flock-core 0.5.0b10__tar.gz → 0.5.0b11__tar.gz

flock_core-0.5.0b11/.python-version

@@ -0,0 +1 @@
+3.12

{flock_core-0.5.0b10 → flock_core-0.5.0b11}/CONTRIBUTING.md

@@ -40,7 +40,7 @@ We follow the [Contributor Covenant](https://www.contributor-covenant.org/) code
 
 <!-- TOC --><a name="-reporting-issues"></a>
 ## ❗ Reporting Issues:
-- Before submitting a new issue, pleas check [existing issues](https://github.com/whiteducksoftware/flock/issues) if it has already been reported.
+- Before submitting a new issue, please check [existing issues](https://github.com/whiteducksoftware/flock/issues) if it has already been reported.
 - To submit a new issue, please use the provided **Issue Templates** and provide a clear and descriptive title along with a detailed description of the problem or feature request, including steps to reproduce if it's a bug.
 
 <!-- TOC --><a name="-pull-requests"></a>
@@ -104,15 +104,15 @@ We follow the [Contributor Covenant](https://www.contributor-covenant.org/) code
 <!-- TOC --><a name="a-few-best-practices-for-writing-good-documentation"></a>
 ### A few best practices for writing good documentation:
 1. Document the **Why**, not just the how:
-    - Documentation should explain the rational behind your decisions, rather than just describing the "how".
-    - This helps other developers understand the context and reasoning for the implementation, making the code more maintainable and modifyiable.
+    - Documentation should explain the rationale behind your decisions, rather than just describing the "how".
+    - This helps other developers understand the context and reasoning for the implementation, making the code more maintainable and modifiable.
 2. Keep it Up to Date:
    - Your documentation should evolve alongside the code. If you change the behavior of an existing component of Flock, please also take care to make sure the documentation reflects this fact.
 3. Write for the Reader:
    - Consider the audience for your documentation.
    - It should be accessible and understandable for developers who are not intimately familiar with the code.
 4. Document Intent and Design:
-   - Refering to Point 1, Document your decisions of **why** you chose to implement a new component or code change the way you did, if it is not immediately obvious.
+   - Referring to Point 1, Document your decisions of **why** you chose to implement a new component or code change the way you did, if it is not immediately obvious.
 5. Code as Documentation:
    - Well-written code can serve as it's own documentation.
    - Code should be clear, expressive and self-explanatory where possible.
@@ -120,19 +120,19 @@ We follow the [Contributor Covenant](https://www.contributor-covenant.org/) code
 6. Provide Examples:
    - Examples can help other developers understand your changes and are therefore encouraged.
 7. Use Comments Wisely:
-   - Aviod redundant comments that merely restate what the code does, which can clutter the codebase and detract from its readability.
+   - Avoid redundant comments that merely restate what the code does, which can clutter the codebase and detract from its readability.
 8. Be Pragmatic:
    - There is no need for you to excessively comment every line of code you provide.
    - Add documentation where necessary and focus on keeping documentation on a high level.
 
 <!-- TOC --><a name="-testing-and-reliability"></a>
 ## 🔭 Testing and Reliability:
-Flock aims to provide a easy and reliable way to implement agentic applications. Therefore, well tested code is crucial.
+Flock aims to provide an easy and reliable way to implement agentic applications. Therefore, well tested code is crucial.
 
 - Test your changes thoroughly! Ensure that existing tests pass and add **new tests** for any new functionality.
 - Follow Flock's testing conventions and use the provided testing framework.
 - Run the tests before submitting your pull request to confirm that nothing is broken.
-- Test can be run locally with `pytest -q`
+- Tests can be run locally with `pytest -q`
 - Place new tests in `tests/` mirroring the package path.
 - Use [`pytest`](https://docs.pytest.org/en/stable/) fixtures instead of duplicating setup code.
 - For Temporal code, rely on the *Temporal Test Server* fixture.
@@ -140,7 +140,7 @@ Flock aims to provide a easy and reliable way to implement agentic applications.
 
 <!-- TOC --><a name="release-process"></a>
 ## Release Process:
-1. Maintainer bumps versiion in `pyproject.toml` following **SemVer**.
+1. Maintainer bumps version in `pyproject.toml` following **SemVer**.
 2. Changelog entry added in `docs/about/changelog.md`.
 3. `uv pip install -e .[all] && pytest`
 4. `git tag v.X.Y.Z && git push --tags`

{flock_core-0.5.0b10 → flock_core-0.5.0b11}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: flock-core
-Version: 0.5.0b10
+Version: 0.5.0b11
 Summary: Declarative LLM Orchestration at Scale
 Author-email: Andre Ratzenberger <andre.ratzenberger@whiteduck.de>
 License-File: LICENSE
@@ -10,6 +10,7 @@ Classifier: Programming Language :: Python :: 3
 Requires-Python: >=3.10
 Requires-Dist: aiosqlite>=0.21.0
 Requires-Dist: azure-data-tables>=12.7.0
+Requires-Dist: azure-storage-blob>=12.25.1
 Requires-Dist: chromadb>=0.6.3
 Requires-Dist: cloudpickle>=3.1.1
 Requires-Dist: croniter>=6.0.0
@@ -54,6 +55,8 @@ Requires-Dist: tqdm>=4.60.1
 Requires-Dist: uvicorn>=0.34.0
 Requires-Dist: wd-di>=0.2.14
 Requires-Dist: websockets>=15.0.1
+Requires-Dist: werkzeug>=3.1.3
+Requires-Dist: xlsxwriter>=3.2.3
 Provides-Extra: memory
 Requires-Dist: matplotlib>=3.10.0; extra == 'memory'
 Requires-Dist: mem0ai[graph]>=0.1.101; extra == 'memory'

{flock_core-0.5.0b10 → flock_core-0.5.0b11}/SECURITY.md

@@ -15,7 +15,7 @@ and actively encourage our community-members to report
 any issues with the Flock framework as soon as possible
 in order to mitigate any potential risks.
 
-To report a vulnerability, you have serveral options available:
+To report a vulnerability, you have several options  available:
 
 ### 1. Creating a Vulnerability Report (preferred):
 

flock_core-0.5.0b11/docs/about/changelog.md

@@ -0,0 +1,133 @@
+---
+hide: # Optional: Hide table of contents on simple pages
+  - toc
+---
+
+# Changelog 📝
+
+All notable changes to **Flock** will be documented in this file.
+
+The format loosely follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/) and adheres to [Semantic Versioning](https://semver.org/).
+
+## [Unreleased]
+
+### Added
+- Core concepts & component documentation.
+- Placeholder replacement across docs.
+- Documentation improvements and typo fixes.
+
+---
+
+## [0.4.52] – 2025-05-30
+
+### Added
+- Package versioning updates and dependency improvements.
+
+### Fixed
+- Various bug fixes and stability improvements.
+
+---
+
+## [0.4.51] – 2025-05-24
+
+### Added
+- Enhanced error logging as default log level.
+- Zendesk article count feature.
+- Zendesk tools as MCP server.
+- Configurable protocol support.
+
+### Fixed
+- Removed init definitions for tools to avoid requiring all tool dependencies.
+- Chat in sidebar functionality.
+
+---
+
+## [0.4.5] – 2025-05-21 "MCP Integration"
+
+### Added
+- **Model Context Protocol (MCP) Support**: Declaratively connect to thousands of different tools.
+- MCP server creation with `FlockFactory.create_mcp_server()`.
+- Support for WebSocket, SSE, and STDIO transport protocols.
+- Tool discovery and integration through MCP servers.
+- Enhanced server management and client handling.
+
+### Fixed
+- OTLPSpanExporter crash issues.
+- Literal data type handling in Flock agents.
+- Various serialization and deserialization improvements.
+
+---
+
+## [0.4.3] – 2025-05-21
+
+### Added
+- High-level changelog documentation in README.
+- Enhanced REST API deployment features.
+
+### Changed
+- Updated documentation structure and content.
+
+---
+
+## [0.4.1] – 2025-05-21 "Magpie"
+
+### Added
+- **Magpie** release branding and logo.
+- Enhanced CLI messaging with release information.
+
+### Changed
+- Updated version display in CLI helper.
+- Improved UI design elements.
+
+---
+
+## [0.4.0] – 2025-04-30 "Magpie" 🐤
+
+### Added
+- **REST API Deployment**: Deploy Flock agents as scalable REST API endpoints with `flock.serve()`.
+- **Web UI**: Test and interact with Flock agents directly in browser with integrated web interface.
+- **CLI Tool**: Manage configurations, run agents, and inspect results from terminal.
+- **Enhanced Serialization**: Share, deploy, and run Flocks from YAML files with complete portability.
+- **Batch and Evaluation Modes**: Process multiple inputs and benchmark agents against Q/A pairs.
+- **First-Class Temporal Integration**: Production-grade workflows with retry policies and timeout control.
+- **@flockclass Hydrator**: Turn any Pydantic model into a self-hydrating agent.
+- Custom endpoint support with `FlockEndpoint` for business logic integration.
+- Chat functionality and UI modes (standalone chat, agent execution).
+- Shareable links with frozen agent configurations.
+- Direct feedback system for issue reproduction.
+
+### Changed
+- Major architecture improvements for production deployment.
+- Enhanced documentation with comprehensive guides and examples.
+- Improved serialization system with type safety.
+
+---
+
+## [0.3.0] – 2025-02-24 "Hummingbird"
+
+### Added
+- **Redesigned Core Architecture**: Modular and flexible design with Modules and Evaluators.
+- **FlockFactory**: Pre-configured agents for rapid development.
+- **Module System**: Lifecycle hooks (`initialize`, `pre_evaluate`, `post_evaluate`, `terminate`).
+- **Evaluator System**: `DeclarativeEvaluator` and `NaturalLanguageEvaluator`.
+- **Built-in Modules**: `MemoryModule`, `OutputModule`, and `MetricsModule`.
+- **CLI Interface**: Load flocks, theme builder, settings, advanced mode, and web server.
+- Release notes system with CLI integration.
+
+### Changed
+- `Flock` class initialization updated to include `init_console`.
+- Improved modularity and extensibility throughout the framework.
+
+---
+
+## [0.2.1] – 2025-01-15
+
+### Added
+- Initial public release to PyPI.
+- Declarative agent framework foundation.
+- Basic Temporal execution support.
+- Core tools: `get_web_content_as_markdown`, Azure Blob helper, markdown utilities.
+
+---
+
+*Older history prior to open-source release is maintained internally.*

{flock_core-0.5.0b10 → flock_core-0.5.0b11}/docs/about/contributing.md

@@ -23,7 +23,7 @@ First off, thanks for taking the time to contribute!  Flock is still early but w
 
 
 ## 2. Reporting Issues:
-* Before submitting a new issue, pleas check [existing issues](https://github.com/whiteducksoftware/flock/issues) if it has already been reported.
+* Before submitting a new issue, please check [existing issues](https://github.com/whiteducksoftware/flock/issues) if it has already been reported.
 * To submit a new issue, please use the provided **Issue Templates** and provide a clear and descriptive title along with a detailed description of the problem or feature request, including steps to reproduce if it's a bug.
 
 ---
@@ -84,8 +84,4 @@ mkdocs serve  # live-reload at http://localhost:8000
 
 --- 
 
-
-
-
-
 Happy hacking! 🐦

{flock_core-0.5.0b10 → flock_core-0.5.0b11}/docs/getting-started/installation.md

@@ -98,6 +98,6 @@ print("Flock imported successfully!")
 
 If this runs without errors, you're all set!
 
-Next Steps
+## Next Steps
 
-With Flock installed, you're ready for the Quick Start guide to build and run your first agent!
+With Flock installed, you're ready for the Quick Start guide to build and run your first agent!

{flock_core-0.5.0b10 → flock_core-0.5.0b11}/docs/getting-started/quickstart.md

@@ -102,14 +102,14 @@ Let's break down the magic:
 
 **Define Your Agent Declaratively**: This is the core of Flock! Instead of writing a long prompt, you used FlockFactory.create_default_agent and simply declared:
 
-input="topic: str": The agent needs one input called topic, which should be a string.
+`input="topic: str"`: The agent needs one input called topic, which should be a string.
 
-output="fun_title: str, fun_slide_headers: list[str]": The agent should produce two outputs: fun_title (a string) and fun_slide_headers (a list of strings).
+`output="fun_title: str, fun_slide_headers: list[str]"`: The agent should produce two outputs: fun_title (a string) and fun_slide_headers (a list of strings).
 Flock's default evaluator takes care of constructing the necessary instructions for the LLM based on these declarations and the agent's description.
 
 **Add the Agent**: You registered your presentation_agent with the flock.
 
-**Run the Flock**: flock.run() kicked off the process, starting with your specified agent and input.
+**Run the Flock**: `flock.run()` kicked off the process, starting with your specified agent and input.
 
 **Admire the Results**: Flock executed the agent (calling the LLM behind the scenes) and returned the output as a convenient Box object, allowing you to access the results using dot notation (like result.fun_title).
 
@@ -121,4 +121,4 @@ Explore adding Tools to give your agents superpowers (like web search or code ex
 
 Learn how to Chain Agents together for more complex workflows.
 
-Dive deeper into the Core Concepts that make Flock tick.
+Dive deeper into the Core Concepts that make Flock tick.

{flock_core-0.5.0b10 → flock_core-0.5.0b11}/docs/interacting-with-flock/web-ui.md

@@ -73,3 +73,17 @@ The Web UI is excellent for:
 - Demonstrating Flock capabilities without writing client code.
 - Simple internal tools where a basic web interface is sufficient.
 
+
+## Collecting Feedback
+
+Sometimes, you might need to collect feedback on the
+performance of your agents from your users as you iteratively refine your application.
+
+The WebUI offers a simple feedback-mechanism, allowing
+you to collect feedback from your users or team as you 
+iteratively refine your application.
+
+You can retrieve a CSV-File with the collected
+feedbacks for a specific agent by selecting 
+the `Download feedback for the selected agent...`
+option below the `Run Flock`-Button.

{flock_core-0.5.0b10 → flock_core-0.5.0b11}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "flock-core"
-version = "0.5.0b10"
+version = "0.5.0b11"
 description = "Declarative LLM Orchestration at Scale"
 readme = "README.md"
 authors = [
@@ -54,11 +54,14 @@ dependencies = [
     "opik>=1.7.26",
     "azure-data-tables>=12.7.0",
     "croniter>=6.0.0",
+    "werkzeug>=3.1.3",
     "chromadb>=0.6.3",
     "datasets>=3.2.0",
     "rouge-score>=0.1.2",
     "sentence-transformers>=3.4.1",
     "neo4j>=5.28.1",
+    "azure-storage-blob>=12.25.1",
+    "xlsxwriter>=3.2.3",
 ]
 
 [project.optional-dependencies]
@@ -178,4 +181,4 @@ torch = { index = "pytorch" }
 [[tool.uv.index]]
 name = "pytorch"
 url = "https://download.pytorch.org/whl/cpu"
-explicit = true
+explicit = true

{flock_core-0.5.0b10 → flock_core-0.5.0b11}/src/flock/components/evaluation/declarative_evaluation_component.py

@@ -2,7 +2,7 @@
 """DeclarativeEvaluationComponent - DSPy-based evaluation using the unified component system."""
 
 from collections.abc import Generator
-from typing import Any
+from typing import Any, override
 
 from temporalio import workflow
 
@@ -29,7 +29,7 @@ class DeclarativeEvaluationConfig(AgentComponentConfig):
     model: str | None = "openai/gpt-4o"
     use_cache: bool = True
     temperature: float = 0.0
-    max_tokens: int = 4096
+    max_tokens: int = 8192
     max_retries: int = 3
     max_tool_calls: int = 10
     stream: bool = Field(
@@ -69,6 +69,14 @@ class DeclarativeEvaluationComponent(
     def __init__(self, **data):
         super().__init__(**data)
 
+    @override
+    def set_model(self, model: str, temperature: float = 0.0, max_tokens: int = 8192) -> None:
+        """Set the model for the evaluation component."""
+        self.config.model = model
+        if "gpt-oss" in model and temperature == 0.0 and max_tokens == 8192:
+            self.config.temperature = 1.0
+            self.config.max_tokens = 32768
+
     async def evaluate_core(
         self,
         agent: Any,

{flock_core-0.5.0b10 → flock_core-0.5.0b11}/src/flock/core/component/evaluation_component.py

@@ -24,6 +24,12 @@ class EvaluationComponent(AgentComponent):
     - LLMEvaluationComponent (direct LLM API)
     """
 
+    @abstractmethod
+    def set_model(self, model: str, temperature: float = 0.0, max_tokens: int = 4096) -> None:
+        """Set the model for the evaluation component."""
+        pass
+
+
     @abstractmethod
     async def evaluate_core(
         self,

{flock_core-0.5.0b10 → flock_core-0.5.0b11}/src/flock/core/flock_agent.py

@@ -258,7 +258,7 @@ class FlockAgent(BaseModel, Serializable, DSPyIntegrationMixin, ABC):
         """
         self.model = model
         if self.evaluator and hasattr(self.evaluator, "config"):
-            self.evaluator.config.model = model
+            self.evaluator.set_model(model)
             logger.info(
                 f"Set model to '{model}' for agent '{self.name}' and its evaluator."
             )

{flock_core-0.5.0b10 → flock_core-0.5.0b11}/src/flock/core/flock_factory.py

@@ -435,6 +435,10 @@ class FlockFactory:
             OutputUtilityConfig,
         )
 
+        if model and "gpt-oss" in model:
+            temperature = 1.0
+            max_tokens = 32768
+
         # Create evaluation component
         eval_config = DeclarativeEvaluationConfig(
             model=model,