versionhq 1.1.10.9__tar.gz → 1.1.11.0__tar.gz

{versionhq-1.1.10.9 → versionhq-1.1.11.0}/.github/workflows/publish_testpypi.yml

@@ -22,7 +22,7 @@ jobs:
 
       - name: Build release distributions
         run: |
-          uv venv --python 3.13.1
+          uv venv --python 3.12.8
           source .venv/bin/activate
           uv pip install --upgrade pip twine
           uv pip install -r requirements.txt

{versionhq-1.1.10.9 → versionhq-1.1.11.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: versionhq
-Version: 1.1.10.9
+Version: 1.1.11.0
 Summary: LLM orchestration frameworks for model-agnostic AI agents that handle complex outbound workflows
 Author-email: Kuriko Iwai <kuriko@versi0n.io>
 License: MIT License
@@ -162,7 +162,7 @@ You can specify which formation you want them to generate, or let the agent deci
 
    task = Task(
       description="Amazing task",
-      pydantic_custom_output=CustomOutput,
+      pydantic_output=CustomOutput,
       callback=dummy_func,
       callback_kwargs=dict(message="Hi! Here is the result: ")
    )
@@ -171,14 +171,17 @@ You can specify which formation you want them to generate, or let the agent deci
    print(res)
    ```
 
-This will return `TaskOutput` that stores a response in string, JSON dict, and Pydantic model: `CustomOutput` formats with a callback result.
+This will return `TaskOutput` instance that stores a response in plane text, JSON serializable dict, and Pydantic model: `CustomOutput` formats with a callback result, tool output (if given), and evaluation results (if given).
 
    ```
    res == TaskOutput(
-      raw="{\\"test1\\": \\"random str\\", \\"test2\\": [\\"item1\\", \\"item2\\"]}",
-      json_dict={"test1": "random str", "test2": ["item1", "item2"]},
-      pydantic=CustomOutput(test1="random str", test2=["item 1", "item 2"]),
-      callback_output="Hi! Here is the result: random str, item 1, item 2",
+      task_id=UUID('<TASK UUID>')
+      raw='{\"test1\":\"random str\", \"test2\":[\"str item 1\", \"str item 2\", \"str item 3\"]}',
+      json_dict={'test1': 'random str', 'test2': ['str item 1', 'str item 2', 'str item 3']},
+      pydantic=<class '__main__.CustomOutput'>
+      tool_output=None,
+      callback_output='Hi! Here is the result: random str, str item 1, str item 2, str item 3',
+      evaluation=None
    )
    ```
 
@@ -404,6 +407,7 @@ Common issues and solutions:
 - API key errors: Ensure all API keys in the `.env` file are correct and up to date. Make sure to add `load_dotenv()` on the top of the python file to apply the latest environment values.
 - Database connection issues: Check if the Chroma DB is properly initialized and accessible.
 - Memory errors: If processing large contracts, you may need to increase the available memory for the Python process.
+- Issues related to the Python version: Docling/Pytorch is not ready for Python 3.13 as of Jan 2025. Use Python 3.12.x as default by running `uv venv --python 3.12.8` and `uv python pin 3.12.8`.
 - Issues related to dependencies: `rm -rf uv.lock`, `uv cache clean`, `uv venv`, and run `uv pip install -r requirements.txt -v`.
 - Issues related to the AI agents or RAG system: Check the `output.log` file for detailed error messages and stack traces.
 - Issues related to `Python quit unexpectedly`: Check [this stackoverflow article](https://stackoverflow.com/questions/59888499/macos-catalina-python-quit-unexpectedly-error).

{versionhq-1.1.10.9 → versionhq-1.1.11.0}/README.md

@@ -97,7 +97,7 @@ You can specify which formation you want them to generate, or let the agent deci
 
    task = Task(
       description="Amazing task",
-      pydantic_custom_output=CustomOutput,
+      pydantic_output=CustomOutput,
       callback=dummy_func,
       callback_kwargs=dict(message="Hi! Here is the result: ")
    )
@@ -106,14 +106,17 @@ You can specify which formation you want them to generate, or let the agent deci
    print(res)
    ```
 
-This will return `TaskOutput` that stores a response in string, JSON dict, and Pydantic model: `CustomOutput` formats with a callback result.
+This will return `TaskOutput` instance that stores a response in plane text, JSON serializable dict, and Pydantic model: `CustomOutput` formats with a callback result, tool output (if given), and evaluation results (if given).
 
    ```
    res == TaskOutput(
-      raw="{\\"test1\\": \\"random str\\", \\"test2\\": [\\"item1\\", \\"item2\\"]}",
-      json_dict={"test1": "random str", "test2": ["item1", "item2"]},
-      pydantic=CustomOutput(test1="random str", test2=["item 1", "item 2"]),
-      callback_output="Hi! Here is the result: random str, item 1, item 2",
+      task_id=UUID('<TASK UUID>')
+      raw='{\"test1\":\"random str\", \"test2\":[\"str item 1\", \"str item 2\", \"str item 3\"]}',
+      json_dict={'test1': 'random str', 'test2': ['str item 1', 'str item 2', 'str item 3']},
+      pydantic=<class '__main__.CustomOutput'>
+      tool_output=None,
+      callback_output='Hi! Here is the result: random str, str item 1, str item 2, str item 3',
+      evaluation=None
    )
    ```
 
@@ -339,6 +342,7 @@ Common issues and solutions:
 - API key errors: Ensure all API keys in the `.env` file are correct and up to date. Make sure to add `load_dotenv()` on the top of the python file to apply the latest environment values.
 - Database connection issues: Check if the Chroma DB is properly initialized and accessible.
 - Memory errors: If processing large contracts, you may need to increase the available memory for the Python process.
+- Issues related to the Python version: Docling/Pytorch is not ready for Python 3.13 as of Jan 2025. Use Python 3.12.x as default by running `uv venv --python 3.12.8` and `uv python pin 3.12.8`.
 - Issues related to dependencies: `rm -rf uv.lock`, `uv cache clean`, `uv venv`, and run `uv pip install -r requirements.txt -v`.
 - Issues related to the AI agents or RAG system: Check the `output.log` file for detailed error messages and stack traces.
 - Issues related to `Python quit unexpectedly`: Check [this stackoverflow article](https://stackoverflow.com/questions/59888499/macos-catalina-python-quit-unexpectedly-error).

{versionhq-1.1.10.9 → versionhq-1.1.11.0}/pyproject.toml

@@ -15,7 +15,7 @@ exclude = ["test*", "__pycache__"]
 
 [project]
 name = "versionhq"
-version = "1.1.10.9"
+version = "1.1.11.0"
 authors = [{ name = "Kuriko Iwai", email = "kuriko@versi0n.io" }]
 description = "LLM orchestration frameworks for model-agnostic AI agents that handle complex outbound workflows"
 readme = "README.md"

{versionhq-1.1.10.9 → versionhq-1.1.11.0}/src/versionhq/__init__.py

@@ -18,7 +18,7 @@ from versionhq.tool.model import Tool
 from versionhq.tool.composio_tool import ComposioHandler
 
 
-__version__ = "1.1.10.9"
+__version__ = "1.1.11.0"
 __all__ = [
     "Agent",
     "Customer",

{versionhq-1.1.10.9 → versionhq-1.1.11.0}/src/versionhq/agent/default_agents.py

@@ -7,4 +7,9 @@ List up agents to be called across the project.
 
 client_manager = Agent(role="Client Manager", goal="communicate with clients on the task progress", llm=DEFAULT_MODEL_NAME)
 
-task_evaluator = Agent(role="Task Evaluator", goal="score the output according to the given evaluation criteria.", llm=DEFAULT_MODEL_NAME)
+task_evaluator = Agent(
+    role="Task Evaluator",
+    goal="score the output according to the given evaluation criteria.",
+    llm=DEFAULT_MODEL_NAME,
+    llm_config=dict(top_p=0.8, top_k=30, max_tokens=5000, temperature=0.9)
+)

versionhq-1.1.11.0/src/versionhq/task/TEMPLATES/Description.py

@@ -0,0 +1,5 @@
+EVALUATE="""Assess the accuracy and quality of the following task output to the task described below. Score based on the criterion (0-1, 0=worst, 1=best) and suggest improvements. Vary scores; don't assign identical values. Store criteria in the "criteria" field.
+Task: {task_description}
+Task Output: {task_output}
+Evaluation criteria: {eval_criteria}
+"""

{versionhq-1.1.10.9 → versionhq-1.1.11.0}/src/versionhq.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: versionhq
-Version: 1.1.10.9
+Version: 1.1.11.0
 Summary: LLM orchestration frameworks for model-agnostic AI agents that handle complex outbound workflows
 Author-email: Kuriko Iwai <kuriko@versi0n.io>
 License: MIT License
@@ -162,7 +162,7 @@ You can specify which formation you want them to generate, or let the agent deci
 
    task = Task(
       description="Amazing task",
-      pydantic_custom_output=CustomOutput,
+      pydantic_output=CustomOutput,
       callback=dummy_func,
       callback_kwargs=dict(message="Hi! Here is the result: ")
    )
@@ -171,14 +171,17 @@ You can specify which formation you want them to generate, or let the agent deci
    print(res)
    ```
 
-This will return `TaskOutput` that stores a response in string, JSON dict, and Pydantic model: `CustomOutput` formats with a callback result.
+This will return `TaskOutput` instance that stores a response in plane text, JSON serializable dict, and Pydantic model: `CustomOutput` formats with a callback result, tool output (if given), and evaluation results (if given).
 
    ```
    res == TaskOutput(
-      raw="{\\"test1\\": \\"random str\\", \\"test2\\": [\\"item1\\", \\"item2\\"]}",
-      json_dict={"test1": "random str", "test2": ["item1", "item2"]},
-      pydantic=CustomOutput(test1="random str", test2=["item 1", "item 2"]),
-      callback_output="Hi! Here is the result: random str, item 1, item 2",
+      task_id=UUID('<TASK UUID>')
+      raw='{\"test1\":\"random str\", \"test2\":[\"str item 1\", \"str item 2\", \"str item 3\"]}',
+      json_dict={'test1': 'random str', 'test2': ['str item 1', 'str item 2', 'str item 3']},
+      pydantic=<class '__main__.CustomOutput'>
+      tool_output=None,
+      callback_output='Hi! Here is the result: random str, str item 1, str item 2, str item 3',
+      evaluation=None
    )
    ```
 
@@ -404,6 +407,7 @@ Common issues and solutions:
 - API key errors: Ensure all API keys in the `.env` file are correct and up to date. Make sure to add `load_dotenv()` on the top of the python file to apply the latest environment values.
 - Database connection issues: Check if the Chroma DB is properly initialized and accessible.
 - Memory errors: If processing large contracts, you may need to increase the available memory for the Python process.
+- Issues related to the Python version: Docling/Pytorch is not ready for Python 3.13 as of Jan 2025. Use Python 3.12.x as default by running `uv venv --python 3.12.8` and `uv python pin 3.12.8`.
 - Issues related to dependencies: `rm -rf uv.lock`, `uv cache clean`, `uv venv`, and run `uv pip install -r requirements.txt -v`.
 - Issues related to the AI agents or RAG system: Check the `output.log` file for detailed error messages and stack traces.
 - Issues related to `Python quit unexpectedly`: Check [this stackoverflow article](https://stackoverflow.com/questions/59888499/macos-catalina-python-quit-unexpectedly-error).

versionhq-1.1.10.9/src/versionhq/task/TEMPLATES/Description.py

@@ -1,5 +0,0 @@
-EVALUATE="""Evaluate the accuracy and quality of the following task output. For each criterion defined below, provide a score between 0 (completely inaccurate/unacceptable) and 1 (perfectly accurate/acceptable), and suggest specific improvements to address any shortcomings.
-Task: {task_description}
-Task Output: {task_output}
-Evaluation criteria: {eval_criteria}
-"""