lives in San Francisco. "
+        "He enjoys hiking and often visits the trails in the Bay Area. "
+        "Brandon has a pet dog named Max, who is a golden retriever. "
+        "He loves reading science fiction books, and his favorite author is Isaac Asimov. "
+        "Brandon's favorite movie is Inception, and he enjoys watching it with his friends. "
+        "He is also a fan of Mexican cuisine, especially tacos and burritos. "
+        "Brandon plays the guitar and often performs at local open mic nights. "
+        "He is learning French and plans to visit Paris next year. "
+        "Brandon is passionate about technology and often attends tech meetups in the city. "
+        "He is also interested in AI and machine learning, and he is currently working on a project related to natural language processing. "
+        "Brandon's favorite color is blue, and he often wears blue shirts. "
+        "He enjoys cooking and often tries new recipes on weekends. "
+        "Brandon is a morning person and likes to start his day with a run in the park. "
+        "He is also a coffee enthusiast and enjoys trying different coffee blends. "
+        "Brandon is a member of a local book club and enjoys discussing books with fellow members. "
+        "He is also a fan of board games and often hosts game nights at his place. "
+        "Brandon is an advocate for environmental conservation and volunteers for local clean-up drives. "
+        "He is also a mentor for aspiring software developers and enjoys sharing his knowledge with others. "
+        "Brandon's favorite sport is basketball, and he often plays with his friends on weekends. "
+        "He is also a fan of the Golden State Warriors and enjoys watching their games. "
+    )
+    string_source = StringKnowledgeSource(
+        content=content, metadata={"preference": "personal"}
+    )
+    mock_vector_db.sources = [string_source]
+    mock_vector_db.query.return_value = [{"context": content, "score": 0.9}]
+
+    # Perform a query
+    query = "What is Brandon's favorite movie?"
+    results = mock_vector_db.query(query)
+
+    # Assert that the results contain the expected information
+    assert any("inception" in result["context"].lower() for result in results)
+    mock_vector_db.query.assert_called_once()
+
+
+def test_multiple_short_strings(mock_vector_db):
+    # Create multiple short string sources
+    contents = [
+        "Brandon loves hiking.",
+        "Brandon has a dog named Max.",
+        "Brandon enjoys painting landscapes.",
+    ]
+    string_sources = [
+        StringKnowledgeSource(content=content, metadata={"preference": "personal"})
+        for content in contents
+    ]
+
+    # Mock the vector db query response
+    mock_vector_db.query.return_value = [
+        {"context": "Brandon has a dog named Max.", "score": 0.9}
+    ]
+
+    mock_vector_db.sources = string_sources
+
+    # Perform a query
+    query = "What is the name of Brandon's pet?"
+    results = mock_vector_db.query(query)
+
+    # Assert that the correct information is retrieved
+    assert any("max" in result["context"].lower() for result in results)
+    # Verify the mock was called
+    mock_vector_db.query.assert_called_once()
+
+
+def test_multiple_2k_character_strings(mock_vector_db):
+    # Create multiple 2k character strings with various facts about Brandon
+    contents = [
+        (
+            "Brandon is a software engineer who lives in San Francisco. "
+            "He enjoys hiking and often visits the trails in the Bay Area. "
+            "Brandon has a pet dog named Max, who is a golden retriever. "
+            "He loves reading science fiction books, and his favorite author is Isaac Asimov. "
+            "Brandon's favorite movie is Inception, and he enjoys watching it with his friends. "
+            "He is also a fan of Mexican cuisine, especially tacos and burritos. "
+            "Brandon plays the guitar and often performs at local open mic nights. "
+            "He is learning French and plans to visit Paris next year. "
+            "Brandon is passionate about technology and often attends tech meetups in the city. "
+            "He is also interested in AI and machine learning, and he is currently working on a project related to natural language processing. "
+            "Brandon's favorite color is blue, and he often wears blue shirts. "
+            "He enjoys cooking and often tries new recipes on weekends. "
+            "Brandon is a morning person and likes to start his day with a run in the park. "
+            "He is also a coffee enthusiast and enjoys trying different coffee blends. "
+            "Brandon is a member of a local book club and enjoys discussing books with fellow members. "
+            "He is also a fan of board games and often hosts game nights at his place. "
+            "Brandon is an advocate for environmental conservation and volunteers for local clean-up drives. "
+            "He is also a mentor for aspiring software developers and enjoys sharing his knowledge with others. "
+            "Brandon's favorite sport is basketball, and he often plays with his friends on weekends. "
+            "He is also a fan of the Golden State Warriors and enjoys watching their games. "
+        )
+        * 2,  # Repeat to ensure it's 2k characters
+        (
+            "Brandon loves traveling and has visited over 20 countries. "
+            "He is fluent in Spanish and often practices with his friends. "
+            "Brandon's favorite city is Barcelona, where he enjoys the architecture and culture. "
+            "He is a foodie and loves trying new cuisines, with a particular fondness for sushi. "
+            "Brandon is an avid cyclist and participates in local cycling events. "
+            "He is also a photographer and enjoys capturing landscapes and cityscapes. "
+            "Brandon is a tech enthusiast and follows the latest trends in gadgets and software. "
+            "He is also a fan of virtual reality and owns a VR headset. "
+            "Brandon's favorite book is 'The Hitchhiker's Guide to the Galaxy'. "
+            "He enjoys watching documentaries and learning about history and science. "
+            "Brandon is a coffee lover and has a collection of coffee mugs from different countries. "
+            "He is also a fan of jazz music and often attends live performances. "
+            "Brandon is a member of a local running club and participates in marathons. "
+            "He is also a volunteer at a local animal shelter and helps with dog walking. "
+            "Brandon's favorite holiday is Christmas, and he enjoys decorating his home. "
+            "He is also a fan of classic movies and has a collection of DVDs. "
+            "Brandon is a mentor for young professionals and enjoys giving career advice. "
+            "He is also a fan of puzzles and enjoys solving them in his free time. "
+            "Brandon's favorite sport is soccer, and he often plays with his friends. "
+            "He is also a fan of FC Barcelona and enjoys watching their matches. "
+        )
+        * 2,  # Repeat to ensure it's 2k characters
+    ]
+    string_sources = [
+        StringKnowledgeSource(content=content, metadata={"preference": "personal"})
+        for content in contents
+    ]
+
+    mock_vector_db.sources = string_sources
+    mock_vector_db.query.return_value = [{"context": contents[1], "score": 0.9}]
+
+    # Perform a query
+    query = "What is Brandon's favorite book?"
+    results = mock_vector_db.query(query)
+
+    # Assert that the correct information is retrieved
+    assert any(
+        "the hitchhiker's guide to the galaxy" in result["context"].lower()
+        for result in results
+    )
+    mock_vector_db.query.assert_called_once()
+
+
+def test_single_short_file(mock_vector_db, tmpdir):
+    # Create a single short text file
+    content = "Brandon's favorite sport is basketball."
+    file_path = Path(tmpdir.join("short_file.txt"))
+    with open(file_path, "w") as f:
+        f.write(content)
+
+    file_source = TextFileKnowledgeSource(
+        file_path=file_path, metadata={"preference": "personal"}
+    )
+    mock_vector_db.sources = [file_source]
+    mock_vector_db.query.return_value = [{"context": content, "score": 0.9}]
+    # Perform a query
+    query = "What sport does Brandon like?"
+    results = mock_vector_db.query(query)
+
+    # Assert that the results contain the expected information
+    assert any("basketball" in result["context"].lower() for result in results)
+    mock_vector_db.query.assert_called_once()
+
+
+def test_single_2k_character_file(mock_vector_db, tmpdir):
+    # Create a single 2k character text file with various facts about Brandon
+    content = (
+        "Brandon is a software engineer who lives in San Francisco. "
+        "He enjoys hiking and often visits the trails in the Bay Area. "
+        "Brandon has a pet dog named Max, who is a golden retriever. "
+        "He loves reading science fiction books, and his favorite author is Isaac Asimov. "
+        "Brandon's favorite movie is Inception, and he enjoys watching it with his friends. "
+        "He is also a fan of Mexican cuisine, especially tacos and burritos. "
+        "Brandon plays the guitar and often performs at local open mic nights. "
+        "He is learning French and plans to visit Paris next year. "
+        "Brandon is passionate about technology and often attends tech meetups in the city. "
+        "He is also interested in AI and machine learning, and he is currently working on a project related to natural language processing. "
+        "Brandon's favorite color is blue, and he often wears blue shirts. "
+        "He enjoys cooking and often tries new recipes on weekends. "
+        "Brandon is a morning person and likes to start his day with a run in the park. "
+        "He is also a coffee enthusiast and enjoys trying different coffee blends. "
+        "Brandon is a member of a local book club and enjoys discussing books with fellow members. "
+        "He is also a fan of board games and often hosts game nights at his place. "
+        "Brandon is an advocate for environmental conservation and volunteers for local clean-up drives. "
+        "He is also a mentor for aspiring software developers and enjoys sharing his knowledge with others. "
+        "Brandon's favorite sport is basketball, and he often plays with his friends on weekends. "
+        "He is also a fan of the Golden State Warriors and enjoys watching their games. "
+    ) * 2  # Repeat to ensure it's 2k characters
+    file_path = Path(tmpdir.join("long_file.txt"))
+    with open(file_path, "w") as f:
+        f.write(content)
+
+    file_source = TextFileKnowledgeSource(
+        file_path=file_path, metadata={"preference": "personal"}
+    )
+    mock_vector_db.sources = [file_source]
+    mock_vector_db.query.return_value = [{"context": content, "score": 0.9}]
+    # Perform a query
+    query = "What is Brandon's favorite movie?"
+    results = mock_vector_db.query(query)
+
+    # Assert that the results contain the expected information
+    assert any("inception" in result["context"].lower() for result in results)
+    mock_vector_db.query.assert_called_once()
+
+
+def test_multiple_short_files(mock_vector_db, tmpdir):
+    # Create multiple short text files
+    contents = [
+        {
+            "content": "Brandon works as a software engineer.",
+            "metadata": {"category": "profession", "source": "occupation"},
+        },
+        {
+            "content": "Brandon lives in New York.",
+            "metadata": {"category": "city", "source": "personal"},
+        },
+        {
+            "content": "Brandon enjoys cooking Italian food.",
+            "metadata": {"category": "hobby", "source": "personal"},
+        },
+    ]
+    file_paths = []
+    for i, item in enumerate(contents):
+        file_path = Path(tmpdir.join(f"file_{i}.txt"))
+        with open(file_path, "w") as f:
+            f.write(item["content"])
+        file_paths.append((file_path, item["metadata"]))
+
+    file_sources = [
+        TextFileKnowledgeSource(file_path=path, metadata=metadata)
+        for path, metadata in file_paths
+    ]
+    mock_vector_db.sources = file_sources
+    mock_vector_db.query.return_value = [
+        {"context": "Brandon lives in New York.", "score": 0.9}
+    ]
+    # Perform a query
+    query = "What city does he reside in?"
+    results = mock_vector_db.query(query)
+    # Assert that the correct information is retrieved
+    assert any("new york" in result["context"].lower() for result in results)
+    mock_vector_db.query.assert_called_once()
+
+
+def test_multiple_2k_character_files(mock_vector_db, tmpdir):
+    # Create multiple 2k character text files with various facts about Brandon
+    contents = [
+        (
+            "Brandon loves traveling and has visited over 20 countries. "
+            "He is fluent in Spanish and often practices with his friends. "
+            "Brandon's favorite city is Barcelona, where he enjoys the architecture and culture. "
+            "He is a foodie and loves trying new cuisines, with a particular fondness for sushi. "
+            "Brandon is an avid cyclist and participates in local cycling events. "
+            "He is also a photographer and enjoys capturing landscapes and cityscapes. "
+            "Brandon is a tech enthusiast and follows the latest trends in gadgets and software. "
+            "He is also a fan of virtual reality and owns a VR headset. "
+            "Brandon's favorite book is 'The Hitchhiker's Guide to the Galaxy'. "
+            "He enjoys watching documentaries and learning about history and science. "
+            "Brandon is a coffee lover and has a collection of coffee mugs from different countries. "
+            "He is also a fan of jazz music and often attends live performances. "
+            "Brandon is a member of a local running club and participates in marathons. "
+            "He is also a volunteer at a local animal shelter and helps with dog walking. "
+            "Brandon's favorite holiday is Christmas, and he enjoys decorating his home. "
+            "He is also a fan of classic movies and has a collection of DVDs. "
+            "Brandon is a mentor for young professionals and enjoys giving career advice. "
+            "He is also a fan of puzzles and enjoys solving them in his free time. "
+            "Brandon's favorite sport is soccer, and he often plays with his friends. "
+            "He is also a fan of FC Barcelona and enjoys watching their matches. "
+        )
+        * 2,  # Repeat to ensure it's 2k characters
+        (
+            "Brandon is a software engineer who lives in San Francisco. "
+            "He enjoys hiking and often visits the trails in the Bay Area. "
+            "Brandon has a pet dog named Max, who is a golden retriever. "
+            "He loves reading science fiction books, and his favorite author is Isaac Asimov. "
+            "Brandon's favorite movie is Inception, and he enjoys watching it with his friends. "
+            "He is also a fan of Mexican cuisine, especially tacos and burritos. "
+            "Brandon plays the guitar and often performs at local open mic nights. "
+            "He is learning French and plans to visit Paris next year. "
+            "Brandon is passionate about technology and often attends tech meetups in the city. "
+            "He is also interested in AI and machine learning, and he is currently working on a project related to natural language processing. "
+            "Brandon's favorite color is blue, and he often wears blue shirts. "
+            "He enjoys cooking and often tries new recipes on weekends. "
+            "Brandon is a morning person and likes to start his day with a run in the park. "
+            "He is also a coffee enthusiast and enjoys trying different coffee blends. "
+            "Brandon is a member of a local book club and enjoys discussing books with fellow members. "
+            "He is also a fan of board games and often hosts game nights at his place. "
+            "Brandon is an advocate for environmental conservation and volunteers for local clean-up drives. "
+            "He is also a mentor for aspiring software developers and enjoys sharing his knowledge with others. "
+            "Brandon's favorite sport is basketball, and he often plays with his friends on weekends. "
+            "He is also a fan of the Golden State Warriors and enjoys watching their games. "
+        )
+        * 2,  # Repeat to ensure it's 2k characters
+    ]
+    file_paths = []
+    for i, content in enumerate(contents):
+        file_path = Path(tmpdir.join(f"long_file_{i}.txt"))
+        with open(file_path, "w") as f:
+            f.write(content)
+        file_paths.append(file_path)
+
+    file_sources = [
+        TextFileKnowledgeSource(file_path=path, metadata={"preference": "personal"})
+        for path in file_paths
+    ]
+    mock_vector_db.sources = file_sources
+    mock_vector_db.query.return_value = [
+        {
+            "context": "Brandon's favorite book is 'The Hitchhiker's Guide to the Galaxy'.",
+            "score": 0.9,
+        }
+    ]
+    # Perform a query
+    query = "What is Brandon's favorite book?"
+    results = mock_vector_db.query(query)
+
+    # Assert that the correct information is retrieved
+    assert any(
+        "the hitchhiker's guide to the galaxy" in result["context"].lower()
+        for result in results
+    )
+    mock_vector_db.query.assert_called_once()
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_hybrid_string_and_files(mock_vector_db, tmpdir):
+    # Create string sources
+    string_contents = [
+        "Brandon is learning French.",
+        "Brandon visited Paris last summer.",
+    ]
+    string_sources = [
+        StringKnowledgeSource(content=content, metadata={"preference": "personal"})
+        for content in string_contents
+    ]
+
+    # Create file sources
+    file_contents = [
+        "Brandon prefers tea over coffee.",
+        "Brandon's favorite book is 'The Alchemist'.",
+    ]
+    file_paths = []
+    for i, content in enumerate(file_contents):
+        file_path = Path(tmpdir.join(f"file_{i}.txt"))
+        with open(file_path, "w") as f:
+            f.write(content)
+        file_paths.append(file_path)
+
+    file_sources = [
+        TextFileKnowledgeSource(file_path=path, metadata={"preference": "personal"})
+        for path in file_paths
+    ]
+
+    # Combine string and file sources
+    mock_vector_db.sources = string_sources + file_sources
+    mock_vector_db.query.return_value = [{"context": file_contents[1], "score": 0.9}]
+
+    # Perform a query
+    query = "What is Brandon's favorite book?"
+    results = mock_vector_db.query(query)
+
+    # Assert that the correct information is retrieved
+    assert any("the alchemist" in result["context"].lower() for result in results)
+    mock_vector_db.query.assert_called_once()
+
+
+def test_pdf_knowledge_source(mock_vector_db):
+    # Get the directory of the current file
+    current_dir = Path(__file__).parent
+    # Construct the path to the PDF file
+    pdf_path = current_dir / "crewai_quickstart.pdf"
+
+    # Create a PDFKnowledgeSource
+    pdf_source = PDFKnowledgeSource(
+        file_path=pdf_path, metadata={"preference": "personal"}
+    )
+    mock_vector_db.sources = [pdf_source]
+    mock_vector_db.query.return_value = [
+        {"context": "crewai create crew latest-ai-development", "score": 0.9}
+    ]
+
+    # Perform a query
+    query = "How do you create a crew?"
+    results = mock_vector_db.query(query)
+
+    # Assert that the correct information is retrieved
+    assert any(
+        "crewai create crew latest-ai-development" in result["context"].lower()
+        for result in results
+    )
+    mock_vector_db.query.assert_called_once()
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_csv_knowledge_source(mock_vector_db, tmpdir):
+    """Test CSVKnowledgeSource with a simple CSV file."""
+
+    # Create a CSV file with sample data
+    csv_content = [
+        ["Name", "Age", "City"],
+        ["Brandon", "30", "New York"],
+        ["Alice", "25", "Los Angeles"],
+        ["Bob", "35", "Chicago"],
+    ]
+    csv_path = Path(tmpdir.join("data.csv"))
+    with open(csv_path, "w", encoding="utf-8") as f:
+        for row in csv_content:
+            f.write(",".join(row) + "\n")
+
+    # Create a CSVKnowledgeSource
+    csv_source = CSVKnowledgeSource(
+        file_path=csv_path, metadata={"preference": "personal"}
+    )
+    mock_vector_db.sources = [csv_source]
+    mock_vector_db.query.return_value = [
+        {"context": "Brandon is 30 years old.", "score": 0.9}
+    ]
+
+    # Perform a query
+    query = "How old is Brandon?"
+    results = mock_vector_db.query(query)
+
+    # Assert that the correct information is retrieved
+    assert any("30" in result["context"] for result in results)
+    mock_vector_db.query.assert_called_once()
+
+
+def test_json_knowledge_source(mock_vector_db, tmpdir):
+    """Test JSONKnowledgeSource with a simple JSON file."""
+
+    # Create a JSON file with sample data
+    json_data = {
+        "people": [
+            {"name": "Brandon", "age": 30, "city": "New York"},
+            {"name": "Alice", "age": 25, "city": "Los Angeles"},
+            {"name": "Bob", "age": 35, "city": "Chicago"},
+        ]
+    }
+    json_path = Path(tmpdir.join("data.json"))
+    with open(json_path, "w", encoding="utf-8") as f:
+        import json
+
+        json.dump(json_data, f)
+
+    # Create a JSONKnowledgeSource
+    json_source = JSONKnowledgeSource(
+        file_path=json_path, metadata={"preference": "personal"}
+    )
+    mock_vector_db.sources = [json_source]
+    mock_vector_db.query.return_value = [
+        {"context": "Alice lives in Los Angeles.", "score": 0.9}
+    ]
+
+    # Perform a query
+    query = "Where does Alice reside?"
+    results = mock_vector_db.query(query)
+
+    # Assert that the correct information is retrieved
+    assert any("los angeles" in result["context"].lower() for result in results)
+    mock_vector_db.query.assert_called_once()
+
+
+def test_excel_knowledge_source(mock_vector_db, tmpdir):
+    """Test ExcelKnowledgeSource with a simple Excel file."""
+
+    # Create an Excel file with sample data
+    import pandas as pd
+
+    excel_data = {
+        "Name": ["Brandon", "Alice", "Bob"],
+        "Age": [30, 25, 35],
+        "City": ["New York", "Los Angeles", "Chicago"],
+    }
+    df = pd.DataFrame(excel_data)
+    excel_path = Path(tmpdir.join("data.xlsx"))
+    df.to_excel(excel_path, index=False)
+
+    # Create an ExcelKnowledgeSource
+    excel_source = ExcelKnowledgeSource(
+        file_path=excel_path, metadata={"preference": "personal"}
+    )
+    mock_vector_db.sources = [excel_source]
+    mock_vector_db.query.return_value = [
+        {"context": "Brandon is 30 years old.", "score": 0.9}
+    ]
+
+    # Perform a query
+    query = "What is Brandon's age?"
+    results = mock_vector_db.query(query)
+
+    # Assert that the correct information is retrieved
+    assert any("30" in result["context"] for result in results)
+    mock_vector_db.query.assert_called_once()

tests/pipeline/test_pipeline.py

@@ -38,6 +38,7 @@ def mock_crew_factory():
 
         crew = MockCrew()
         crew.name = name
+        crew.knowledge = None
 
         task_output = TaskOutput(
             description="Test task", raw="Task output", agent="Test Agent"
@@ -67,6 +68,7 @@ def mock_crew_factory():
         crew.process = Process.sequential
         crew.config = None
         crew.cache = True
+        crew.embedder = None
 
         # Add non-empty agents and tasks
         mock_agent = MagicMock(spec=Agent)

uv.lock

@@ -608,7 +608,7 @@ wheels = [
 
 [[package]]
 name = "crewai"
-version = "0.80.0"
+version = "0.83.0"
 source = { editable = "." }
 dependencies = [
     { name = "appdirs" },
@@ -622,9 +622,11 @@ dependencies = [
     { name = "langchain" },
     { name = "litellm" },
     { name = "openai" },
+    { name = "openpyxl" },
     { name = "opentelemetry-api" },
     { name = "opentelemetry-exporter-otlp-proto-http" },
     { name = "opentelemetry-sdk" },
+    { name = "pdfplumber" },
     { name = "pydantic" },
     { name = "python-dotenv" },
     { name = "pyvis" },
@@ -638,9 +640,21 @@ dependencies = [
 agentops = [
     { name = "agentops" },
 ]
+fastembed = [
+    { name = "fastembed" },
+]
 mem0 = [
     { name = "mem0ai" },
 ]
+openpyxl = [
+    { name = "openpyxl" },
+]
+pandas = [
+    { name = "pandas" },
+]
+pdfplumber = [
+    { name = "pdfplumber" },
+]
 tools = [
     { name = "crewai-tools" },
 ]
@@ -674,6 +688,7 @@ requires-dist = [
     { name = "click", specifier = ">=8.1.7" },
     { name = "crewai-tools", specifier = ">=0.14.0" },
     { name = "crewai-tools", marker = "extra == 'tools'", specifier = ">=0.14.0" },
+    { name = "fastembed", marker = "extra == 'fastembed'", specifier = ">=0.4.1" },
     { name = "instructor", specifier = ">=1.3.3" },
     { name = "json-repair", specifier = ">=0.25.2" },
     { name = "jsonref", specifier = ">=1.1.0" },
@@ -681,9 +696,14 @@ requires-dist = [
     { name = "litellm", specifier = ">=1.44.22" },
     { name = "mem0ai", marker = "extra == 'mem0'", specifier = ">=0.1.29" },
     { name = "openai", specifier = ">=1.13.3" },
+    { name = "openpyxl", specifier = ">=3.1.5" },
+    { name = "openpyxl", marker = "extra == 'openpyxl'", specifier = ">=3.1.5" },
     { name = "opentelemetry-api", specifier = ">=1.22.0" },
     { name = "opentelemetry-exporter-otlp-proto-http", specifier = ">=1.22.0" },
     { name = "opentelemetry-sdk", specifier = ">=1.22.0" },
+    { name = "pandas", marker = "extra == 'pandas'", specifier = ">=2.2.3" },
+    { name = "pdfplumber", specifier = ">=0.11.4" },
+    { name = "pdfplumber", marker = "extra == 'pdfplumber'", specifier = ">=0.11.4" },
     { name = "pydantic", specifier = ">=2.4.2" },
     { name = "python-dotenv", specifier = ">=1.0.0" },
     { name = "pyvis", specifier = ">=0.3.2" },
@@ -927,6 +947,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/52/82/3d0355c22bc68cfbb8fbcf670da4c01b31bd7eb516974a08cf7533e89887/embedchain-0.1.125-py3-none-any.whl", hash = "sha256:f87b49732dc192c6b61221830f29e59cf2aff26d8f5d69df81f6f6cf482715c2", size = 211367 },
 ]
 
+[[package]]
+name = "et-xmlfile"
+version = "2.0.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/d3/38/af70d7ab1ae9d4da450eeec1fa3918940a5fafb9055e934af8d6eb0c2313/et_xmlfile-2.0.0.tar.gz", hash = "sha256:dab3f4764309081ce75662649be815c4c9081e88f0837825f90fd28317d4da54", size = 17234 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/c1/8b/5fe2cc11fee489817272089c4203e679c63b570a5aaeb18d852ae3cbba6a/et_xmlfile-2.0.0-py3-none-any.whl", hash = "sha256:7a91720bc756843502c3b7504c77b8fe44217c85c537d85037f0f536151b2caa", size = 18059 },
+]
+
 [[package]]
 name = "exceptiongroup"
 version = "1.2.2"
@@ -985,6 +1014,28 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/c8/0c/92b468e4649e61eaa2d93a92e19a5b57a0f6cecaa236c53a76f3f72a4696/fastavro-1.9.7-cp312-cp312-win_amd64.whl", hash = "sha256:b6b2ccdc78f6afc18c52e403ee68c00478da12142815c1bd8a00973138a166d0", size = 487778 },
 ]
 
+[[package]]
+name = "fastembed"
+version = "0.4.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "huggingface-hub" },
+    { name = "loguru" },
+    { name = "mmh3" },
+    { name = "numpy" },
+    { name = "onnx" },
+    { name = "onnxruntime" },
+    { name = "pillow" },
+    { name = "py-rust-stemmers" },
+    { name = "requests" },
+    { name = "tokenizers" },
+    { name = "tqdm" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/0c/75/0883d15b54016fa99a32cc333182bf862025bf0983daac417a1beabb53bf/fastembed-0.4.1.tar.gz", hash = "sha256:d5dcfffc3554dca48caf16eec35e38c20544c58e396a5d215f238d40c8442718", size = 40461 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/19/ae/1303f005be08ff31686a30421121680b864cc6d82f7cd82cee74a6ff9416/fastembed-0.4.1-py3-none-any.whl", hash = "sha256:f75f02468aafa8de474844f9fbaa89683a3dcfd76521fa83cfc3efc885db61f3", size = 65123 },
+]
+
 [[package]]
 name = "filelock"
 version = "3.16.1"
@@ -2042,6 +2093,19 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/22/f3/89a4d65d1b9286eb5ac6a6e92dd93523d92f3142a832e60c00d5cad64176/litellm-1.50.2-py3-none-any.whl", hash = "sha256:99cac60c78037946ab809b7cfbbadad53507bb2db8ae39391b4be215a0869fdd", size = 6318265 },
 ]
 
+[[package]]
+name = "loguru"
+version = "0.7.2"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "colorama", marker = "sys_platform == 'win32'" },
+    { name = "win32-setctime", marker = "sys_platform == 'win32'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/9e/30/d87a423766b24db416a46e9335b9602b054a72b96a88a241f2b09b560fa8/loguru-0.7.2.tar.gz", hash = "sha256:e671a53522515f34fd406340ee968cb9ecafbc4b36c679da03c18fd8d0bd51ac", size = 145103 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/03/0a/4f6fed21aa246c6b49b561ca55facacc2a44b87d65b8b92362a8e99ba202/loguru-0.7.2-py3-none-any.whl", hash = "sha256:003d71e3d3ed35f0f8984898359d65b79e5b21943f78af86aa5491210429b8eb", size = 62549 },
+]
+
 [[package]]
 name = "mako"
 version = "1.3.6"
@@ -2310,74 +2374,58 @@ wheels = [
 
 [[package]]
 name = "mmh3"
-version = "5.0.1"
+version = "4.1.0"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/e2/08/04ad6419f072ea3f51f9a0f429dd30f5f0a0b02ead7ca11a831117b6f9e8/mmh3-5.0.1.tar.gz", hash = "sha256:7dab080061aeb31a6069a181f27c473a1f67933854e36a3464931f2716508896", size = 32008 }
+sdist = { url = "https://files.pythonhosted.org/packages/63/96/aa247e82878b123468f0079ce2ac77e948315bab91ce45d2934a62e0af95/mmh3-4.1.0.tar.gz", hash = "sha256:a1cf25348b9acd229dda464a094d6170f47d2850a1fcb762a3b6172d2ce6ca4a", size = 26357 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/fa/b9/9a91b0a0e330557cdbf51fc43ca0ba306633f2ec6d2b15e871e288592a32/mmh3-5.0.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:f0a4b4bf05778ed77d820d6e7d0e9bd6beb0c01af10e1ce9233f5d2f814fcafa", size = 52867 },
-    { url = "https://files.pythonhosted.org/packages/da/28/6b37f0d6707872764e1af49f327b0940b6a3ad995d91b3839b90ba35f559/mmh3-5.0.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:ac7a391039aeab95810c2d020b69a94eb6b4b37d4e2374831e92db3a0cdf71c6", size = 38352 },
-    { url = "https://files.pythonhosted.org/packages/76/84/a98f59a620b522f218876a0630b02fc345ecf078f6393595756ddb3aa0b5/mmh3-5.0.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:3a2583b5521ca49756d8d8bceba80627a9cc295f255dcab4e3df7ccc2f09679a", size = 38214 },
-    { url = "https://files.pythonhosted.org/packages/35/cb/4980c7eb6cd31f49d1913a4066562bc9e0af28526750f1232be9688a9cd4/mmh3-5.0.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:081a8423fe53c1ac94f87165f3e4c500125d343410c1a0c5f1703e898a3ef038", size = 93502 },
-    { url = "https://files.pythonhosted.org/packages/65/f3/29726296fadeaf06134a6978f7c453dfa562cf2f0f1faf9ae28b9b8ef76e/mmh3-5.0.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b8b4d72713799755dc8954a7d36d5c20a6c8de7b233c82404d122c7c7c1707cc", size = 98394 },
-    { url = "https://files.pythonhosted.org/packages/35/fd/e181f4f4b250f7b63ee27a7d65e5e290a3ea0e26cc633f4bfd906f04558b/mmh3-5.0.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:389a6fd51efc76d3182d36ec306448559c1244f11227d2bb771bdd0e6cc91321", size = 98052 },
-    { url = "https://files.pythonhosted.org/packages/61/5c/8a5d838da3eb3fb91035ef5eaaea469abab4e8e3fae55607c27a1a07d162/mmh3-5.0.1-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:39f4128edaa074bff721b1d31a72508cba4d2887ee7867f22082e1fe9d4edea0", size = 86320 },
-    { url = "https://files.pythonhosted.org/packages/10/80/3f33a8f4de12cea322607da1a84d001513affb741b3c3cc1277ecb85d34b/mmh3-5.0.1-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1d5d23a94d91aabba3386b3769048d5f4210fdfef80393fece2f34ba5a7b466c", size = 93232 },
-    { url = "https://files.pythonhosted.org/packages/9e/1c/d0ce5f498493be4de2e7e7596e1cbf63315a4c0bb8bb94e3c37c4fad965d/mmh3-5.0.1-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:16347d038361f8b8f24fd2b7ef378c9b68ddee9f7706e46269b6e0d322814713", size = 93590 },
-    { url = "https://files.pythonhosted.org/packages/d9/66/770b5ad35b5a2eb7965f3fcaeaa76148e59543575d2e27b80690c1b0795c/mmh3-5.0.1-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:6e299408565af7d61f2d20a5ffdd77cf2ed902460fe4e6726839d59ba4b72316", size = 88433 },
-    { url = "https://files.pythonhosted.org/packages/14/58/e0d258b18749d8640233976493716a40aa27352dcb1cea941836357dac24/mmh3-5.0.1-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:42050af21ddfc5445ee5a66e73a8fc758c71790305e3ee9e4a85a8e69e810f94", size = 99339 },
-    { url = "https://files.pythonhosted.org/packages/38/26/7267146122deb584cf377975b994d80c6d72c4c8d0e8eedff4d0cc5cd4c8/mmh3-5.0.1-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:2ae9b1f5ef27ec54659920f0404b7ceb39966e28867c461bfe83a05e8d18ddb0", size = 93944 },
-    { url = "https://files.pythonhosted.org/packages/8d/6b/df60b14a2dd383d8848f6f35496c86c7003be3ffb236789e98d002c542c6/mmh3-5.0.1-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:50c2495a02045f3047d71d4ae9cdd7a15efc0bcbb7ff17a18346834a8e2d1d19", size = 92798 },
-    { url = "https://files.pythonhosted.org/packages/0a/3f/d5fecf13915163a15b449e5cc89232a4df90e836ecad1c38121318119d27/mmh3-5.0.1-cp310-cp310-win32.whl", hash = "sha256:c028fa77cddf351ca13b4a56d43c1775652cde0764cadb39120b68f02a23ecf6", size = 39185 },
-    { url = "https://files.pythonhosted.org/packages/74/8e/4bb5ade332a87de633cda21dae09d6002d69601f2b93e9f40302ab2d9acf/mmh3-5.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:c5e741e421ec14400c4aae30890515c201f518403bdef29ae1e00d375bb4bbb5", size = 39766 },
-    { url = "https://files.pythonhosted.org/packages/16/2b/cd5cfa4d7ad40a37655af491f9270909d63fc27bcf0558ec36000ee5347f/mmh3-5.0.1-cp310-cp310-win_arm64.whl", hash = "sha256:b17156d56fabc73dbf41bca677ceb6faed435cc8544f6566d72ea77d8a17e9d0", size = 36540 },
-    { url = "https://files.pythonhosted.org/packages/fb/8a/f3b9cf8b7110fef0f130158d7602af6f5b09f2cf568130814b7c92e2507b/mmh3-5.0.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:9a6d5a9b1b923f1643559ba1fc0bf7a5076c90cbb558878d3bf3641ce458f25d", size = 52867 },
-    { url = "https://files.pythonhosted.org/packages/bf/06/f466e0da3c5bd6fbb1e047f70fd4e9e9563d0268aa56de511f363478dbf2/mmh3-5.0.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:3349b968be555f7334bbcce839da98f50e1e80b1c615d8e2aa847ea4a964a012", size = 38349 },
-    { url = "https://files.pythonhosted.org/packages/13/f0/2d3daca276a4673f82af859e4b0b18befd4e6e54f1017ba48ea9735b2f1b/mmh3-5.0.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:1bd3c94b110e55db02ab9b605029f48a2f7f677c6e58c09d44e42402d438b7e1", size = 38211 },
-    { url = "https://files.pythonhosted.org/packages/e3/56/a2d203ca97702d4e045ac1a46a608393da1a1dddb24f81de664dae940518/mmh3-5.0.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d47ba84d48608f79adbb10bb09986b6dc33eeda5c2d1bd75d00820081b73bde9", size = 95104 },
-    { url = "https://files.pythonhosted.org/packages/ec/45/c7c8ae64e3ae024776a0ce5377c16c6741a3359f3e9505fc35fc5012beb2/mmh3-5.0.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c0217987a8b8525c8d9170f66d036dec4ab45cfbd53d47e8d76125791ceb155e", size = 100049 },
-    { url = "https://files.pythonhosted.org/packages/d5/74/681113776fe406c09870ab2152ffbd214a15bbc8f1d1da9ad73ce594b878/mmh3-5.0.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b2797063a34e78d1b61639a98b0edec1c856fa86ab80c7ec859f1796d10ba429", size = 99671 },
-    { url = "https://files.pythonhosted.org/packages/bf/4f/dbb8be18ce9b6ff8df14bc14348c0404b3091fb51df9c673ebfcf5877db3/mmh3-5.0.1-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8bba16340adcbd47853a2fbe5afdb397549e8f2e79324ff1dced69a3f8afe7c3", size = 87549 },
-    { url = "https://files.pythonhosted.org/packages/5f/82/274d646f3f604c35b7e3d4eb7f3ff08b3bdc6a2c87d797709bb6f084a611/mmh3-5.0.1-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:282797957c9f60b51b9d768a602c25f579420cc9af46feb77d457a27823d270a", size = 94780 },
-    { url = "https://files.pythonhosted.org/packages/c9/a1/f094ca8b8fb5e2ac53201070bda42b0fee80ceb92c153eb99a1453e3aed3/mmh3-5.0.1-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:e4fb670c29e63f954f9e7a2cdcd57b36a854c2538f579ef62681ccbaa1de2b69", size = 90430 },
-    { url = "https://files.pythonhosted.org/packages/d9/23/4732ba68c6ef7242b69bb53b9e1bcb2ef065d68ed85fd26e829fb911ab5a/mmh3-5.0.1-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:8ee7d85438dc6aff328e19ab052086a3c29e8a9b632998a49e5c4b0034e9e8d6", size = 89451 },
-    { url = "https://files.pythonhosted.org/packages/3c/c5/daea5d534fcf20b2399c2a7b1cd00a8d29d4d474247c15c2c94548a1a272/mmh3-5.0.1-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:b7fb5db231f3092444bc13901e6a8d299667126b00636ffbad4a7b45e1051e2f", size = 94703 },
-    { url = "https://files.pythonhosted.org/packages/5e/4a/34d5691e7be7c63c34181387bc69bdcc0005ca93c8b562d68cb5775e0e78/mmh3-5.0.1-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:c100dd441703da5ec136b1d9003ed4a041d8a1136234c9acd887499796df6ad8", size = 91054 },
-    { url = "https://files.pythonhosted.org/packages/5c/3a/ab31bb5e9e1a19a4a997593cbe6ce56710308218ff36c7f76d40ff9c8d2e/mmh3-5.0.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:71f3b765138260fd7a7a2dba0ea5727dabcd18c1f80323c9cfef97a7e86e01d0", size = 89571 },
-    { url = "https://files.pythonhosted.org/packages/0b/79/b986bb067dbfcba6879afe6e723aad1bd53f223450532dd9a4606d0af389/mmh3-5.0.1-cp311-cp311-win32.whl", hash = "sha256:9a76518336247fd17689ce3ae5b16883fd86a490947d46a0193d47fb913e26e3", size = 39187 },
-    { url = "https://files.pythonhosted.org/packages/48/69/97029eda3df0f84edde16a496a2e71bac508fc5d1f0a31e163da071e2670/mmh3-5.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:336bc4df2e44271f1c302d289cc3d78bd52d3eed8d306c7e4bff8361a12bf148", size = 39766 },
-    { url = "https://files.pythonhosted.org/packages/c7/51/538f2b8412303281d8ce2a9a5c4ea84ff81f06de98af0b7c72059727a3bb/mmh3-5.0.1-cp311-cp311-win_arm64.whl", hash = "sha256:af6522722fbbc5999aa66f7244d0986767a46f1fb05accc5200f75b72428a508", size = 36540 },
-    { url = "https://files.pythonhosted.org/packages/75/c7/5b52d0882e7c0dccfaf8786a648e2b26c5307c594abe5cbe98c092607c97/mmh3-5.0.1-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:f2730bb263ed9c388e8860438b057a53e3cc701134a6ea140f90443c4c11aa40", size = 52907 },
-    { url = "https://files.pythonhosted.org/packages/01/b5/9609fa353c27188292748db033323c206f3fc6fbfa124bccf6a42af0da08/mmh3-5.0.1-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:6246927bc293f6d56724536400b85fb85f5be26101fa77d5f97dd5e2a4c69bf2", size = 38389 },
-    { url = "https://files.pythonhosted.org/packages/33/99/49bf3c86244857b3b250c2f54aff22a5a78ef12258af556fa39bb1e80699/mmh3-5.0.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:fbca322519a6e6e25b6abf43e940e1667cf8ea12510e07fb4919b48a0cd1c411", size = 38204 },
-    { url = "https://files.pythonhosted.org/packages/f8/04/8860cab35b48aaefe40cf88344437e79ddc93cf7ff745dacd1cd56a2be1e/mmh3-5.0.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:eae8c19903ed8a1724ad9e67e86f15d198a7a1271a4f9be83d47e38f312ed672", size = 95091 },
-    { url = "https://files.pythonhosted.org/packages/fa/e9/4ac56001a5bab6d26aa3dfabeddea6d7f037fd2972c76803259f51a5af75/mmh3-5.0.1-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a09fd6cc72c07c0c07c3357714234b646d78052487c4a3bd5f7f6e08408cff60", size = 100055 },
-    { url = "https://files.pythonhosted.org/packages/18/e8/7d5fd73f559c423ed5b72f940130c27803a406ee0ffc32ef5422f733df67/mmh3-5.0.1-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2ff8551fee7ae3b11c5d986b6347ade0dccaadd4670ffdb2b944dee120ffcc84", size = 99764 },
-    { url = "https://files.pythonhosted.org/packages/54/d8/c0d89da6c729feec997a9b3b68698894cef12359ade0da95eba9e03b1d5d/mmh3-5.0.1-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e39694c73a5a20c8bf36dfd8676ed351e5234d55751ba4f7562d85449b21ef3f", size = 87650 },
-    { url = "https://files.pythonhosted.org/packages/dd/41/ec0ee3fd5124c83cb767dcea8569bb326f8981cc88c991e3e4e948a31e24/mmh3-5.0.1-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:eba6001989a92f72a89c7cf382fda831678bd780707a66b4f8ca90239fdf2123", size = 94976 },
-    { url = "https://files.pythonhosted.org/packages/8e/fa/e8059199fe6fbb2fd6494302904cb1209b2f8b6899d58059858a280e89a5/mmh3-5.0.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:0771f90c9911811cc606a5c7b7b58f33501c9ee896ed68a6ac22c7d55878ecc0", size = 90485 },
-    { url = "https://files.pythonhosted.org/packages/3a/a0/eb9da5f93dea3f44b8e970f013279d1543ab210ccf63bb030830968682aa/mmh3-5.0.1-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:09b31ed0c0c0920363e96641fac4efde65b1ab62b8df86293142f35a254e72b4", size = 89554 },
-    { url = "https://files.pythonhosted.org/packages/e7/e8/5803181eac4e015b4caf307af22fea74292dca48e580d93afe402dcdc138/mmh3-5.0.1-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:5cf4a8deda0235312db12075331cb417c4ba163770edfe789bde71d08a24b692", size = 94872 },
-    { url = "https://files.pythonhosted.org/packages/ed/f9/4d55063f9dcaed41524f078a85989efdf1d335159af5e70af29942ebae67/mmh3-5.0.1-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:41f7090a95185ef20ac018581a99337f0cbc84a2135171ee3290a9c0d9519585", size = 91326 },
-    { url = "https://files.pythonhosted.org/packages/80/75/0a5acab5291480acd939db80e94448ac937fc7fbfddc0a67b3e721ebfc9c/mmh3-5.0.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:b97b5b368fb7ff22194ec5854f5b12d8de9ab67a0f304728c7f16e5d12135b76", size = 89810 },
-    { url = "https://files.pythonhosted.org/packages/9b/fd/eb1a3573cda74d4c2381d10ded62c128e869954ced1881c15e2bcd97a48f/mmh3-5.0.1-cp312-cp312-win32.whl", hash = "sha256:842516acf04da546f94fad52db125ee619ccbdcada179da51c326a22c4578cb9", size = 39206 },
-    { url = "https://files.pythonhosted.org/packages/66/e8/542ed252924002b84c43a68a080cfd4facbea0d5df361e4f59637638d3c7/mmh3-5.0.1-cp312-cp312-win_amd64.whl", hash = "sha256:d963be0dbfd9fca209c17172f6110787ebf78934af25e3694fe2ba40e55c1e2b", size = 39799 },
-    { url = "https://files.pythonhosted.org/packages/bd/25/ff2cd36c82a23afa57a05cdb52ab467a911fb12c055c8a8238c0d426cbf0/mmh3-5.0.1-cp312-cp312-win_arm64.whl", hash = "sha256:a5da292ceeed8ce8e32b68847261a462d30fd7b478c3f55daae841404f433c15", size = 36537 },
-    { url = "https://files.pythonhosted.org/packages/09/e0/fb19c46265c18311b422ba5ce3e18046ad45c48cfb213fd6dbec23ae6b51/mmh3-5.0.1-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:673e3f1c8d4231d6fb0271484ee34cb7146a6499fc0df80788adb56fd76842da", size = 52909 },
-    { url = "https://files.pythonhosted.org/packages/c3/94/54fc591e7a24c7ce2c531ecfc5715cff932f9d320c2936550cc33d67304d/mmh3-5.0.1-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:f795a306bd16a52ad578b663462cc8e95500b3925d64118ae63453485d67282b", size = 38396 },
-    { url = "https://files.pythonhosted.org/packages/1f/9a/142bcc9d0d28fc8ae45bbfb83926adc069f984cdf3495a71534cc22b8e27/mmh3-5.0.1-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:5ed57a5e28e502a1d60436cc25c76c3a5ba57545f250f2969af231dc1221e0a5", size = 38207 },
-    { url = "https://files.pythonhosted.org/packages/f8/5b/f1c9110aa70321bb1ee713f17851b9534586c63bc25e0110e4fc03ae2450/mmh3-5.0.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:632c28e7612e909dbb6cbe2fe496201ada4695b7715584005689c5dc038e59ad", size = 94988 },
-    { url = "https://files.pythonhosted.org/packages/87/e5/4dc67e7e0e716c641ab0a5875a659e37258417439590feff5c3bd3ff4538/mmh3-5.0.1-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:53fd6bd525a5985e391c43384672d9d6b317fcb36726447347c7fc75bfed34ec", size = 99969 },
-    { url = "https://files.pythonhosted.org/packages/ac/68/d148327337687c53f04ad9ceaedfa9ad155ee0111d0cb06220f044d66720/mmh3-5.0.1-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:dceacf6b0b961a0e499836af3aa62d60633265607aef551b2a3e3c48cdaa5edd", size = 99662 },
-    { url = "https://files.pythonhosted.org/packages/13/79/782adb6df6397947c1097b1e94b7f8d95629a4a73df05cf7207bd5148c1f/mmh3-5.0.1-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8f0738d478fdfb5d920f6aff5452c78f2c35b0eff72caa2a97dfe38e82f93da2", size = 87606 },
-    { url = "https://files.pythonhosted.org/packages/f2/c2/0404383281df049d0e4ccf07fabd659fc1f3da834df6708d934116cbf45d/mmh3-5.0.1-cp313-cp313-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8e70285e7391ab88b872e5bef632bad16b9d99a6d3ca0590656a4753d55988af", size = 94836 },
-    { url = "https://files.pythonhosted.org/packages/c8/33/fda67c5f28e4c2131891cf8cbc3513cfc55881e3cfe26e49328e38ffacb3/mmh3-5.0.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:27e5fc6360aa6b828546a4318da1a7da6bf6e5474ccb053c3a6aa8ef19ff97bd", size = 90492 },
-    { url = "https://files.pythonhosted.org/packages/64/2f/0ed38aefe2a87f30bb1b12e5b75dc69fcffdc16def40d1752d6fc7cbbf96/mmh3-5.0.1-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:7989530c3c1e2c17bf5a0ec2bba09fd19819078ba90beedabb1c3885f5040b0d", size = 89594 },
-    { url = "https://files.pythonhosted.org/packages/95/ab/6e7a5e765fc78e3dbd0a04a04cfdf72e91eb8e31976228e69d82c741a5b4/mmh3-5.0.1-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:cdad7bee649950da7ecd3cbbbd12fb81f1161072ecbdb5acfa0018338c5cb9cf", size = 94929 },
-    { url = "https://files.pythonhosted.org/packages/74/51/f748f00c072006f4a093d9b08853a0e2e3cd5aeaa91343d4e2d942851978/mmh3-5.0.1-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:e143b8f184c1bb58cecd85ab4a4fd6dc65a2d71aee74157392c3fddac2a4a331", size = 91317 },
-    { url = "https://files.pythonhosted.org/packages/df/a1/21ee8017a7feb0270c49f756ff56da9f99bd150dcfe3b3f6f0d4b243423d/mmh3-5.0.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:e5eb12e886f3646dd636f16b76eb23fc0c27e8ff3c1ae73d4391e50ef60b40f6", size = 89861 },
-    { url = "https://files.pythonhosted.org/packages/c2/d2/46a6d070de4659bdf91cd6a62d659f8cc547dadee52b6d02bcbacb3262ed/mmh3-5.0.1-cp313-cp313-win32.whl", hash = "sha256:16e6dddfa98e1c2d021268e72c78951234186deb4df6630e984ac82df63d0a5d", size = 39201 },
-    { url = "https://files.pythonhosted.org/packages/ed/07/316c062f09019b99b248a4183c5333f8eeebe638345484774908a8f2c9c0/mmh3-5.0.1-cp313-cp313-win_amd64.whl", hash = "sha256:d3ffb792d70b8c4a2382af3598dad6ae0c5bd9cee5b7ffcc99aa2f5fd2c1bf70", size = 39807 },
-    { url = "https://files.pythonhosted.org/packages/9d/d3/f7e6d7d062b8d7072c3989a528d9d47486ee5d5ae75250f6e26b4976d098/mmh3-5.0.1-cp313-cp313-win_arm64.whl", hash = "sha256:122fa9ec148383f9124292962bda745f192b47bfd470b2af5fe7bb3982b17896", size = 36539 },
+    { url = "https://files.pythonhosted.org/packages/ef/5a/8609dc74421858f7e94a89dc69221ab9b2c14d0d63a139b46ec190eedc44/mmh3-4.1.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:be5ac76a8b0cd8095784e51e4c1c9c318c19edcd1709a06eb14979c8d850c31a", size = 39433 },
+    { url = "https://files.pythonhosted.org/packages/93/6c/e7a0f07c7082c76964b1ff46aa852f36e2ec6a9c3530dec0afa0b3162fc2/mmh3-4.1.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:98a49121afdfab67cd80e912b36404139d7deceb6773a83620137aaa0da5714c", size = 29280 },
+    { url = "https://files.pythonhosted.org/packages/76/84/60ca728ec7d7e1779a98000d64941c6221786124b4f07bf105a627055890/mmh3-4.1.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:5259ac0535874366e7d1a5423ef746e0d36a9e3c14509ce6511614bdc5a7ef5b", size = 30130 },
+    { url = "https://files.pythonhosted.org/packages/2a/22/f2ec190b491f712d9ef5ea6252204b6f05255ac9af54a7b505adc3128aed/mmh3-4.1.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c5950827ca0453a2be357696da509ab39646044e3fa15cad364eb65d78797437", size = 68837 },
+    { url = "https://files.pythonhosted.org/packages/ae/b9/c1e8065671e1d2f4e280c9c57389e74964f4a5792cac26717ad592002c7d/mmh3-4.1.0-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1dd0f652ae99585b9dd26de458e5f08571522f0402155809fd1dc8852a613a39", size = 72275 },
+    { url = "https://files.pythonhosted.org/packages/6b/18/92bbdb102ab2b4e80084e927187d871758280eb067c649693e42bfc6d0d1/mmh3-4.1.0-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:99d25548070942fab1e4a6f04d1626d67e66d0b81ed6571ecfca511f3edf07e6", size = 70919 },
+    { url = "https://files.pythonhosted.org/packages/e2/cd/391ce1d1bb559871a5d3a6bbb30b82bf51d3e3b42c4e8589cccb201953da/mmh3-4.1.0-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:53db8d9bad3cb66c8f35cbc894f336273f63489ce4ac416634932e3cbe79eb5b", size = 65885 },
+    { url = "https://files.pythonhosted.org/packages/03/87/4b01a43336bd506478850d1bc3d180648b2d26b4acf1fc4bf1df72bf562f/mmh3-4.1.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:75da0f615eb55295a437264cc0b736753f830b09d102aa4c2a7d719bc445ec05", size = 67610 },
+    { url = "https://files.pythonhosted.org/packages/e8/12/b464149a1b7181c7ce431ebf3d24fa994863f2f1abc75b78d202dde966e0/mmh3-4.1.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:b926b07fd678ea84b3a2afc1fa22ce50aeb627839c44382f3d0291e945621e1a", size = 74888 },
+    { url = "https://files.pythonhosted.org/packages/fc/3e/f4eb45a23fc17b970394c1fe74eba157514577ae2d63757684241651d754/mmh3-4.1.0-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:c5b053334f9b0af8559d6da9dc72cef0a65b325ebb3e630c680012323c950bb6", size = 72969 },
+    { url = "https://files.pythonhosted.org/packages/c0/3b/83934fd9494371357da0ca026d55ad427c199d611b97b6ffeecacfd8e720/mmh3-4.1.0-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:5bf33dc43cd6de2cb86e0aa73a1cc6530f557854bbbe5d59f41ef6de2e353d7b", size = 80338 },
+    { url = "https://files.pythonhosted.org/packages/b6/c4/5bcd709ea7269173d7e925402f05e05cf12194ef53cc9912a5ad166f8ded/mmh3-4.1.0-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:fa7eacd2b830727ba3dd65a365bed8a5c992ecd0c8348cf39a05cc77d22f4970", size = 76580 },
+    { url = "https://files.pythonhosted.org/packages/da/6a/4c0680d64475e551d7f4cc78bf0fd247c711ed2717f6bb311934993d1e69/mmh3-4.1.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:42dfd6742b9e3eec599f85270617debfa0bbb913c545bb980c8a4fa7b2d047da", size = 75325 },
+    { url = "https://files.pythonhosted.org/packages/70/bc/e2ed99e580b3dd121f6462147bd5f521c57b3c81c692aa2d416b0678c89f/mmh3-4.1.0-cp310-cp310-win32.whl", hash = "sha256:2974ad343f0d39dcc88e93ee6afa96cedc35a9883bc067febd7ff736e207fa47", size = 31235 },
+    { url = "https://files.pythonhosted.org/packages/73/2b/3aec865da7feb52830782d9fb7c54115cc18815680c244301adf9080622f/mmh3-4.1.0-cp310-cp310-win_amd64.whl", hash = "sha256:74699a8984ded645c1a24d6078351a056f5a5f1fe5838870412a68ac5e28d865", size = 31271 },
+    { url = "https://files.pythonhosted.org/packages/17/2a/925439189ccf562bdcb839aed6263d718359f0c376d673beb3b83d3864ac/mmh3-4.1.0-cp310-cp310-win_arm64.whl", hash = "sha256:f0dc874cedc23d46fc488a987faa6ad08ffa79e44fb08e3cd4d4cf2877c00a00", size = 30147 },
+    { url = "https://files.pythonhosted.org/packages/2e/d6/86beea107e7e9700df9522466346c23a2f54faa81337c86fd17002aa95a6/mmh3-4.1.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:3280a463855b0eae64b681cd5b9ddd9464b73f81151e87bb7c91a811d25619e6", size = 39427 },
+    { url = "https://files.pythonhosted.org/packages/1c/08/65fa5489044e2afc304e8540c6c607d5d7b136ddc5cd8315c13de0adc34c/mmh3-4.1.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:97ac57c6c3301769e757d444fa7c973ceb002cb66534b39cbab5e38de61cd896", size = 29281 },
+    { url = "https://files.pythonhosted.org/packages/b3/aa/98511d3ea3f6ba958136d913be3be3c1009be935a20ecc7b2763f0a605b6/mmh3-4.1.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:a7b6502cdb4dbd880244818ab363c8770a48cdccecf6d729ade0241b736b5ec0", size = 30130 },
+    { url = "https://files.pythonhosted.org/packages/3c/b7/1a93f81643435b0e57f1046c4ffe46f0214693eaede0d9b0a1a236776e70/mmh3-4.1.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:52ba2da04671a9621580ddabf72f06f0e72c1c9c3b7b608849b58b11080d8f14", size = 69072 },
+    { url = "https://files.pythonhosted.org/packages/45/9e/2ff70246aefd9cf146bc6a420c28ed475a0d1a325f31ee203be02f9215d4/mmh3-4.1.0-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:5a5fef4c4ecc782e6e43fbeab09cff1bac82c998a1773d3a5ee6a3605cde343e", size = 72470 },
+    { url = "https://files.pythonhosted.org/packages/dc/cb/57bc1fdbdbe6837aebfca982494e23e2498ee2a89585c9054713b22e4167/mmh3-4.1.0-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5135358a7e00991f73b88cdc8eda5203bf9de22120d10a834c5761dbeb07dd13", size = 71251 },
+    { url = "https://files.pythonhosted.org/packages/4d/c2/46d7d2721b69fbdfd30231309e6395f62ff6744e5c00dd8113b9faa06fba/mmh3-4.1.0-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:cff9ae76a54f7c6fe0167c9c4028c12c1f6de52d68a31d11b6790bb2ae685560", size = 66035 },
+    { url = "https://files.pythonhosted.org/packages/6f/a4/7ba4bcc838818bcf018e26d118d5ddb605c23c4fad040dc4d811f1cfcb04/mmh3-4.1.0-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f6f02576a4d106d7830ca90278868bf0983554dd69183b7bbe09f2fcd51cf54f", size = 67844 },
+    { url = "https://files.pythonhosted.org/packages/71/ed/8e80d1038e7bb15eaf739711d1fc36f2341acb6b1b95fa77003f2799c91e/mmh3-4.1.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:073d57425a23721730d3ff5485e2da489dd3c90b04e86243dd7211f889898106", size = 76724 },
+    { url = "https://files.pythonhosted.org/packages/1c/22/a6a70ca81f0ce8fe2f3a68d89c1184c2d2d0fbe0ee305da50e972c5ff9fa/mmh3-4.1.0-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:71e32ddec7f573a1a0feb8d2cf2af474c50ec21e7a8263026e8d3b4b629805db", size = 75004 },
+    { url = "https://files.pythonhosted.org/packages/73/20/abe50b605760f1f5b6e0b436c650649e69ca478d0f41b154f300367c09e4/mmh3-4.1.0-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:7cbb20b29d57e76a58b40fd8b13a9130db495a12d678d651b459bf61c0714cea", size = 82230 },
+    { url = "https://files.pythonhosted.org/packages/45/80/a1fc99d3ee50b573df0bfbb1ad518463af78d2ebca44bfca3b3f9473d651/mmh3-4.1.0-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:a42ad267e131d7847076bb7e31050f6c4378cd38e8f1bf7a0edd32f30224d5c9", size = 78679 },
+    { url = "https://files.pythonhosted.org/packages/9e/51/6c9ee2ddf3b386f45ff83b6926a5e826635757d91dab04cbf16eee05f9a7/mmh3-4.1.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:4a013979fc9390abadc445ea2527426a0e7a4495c19b74589204f9b71bcaafeb", size = 77382 },
+    { url = "https://files.pythonhosted.org/packages/ee/fa/4b377f244c27fac5f0343cc4dc0d2eb0a08049afc8d5322d07be7461a768/mmh3-4.1.0-cp311-cp311-win32.whl", hash = "sha256:1d3b1cdad7c71b7b88966301789a478af142bddcb3a2bee563f7a7d40519a00f", size = 31232 },
+    { url = "https://files.pythonhosted.org/packages/d1/b0/500ef56c29b276d796bfdb47c16d34fa18a68945e4d730a6fa7d483583ed/mmh3-4.1.0-cp311-cp311-win_amd64.whl", hash = "sha256:0dc6dc32eb03727467da8e17deffe004fbb65e8b5ee2b502d36250d7a3f4e2ec", size = 31276 },
+    { url = "https://files.pythonhosted.org/packages/cc/84/94795e6e710c3861f8f355a12be9c9f4b8433a538c983e75bd4c00496a8a/mmh3-4.1.0-cp311-cp311-win_arm64.whl", hash = "sha256:9ae3a5c1b32dda121c7dc26f9597ef7b01b4c56a98319a7fe86c35b8bc459ae6", size = 30142 },
+    { url = "https://files.pythonhosted.org/packages/18/45/b4d41e86b00eed8c500adbe0007129861710e181c7f49c507ef6beae9496/mmh3-4.1.0-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:0033d60c7939168ef65ddc396611077a7268bde024f2c23bdc283a19123f9e9c", size = 39495 },
+    { url = "https://files.pythonhosted.org/packages/a6/d4/f041b8704cb8d1aad3717105daa582e29818b78a540622dfed84cd00d88f/mmh3-4.1.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:d6af3e2287644b2b08b5924ed3a88c97b87b44ad08e79ca9f93d3470a54a41c5", size = 29334 },
+    { url = "https://files.pythonhosted.org/packages/cb/bb/8f75378e1a83b323f9ed06248333c383e7dac614c2f95e1419965cb91693/mmh3-4.1.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:d82eb4defa245e02bb0b0dc4f1e7ee284f8d212633389c91f7fba99ba993f0a2", size = 30144 },
+    { url = "https://files.pythonhosted.org/packages/3e/50/5e36c1945bd83e780a37361fc1999fc4c5a59ecc10a373557fdf0e58eb1f/mmh3-4.1.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ba245e94b8d54765e14c2d7b6214e832557e7856d5183bc522e17884cab2f45d", size = 69094 },
+    { url = "https://files.pythonhosted.org/packages/70/c7/6ae37e7519a938226469476b84bcea2650e2a2cc7a848e6a206ea98ecee3/mmh3-4.1.0-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:bb04e2feeabaad6231e89cd43b3d01a4403579aa792c9ab6fdeef45cc58d4ec0", size = 72611 },
+    { url = "https://files.pythonhosted.org/packages/5e/47/6613f69f57f1e5045e66b22fae9c2fb39ef754c455805d3917f6073e316e/mmh3-4.1.0-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:1e3b1a27def545ce11e36158ba5d5390cdbc300cfe456a942cc89d649cf7e3b2", size = 71462 },
+    { url = "https://files.pythonhosted.org/packages/e0/0a/e423db18ce7b479c4b96381a112b443f0985c611de420f95c58a9f934080/mmh3-4.1.0-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ce0ab79ff736d7044e5e9b3bfe73958a55f79a4ae672e6213e92492ad5e734d5", size = 66165 },
+    { url = "https://files.pythonhosted.org/packages/4c/7b/bfeb68bee5bddc8baf7ef630b93edc0a533202d84eb076dbb6c77e7e5fd5/mmh3-4.1.0-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3b02268be6e0a8eeb8a924d7db85f28e47344f35c438c1e149878bb1c47b1cd3", size = 68088 },
+    { url = "https://files.pythonhosted.org/packages/d4/a6/b82e30143997c05776887f5177f724e3b714aa7e7346fbe2ec70f52abcd0/mmh3-4.1.0-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:deb887f5fcdaf57cf646b1e062d56b06ef2f23421c80885fce18b37143cba828", size = 76241 },
+    { url = "https://files.pythonhosted.org/packages/6c/60/a3d5872cf7610fcb13e36c472476020c5cf217b23c092bad452eb7784407/mmh3-4.1.0-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:99dd564e9e2b512eb117bd0cbf0f79a50c45d961c2a02402787d581cec5448d5", size = 74538 },
+    { url = "https://files.pythonhosted.org/packages/f6/d5/742173a94c78f4edab71c04097f6f9150c47f8fd034d592f5f34a9444719/mmh3-4.1.0-cp312-cp312-musllinux_1_1_ppc64le.whl", hash = "sha256:08373082dfaa38fe97aa78753d1efd21a1969e51079056ff552e687764eafdfe", size = 81793 },
+    { url = "https://files.pythonhosted.org/packages/d0/7a/a1db0efe7c67b761d83be3d50e35ef26628ef56b3b8bc776d07412ee8b16/mmh3-4.1.0-cp312-cp312-musllinux_1_1_s390x.whl", hash = "sha256:54b9c6a2ea571b714e4fe28d3e4e2db37abfd03c787a58074ea21ee9a8fd1740", size = 78217 },
+    { url = "https://files.pythonhosted.org/packages/b3/78/1ff8da7c859cd09704e2f500588d171eda9688fcf6f29e028ef261262a16/mmh3-4.1.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:a7b1edf24c69e3513f879722b97ca85e52f9032f24a52284746877f6a7304086", size = 77052 },
+    { url = "https://files.pythonhosted.org/packages/ed/c7/cf16ace81fc9fbe54a75c914306252af26c6ea485366bb3b579bf6e3dbb8/mmh3-4.1.0-cp312-cp312-win32.whl", hash = "sha256:411da64b951f635e1e2284b71d81a5a83580cea24994b328f8910d40bed67276", size = 31277 },
+    { url = "https://files.pythonhosted.org/packages/d2/0b/b3b1637dca9414451edf287fd91e667e7231d5ffd7498137fe011951fc0a/mmh3-4.1.0-cp312-cp312-win_amd64.whl", hash = "sha256:bebc3ecb6ba18292e3d40c8712482b4477abd6981c2ebf0e60869bd90f8ac3a9", size = 31318 },
+    { url = "https://files.pythonhosted.org/packages/dd/6c/c0f06040c58112ccbd0df989055ede98f7c1a1f392dc6a3fc63ec6c124ec/mmh3-4.1.0-cp312-cp312-win_arm64.whl", hash = "sha256:168473dd608ade6a8d2ba069600b35199a9af837d96177d3088ca91f2b3798e3", size = 30147 },
 ]
 
 [[package]]
@@ -2572,6 +2620,33 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/7e/80/cab10959dc1faead58dc8384a781dfbf93cb4d33d50988f7a69f1b7c9bbe/oauthlib-3.2.2-py3-none-any.whl", hash = "sha256:8139f29aac13e25d502680e9e19963e83f16838d48a0d71c287fe40e7067fbca", size = 151688 },
 ]
 
+[[package]]
+name = "onnx"
+version = "1.17.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "numpy" },
+    { name = "protobuf" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/9a/54/0e385c26bf230d223810a9c7d06628d954008a5e5e4b73ee26ef02327282/onnx-1.17.0.tar.gz", hash = "sha256:48ca1a91ff73c1d5e3ea2eef20ae5d0e709bb8a2355ed798ffc2169753013fd3", size = 12165120 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/2e/29/57053ba7787788ac75efb095cfc1ae290436b6d3a26754693cd7ed1b4fac/onnx-1.17.0-cp310-cp310-macosx_12_0_universal2.whl", hash = "sha256:38b5df0eb22012198cdcee527cc5f917f09cce1f88a69248aaca22bd78a7f023", size = 16645616 },
+    { url = "https://files.pythonhosted.org/packages/75/0d/831807a18db2a5e8f7813848c59272b904a4ef3939fe4d1288cbce9ea735/onnx-1.17.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d545335cb49d4d8c47cc803d3a805deb7ad5d9094dc67657d66e568610a36d7d", size = 15908420 },
+    { url = "https://files.pythonhosted.org/packages/dd/5b/c4f95dbe652d14aeba9afaceb177e9ffc48ac3c03048dd3f872f26f07e34/onnx-1.17.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3193a3672fc60f1a18c0f4c93ac81b761bc72fd8a6c2035fa79ff5969f07713e", size = 16046244 },
+    { url = "https://files.pythonhosted.org/packages/08/a9/c1f218085043dccc6311460239e253fa6957cf12ee4b0a56b82014938d0b/onnx-1.17.0-cp310-cp310-win32.whl", hash = "sha256:0141c2ce806c474b667b7e4499164227ef594584da432fd5613ec17c1855e311", size = 14423516 },
+    { url = "https://files.pythonhosted.org/packages/0e/d3/d26ebf590a65686dde6b27fef32493026c5be9e42083340d947395f93405/onnx-1.17.0-cp310-cp310-win_amd64.whl", hash = "sha256:dfd777d95c158437fda6b34758f0877d15b89cbe9ff45affbedc519b35345cf9", size = 14528496 },
+    { url = "https://files.pythonhosted.org/packages/e5/a9/8d1b1d53aec70df53e0f57e9f9fcf47004276539e29230c3d5f1f50719ba/onnx-1.17.0-cp311-cp311-macosx_12_0_universal2.whl", hash = "sha256:d6fc3a03fc0129b8b6ac03f03bc894431ffd77c7d79ec023d0afd667b4d35869", size = 16647991 },
+    { url = "https://files.pythonhosted.org/packages/7b/e3/cc80110e5996ca61878f7b4c73c7a286cd88918ff35eacb60dc75ab11ef5/onnx-1.17.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f01a4b63d4e1d8ec3e2f069e7b798b2955810aa434f7361f01bc8ca08d69cce4", size = 15908949 },
+    { url = "https://files.pythonhosted.org/packages/b1/2f/91092557ed478e323a2b4471e2081fdf88d1dd52ae988ceaf7db4e4506ff/onnx-1.17.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4a183c6178be001bf398260e5ac2c927dc43e7746e8638d6c05c20e321f8c949", size = 16048190 },
+    { url = "https://files.pythonhosted.org/packages/ac/59/9ea23fc22d0bb853133f363e6248e31bcbc6c1c90543a3938c00412ac02a/onnx-1.17.0-cp311-cp311-win32.whl", hash = "sha256:081ec43a8b950171767d99075b6b92553901fa429d4bc5eb3ad66b36ef5dbe3a", size = 14424299 },
+    { url = "https://files.pythonhosted.org/packages/51/a5/19b0dfcb567b62e7adf1a21b08b23224f0c2d13842aee4d0abc6f07f9cf5/onnx-1.17.0-cp311-cp311-win_amd64.whl", hash = "sha256:95c03e38671785036bb704c30cd2e150825f6ab4763df3a4f1d249da48525957", size = 14529142 },
+    { url = "https://files.pythonhosted.org/packages/b4/dd/c416a11a28847fafb0db1bf43381979a0f522eb9107b831058fde012dd56/onnx-1.17.0-cp312-cp312-macosx_12_0_universal2.whl", hash = "sha256:0e906e6a83437de05f8139ea7eaf366bf287f44ae5cc44b2850a30e296421f2f", size = 16651271 },
+    { url = "https://files.pythonhosted.org/packages/f0/6c/f040652277f514ecd81b7251841f96caa5538365af7df07f86c6018cda2b/onnx-1.17.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3d955ba2939878a520a97614bcf2e79c1df71b29203e8ced478fa78c9a9c63c2", size = 15907522 },
+    { url = "https://files.pythonhosted.org/packages/3d/7c/67f4952d1b56b3f74a154b97d0dd0630d525923b354db117d04823b8b49b/onnx-1.17.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4f3fb5cc4e2898ac5312a7dc03a65133dd2abf9a5e520e69afb880a7251ec97a", size = 16046307 },
+    { url = "https://files.pythonhosted.org/packages/ae/20/6da11042d2ab870dfb4ce4a6b52354d7651b6b4112038b6d2229ab9904c4/onnx-1.17.0-cp312-cp312-win32.whl", hash = "sha256:317870fca3349d19325a4b7d1b5628f6de3811e9710b1e3665c68b073d0e68d7", size = 14424235 },
+    { url = "https://files.pythonhosted.org/packages/35/55/c4d11bee1fdb0c4bd84b4e3562ff811a19b63266816870ae1f95567aa6e1/onnx-1.17.0-cp312-cp312-win_amd64.whl", hash = "sha256:659b8232d627a5460d74fd3c96947ae83db6d03f035ac633e20cd69cfa029227", size = 14530453 },
+]
+
 [[package]]
 name = "onnxruntime"
 version = "1.19.2"
@@ -2621,6 +2696,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/ad/31/28a83e124e9f9dd04c83b5aeb6f8b1770f45addde4dd3d34d9a9091590ad/openai-1.52.1-py3-none-any.whl", hash = "sha256:f23e83df5ba04ee0e82c8562571e8cb596cd88f9a84ab783e6c6259e5ffbfb4a", size = 386945 },
 ]
 
+[[package]]
+name = "openpyxl"
+version = "3.1.5"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "et-xmlfile" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/3d/f9/88d94a75de065ea32619465d2f77b29a0469500e99012523b91cc4141cd1/openpyxl-3.1.5.tar.gz", hash = "sha256:cf0e3cf56142039133628b5acffe8ef0c12bc902d2aadd3e0fe5878dc08d1050", size = 186464 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/c0/da/977ded879c29cbd04de313843e76868e6e13408a94ed6b987245dc7c8506/openpyxl-3.1.5-py2.py3-none-any.whl", hash = "sha256:5282c12b107bffeef825f4617dc029afaf41d0ea60823bbb665ef3079dc79de2", size = 250910 },
+]
+
 [[package]]
 name = "opentelemetry-api"
 version = "1.27.0"
@@ -2935,6 +3022,33 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/cc/20/ff623b09d963f88bfde16306a54e12ee5ea43e9b597108672ff3a408aad6/pathspec-0.12.1-py3-none-any.whl", hash = "sha256:a0d503e138a4c123b27490a4f7beda6a01c6f288df0e4a8b79c7eb0dc7b4cc08", size = 31191 },
 ]
 
+[[package]]
+name = "pdfminer-six"
+version = "20231228"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "charset-normalizer" },
+    { name = "cryptography" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/31/b1/a43e3bd872ded4deea4f8efc7aff1703fca8c5455d0c06e20506a06a44ff/pdfminer.six-20231228.tar.gz", hash = "sha256:6004da3ad1a7a4d45930cb950393df89b068e73be365a6ff64a838d37bcb08c4", size = 7362505 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/eb/9c/e46fe7502b32d7db6af6e36a9105abb93301fa1ec475b5ddcba8b35ae23a/pdfminer.six-20231228-py3-none-any.whl", hash = "sha256:e8d3c3310e6fbc1fe414090123ab01351634b4ecb021232206c4c9a8ca3e3b8f", size = 5614515 },
+]
+
+[[package]]
+name = "pdfplumber"
+version = "0.11.4"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "pdfminer-six" },
+    { name = "pillow" },
+    { name = "pypdfium2" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/ca/f0/457bda3629dfa5b01c645519fe30230e1739751f6645e23fca2dabf6c2e5/pdfplumber-0.11.4.tar.gz", hash = "sha256:147b55cde2351fcb9523b46b09cc771eea3602faecfb60d463c6bf951694fbe8", size = 113305 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/d0/87/415cb472981a8d2e36beeeadf074ebb686cc2bfe8d18de973232da291bd5/pdfplumber-0.11.4-py3-none-any.whl", hash = "sha256:6150f0678c7aaba974ac09839c17475d6c0c4d126b5f92cb85154885f31c6d73", size = 59182 },
+]
+
 [[package]]
 name = "pexpect"
 version = "4.9.0"
@@ -2949,69 +3063,61 @@ wheels = [
 
 [[package]]
 name = "pillow"
-version = "11.0.0"
+version = "10.4.0"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/a5/26/0d95c04c868f6bdb0c447e3ee2de5564411845e36a858cfd63766bc7b563/pillow-11.0.0.tar.gz", hash = "sha256:72bacbaf24ac003fea9bff9837d1eedb6088758d41e100c1552930151f677739", size = 46737780 }
+sdist = { url = "https://files.pythonhosted.org/packages/cd/74/ad3d526f3bf7b6d3f408b73fde271ec69dfac8b81341a318ce825f2b3812/pillow-10.4.0.tar.gz", hash = "sha256:166c1cd4d24309b30d61f79f4a9114b7b2313d7450912277855ff5dfd7cd4a06", size = 46555059 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/98/fb/a6ce6836bd7fd93fbf9144bf54789e02babc27403b50a9e1583ee877d6da/pillow-11.0.0-cp310-cp310-macosx_10_10_x86_64.whl", hash = "sha256:6619654954dc4936fcff82db8eb6401d3159ec6be81e33c6000dfd76ae189947", size = 3154708 },
-    { url = "https://files.pythonhosted.org/packages/6a/1d/1f51e6e912d8ff316bb3935a8cda617c801783e0b998bf7a894e91d3bd4c/pillow-11.0.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:b3c5ac4bed7519088103d9450a1107f76308ecf91d6dabc8a33a2fcfb18d0fba", size = 2979223 },
-    { url = "https://files.pythonhosted.org/packages/90/83/e2077b0192ca8a9ef794dbb74700c7e48384706467067976c2a95a0f40a1/pillow-11.0.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a65149d8ada1055029fcb665452b2814fe7d7082fcb0c5bed6db851cb69b2086", size = 4183167 },
-    { url = "https://files.pythonhosted.org/packages/0e/74/467af0146970a98349cdf39e9b79a6cc8a2e7558f2c01c28a7b6b85c5bda/pillow-11.0.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:88a58d8ac0cc0e7f3a014509f0455248a76629ca9b604eca7dc5927cc593c5e9", size = 4283912 },
-    { url = "https://files.pythonhosted.org/packages/85/b1/d95d4f7ca3a6c1ae120959605875a31a3c209c4e50f0029dc1a87566cf46/pillow-11.0.0-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:c26845094b1af3c91852745ae78e3ea47abf3dbcd1cf962f16b9a5fbe3ee8488", size = 4195815 },
-    { url = "https://files.pythonhosted.org/packages/41/c3/94f33af0762ed76b5a237c5797e088aa57f2b7fa8ee7932d399087be66a8/pillow-11.0.0-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:1a61b54f87ab5786b8479f81c4b11f4d61702830354520837f8cc791ebba0f5f", size = 4366117 },
-    { url = "https://files.pythonhosted.org/packages/ba/3c/443e7ef01f597497268899e1cca95c0de947c9bbf77a8f18b3c126681e5d/pillow-11.0.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:674629ff60030d144b7bca2b8330225a9b11c482ed408813924619c6f302fdbb", size = 4278607 },
-    { url = "https://files.pythonhosted.org/packages/26/95/1495304448b0081e60c0c5d63f928ef48bb290acee7385804426fa395a21/pillow-11.0.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:598b4e238f13276e0008299bd2482003f48158e2b11826862b1eb2ad7c768b97", size = 4410685 },
-    { url = "https://files.pythonhosted.org/packages/45/da/861e1df971ef0de9870720cb309ca4d553b26a9483ec9be3a7bf1de4a095/pillow-11.0.0-cp310-cp310-win32.whl", hash = "sha256:9a0f748eaa434a41fccf8e1ee7a3eed68af1b690e75328fd7a60af123c193b50", size = 2249185 },
-    { url = "https://files.pythonhosted.org/packages/d5/4e/78f7c5202ea2a772a5ab05069c1b82503e6353cd79c7e474d4945f4b82c3/pillow-11.0.0-cp310-cp310-win_amd64.whl", hash = "sha256:a5629742881bcbc1f42e840af185fd4d83a5edeb96475a575f4da50d6ede337c", size = 2566726 },
-    { url = "https://files.pythonhosted.org/packages/77/e4/6e84eada35cbcc646fc1870f72ccfd4afacb0fae0c37ffbffe7f5dc24bf1/pillow-11.0.0-cp310-cp310-win_arm64.whl", hash = "sha256:ee217c198f2e41f184f3869f3e485557296d505b5195c513b2bfe0062dc537f1", size = 2254585 },
-    { url = "https://files.pythonhosted.org/packages/f0/eb/f7e21b113dd48a9c97d364e0915b3988c6a0b6207652f5a92372871b7aa4/pillow-11.0.0-cp311-cp311-macosx_10_10_x86_64.whl", hash = "sha256:1c1d72714f429a521d8d2d018badc42414c3077eb187a59579f28e4270b4b0fc", size = 3154705 },
-    { url = "https://files.pythonhosted.org/packages/25/b3/2b54a1d541accebe6bd8b1358b34ceb2c509f51cb7dcda8687362490da5b/pillow-11.0.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:499c3a1b0d6fc8213519e193796eb1a86a1be4b1877d678b30f83fd979811d1a", size = 2979222 },
-    { url = "https://files.pythonhosted.org/packages/20/12/1a41eddad8265c5c19dda8fb6c269ce15ee25e0b9f8f26286e6202df6693/pillow-11.0.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c8b2351c85d855293a299038e1f89db92a2f35e8d2f783489c6f0b2b5f3fe8a3", size = 4190220 },
-    { url = "https://files.pythonhosted.org/packages/a9/9b/8a8c4d07d77447b7457164b861d18f5a31ae6418ef5c07f6f878fa09039a/pillow-11.0.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6f4dba50cfa56f910241eb7f883c20f1e7b1d8f7d91c750cd0b318bad443f4d5", size = 4291399 },
-    { url = "https://files.pythonhosted.org/packages/fc/e4/130c5fab4a54d3991129800dd2801feeb4b118d7630148cd67f0e6269d4c/pillow-11.0.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:5ddbfd761ee00c12ee1be86c9c0683ecf5bb14c9772ddbd782085779a63dd55b", size = 4202709 },
-    { url = "https://files.pythonhosted.org/packages/39/63/b3fc299528d7df1f678b0666002b37affe6b8751225c3d9c12cf530e73ed/pillow-11.0.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:45c566eb10b8967d71bf1ab8e4a525e5a93519e29ea071459ce517f6b903d7fa", size = 4372556 },
-    { url = "https://files.pythonhosted.org/packages/c6/a6/694122c55b855b586c26c694937d36bb8d3b09c735ff41b2f315c6e66a10/pillow-11.0.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:b4fd7bd29610a83a8c9b564d457cf5bd92b4e11e79a4ee4716a63c959699b306", size = 4287187 },
-    { url = "https://files.pythonhosted.org/packages/ba/a9/f9d763e2671a8acd53d29b1e284ca298bc10a595527f6be30233cdb9659d/pillow-11.0.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:cb929ca942d0ec4fac404cbf520ee6cac37bf35be479b970c4ffadf2b6a1cad9", size = 4418468 },
-    { url = "https://files.pythonhosted.org/packages/6e/0e/b5cbad2621377f11313a94aeb44ca55a9639adabcaaa073597a1925f8c26/pillow-11.0.0-cp311-cp311-win32.whl", hash = "sha256:006bcdd307cc47ba43e924099a038cbf9591062e6c50e570819743f5607404f5", size = 2249249 },
-    { url = "https://files.pythonhosted.org/packages/dc/83/1470c220a4ff06cd75fc609068f6605e567ea51df70557555c2ab6516b2c/pillow-11.0.0-cp311-cp311-win_amd64.whl", hash = "sha256:52a2d8323a465f84faaba5236567d212c3668f2ab53e1c74c15583cf507a0291", size = 2566769 },
-    { url = "https://files.pythonhosted.org/packages/52/98/def78c3a23acee2bcdb2e52005fb2810ed54305602ec1bfcfab2bda6f49f/pillow-11.0.0-cp311-cp311-win_arm64.whl", hash = "sha256:16095692a253047fe3ec028e951fa4221a1f3ed3d80c397e83541a3037ff67c9", size = 2254611 },
-    { url = "https://files.pythonhosted.org/packages/1c/a3/26e606ff0b2daaf120543e537311fa3ae2eb6bf061490e4fea51771540be/pillow-11.0.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:d2c0a187a92a1cb5ef2c8ed5412dd8d4334272617f532d4ad4de31e0495bd923", size = 3147642 },
-    { url = "https://files.pythonhosted.org/packages/4f/d5/1caabedd8863526a6cfa44ee7a833bd97f945dc1d56824d6d76e11731939/pillow-11.0.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:084a07ef0821cfe4858fe86652fffac8e187b6ae677e9906e192aafcc1b69903", size = 2978999 },
-    { url = "https://files.pythonhosted.org/packages/d9/ff/5a45000826a1aa1ac6874b3ec5a856474821a1b59d838c4f6ce2ee518fe9/pillow-11.0.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8069c5179902dcdce0be9bfc8235347fdbac249d23bd90514b7a47a72d9fecf4", size = 4196794 },
-    { url = "https://files.pythonhosted.org/packages/9d/21/84c9f287d17180f26263b5f5c8fb201de0f88b1afddf8a2597a5c9fe787f/pillow-11.0.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f02541ef64077f22bf4924f225c0fd1248c168f86e4b7abdedd87d6ebaceab0f", size = 4300762 },
-    { url = "https://files.pythonhosted.org/packages/84/39/63fb87cd07cc541438b448b1fed467c4d687ad18aa786a7f8e67b255d1aa/pillow-11.0.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:fcb4621042ac4b7865c179bb972ed0da0218a076dc1820ffc48b1d74c1e37fe9", size = 4210468 },
-    { url = "https://files.pythonhosted.org/packages/7f/42/6e0f2c2d5c60f499aa29be14f860dd4539de322cd8fb84ee01553493fb4d/pillow-11.0.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:00177a63030d612148e659b55ba99527803288cea7c75fb05766ab7981a8c1b7", size = 4381824 },
-    { url = "https://files.pythonhosted.org/packages/31/69/1ef0fb9d2f8d2d114db982b78ca4eeb9db9a29f7477821e160b8c1253f67/pillow-11.0.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:8853a3bf12afddfdf15f57c4b02d7ded92c7a75a5d7331d19f4f9572a89c17e6", size = 4296436 },
-    { url = "https://files.pythonhosted.org/packages/44/ea/dad2818c675c44f6012289a7c4f46068c548768bc6c7f4e8c4ae5bbbc811/pillow-11.0.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:3107c66e43bda25359d5ef446f59c497de2b5ed4c7fdba0894f8d6cf3822dafc", size = 4429714 },
-    { url = "https://files.pythonhosted.org/packages/af/3a/da80224a6eb15bba7a0dcb2346e2b686bb9bf98378c0b4353cd88e62b171/pillow-11.0.0-cp312-cp312-win32.whl", hash = "sha256:86510e3f5eca0ab87429dd77fafc04693195eec7fd6a137c389c3eeb4cfb77c6", size = 2249631 },
-    { url = "https://files.pythonhosted.org/packages/57/97/73f756c338c1d86bb802ee88c3cab015ad7ce4b838f8a24f16b676b1ac7c/pillow-11.0.0-cp312-cp312-win_amd64.whl", hash = "sha256:8ec4a89295cd6cd4d1058a5e6aec6bf51e0eaaf9714774e1bfac7cfc9051db47", size = 2567533 },
-    { url = "https://files.pythonhosted.org/packages/0b/30/2b61876e2722374558b871dfbfcbe4e406626d63f4f6ed92e9c8e24cac37/pillow-11.0.0-cp312-cp312-win_arm64.whl", hash = "sha256:27a7860107500d813fcd203b4ea19b04babe79448268403172782754870dac25", size = 2254890 },
-    { url = "https://files.pythonhosted.org/packages/63/24/e2e15e392d00fcf4215907465d8ec2a2f23bcec1481a8ebe4ae760459995/pillow-11.0.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:bcd1fb5bb7b07f64c15618c89efcc2cfa3e95f0e3bcdbaf4642509de1942a699", size = 3147300 },
-    { url = "https://files.pythonhosted.org/packages/43/72/92ad4afaa2afc233dc44184adff289c2e77e8cd916b3ddb72ac69495bda3/pillow-11.0.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:0e038b0745997c7dcaae350d35859c9715c71e92ffb7e0f4a8e8a16732150f38", size = 2978742 },
-    { url = "https://files.pythonhosted.org/packages/9e/da/c8d69c5bc85d72a8523fe862f05ababdc52c0a755cfe3d362656bb86552b/pillow-11.0.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0ae08bd8ffc41aebf578c2af2f9d8749d91f448b3bfd41d7d9ff573d74f2a6b2", size = 4194349 },
-    { url = "https://files.pythonhosted.org/packages/cd/e8/686d0caeed6b998351d57796496a70185376ed9c8ec7d99e1d19ad591fc6/pillow-11.0.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d69bfd8ec3219ae71bcde1f942b728903cad25fafe3100ba2258b973bd2bc1b2", size = 4298714 },
-    { url = "https://files.pythonhosted.org/packages/ec/da/430015cec620d622f06854be67fd2f6721f52fc17fca8ac34b32e2d60739/pillow-11.0.0-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:61b887f9ddba63ddf62fd02a3ba7add935d053b6dd7d58998c630e6dbade8527", size = 4208514 },
-    { url = "https://files.pythonhosted.org/packages/44/ae/7e4f6662a9b1cb5f92b9cc9cab8321c381ffbee309210940e57432a4063a/pillow-11.0.0-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:c6a660307ca9d4867caa8d9ca2c2658ab685de83792d1876274991adec7b93fa", size = 4380055 },
-    { url = "https://files.pythonhosted.org/packages/74/d5/1a807779ac8a0eeed57f2b92a3c32ea1b696e6140c15bd42eaf908a261cd/pillow-11.0.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:73e3a0200cdda995c7e43dd47436c1548f87a30bb27fb871f352a22ab8dcf45f", size = 4296751 },
-    { url = "https://files.pythonhosted.org/packages/38/8c/5fa3385163ee7080bc13026d59656267daaaaf3c728c233d530e2c2757c8/pillow-11.0.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:fba162b8872d30fea8c52b258a542c5dfd7b235fb5cb352240c8d63b414013eb", size = 4430378 },
-    { url = "https://files.pythonhosted.org/packages/ca/1d/ad9c14811133977ff87035bf426875b93097fb50af747793f013979facdb/pillow-11.0.0-cp313-cp313-win32.whl", hash = "sha256:f1b82c27e89fffc6da125d5eb0ca6e68017faf5efc078128cfaa42cf5cb38798", size = 2249588 },
-    { url = "https://files.pythonhosted.org/packages/fb/01/3755ba287dac715e6afdb333cb1f6d69740a7475220b4637b5ce3d78cec2/pillow-11.0.0-cp313-cp313-win_amd64.whl", hash = "sha256:8ba470552b48e5835f1d23ecb936bb7f71d206f9dfeee64245f30c3270b994de", size = 2567509 },
-    { url = "https://files.pythonhosted.org/packages/c0/98/2c7d727079b6be1aba82d195767d35fcc2d32204c7a5820f822df5330152/pillow-11.0.0-cp313-cp313-win_arm64.whl", hash = "sha256:846e193e103b41e984ac921b335df59195356ce3f71dcfd155aa79c603873b84", size = 2254791 },
-    { url = "https://files.pythonhosted.org/packages/eb/38/998b04cc6f474e78b563716b20eecf42a2fa16a84589d23c8898e64b0ffd/pillow-11.0.0-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:4ad70c4214f67d7466bea6a08061eba35c01b1b89eaa098040a35272a8efb22b", size = 3150854 },
-    { url = "https://files.pythonhosted.org/packages/13/8e/be23a96292113c6cb26b2aa3c8b3681ec62b44ed5c2bd0b258bd59503d3c/pillow-11.0.0-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:6ec0d5af64f2e3d64a165f490d96368bb5dea8b8f9ad04487f9ab60dc4bb6003", size = 2982369 },
-    { url = "https://files.pythonhosted.org/packages/97/8a/3db4eaabb7a2ae8203cd3a332a005e4aba00067fc514aaaf3e9721be31f1/pillow-11.0.0-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c809a70e43c7977c4a42aefd62f0131823ebf7dd73556fa5d5950f5b354087e2", size = 4333703 },
-    { url = "https://files.pythonhosted.org/packages/28/ac/629ffc84ff67b9228fe87a97272ab125bbd4dc462745f35f192d37b822f1/pillow-11.0.0-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:4b60c9520f7207aaf2e1d94de026682fc227806c6e1f55bba7606d1c94dd623a", size = 4412550 },
-    { url = "https://files.pythonhosted.org/packages/d6/07/a505921d36bb2df6868806eaf56ef58699c16c388e378b0dcdb6e5b2fb36/pillow-11.0.0-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:1e2688958a840c822279fda0086fec1fdab2f95bf2b717b66871c4ad9859d7e8", size = 4461038 },
-    { url = "https://files.pythonhosted.org/packages/d6/b9/fb620dd47fc7cc9678af8f8bd8c772034ca4977237049287e99dda360b66/pillow-11.0.0-cp313-cp313t-win32.whl", hash = "sha256:607bbe123c74e272e381a8d1957083a9463401f7bd01287f50521ecb05a313f8", size = 2253197 },
-    { url = "https://files.pythonhosted.org/packages/df/86/25dde85c06c89d7fc5db17940f07aae0a56ac69aa9ccb5eb0f09798862a8/pillow-11.0.0-cp313-cp313t-win_amd64.whl", hash = "sha256:5c39ed17edea3bc69c743a8dd3e9853b7509625c2462532e62baa0732163a904", size = 2572169 },
-    { url = "https://files.pythonhosted.org/packages/51/85/9c33f2517add612e17f3381aee7c4072779130c634921a756c97bc29fb49/pillow-11.0.0-cp313-cp313t-win_arm64.whl", hash = "sha256:75acbbeb05b86bc53cbe7b7e6fe00fbcf82ad7c684b3ad82e3d711da9ba287d3", size = 2256828 },
-    { url = "https://files.pythonhosted.org/packages/36/57/42a4dd825eab762ba9e690d696d894ba366e06791936056e26e099398cda/pillow-11.0.0-pp310-pypy310_pp73-macosx_10_15_x86_64.whl", hash = "sha256:1187739620f2b365de756ce086fdb3604573337cc28a0d3ac4a01ab6b2d2a6d2", size = 3119239 },
-    { url = "https://files.pythonhosted.org/packages/98/f7/25f9f9e368226a1d6cf3507081a1a7944eddd3ca7821023377043f5a83c8/pillow-11.0.0-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:fbbcb7b57dc9c794843e3d1258c0fbf0f48656d46ffe9e09b63bbd6e8cd5d0a2", size = 2950803 },
-    { url = "https://files.pythonhosted.org/packages/59/01/98ead48a6c2e31e6185d4c16c978a67fe3ccb5da5c2ff2ba8475379bb693/pillow-11.0.0-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5d203af30149ae339ad1b4f710d9844ed8796e97fda23ffbc4cc472968a47d0b", size = 3281098 },
-    { url = "https://files.pythonhosted.org/packages/51/c0/570255b2866a0e4d500a14f950803a2ec273bac7badc43320120b9262450/pillow-11.0.0-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:21a0d3b115009ebb8ac3d2ebec5c2982cc693da935f4ab7bb5c8ebe2f47d36f2", size = 3323665 },
-    { url = "https://files.pythonhosted.org/packages/0e/75/689b4ec0483c42bfc7d1aacd32ade7a226db4f4fac57c6fdcdf90c0731e3/pillow-11.0.0-pp310-pypy310_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:73853108f56df97baf2bb8b522f3578221e56f646ba345a372c78326710d3830", size = 3310533 },
-    { url = "https://files.pythonhosted.org/packages/3d/30/38bd6149cf53da1db4bad304c543ade775d225961c4310f30425995cb9ec/pillow-11.0.0-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:e58876c91f97b0952eb766123bfef372792ab3f4e3e1f1a2267834c2ab131734", size = 3414886 },
-    { url = "https://files.pythonhosted.org/packages/ec/3d/c32a51d848401bd94cabb8767a39621496491ee7cd5199856b77da9b18ad/pillow-11.0.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:224aaa38177597bb179f3ec87eeefcce8e4f85e608025e9cfac60de237ba6316", size = 2567508 },
+    { url = "https://files.pythonhosted.org/packages/0e/69/a31cccd538ca0b5272be2a38347f8839b97a14be104ea08b0db92f749c74/pillow-10.4.0-cp310-cp310-macosx_10_10_x86_64.whl", hash = "sha256:4d9667937cfa347525b319ae34375c37b9ee6b525440f3ef48542fcf66f2731e", size = 3509271 },
+    { url = "https://files.pythonhosted.org/packages/9a/9e/4143b907be8ea0bce215f2ae4f7480027473f8b61fcedfda9d851082a5d2/pillow-10.4.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:543f3dc61c18dafb755773efc89aae60d06b6596a63914107f75459cf984164d", size = 3375658 },
+    { url = "https://files.pythonhosted.org/packages/8a/25/1fc45761955f9359b1169aa75e241551e74ac01a09f487adaaf4c3472d11/pillow-10.4.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7928ecbf1ece13956b95d9cbcfc77137652b02763ba384d9ab508099a2eca856", size = 4332075 },
+    { url = "https://files.pythonhosted.org/packages/5e/dd/425b95d0151e1d6c951f45051112394f130df3da67363b6bc75dc4c27aba/pillow-10.4.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e4d49b85c4348ea0b31ea63bc75a9f3857869174e2bf17e7aba02945cd218e6f", size = 4444808 },
+    { url = "https://files.pythonhosted.org/packages/b1/84/9a15cc5726cbbfe7f9f90bfb11f5d028586595907cd093815ca6644932e3/pillow-10.4.0-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:6c762a5b0997f5659a5ef2266abc1d8851ad7749ad9a6a5506eb23d314e4f46b", size = 4356290 },
+    { url = "https://files.pythonhosted.org/packages/b5/5b/6651c288b08df3b8c1e2f8c1152201e0b25d240e22ddade0f1e242fc9fa0/pillow-10.4.0-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:a985e028fc183bf12a77a8bbf36318db4238a3ded7fa9df1b9a133f1cb79f8fc", size = 4525163 },
+    { url = "https://files.pythonhosted.org/packages/07/8b/34854bf11a83c248505c8cb0fcf8d3d0b459a2246c8809b967963b6b12ae/pillow-10.4.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:812f7342b0eee081eaec84d91423d1b4650bb9828eb53d8511bcef8ce5aecf1e", size = 4463100 },
+    { url = "https://files.pythonhosted.org/packages/78/63/0632aee4e82476d9cbe5200c0cdf9ba41ee04ed77887432845264d81116d/pillow-10.4.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:ac1452d2fbe4978c2eec89fb5a23b8387aba707ac72810d9490118817d9c0b46", size = 4592880 },
+    { url = "https://files.pythonhosted.org/packages/df/56/b8663d7520671b4398b9d97e1ed9f583d4afcbefbda3c6188325e8c297bd/pillow-10.4.0-cp310-cp310-win32.whl", hash = "sha256:bcd5e41a859bf2e84fdc42f4edb7d9aba0a13d29a2abadccafad99de3feff984", size = 2235218 },
+    { url = "https://files.pythonhosted.org/packages/f4/72/0203e94a91ddb4a9d5238434ae6c1ca10e610e8487036132ea9bf806ca2a/pillow-10.4.0-cp310-cp310-win_amd64.whl", hash = "sha256:ecd85a8d3e79cd7158dec1c9e5808e821feea088e2f69a974db5edf84dc53141", size = 2554487 },
+    { url = "https://files.pythonhosted.org/packages/bd/52/7e7e93d7a6e4290543f17dc6f7d3af4bd0b3dd9926e2e8a35ac2282bc5f4/pillow-10.4.0-cp310-cp310-win_arm64.whl", hash = "sha256:ff337c552345e95702c5fde3158acb0625111017d0e5f24bf3acdb9cc16b90d1", size = 2243219 },
+    { url = "https://files.pythonhosted.org/packages/a7/62/c9449f9c3043c37f73e7487ec4ef0c03eb9c9afc91a92b977a67b3c0bbc5/pillow-10.4.0-cp311-cp311-macosx_10_10_x86_64.whl", hash = "sha256:0a9ec697746f268507404647e531e92889890a087e03681a3606d9b920fbee3c", size = 3509265 },
+    { url = "https://files.pythonhosted.org/packages/f4/5f/491dafc7bbf5a3cc1845dc0430872e8096eb9e2b6f8161509d124594ec2d/pillow-10.4.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:dfe91cb65544a1321e631e696759491ae04a2ea11d36715eca01ce07284738be", size = 3375655 },
+    { url = "https://files.pythonhosted.org/packages/73/d5/c4011a76f4207a3c151134cd22a1415741e42fa5ddecec7c0182887deb3d/pillow-10.4.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5dc6761a6efc781e6a1544206f22c80c3af4c8cf461206d46a1e6006e4429ff3", size = 4340304 },
+    { url = "https://files.pythonhosted.org/packages/ac/10/c67e20445a707f7a610699bba4fe050583b688d8cd2d202572b257f46600/pillow-10.4.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5e84b6cc6a4a3d76c153a6b19270b3526a5a8ed6b09501d3af891daa2a9de7d6", size = 4452804 },
+    { url = "https://files.pythonhosted.org/packages/a9/83/6523837906d1da2b269dee787e31df3b0acb12e3d08f024965a3e7f64665/pillow-10.4.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:bbc527b519bd3aa9d7f429d152fea69f9ad37c95f0b02aebddff592688998abe", size = 4365126 },
+    { url = "https://files.pythonhosted.org/packages/ba/e5/8c68ff608a4203085158cff5cc2a3c534ec384536d9438c405ed6370d080/pillow-10.4.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:76a911dfe51a36041f2e756b00f96ed84677cdeb75d25c767f296c1c1eda1319", size = 4533541 },
+    { url = "https://files.pythonhosted.org/packages/f4/7c/01b8dbdca5bc6785573f4cee96e2358b0918b7b2c7b60d8b6f3abf87a070/pillow-10.4.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:59291fb29317122398786c2d44427bbd1a6d7ff54017075b22be9d21aa59bd8d", size = 4471616 },
+    { url = "https://files.pythonhosted.org/packages/c8/57/2899b82394a35a0fbfd352e290945440e3b3785655a03365c0ca8279f351/pillow-10.4.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:416d3a5d0e8cfe4f27f574362435bc9bae57f679a7158e0096ad2beb427b8696", size = 4600802 },
+    { url = "https://files.pythonhosted.org/packages/4d/d7/a44f193d4c26e58ee5d2d9db3d4854b2cfb5b5e08d360a5e03fe987c0086/pillow-10.4.0-cp311-cp311-win32.whl", hash = "sha256:7086cc1d5eebb91ad24ded9f58bec6c688e9f0ed7eb3dbbf1e4800280a896496", size = 2235213 },
+    { url = "https://files.pythonhosted.org/packages/c1/d0/5866318eec2b801cdb8c82abf190c8343d8a1cd8bf5a0c17444a6f268291/pillow-10.4.0-cp311-cp311-win_amd64.whl", hash = "sha256:cbed61494057c0f83b83eb3a310f0bf774b09513307c434d4366ed64f4128a91", size = 2554498 },
+    { url = "https://files.pythonhosted.org/packages/d4/c8/310ac16ac2b97e902d9eb438688de0d961660a87703ad1561fd3dfbd2aa0/pillow-10.4.0-cp311-cp311-win_arm64.whl", hash = "sha256:f5f0c3e969c8f12dd2bb7e0b15d5c468b51e5017e01e2e867335c81903046a22", size = 2243219 },
+    { url = "https://files.pythonhosted.org/packages/05/cb/0353013dc30c02a8be34eb91d25e4e4cf594b59e5a55ea1128fde1e5f8ea/pillow-10.4.0-cp312-cp312-macosx_10_10_x86_64.whl", hash = "sha256:673655af3eadf4df6b5457033f086e90299fdd7a47983a13827acf7459c15d94", size = 3509350 },
+    { url = "https://files.pythonhosted.org/packages/e7/cf/5c558a0f247e0bf9cec92bff9b46ae6474dd736f6d906315e60e4075f737/pillow-10.4.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:866b6942a92f56300012f5fbac71f2d610312ee65e22f1aa2609e491284e5597", size = 3374980 },
+    { url = "https://files.pythonhosted.org/packages/84/48/6e394b86369a4eb68b8a1382c78dc092245af517385c086c5094e3b34428/pillow-10.4.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:29dbdc4207642ea6aad70fbde1a9338753d33fb23ed6956e706936706f52dd80", size = 4343799 },
+    { url = "https://files.pythonhosted.org/packages/3b/f3/a8c6c11fa84b59b9df0cd5694492da8c039a24cd159f0f6918690105c3be/pillow-10.4.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bf2342ac639c4cf38799a44950bbc2dfcb685f052b9e262f446482afaf4bffca", size = 4459973 },
+    { url = "https://files.pythonhosted.org/packages/7d/1b/c14b4197b80150fb64453585247e6fb2e1d93761fa0fa9cf63b102fde822/pillow-10.4.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:f5b92f4d70791b4a67157321c4e8225d60b119c5cc9aee8ecf153aace4aad4ef", size = 4370054 },
+    { url = "https://files.pythonhosted.org/packages/55/77/40daddf677897a923d5d33329acd52a2144d54a9644f2a5422c028c6bf2d/pillow-10.4.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:86dcb5a1eb778d8b25659d5e4341269e8590ad6b4e8b44d9f4b07f8d136c414a", size = 4539484 },
+    { url = "https://files.pythonhosted.org/packages/40/54/90de3e4256b1207300fb2b1d7168dd912a2fb4b2401e439ba23c2b2cabde/pillow-10.4.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:780c072c2e11c9b2c7ca37f9a2ee8ba66f44367ac3e5c7832afcfe5104fd6d1b", size = 4477375 },
+    { url = "https://files.pythonhosted.org/packages/13/24/1bfba52f44193860918ff7c93d03d95e3f8748ca1de3ceaf11157a14cf16/pillow-10.4.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:37fb69d905be665f68f28a8bba3c6d3223c8efe1edf14cc4cfa06c241f8c81d9", size = 4608773 },
+    { url = "https://files.pythonhosted.org/packages/55/04/5e6de6e6120451ec0c24516c41dbaf80cce1b6451f96561235ef2429da2e/pillow-10.4.0-cp312-cp312-win32.whl", hash = "sha256:7dfecdbad5c301d7b5bde160150b4db4c659cee2b69589705b6f8a0c509d9f42", size = 2235690 },
+    { url = "https://files.pythonhosted.org/packages/74/0a/d4ce3c44bca8635bd29a2eab5aa181b654a734a29b263ca8efe013beea98/pillow-10.4.0-cp312-cp312-win_amd64.whl", hash = "sha256:1d846aea995ad352d4bdcc847535bd56e0fd88d36829d2c90be880ef1ee4668a", size = 2554951 },
+    { url = "https://files.pythonhosted.org/packages/b5/ca/184349ee40f2e92439be9b3502ae6cfc43ac4b50bc4fc6b3de7957563894/pillow-10.4.0-cp312-cp312-win_arm64.whl", hash = "sha256:e553cad5179a66ba15bb18b353a19020e73a7921296a7979c4a2b7f6a5cd57f9", size = 2243427 },
+    { url = "https://files.pythonhosted.org/packages/c3/00/706cebe7c2c12a6318aabe5d354836f54adff7156fd9e1bd6c89f4ba0e98/pillow-10.4.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:8bc1a764ed8c957a2e9cacf97c8b2b053b70307cf2996aafd70e91a082e70df3", size = 3525685 },
+    { url = "https://files.pythonhosted.org/packages/cf/76/f658cbfa49405e5ecbfb9ba42d07074ad9792031267e782d409fd8fe7c69/pillow-10.4.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:6209bb41dc692ddfee4942517c19ee81b86c864b626dbfca272ec0f7cff5d9fb", size = 3374883 },
+    { url = "https://files.pythonhosted.org/packages/46/2b/99c28c4379a85e65378211971c0b430d9c7234b1ec4d59b2668f6299e011/pillow-10.4.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:bee197b30783295d2eb680b311af15a20a8b24024a19c3a26431ff83eb8d1f70", size = 4339837 },
+    { url = "https://files.pythonhosted.org/packages/f1/74/b1ec314f624c0c43711fdf0d8076f82d9d802afd58f1d62c2a86878e8615/pillow-10.4.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1ef61f5dd14c300786318482456481463b9d6b91ebe5ef12f405afbba77ed0be", size = 4455562 },
+    { url = "https://files.pythonhosted.org/packages/4a/2a/4b04157cb7b9c74372fa867096a1607e6fedad93a44deeff553ccd307868/pillow-10.4.0-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:297e388da6e248c98bc4a02e018966af0c5f92dfacf5a5ca22fa01cb3179bca0", size = 4366761 },
+    { url = "https://files.pythonhosted.org/packages/ac/7b/8f1d815c1a6a268fe90481232c98dd0e5fa8c75e341a75f060037bd5ceae/pillow-10.4.0-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:e4db64794ccdf6cb83a59d73405f63adbe2a1887012e308828596100a0b2f6cc", size = 4536767 },
+    { url = "https://files.pythonhosted.org/packages/e5/77/05fa64d1f45d12c22c314e7b97398ffb28ef2813a485465017b7978b3ce7/pillow-10.4.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:bd2880a07482090a3bcb01f4265f1936a903d70bc740bfcb1fd4e8a2ffe5cf5a", size = 4477989 },
+    { url = "https://files.pythonhosted.org/packages/12/63/b0397cfc2caae05c3fb2f4ed1b4fc4fc878f0243510a7a6034ca59726494/pillow-10.4.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:4b35b21b819ac1dbd1233317adeecd63495f6babf21b7b2512d244ff6c6ce309", size = 4610255 },
+    { url = "https://files.pythonhosted.org/packages/7b/f9/cfaa5082ca9bc4a6de66ffe1c12c2d90bf09c309a5f52b27759a596900e7/pillow-10.4.0-cp313-cp313-win32.whl", hash = "sha256:551d3fd6e9dc15e4c1eb6fc4ba2b39c0c7933fa113b220057a34f4bb3268a060", size = 2235603 },
+    { url = "https://files.pythonhosted.org/packages/01/6a/30ff0eef6e0c0e71e55ded56a38d4859bf9d3634a94a88743897b5f96936/pillow-10.4.0-cp313-cp313-win_amd64.whl", hash = "sha256:030abdbe43ee02e0de642aee345efa443740aa4d828bfe8e2eb11922ea6a21ea", size = 2554972 },
+    { url = "https://files.pythonhosted.org/packages/48/2c/2e0a52890f269435eee38b21c8218e102c621fe8d8df8b9dd06fabf879ba/pillow-10.4.0-cp313-cp313-win_arm64.whl", hash = "sha256:5b001114dd152cfd6b23befeb28d7aee43553e2402c9f159807bf55f33af8a8d", size = 2243375 },
+    { url = "https://files.pythonhosted.org/packages/38/30/095d4f55f3a053392f75e2eae45eba3228452783bab3d9a920b951ac495c/pillow-10.4.0-pp310-pypy310_pp73-macosx_10_15_x86_64.whl", hash = "sha256:5b4815f2e65b30f5fbae9dfffa8636d992d49705723fe86a3661806e069352d4", size = 3493889 },
+    { url = "https://files.pythonhosted.org/packages/f3/e8/4ff79788803a5fcd5dc35efdc9386af153569853767bff74540725b45863/pillow-10.4.0-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:8f0aef4ef59694b12cadee839e2ba6afeab89c0f39a3adc02ed51d109117b8da", size = 3346160 },
+    { url = "https://files.pythonhosted.org/packages/d7/ac/4184edd511b14f760c73f5bb8a5d6fd85c591c8aff7c2229677a355c4179/pillow-10.4.0-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9f4727572e2918acaa9077c919cbbeb73bd2b3ebcfe033b72f858fc9fbef0026", size = 3435020 },
+    { url = "https://files.pythonhosted.org/packages/da/21/1749cd09160149c0a246a81d646e05f35041619ce76f6493d6a96e8d1103/pillow-10.4.0-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ff25afb18123cea58a591ea0244b92eb1e61a1fd497bf6d6384f09bc3262ec3e", size = 3490539 },
+    { url = "https://files.pythonhosted.org/packages/b6/f5/f71fe1888b96083b3f6dfa0709101f61fc9e972c0c8d04e9d93ccef2a045/pillow-10.4.0-pp310-pypy310_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:dc3e2db6ba09ffd7d02ae9141cfa0ae23393ee7687248d46a7507b75d610f4f5", size = 3476125 },
+    { url = "https://files.pythonhosted.org/packages/96/b9/c0362c54290a31866c3526848583a2f45a535aa9d725fd31e25d318c805f/pillow-10.4.0-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:02a2be69f9c9b8c1e97cf2713e789d4e398c751ecfd9967c18d0ce304efbf885", size = 3579373 },
+    { url = "https://files.pythonhosted.org/packages/52/3b/ce7a01026a7cf46e5452afa86f97a5e88ca97f562cafa76570178ab56d8d/pillow-10.4.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:0755ffd4a0c6f267cccbae2e9903d95477ca2f77c4fcf3a3a09570001856c8a5", size = 2554661 },
 ]
 
 [[package]]
@@ -3228,6 +3334,48 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/f6/f0/10642828a8dfb741e5f3fbaac830550a518a775c7fff6f04a007259b0548/py-1.11.0-py2.py3-none-any.whl", hash = "sha256:607c53218732647dff4acdfcd50cb62615cedf612e72d1724fb1a0cc6405b378", size = 98708 },
 ]
 
+[[package]]
+name = "py-rust-stemmers"
+version = "0.1.3"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/f4/8a/c7481c6e324da825f13bafb362dbca47dbf8a7dd1a3a3502f47cdb05bfa9/py_rust_stemmers-0.1.3.tar.gz", hash = "sha256:ad796d47874181a25addb505a04245e34620bd7a0c5055671f52d9ce993253e2", size = 8676 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/3e/ed/4c85aa5f2046f7c34db174b89f92d24daaa347a149343f43614a6329c006/py_rust_stemmers-0.1.3-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:8b4861673bc690a5830a5d84d61c64a95ede86f79c9952df66e99e0559fe8264", size = 287578 },
+    { url = "https://files.pythonhosted.org/packages/72/7c/b3df3222e375cb838572952217cedf3d7925f85f3449c3c87142417e9fab/py_rust_stemmers-0.1.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:b0d2108c758e8081064cbbb7fc70d3cdfd32e0cccf7d051c1d888d16c91c1e78", size = 273908 },
+    { url = "https://files.pythonhosted.org/packages/48/d2/2c422476a6e21d9adbf4355b306269ac396eaa853efc896afdb2c628a334/py_rust_stemmers-0.1.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fdf43a726b81dd5439a98973200546660e10379e805bb6fd6366dbd8d0857666", size = 309863 },
+    { url = "https://files.pythonhosted.org/packages/ff/4f/42cd09a77639f3b0b2d662cbbc19248355ce40ba69eaac796007aae37b7e/py_rust_stemmers-0.1.3-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:03acb3d89f8090f67698d2c64172492618585927dfb56d0b5f6070ff54269940", size = 313215 },
+    { url = "https://files.pythonhosted.org/packages/8a/2c/39bfcdf674c799cb486fd1f10a9ce1599030884b47f2819aabb39db0398a/py_rust_stemmers-0.1.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b3f8cd1139a641ed53e9a1d7f25ae9cf3757cae96a2b0ce0d9399332ec8b148f", size = 323524 },
+    { url = "https://files.pythonhosted.org/packages/95/b4/38e66537da1864538912aae92f8285badf8201bccdddfdbe06c3c27e99ac/py_rust_stemmers-0.1.3-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:0a5906aa2eec31f647b94d6cc9b2b065bf77ca31be095fcbb1b412ba42f0e473", size = 323903 },
+    { url = "https://files.pythonhosted.org/packages/78/a5/7f219ff3547bfc1337b00761c6cd857fe51b90014b9d51aeba325e33d548/py_rust_stemmers-0.1.3-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:b89fe8e55201604e89bdbd7559b19337ef9ae703a5545878d37664507c1067e9", size = 485483 },
+    { url = "https://files.pythonhosted.org/packages/66/59/43c89cb1388a9c508d28868ce04900d0f3b4457a74b1c61411c9306a3aa4/py_rust_stemmers-0.1.3-cp310-cp310-musllinux_1_2_armv7l.whl", hash = "sha256:0d43981b272c73709d3885ed096a332b2a160db2317fbe16cc9ef3b1d974d39a", size = 567275 },
+    { url = "https://files.pythonhosted.org/packages/7d/3a/08722448c51e7b926b8f40a55f363e92236a89b761e89e5ee76b0e11baa8/py_rust_stemmers-0.1.3-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:1b379c3901a87ee63d7cbb01a68ece78af7040e0c3e3d52fe7b108bfa399feb2", size = 488902 },
+    { url = "https://files.pythonhosted.org/packages/c3/74/41efa33c0eb008eb2b1337f40021debf487e8cea5dbe4af97241a43d54b7/py_rust_stemmers-0.1.3-cp310-none-win_amd64.whl", hash = "sha256:0f571ee0f2a4b2314d4cd8ef26af83e1fd24ea3e3ff97407d536184167f05957", size = 208973 },
+    { url = "https://files.pythonhosted.org/packages/da/3b/f61826b786ed06f195c80b542abe082dcdd1747341c1194f6f782d566a02/py_rust_stemmers-0.1.3-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:2d8b8e6b6d5839a168dae510a00ff4662c7d0a22d12f24fe81caa0ac59265711", size = 287577 },
+    { url = "https://files.pythonhosted.org/packages/59/fd/322bf0dbc142ae71516c06c2026f4ac0a4685f108a873935581b7eef3d9d/py_rust_stemmers-0.1.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:02b347ab8fe686a88aef0432060471d501b37a6b9a868e7c50bffcd382269cf2", size = 273910 },
+    { url = "https://files.pythonhosted.org/packages/10/34/02aa64046e4a21b1dd5f7d602fb33b1c79bd0dd57c8ebfe5897efcf62ac3/py_rust_stemmers-0.1.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d4a65b429eb1282934a1cc3c1b2698ae32a6dc00d6be00dd747e688c642eb110", size = 309863 },
+    { url = "https://files.pythonhosted.org/packages/10/a4/f4fd2afc713b0497b76023c6e491f356962213bd518f148cbd28b7144e78/py_rust_stemmers-0.1.3-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:9fbbb37e0df579859b42b3f850aa08fe829d190d32c6338349eccb0e762b74c6", size = 313218 },
+    { url = "https://files.pythonhosted.org/packages/98/78/f64e096df43d730fb5f6e2201e6d6ca05ed18e94946f11cdeddd0205f099/py_rust_stemmers-0.1.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d6f9790fe1e9962787817b1894486df7e0b5fc59e4adad423e189530530fae11", size = 323525 },
+    { url = "https://files.pythonhosted.org/packages/21/38/09beb9ca8ec3af8dbfd441f77fc003472ca900f678d1eb25839db08df691/py_rust_stemmers-0.1.3-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:fd5d7388f807f584b4c55bfbe608ef40cff0024c1dc54de95d28265395065d02", size = 323903 },
+    { url = "https://files.pythonhosted.org/packages/fc/63/08af5678a0cb0f6c5a462def7aec0c32f3742574ee36ddd660103d13bc86/py_rust_stemmers-0.1.3-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:72a7b810d8d376c03f0ccebe146f04cbf4c6c97bd74e489b0ddf1342eb40970c", size = 485484 },
+    { url = "https://files.pythonhosted.org/packages/33/a7/740b8dd06cb48ed397d65cabda9d38c2c310869c3bf51b0e0a347cb7fc8f/py_rust_stemmers-0.1.3-cp311-cp311-musllinux_1_2_armv7l.whl", hash = "sha256:658784c0072f7aae67c726be9acac40dd27b29416356c63a3a760a9499a93513", size = 567275 },
+    { url = "https://files.pythonhosted.org/packages/6e/75/e785900047b4fc5773d0bea37c565825df26de81f25ab2d341ecaa2f55f5/py_rust_stemmers-0.1.3-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:e6afcd19da56d4182eecb43bdb6c5b9686370063f2538df877fc23f1d16f909e", size = 488906 },
+    { url = "https://files.pythonhosted.org/packages/5b/ee/86ee4eb3188f45cf0831318dab9afddc231ae71b8fecc0dbbc79eb885ded/py_rust_stemmers-0.1.3-cp311-none-win_amd64.whl", hash = "sha256:47211ac6252eb484f5067d30b1812667936deffcef89b4b0acd2efe881a99aed", size = 208976 },
+    { url = "https://files.pythonhosted.org/packages/cc/08/f9c9ef78c7dca7a69c451b1df754195e02a3a1e7a450becdce687102aae7/py_rust_stemmers-0.1.3-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:a36bfbd9219a55bdf5aa9c5d74b8a3741cb092495190ca18551dc39f57272d57", size = 287577 },
+    { url = "https://files.pythonhosted.org/packages/50/3a/5c518bc2761f8a873b1ec9333f7f74a8f58e7e8b39d5de065038427b114b/py_rust_stemmers-0.1.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:ca1ab04ff2fa15a1d0685007293ffdf4679dcfdc02fc5b36c1af0111670908a1", size = 273906 },
+    { url = "https://files.pythonhosted.org/packages/b4/ae/3cae1a65a99687e4bf830ab733b3adde13e458a7908b6826dd9025c8c5c3/py_rust_stemmers-0.1.3-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ccaa08251b9cb421429976d56365ddf9db63b5a8ac4e7817723fb0b62adf8b19", size = 309864 },
+    { url = "https://files.pythonhosted.org/packages/a9/f2/b4167a4a64b0bade1695b32e4bd13ca752085d43559670fd7173cfb59b9e/py_rust_stemmers-0.1.3-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:6262b40f989c0b0bcb3eaef5511268ba63703428c4ab1aa9353a58c8572735b7", size = 313217 },
+    { url = "https://files.pythonhosted.org/packages/54/ff/f27e0762a74668bf520525d7bad8daa4dd621ef5b3155c464c5bd8a7dd3f/py_rust_stemmers-0.1.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a073701b492ef900cee5185961c23006ba13fa6126cf716f241c929adbdfad6e", size = 323525 },
+    { url = "https://files.pythonhosted.org/packages/d3/f2/2f4599ef5481be24378a23f93af405b4ca968450873d48d0a56ba925d7b5/py_rust_stemmers-0.1.3-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:39c75f10da70380076b68398d84cdc42b42966180bdb8216b81d21a824278b50", size = 323903 },
+    { url = "https://files.pythonhosted.org/packages/dd/84/1aea103917659abc12456ce061621557eed0a44e174270908e3fb28f2cc3/py_rust_stemmers-0.1.3-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:34f7d92abc85f0f0b1fa407410b3f2daaf2c36b8277a2ffff2ff0beb2f2acc2f", size = 485487 },
+    { url = "https://files.pythonhosted.org/packages/bd/67/16d48e7f02b285b39028aa47f847b3a279c903bc5cd49c8012ea90255317/py_rust_stemmers-0.1.3-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:fbb9f7933239a57d1d9c0fcdfbe0c5283a081e9e64ddc48ed878783be3d52b2b", size = 567278 },
+    { url = "https://files.pythonhosted.org/packages/ad/1c/cb8cc9680f8aa04f96cb5c814887b3bb8d23a2e9abf460ef861ae16bfe50/py_rust_stemmers-0.1.3-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:921803a6f8259f10bf348ac0e32a767c28ab587c9ad5c3b1ee593a4bbbe98d39", size = 488907 },
+    { url = "https://files.pythonhosted.org/packages/cd/29/88217de06239e3e526fa6286a11e3662d94acb0be4216c1310301a252dab/py_rust_stemmers-0.1.3-cp312-none-win_amd64.whl", hash = "sha256:576206b540575e81bb84a0f620b7a8529f5e89b0b2ec7d4487f3183789dd5cfd", size = 208980 },
+    { url = "https://files.pythonhosted.org/packages/f1/45/e1ec9e76b4462e70fa42f6ac8be9f1bfe6565c1c260b9e5824e772157edf/py_rust_stemmers-0.1.3-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:59eacf7687738b20886a7c0ceeae999d501902b4e6234cf11eecd2f45f2c26bb", size = 288041 },
+    { url = "https://files.pythonhosted.org/packages/4a/5b/eb594ca68715c23dd3b8f52dd700c10cbdd8133faaaf19886962c8f97c90/py_rust_stemmers-0.1.3-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:e39d5d273e13aec2f07a2c3ea0050b3bf3aaa7b6e9f6bef3d4e728ab49979ae8", size = 274089 },
+    { url = "https://files.pythonhosted.org/packages/79/55/b62b14cdeb7268a818f21e4c8cfd543261c563dc9bd89ba7116293ce3008/py_rust_stemmers-0.1.3-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f95b25138431c4a457d684c49c6de5ff0c1852cf1cb3657e187ea63610fc7c21", size = 310373 },
+    { url = "https://files.pythonhosted.org/packages/a4/71/f0b7131505013eaaa4fbfcd821b30b36431d01b7fe96951d84721cdb4ef8/py_rust_stemmers-0.1.3-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1cc9df57dff15d12d7fec65a541af6fdcefd40ea5f7ebd48ad5202a1b9a56f89", size = 324052 },
+]
+
 [[package]]
 name = "pyarrow"
 version = "17.0.0"
@@ -3444,6 +3592,26 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/48/8f/9bbf22ba6a00001a45dbc54337e5bbbd43e7d8f34c8158c92cddc45736af/pypdf-5.0.1-py3-none-any.whl", hash = "sha256:ff8a32da6c7a63fea9c32fa4dd837cdd0db7966adf6c14f043e3f12592e992db", size = 294470 },
 ]
 
+[[package]]
+name = "pypdfium2"
+version = "4.30.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/a1/14/838b3ba247a0ba92e4df5d23f2bea9478edcfd72b78a39d6ca36ccd84ad2/pypdfium2-4.30.0.tar.gz", hash = "sha256:48b5b7e5566665bc1015b9d69c1ebabe21f6aee468b509531c3c8318eeee2e16", size = 140239 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/c7/9a/c8ff5cc352c1b60b0b97642ae734f51edbab6e28b45b4fcdfe5306ee3c83/pypdfium2-4.30.0-py3-none-macosx_10_13_x86_64.whl", hash = "sha256:b33ceded0b6ff5b2b93bc1fe0ad4b71aa6b7e7bd5875f1ca0cdfb6ba6ac01aab", size = 2837254 },
+    { url = "https://files.pythonhosted.org/packages/21/8b/27d4d5409f3c76b985f4ee4afe147b606594411e15ac4dc1c3363c9a9810/pypdfium2-4.30.0-py3-none-macosx_11_0_arm64.whl", hash = "sha256:4e55689f4b06e2d2406203e771f78789bd4f190731b5d57383d05cf611d829de", size = 2707624 },
+    { url = "https://files.pythonhosted.org/packages/11/63/28a73ca17c24b41a205d658e177d68e198d7dde65a8c99c821d231b6ee3d/pypdfium2-4.30.0-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4e6e50f5ce7f65a40a33d7c9edc39f23140c57e37144c2d6d9e9262a2a854854", size = 2793126 },
+    { url = "https://files.pythonhosted.org/packages/d1/96/53b3ebf0955edbd02ac6da16a818ecc65c939e98fdeb4e0958362bd385c8/pypdfium2-4.30.0-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:3d0dd3ecaffd0b6dbda3da663220e705cb563918249bda26058c6036752ba3a2", size = 2591077 },
+    { url = "https://files.pythonhosted.org/packages/ec/ee/0394e56e7cab8b5b21f744d988400948ef71a9a892cbeb0b200d324ab2c7/pypdfium2-4.30.0-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:cc3bf29b0db8c76cdfaac1ec1cde8edf211a7de7390fbf8934ad2aa9b4d6dfad", size = 2864431 },
+    { url = "https://files.pythonhosted.org/packages/65/cd/3f1edf20a0ef4a212a5e20a5900e64942c5a374473671ac0780eaa08ea80/pypdfium2-4.30.0-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f1f78d2189e0ddf9ac2b7a9b9bd4f0c66f54d1389ff6c17e9fd9dc034d06eb3f", size = 2812008 },
+    { url = "https://files.pythonhosted.org/packages/c8/91/2d517db61845698f41a2a974de90762e50faeb529201c6b3574935969045/pypdfium2-4.30.0-py3-none-musllinux_1_1_aarch64.whl", hash = "sha256:5eda3641a2da7a7a0b2f4dbd71d706401a656fea521b6b6faa0675b15d31a163", size = 6181543 },
+    { url = "https://files.pythonhosted.org/packages/ba/c4/ed1315143a7a84b2c7616569dfb472473968d628f17c231c39e29ae9d780/pypdfium2-4.30.0-py3-none-musllinux_1_1_i686.whl", hash = "sha256:0dfa61421b5eb68e1188b0b2231e7ba35735aef2d867d86e48ee6cab6975195e", size = 6175911 },
+    { url = "https://files.pythonhosted.org/packages/7a/c4/9e62d03f414e0e3051c56d5943c3bf42aa9608ede4e19dc96438364e9e03/pypdfium2-4.30.0-py3-none-musllinux_1_1_x86_64.whl", hash = "sha256:f33bd79e7a09d5f7acca3b0b69ff6c8a488869a7fab48fdf400fec6e20b9c8be", size = 6267430 },
+    { url = "https://files.pythonhosted.org/packages/90/47/eda4904f715fb98561e34012826e883816945934a851745570521ec89520/pypdfium2-4.30.0-py3-none-win32.whl", hash = "sha256:ee2410f15d576d976c2ab2558c93d392a25fb9f6635e8dd0a8a3a5241b275e0e", size = 2775951 },
+    { url = "https://files.pythonhosted.org/packages/25/bd/56d9ec6b9f0fc4e0d95288759f3179f0fcd34b1a1526b75673d2f6d5196f/pypdfium2-4.30.0-py3-none-win_amd64.whl", hash = "sha256:90dbb2ac07be53219f56be09961eb95cf2473f834d01a42d901d13ccfad64b4c", size = 2892098 },
+    { url = "https://files.pythonhosted.org/packages/be/7a/097801205b991bc3115e8af1edb850d30aeaf0118520b016354cf5ccd3f6/pypdfium2-4.30.0-py3-none-win_arm64.whl", hash = "sha256:119b2969a6d6b1e8d55e99caaf05290294f2d0fe49c12a3f17102d01c441bd29", size = 2752118 },
+]
+
 [[package]]
 name = "pypika"
 version = "0.48.9"
@@ -4743,6 +4911,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/56/27/96a5cd2626d11c8280656c6c71d8ab50fe006490ef9971ccd154e0c42cd2/websockets-13.1-py3-none-any.whl", hash = "sha256:a9a396a6ad26130cdae92ae10c36af09d9bfe6cafe69670fd3b6da9b07b4044f", size = 152134 },
 ]
 
+[[package]]
+name = "win32-setctime"
+version = "1.1.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/6b/dd/f95a13d2b235a28d613ba23ebad55191514550debb968b46aab99f2e3a30/win32_setctime-1.1.0.tar.gz", hash = "sha256:15cf5750465118d6929ae4de4eb46e8edae9a5634350c01ba582df868e932cb2", size = 3676 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/0a/e6/a7d828fef907843b2a5773ebff47fb79ac0c1c88d60c0ca9530ee941e248/win32_setctime-1.1.0-py3-none-any.whl", hash = "sha256:231db239e959c2fe7eb1d7dc129f11172354f98361c4fa2d6d2d7e278baa8aad", size = 3604 },
+]
+
 [[package]]
 name = "wrapt"
 version = "1.16.0"