flock-core 0.1.2__py3-none-any.whl → 0.2.1__py3-none-any.whl

flock_core-0.1.2.dist-info/METADATA

@@ -1,476 +0,0 @@
-Metadata-Version: 2.4
-Name: flock-core
-Version: 0.1.2
-Summary: An agent framework for the age of agents
-Author-email: Andre Ratzenberger <andre.ratzenberger@whiteduck.de>
-License-File: LICENSE
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Operating System :: OS Independent
-Classifier: Programming Language :: Python :: 3
-Requires-Python: >=3.10
-Requires-Dist: cloudpickle>=3.1.1
-Requires-Dist: devtools>=0.12.2
-Requires-Dist: dspy>=2.5.42
-Requires-Dist: httpx>=0.28.1
-Requires-Dist: loguru>=0.7.3
-Requires-Dist: marimo>=0.10.15
-Requires-Dist: markdownify>=0.14.1
-Requires-Dist: monsterui>=0.0.23
-Requires-Dist: msgpack>=1.1.0
-Requires-Dist: pydantic>=2.10.5
-Requires-Dist: python-box>=7.3.2
-Requires-Dist: python-fasthtml>=0.12.0
-Requires-Dist: rich>=13.9.4
-Requires-Dist: tavily-python>=0.5.0
-Requires-Dist: temporalio>=1.9.0
-Description-Content-Type: text/markdown
-
-# Flock by white duck
-
-### Declarative LLM Orchestration at Scale
-
-<img src="docs/img/image.png" width="600">
-
-| Traditional Agent Frameworks 🙃          |                        Flock 🐤🐧🐓 🦆                         |
-|-----------------------------------------|------------------------------------------------|
-| 🤖 **Interaction Design**                | 📝 **Simplified Agent Logic**                   |
-| • Requires complex prompt tuning        | • Straightforward input/output definitions      |
-| • Fragile and hard-to-maintain          | • No need for prompt engineering               |
-| • Time-consuming adjustments            | • Focused on business logic                    |
-|                                           |                                                |
-| 💥 **Reliability Challenges**             | ⚡ **Robust & Scalable**                        |
-| • Prone to single points of failure      | • Built-in fault tolerance                     |
-| • Lacks automatic recovery               | • Automated retries & error handling           |
-| • Difficult to monitor                   | • Full observability & logging                 |
-|                                           |                                                |
-| 🏗️ **Execution Constraints**              | 🔄 **Flexible Orchestration**                   |
-| • Linear workflows, limited adaptability | • Dynamic and modular execution                |
-| • Lacks parallelism & batching           | • Supports concurrency & batch processing      |
-| • Struggles with scaling                 | • Persistent state management                  |
-
-## Hello, Bot
-
-```python
-MODEL = "openai/gpt-4o"
-
-async def main():
- 
-    #--------------------------------
-    # Create the flock
-    #--------------------------------
-    # The flock is the place where all the agents are at home
-    flock = Flock(model=MODEL)
-
-    #--------------------------------
-    # Create an agent
-    #--------------------------------
-    # The flock doesn't believe in prompts (continue reading for more info)
-    # The flock just declares what agents get in and what agents produce
-    # bloggy takes in a blog_idea and outputs a funny_blog_title and blog_headers
-    bloggy = Flock(
-        DeclarativeAgent,
-        name="bloggy",
-        input="blog_idea",
-        output="funny_blog_title, blog_headers"  
-    )
-
-    #--------------------------------
-    # Let the flock do its thing
-    #--------------------------------
-    # By giving the flock a start_agent and an input, we can run the flock
-    # local_debug makes it easier to debug the flock
-    result = await flock.run_async(
-        context=context,
-        start_agent=bloggy,
-        input="a blog about cats",
-        local_debug=True
-    )
-    # earn the fruits of the flock's labor
-    print(result)
-
-
-    # Continue reading to give your flock temporal(ly) super powers, heh.
-
-```
-
-Problems with other agent frameworks
-
-- Instead of writing software you need to write pages long natural language prompts
-- One crash and your whole agent system is dead
-- Demand having your system be a real DAG and a real state machine
-
-How flock tries to solve it:
-
-- Just declare what your agents get ind, and what they should return
-- First grade temporalio support. Retry, Error, Timeout etc etc are somethi
-- Chain your agents together in any kind you want
-
-## Philosophy & Design Principles
-
-### Say goodbye to prompting
-
-Sometimes you see agents with a 200 lines of text system prompt.
-How do evaluate if this is the most optimal prompt for your use case? How would changes affect the performance?
-Questions for there is no easy answer.
-
-How does a good prompt look like? What happens with your prompt if you switch models?
-
-With flock you just tell an agent what kind of input it gets, and what it should output. Done. Easy peasy.
-
-The philosophy behind this approach is simple: by focusing on the interface (inputs and outputs) rather than implementation details (prompts), we create more maintainable and adaptable systems. This declarative approach means:
-
-- Your agents are model-agnostic
-- Behavior can be tested and validated objectively
-- Changes are localized and predictable
-- Integration with other systems becomes straightforward
-
-### Testable
-
-Reducing the need for fuzzy natural language to a minimum agents become easily testable, evaluable.
-flock comes with tools to know exactly how good your agents and therefore the agent system is performing.
-
-This focus on testability isn't just about catching bugs - it's about building confidence in your AI systems:
-
-- Clear input/output contracts make unit testing straightforward
-- Type safety ensures data consistency
-- Performance metrics are built into the framework
-- Behavior can be validated systematically
-
-### Production ready
-
-Would you run your agent system in critical environments? The answer is probably no, since with most frameworks one dead endpoint or uncatched exception will break the whole agent system.
-
-flock uses Temporal as its workflow engine which comes with battle-hardened retry, failure, exception options.
-
-This production-readiness is achieved through several key design decisions:
-
-- Temporal workflow engine for durability and reliability
-- Strong typing for predictable behavior
-- Modular architecture for maintainability
-- Built-in monitoring and debugging capabilities
-
-## Core Features
-
-- **Declarative Agent System**: Define agents with clear input/output specifications and optional tool capabilities
-- **Temporal Workflow Integration**: Built-in support for durable execution and state management using Temporal
-- **Tool Integration**: Easy integration of external tools like web search, code evaluation, and math computation
-- **Type Safety**: Strong typing support for agent inputs and outputs
-- **DSPy Integration**: Seamless integration with DSPy for LLM interactions
-- **Flexible Architecture**: Support for agent chaining, hand-offs, and complex workflows
-
-## Architecture and Flow
-
-![alt text](docs/img/charts/agent_workflow_inv.png)
-
-![alt text](docs/img/charts/core_architecture_inv.png)
-
-## Requirements
-
-Nothing. Temporal is not needed for development but recommended
-
-Either clone <https://github.com/temporalio/docker-compose> and up the compose
-
-or install the temporal cli
-
-<https://docs.temporal.io/cli>
-
-## Installation
-
-```bash
-pip install flock
-```
-
-## Quick Start
-
-Here's a simple example of creating and using an agent:
-
-```python
-import asyncio
-from flock.core.agents.declarative_agent import DeclarativeAgent
-from flock.core.flock import flock
-
-async def main():
-    # Initialize flock
-    agent_runner = flock()
-
-    # Create a simple agent
-    agent = DeclarativeAgent(
-        name="blog_title_agent",
-        input="blog_idea",
-        output="funny_blog_title",
-    )
-    agent_runner.add_agent(agent)
-
-    # Run the agent
-    result = await agent_runner.run_async(
-        start_agent=agent,
-        input="a blog about cats",
-        local_debug=True,
-    )
-    print(result)
-
-if __name__ == "__main__":
-    asyncio.run(main())
-```
-
-## Web Application
-
-![alt text](docs/img/app.png)
-
-flock comes with a built-in web interface for managing and monitoring your agents. The web app provides a rich, interactive environment for working with your agent systems.
-
-TODO: Expand
-
-### Running the Web App
-
-```bash
-# After installing flock
-flock
-# Or with uv
-uv run flock
-```
-
-### Features
-
-- **Dashboard**: Overview of your agent systems and their status
-- **Agent Management**:
-  - List and filter agents
-  - View agent details and configuration
-  - Monitor production readiness
-  - Track agent history
-- **Agent Systems**: Manage complex agent workflows and interactions
-- **History**: View execution history and results
-- **Tools**: Access and manage available tools
-- **Playground**: Interactive environment for testing agents
-- **Settings**: Configure system preferences and integrations
-
-### Technical Details
-
-The web application is built with:
-
-- FastHTML for UI components
-- MonsterUI for enhanced UI elements
-- Interactive features using D3.js and interact.js
-- Real-time updates and monitoring
-- Responsive design for different screen sizes
-
-### Interface Structure
-
-```
-Web Interface
-├── Sidebar Navigation
-│   ├── Dashboard
-│   ├── Agents
-│   ├── Agent Systems
-│   ├── History
-│   ├── Tools
-│   ├── Playground
-│   └── Settings
-├── Main Content Area
-│   ├── Agent List
-│   └── Agent Details
-└── Interactive Features
-    ├── Theme Switching
-    ├── Search Functionality
-    └── Real-time Updates
-```
-
-## Advanced Usage
-
-### Agents with Tools
-
-Agents can use tools to interact with external systems:
-
-```python
-from flock.core.tools import basic_tools
-
-agent = DeclarativeAgent(
-    name="research_agent",
-    input="research_topic",
-    output="research_result",
-    tools=[basic_tools.web_search_tavily],
-)
-```
-
-### Type-Safe Outputs
-
-Define complex output types for structured responses:
-
-```python
-agent = DeclarativeAgent(
-    name="analysis_agent",
-    input="long_text",
-    output="""
-        title: str,
-        headings: list[str],
-        entities_and_metadata: list[dict[str, str]],
-        type: Literal['news', 'blog', 'opinion piece', 'tweet']
-    """,
-)
-```
-
-### Agent Chaining
-
-Create chains of agents that can hand off tasks:
-
-```python
-# First agent in chain
-project_plan_agent = DeclarativeAgent(
-    name="project_plan_agent",
-    input="project_idea",
-    output="catchy_project_name, project_pitch, project_plan_headings: list[str]",
-    tools=[basic_tools.web_search_tavily, basic_tools.code_eval],
-)
-
-# Second agent in chain
-content_agent = DeclarativeAgent(
-    name="content_agent",
-    input="context,project_plan_agent.project_plan_headings.items",
-    output="project_plan_heading, project_plan_content_for_heading",
-)
-
-# Set up hand-off
-project_plan_agent.hand_off = content_agent
-```
-
-## Core Components
-
-### flock Class
-
-The main orchestrator that manages agent creation and execution:
-
-- Handles agent registration
-- Manages workflow execution
-- Supports both local debugging and distributed execution
-
-### DeclarativeAgent
-
-Base class for creating agents with:
-
-- Input/output specifications
-- Tool integration
-- Type validation
-- Hand-off capabilities
-
-### Workflow System
-
-Built on Temporal for:
-
-- Durable execution
-- State management
-- Error handling
-- Activity tracking
-
-### Tools
-
-Built-in tools include:
-
-- Web search (via Tavily)
-- Math evaluation
-- Code execution
-- Extensible tool system for custom integrations
-
-## Architecture
-
-```
-flock Framework
-├── Core
-│   ├── Agents
-│   │   ├── DeclarativeAgent
-│   │   └── Agent Registry
-│   ├── Tools
-│   │   └── Basic Tools
-│   └── flock Manager
-├── Workflow
-│   ├── Activities
-│   ├── Temporal Setup
-│   └── Workflow Definitions
-└── App
-    └── Components
-```
-
-## Development
-
-### Prerequisites
-
-- Python 3.12+
-- Temporal server running locally (for workflow features)
-- Required API keys (e.g., Tavily for web search)
-
-### Setup
-
-1. Clone the repository:
-
-```bash
-git clone https://github.com/yourusername/flock.git
-cd flock
-```
-
-2. Create a virtual environment:
-
-```bash
-python -m venv .venv
-source .venv/bin/activate  # On Windows: .venv\Scripts\activate
-```
-
-3. Install dependencies:
-
-```bash
-pip install -e .
-```
-
-### Running Tests
-
-```bash
-pytest tests/
-```
-
-## Contributing
-
-Contributions are welcome! Please feel free to submit a Pull Request.
-
-## License
-
-This project is licensed under the terms of the LICENSE file included in the repository.
-
-## Acknowledgments
-
-- Built with [DSPy](https://github.com/stanfordnlp/dspy)
-- Uses [Temporal](https://temporal.io/) for workflow management
-- Integrates with [Tavily](https://tavily.com/) for web search capabilities
-- Web interface built with FastHTML and MonsterUI
-
-## Evolution & Future Direction
-
-flock was born from the realization that current agent frameworks often prioritize flexibility at the cost of reliability and maintainability. The framework's design decisions reflect this focus:
-
-### Why Declarative?
-
-The declarative approach wasn't just a stylistic choice - it was a deliberate decision to separate what agents do from how they do it. This separation means:
-
-- Agents can be optimized independently of their interface
-- Different LLM backends can be swapped without changing agent definitions
-- Testing and validation become straightforward
-- Integration with existing systems is simplified
-
-### Why Temporal?
-
-Using Temporal as the workflow engine was crucial for production reliability:
-
-- Automatic retry on failures
-- Built-in state management
-- Scalable execution
-- Detailed execution history
-- Production-grade monitoring
-
-### Future Plans
-
-The framework is actively evolving with several key areas of focus:
-
-- Enhanced type system for more complex agent interactions
-- Expanded tool ecosystem
-- Improved optimization capabilities
-- Advanced monitoring and debugging features
-- Extended testing and validation tools
-
-Join us in building the future of reliable, production-ready AI agent systems!

flock_core-0.1.2.dist-info/RECORD

@@ -1,48 +0,0 @@
-flock/__init__.py,sha256=xbfYMDyjxWYPIzfiMjuuA7zMST-cPVU3wsfFm8kPuJM,129
-flock/agents/__init__.py,sha256=pIcDAbFNP6CX3UH0W5tT1WZ06AW9RH1d1h9VTkCl-fI,95
-flock/agents/batch_agent.py,sha256=MIet5iGDuW5OmHdCas3DuLt7R4e0YQa7eDqdJ5oQAuI,8282
-flock/agents/declarative_agent.py,sha256=KHdobQOpCLJQqBY4gWL2tx6hYI2k_yjEal5RoZp2Uic,7560
-flock/agents/loop_agent.py,sha256=2ajHqNWoRyStGoqLKgkaCFcPCD-EPSyr0RHGFsM5K8I,7392
-flock/agents/trigger_agent.py,sha256=4LpfJ7xgDGAZXjS7_tPfMfLmbZwVLOe8YhikoZOg_og,8224
-flock/agents/user_agent.py,sha256=PexPzGY9S3tmm0s8WvdKf8C89ONMJdpO8tvw3zRpCjo,8575
-flock/app/hive_app.py,sha256=vNyZ3I8PZ_M-CO7joc9XBqdBOEKrxP761AQKX_Fzkv4,2621
-flock/app/components/__init__.py,sha256=wEOcF89JLUdjrOXsODZ-iADxasHBluaW7U8IxxIX3Ak,369
-flock/app/components/history_grid.py,sha256=kbUNdHq_DlhYM2zy_j1kOksvEEhyq-68YnJmFb3CLb0,5629
-flock/app/components/history_grid_alt.py,sha256=V2iJ53aPEpb2_U4Eaat8g0LqgTG3xaCWBXCaUR7ZQWk,6739
-flock/app/components/sidebar.py,sha256=WF_69gie1z7Wjfbdt7rESuhk4wjPle0z8P8IEVGeUog,558
-flock/app/components/theme.py,sha256=tBOi0Fgewke-l3Ifp-An-HRNEsinEFxtX1xYb8w62PE,201
-flock/app/components/util.py,sha256=u_kAo1L_hF0LiHm4gdkRxJUlWJWPU3fmh8o3ZnYNec0,415
-flock/app/components/charts/agent_workflow.py,sha256=XVxMnHsx8YY5jPQ7wbp_36dMPxw3dTkwH1aN3e-Cxrg,10862
-flock/app/components/charts/core_architecture.py,sha256=YqENUkIR8913JvHuYfY-V2vymelDJkH1wZkEckmEqY4,10865
-flock/app/components/charts/tool_system.py,sha256=ExrtqBrEkoXiVCHo424NB3TeMhRb3V_8L3ZIOBiDDvM,10384
-flock/app/html/d3.html,sha256=Wb1dFBmqXeiH3Ol2g3GeyPkvlyGsoOKSUOaEk3_2uUw,5404
-flock/app/modules/__init__.py,sha256=DrK6C1UJpKJt980WqpQPN-w3dyslwfRp4GGK8AefJlg,279
-flock/app/modules/about.py,sha256=BZT6beln4opwk4bhbn6wi1oLQTezcdg3vHmEM7OiTeA,438
-flock/app/modules/agent_detail.py,sha256=JBuAhtTpnrxbq8n0VeQM9FNMd1jZ3iiMQzp1aehkRvo,3128
-flock/app/modules/agent_list.py,sha256=-f6qlNzJkH6Hhd306-Mp1JrWkZQjZf1xUyCzKRXob2Q,2311
-flock/app/modules/playground.py,sha256=CiqrDLUd30eVdoyWsQNCGm-Qsf-O3GE7vvyv7jOamMY,9980
-flock/app/modules/settings.py,sha256=HmVzoV6A6QjYdmMfw4vpF1w8V5TIqRusQhQQhEQCQKw,2970
-flock/core/__init__.py,sha256=tSc7Ix_UVOqsc7VTkPq7-3wGUPbRUeYoLIMADnpisGo,291
-flock/core/agent.py,sha256=TIYlz5hX-ocd7ag1Ixa9RU5i9B59R-tEb11_qDYYj40,6445
-flock/core/agent_registry.py,sha256=OegRMXbE7ebptnF_PcEIewjcNk1OUOxx_2h2K8-1ubc,5672
-flock/core/context.py,sha256=s-Nci1Qp1px9SUwA5Xx66VvIDFlMA1_jcsNaJbsHGuM,11454
-flock/core/context_vars.py,sha256=iP3RnOP0YJtPpMSwbixbpxOm7PmzhiLPJdqw6INRVqc,242
-flock/core/flock.py,sha256=Fa4VrjjniwIxrBaDA9zco6lfz0LlqYkQckp2xLU__fE,8241
-flock/core/serializable.py,sha256=mbsNDwTD-3bBUzfAi7yXR55VhGbYt0XZq44Me1wtBIs,7404
-flock/core/config/declarative_agent_config.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-flock/core/handoff/handoff_base.py,sha256=iXHhpGojrLT3nUGWLuGog5EjsPq50GJ2aKV-AmRRO-I,267
-flock/core/logging/__init__.py,sha256=nYatDGaN5pSyu2eudnhREbS7WRIKFR7ysMTtL7cfupU,605
-flock/core/logging/error_handler.py,sha256=cw2XKGMi-O1HtGjN0bbB46onolW0aAygX3qu2eqB_IE,2602
-flock/core/logging/formatters.py,sha256=Z_wHK7qjIPW2oEFcqkSZm0-ibHv4AizbSZSStsRTSJ0,4747
-flock/core/logging/handlers.py,sha256=C6-P10RuZ_y2odtRipOwCv5r1ezIWBvNnMKcWz6onQ4,4235
-flock/core/logging/logger.py,sha256=w0TMb1jRw25FJKGhcmabXdXKZylubeNDJr5cR2TWBIk,4234
-flock/core/tools/basic_tools.py,sha256=9Qj_Nl5QACvHeWSt6k9pfBEcBqsO--D6XcSuiJWF1Rc,2082
-flock/workflow/activities.py,sha256=YZ0YYJTYPSmoTkpiY7x_pzwY3OpkkWm3ye9g6n-bFO4,5398
-flock/workflow/agent_activities.py,sha256=Shwiphd5Yi3VwbQN9SCuEsuhe6zJxIn0gBwMIpRZh-8,1134
-flock/workflow/temporal_setup.py,sha256=if3fmdy9cxoKGOZlbIfizLrZBYRGn2soMOBYLtP1mPI,1126
-flock/workflow/workflow.py,sha256=JTWFGE2_JltOd2PPJXlYfSeBlwbTQqRKLMszVdeqia0,1813
-flock_core-0.1.2.dist-info/METADATA,sha256=bfJrZD3pUNeIKA07tyaPR82Zu4OYCPE8AgxL7FZo5yY,14179
-flock_core-0.1.2.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-flock_core-0.1.2.dist-info/entry_points.txt,sha256=BoHLk1jgBHMsiQNA8h6lEe8B-dcq3Hqh3sbJGSmavZs,51
-flock_core-0.1.2.dist-info/licenses/LICENSE,sha256=eukczQf9y9W2_CLyGK-S06qMcU5zkTF39gJCjspsDA0,1093
-flock_core-0.1.2.dist-info/RECORD,,

flock_core-0.1.2.dist-info/entry_points.txt

@@ -1,2 +0,0 @@
-[console_scripts]
-flock = flock.app.flock_app:main