versionhq 1.2.0.4__py3-none-any.whl → 1.2.1.1__py3-none-any.whl

{versionhq-1.2.0.4.dist-info → versionhq-1.2.1.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: versionhq
-Version: 1.2.0.4
+Version: 1.2.1.1
 Summary: An agentic orchestration framework for building agent networks that handle task automation.
 Author-email: Kuriko Iwai <kuriko@versi0n.io>
 License: MIT License
@@ -81,10 +81,10 @@ Requires-Dist: pygraphviz>=1.14; extra == "pygraphviz"
 
 # Overview
 
-[![DL](https://img.shields.io/badge/Download-15K+-red)](https://clickpy.clickhouse.com/dashboard/versionhq)
+[![DL](https://img.shields.io/badge/Download-17K+-red)](https://clickpy.clickhouse.com/dashboard/versionhq)
 ![MIT license](https://img.shields.io/badge/License-MIT-green)
 [![Publisher](https://github.com/versionHQ/multi-agent-system/actions/workflows/publish.yml/badge.svg)](https://github.com/versionHQ/multi-agent-system/actions/workflows/publish.yml)
-![PyPI](https://img.shields.io/badge/PyPI-v1.2.0+-blue)
+![PyPI](https://img.shields.io/badge/PyPI-v1.2.1+-blue)
 ![python ver](https://img.shields.io/badge/Python-3.11/3.12-purple)
 ![pyenv ver](https://img.shields.io/badge/pyenv-2.5.0-orange)
 
@@ -106,14 +106,16 @@ A Python framework for agentic orchestration that handles complex task automatio
 <!-- DON'T EDIT THIS SECTION, INSTEAD RE-RUN doctoc TO UPDATE -->
 
 - [Key Features](#key-features)
-  - [Agent formation](#agent-formation)
+  - [Agent Network](#agent-network)
   - [Graph Theory Concept](#graph-theory-concept)
-  - [Agent optimization](#agent-optimization)
+  - [Task Graph](#task-graph)
+  - [Optimization](#optimization)
 - [Quick Start](#quick-start)
   - [Package installation](#package-installation)
   - [Forming a agent network](#forming-a-agent-network)
   - [Executing tasks](#executing-tasks)
   - [Supervising](#supervising)
+- [Supervising](#supervising-1)
 - [Technologies Used](#technologies-used)
 - [Project Structure](#project-structure)
 - [Setting Up a Project](#setting-up-a-project)
@@ -139,14 +141,14 @@ A Python framework for agentic orchestration that handles complex task automatio
 Agents are model-agnostic, and will improve task output, while oprimizing token cost and job latency, by sharing their memory, knowledge base, and RAG tools with other agents in the network.
 
 
-###  Agent formation
+###  Agent Network
 
 Agents adapt their formation based on task complexity.
 
 You can specify a desired formation or allow the agents to determine it autonomously (default).
 
 
-|  | **Solo Agent** | **Supervising** | **Network** | **Random** |
+|  | **Solo Agent** | **Supervising** | **Squad** | **Random** |
 | :--- | :--- | :--- | :--- | :--- |
 | **Formation** | <img src="https://res.cloudinary.com/dfeirxlea/image/upload/v1738818211/pj_m_agents/rbgxttfoeqqis1ettlfz.png" alt="solo" width="200"> | <img src="https://res.cloudinary.com/dfeirxlea/image/upload/v1738818211/pj_m_agents/zhungor3elxzer5dum10.png" alt="solo" width="200"> | <img src="https://res.cloudinary.com/dfeirxlea/image/upload/v1738818211/pj_m_agents/dnusl7iy7kiwkxwlpmg8.png" alt="solo" width="200"> | <img src="https://res.cloudinary.com/dfeirxlea/image/upload/v1738818211/pj_m_agents/sndpczatfzbrosxz9ama.png" alt="solo" width="200"> |
 | **Usage** | <ul><li>A single agent with tools, knowledge, and memory.</li><li>When self-learning mode is on - it will turn into **Random** formation.</li></ul> | <ul><li>Leader agent gives directions, while sharing its knowledge and memory.</li><li>Subordinates can be solo agents or networks.</li></ul> | <ul><li>Share tasks, knowledge, and memory among network members.</li></ul> | <ul><li>A single agent handles tasks, asking help from other agents without sharing its memory or knowledge.</li></ul> |
@@ -192,7 +194,19 @@ task_graph.visualize()
 
 <hr />
 
-### Agent optimization
+### Task Graph
+
+A `TaskGraph` represents tasks as `nodes` and their execution dependencies as `edges`, automating rule-based execution.
+
+`Agent Networks` can handle `TaskGraph` objects by optimizing their formations.
+
+The following example demonstrates a simple concept of a `supervising` agent network handling a task graph with three tasks and one critical edge.
+
+<img src="https://res.cloudinary.com/dfeirxlea/image/upload/v1739337639/pj_m_home/zfg4ccw1m1ww1tpnb0pa.png">
+
+<hr />
+
+### Optimization
 
 Agents are model-agnostic and can handle multiple tasks, leveraging their own and their peers' knowledge sources, memories, and tools.
 
@@ -292,42 +306,50 @@ This will return a `TaskOutput` object that stores response in plane text, JSON,
 
 ### Supervising
 
-   ```python
-   import versionhq as vhq
+## Supervising
 
-   agent_a = vhq.Agent(role="agent a", goal="My amazing goals", llm="llm-of-your-choice")
-   agent_b = vhq.Agent(role="agent b", goal="My amazing goals", llm="llm-of-your-choice")
+To create an agent network with one or more manager agents, designate members using the `is_manager` tag.
 
-   task_1 = vhq.Task(
-      description="Analyze the client's business model.",
-      response_fields=[vhq.ResponseField(title="test1", data_type=str, required=True),],
-      allow_delegation=True
-   )
+```python
+import versionhq as vhq
 
-    task_2 = vhq.Task(
-      description="Define the cohort.",
-      response_fields=[ResponseField(title="test1", data_type=int, required=True),],
-      allow_delegation=False
-   )
+agent_a = vhq.Agent(role="agent a", goal="My amazing goals", llm="llm-of-your-choice")
+agent_b = vhq.Agent(role="agent b", goal="My amazing goals", llm="llm-of-your-choice")
 
-   team = vhq.Team(
-      members=[
-         vhq.Member(agent=agent_a, is_manager=False, task=task_1),
-         vhq.Member(agent=agent_b, is_manager=True, task=task_2),
-      ],
-   )
-   res = team.launch()
-   ```
+task_1 = vhq.Task(
+   description="Analyze the client's business model.",
+   response_fields=[vhq.ResponseField(title="test1", data_type=str, required=True),],
+   allow_delegation=True
+)
+
+task_2 = vhq.Task(
+   description="Define a cohort.",
+   response_fields=[vhq.ResponseField(title="test1", data_type=int, required=True),],
+   allow_delegation=False
+)
+
+network =vhq.AgentNetwork(
+   members=[
+      vhq.Member(agent=agent_a, is_manager=False, tasks=[task_1]),
+      vhq.Member(agent=agent_b, is_manager=True, tasks=[task_2]), # Agent B as a manager
+   ],
+)
+res = network.launch()
+
+assert isinstance(res, vhq.NetworkOutput)
+assert not [item for item in task_1.processed_agents if "vhq-Delegated-Agent" == item]
+assert [item for item in task_1.processed_agents if "agent b" == item]
+```
 
 This will return a list with dictionaries with keys defined in the `ResponseField` of each task.
 
-Tasks can be delegated to a team manager, peers in the team, or completely new agent.
+Tasks can be delegated to a manager, peers within the agent network, or a completely new agent.
 
 <hr />
 
 ## Technologies Used
 
-**Graph Theory (Analysis and Visualization)**
+**Task Graph**
 
 * [NetworkX](https://networkx.org/documentation/stable/reference/introduction.html): A Python package to analyze, create, and manipulate complex graph networks.
 * [Matplotlib](https://matplotlib.org/stable/index.html): Visualization library

{versionhq-1.2.0.4.dist-info → versionhq-1.2.1.1.dist-info}/RECORD

@@ -1,17 +1,19 @@
-versionhq/__init__.py,sha256=9ZKO5IoKeFB9BaNAMZKDRLKf1xGAA_VSpgnMm1xc4GE,2783
+versionhq/__init__.py,sha256=Ct-oSIm8Mw2K2UH9CNTtuKaLgwUTIcUa3ogDAFQYHZo,2817
 versionhq/_utils/__init__.py,sha256=dzoZr4cBlh-2QZuPzTdehPUCe9lP1dmRtauD7qTjUaA,158
 versionhq/_utils/i18n.py,sha256=TwA_PnYfDLA6VqlUDPuybdV9lgi3Frh_ASsb_X8jJo8,1483
-versionhq/_utils/logger.py,sha256=j9SlQPIefdVUlwpGfJY83E2BUt1ejWgZ2M2I8aMyQ3c,1579
+versionhq/_utils/logger.py,sha256=2qkODR6y8ApOoMjQZVecTboXvCLrMy2v_mTSOnNMKFY,1581
 versionhq/_utils/process_config.py,sha256=jbPGXK2Kb4iyCugJ3FwRJuU0wL5Trq2x4xFQz2uOyFY,746
 versionhq/_utils/usage_metrics.py,sha256=NXF18dn5NNvGK7EsQ4AAghpR8ppYOjMx6ABenLLHnmM,1066
 versionhq/_utils/vars.py,sha256=bZ5Dx_bFKlt3hi4-NNGXqdk7B23If_WaTIju2fiTyPQ,57
 versionhq/agent/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-versionhq/agent/inhouse_agents.py,sha256=vSobrH1gXDWlaNsiges3sqETeUrEssRzQvCZCY2hQZA,2374
-versionhq/agent/model.py,sha256=kSYCAiRxF62ztj-S-_KfN0mhPKikjbFZ0fy2Yj5J7Jo,25400
+versionhq/agent/inhouse_agents.py,sha256=snDtgDmvZB2bZKH_RTcz5uFOMl3MTjLJwTQBebFt8hk,2532
+versionhq/agent/model.py,sha256=HiEQulVjXx6fWGaP-DBWmiZv5uwXFPd4S8jyBU3ydm0,25442
 versionhq/agent/parser.py,sha256=riG0dkdQCxH7uJ0AbdVdg7WvL0BXhUgJht0VtQvxJBc,4082
 versionhq/agent/rpm_controller.py,sha256=grezIxyBci_lDlwAlgWFRyR5KOocXeOhYkgN02dNFNE,2360
 versionhq/agent/TEMPLATES/Backstory.py,sha256=IAhGnnt6VUMe3wO6IzeyZPDNu7XE7Uiu3VEXUreOcKs,532
 versionhq/agent/TEMPLATES/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+versionhq/agent_network/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+versionhq/agent_network/model.py,sha256=P3Ntr_OIK60EXjEfaEm31HTBFypZfVr__0aC4VBt9G0,19353
 versionhq/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 versionhq/clients/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 versionhq/clients/customer/__init__.py,sha256=-YXh1FQfvpfLacK8SUC7bD7Wx_eIEi4yrkCC_cUasFg,217
@@ -19,22 +21,20 @@ versionhq/clients/customer/model.py,sha256=_AtaVVMm9MgCwrQ-HTRQ2oXUMKrSCEfZwE2Jd
 versionhq/clients/product/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 versionhq/clients/product/model.py,sha256=3w__pug9XRe4LIm9wX8C8WKqi40r081Eb1q2vWk9UaU,3694
 versionhq/clients/workflow/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-versionhq/clients/workflow/model.py,sha256=FNftenLLoha0bkivrjId32awLHAkBwIT8iNljdic_bw,6003
+versionhq/clients/workflow/model.py,sha256=fqmTx8Y6P6i-sK045ENO88GDbf4WYY4hUA26RfEH8Ek,6011
 versionhq/knowledge/__init__.py,sha256=qW7IgssTA4_bFFV9ziOcYRfGjlq1c8bkb-HnfWknpuQ,567
 versionhq/knowledge/_utils.py,sha256=YWRF8U533cfZes_gZqUvdj-K24MD2ri1R0gjc_aPYyc,402
 versionhq/knowledge/embedding.py,sha256=KfHc__1THxb5jrg1EMrF-v944RDuIr2hE0l-MtM3Bp0,6826
 versionhq/knowledge/model.py,sha256=w29mrJv1kiznCh4P4yJMUQxIuyRw1Sk0XYtBXzCxaG4,1786
-versionhq/knowledge/source.py,sha256=HxlwK7E5qWMknJeswnFCCdTIOB01hV4JrEiMGkp7j1E,13631
-versionhq/knowledge/source_docling.py,sha256=hhHn3rS4KVsFKEPWcfllM8VxSL86PckZdAHDZNQNOq8,5411
+versionhq/knowledge/source.py,sha256=-hEUPtJUHHMx4rUKtiHl19J8xAMw-WVBw34zwa2jZ08,13630
+versionhq/knowledge/source_docling.py,sha256=mg7bgvKePHn2LlA_XzSFCbS0zOo9xfu_aNOf5cEo6c4,5421
 versionhq/knowledge/storage.py,sha256=7oxCg3W9mFjYH1YmuH9kFtTbNxquzYFjuUjd_TlsB9E,8170
 versionhq/llm/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 versionhq/llm/llm_vars.py,sha256=wjQK20cKvph6Vq1v71o4d16zBGcHlwq0bzOT_zWno7w,7041
 versionhq/llm/model.py,sha256=wlzDUMEyIOm808d1vzqu9gmbB4ch-s_EUvwFR60gR80,17177
 versionhq/memory/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 versionhq/memory/contextual_memory.py,sha256=tCsOOAUnfrOL7YiakqGoi3uShzzS870TmGnlGd3z_A4,3556
-versionhq/memory/model.py,sha256=4wow2O3UuMZ0AbC2NyxddGZac3-_GjNZbK9wsA015NA,8145
-versionhq/network/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-versionhq/network/model.py,sha256=fKKMTviIS2uOwLYT_bGN_2-4R0gmnPB8x-dd05k5jFE,19700
+versionhq/memory/model.py,sha256=MPO8dDP5eAuk9td6bMOq5j2huLzCADFJDrTujHhcWQY,8150
 versionhq/storage/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 versionhq/storage/base.py,sha256=p-Jas0fXQan_qotnRD6seQxrT2lj-uw9-SmHQhdppcs,355
 versionhq/storage/ltm_sqlite_storage.py,sha256=wdUiuwHfJocdk0UGqyrdU4S5Nae1rgsoRNu3LWmGFcI,3951
@@ -44,15 +44,14 @@ versionhq/storage/task_output_storage.py,sha256=E1t_Fkt78dPYIOl3MP7LfQ8oGtjlzxBu
 versionhq/storage/utils.py,sha256=ByYXPoEIGJYLUqz-DWjbCAnneNrH1otiYbp12SCILpM,747
 versionhq/task/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 versionhq/task/evaluate.py,sha256=WdUgjbZL62XrxyWe5MTz29scfzwmuAHGxJ7GvAB8Fmk,3954
-versionhq/task/formation.py,sha256=iHhW2webMirYC78G8kHpaMTYjCdq7c3yFD2u2Egd8Eo,6350
+versionhq/task/formation.py,sha256=gBrFmMHvoyqdK9wEa9aBkZImEQV3GMDDX6-RDpw0pEo,6421
 versionhq/task/formatter.py,sha256=N8Kmk9vtrMtBdgJ8J7RmlKNMdZWSmV8O1bDexmCWgU0,643
 versionhq/task/log_handler.py,sha256=LT7YnO7gcPR9IZS7eRvMjnHh8crMBFtqduxd8dxIbkk,1680
-versionhq/task/model.py,sha256=zAnZ-_5YKZRs43gpM2AL9IVtttq5GqGfqfCMj_Oyz9g,30624
+versionhq/task/model.py,sha256=oPnShLU6huN2cfuEiHVO8Zl9_w44G9ZsWEWMBjpHfK4,30675
 versionhq/task/structured_response.py,sha256=4q-hQPu7oMMHHXEzh9YW4SJ7N5eCZ7OfZ65juyl_jCI,5000
 versionhq/task/TEMPLATES/Description.py,sha256=V-4kh8xpQTKOcDMi2xnuP-fcNk6kuoz1_5tYBlDLQWQ,420
-versionhq/team/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-versionhq/team/model.py,sha256=kxrjF3RFGO9l3IsJIffI1nqgl_Vh5RLuhqrwIqbEoBY,19214
-versionhq/team/team_planner.py,sha256=Zc3zvhPR7T0O8RQoq9CKOrvrll4klemY1rONLFeJ96M,3663
+versionhq/task_graph/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+versionhq/task_graph/model.py,sha256=TsszoTJFeJ4TfSdLAjcGa9QSQyf9Uy3WmechTw0qL3k,22832
 versionhq/tool/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 versionhq/tool/cache_handler.py,sha256=iL8FH7X0G-cdT0uhJwzuhLDaadTXOdfybZcDy151-es,1085
 versionhq/tool/composio_tool.py,sha256=38mEiVvTkuw1BLD233Bl1Gwxbpss1yfQiZLTWwX6BdA,8648
@@ -60,8 +59,8 @@ versionhq/tool/composio_tool_vars.py,sha256=FvBuEXsOQUYnN7RTFxT20kAkiEYkxWKkiVtg
 versionhq/tool/decorator.py,sha256=C4ZM7Xi2gwtEMaSeRo-geo_g_MAkY77WkSLkAuY0AyI,1205
 versionhq/tool/model.py,sha256=PO4zNWBZcJhYVur381YL1dy6zqurio2jWjtbxOxZMGI,12194
 versionhq/tool/tool_handler.py,sha256=2m41K8qo5bGCCbwMFferEjT-XZ-mE9F0mDUOBkgivOI,1416
-versionhq-1.2.0.4.dist-info/LICENSE,sha256=cRoGGdM73IiDs6nDWKqPlgSv7aR4n-qBXYnJlCMHCeE,1082
-versionhq-1.2.0.4.dist-info/METADATA,sha256=d0YGN_ulUD-0CLAOAGfyae2FLmY32CxT2RQEQzgjK20,21366
-versionhq-1.2.0.4.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-versionhq-1.2.0.4.dist-info/top_level.txt,sha256=DClQwxDWqIUGeRJkA8vBlgeNsYZs4_nJWMonzFt5Wj0,10
-versionhq-1.2.0.4.dist-info/RECORD,,
+versionhq-1.2.1.1.dist-info/LICENSE,sha256=cRoGGdM73IiDs6nDWKqPlgSv7aR4n-qBXYnJlCMHCeE,1082
+versionhq-1.2.1.1.dist-info/METADATA,sha256=cjE8Ov1BpANLgfAZAbHO0XmorFk9nAR-rVyJg1AczVc,22166
+versionhq-1.2.1.1.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+versionhq-1.2.1.1.dist-info/top_level.txt,sha256=DClQwxDWqIUGeRJkA8vBlgeNsYZs4_nJWMonzFt5Wj0,10
+versionhq-1.2.1.1.dist-info/RECORD,,

versionhq/team/team_planner.py

@@ -1,92 +0,0 @@
-import os
-from typing import Any, List, Optional, Dict
-from pydantic import BaseModel, Field
-
-
-class TeamPlanner:
-    """
-    A class to handle agent formations based on the given task description.
-    1) complexity
-    2) agent built (or use given agents)
-    3) knowledge, memory sharing
-    4) form a team
-    """
-
-    from versionhq.task.model import Task, ResponseField, TaskOutput
-    from versionhq.agent.model import Agent
-
-
-    def __init__(self, tasks: List[Task], planner_llm: Optional[Any] = None):
-        self.tasks = tasks
-        self.planner_llm = planner_llm if planner_llm else os.environ.get("DEFAULT_MODEL_NAME")
-
-
-    def _handle_assign_agents(self, unassigned_tasks: List[Task]) -> List[Any]:
-        """
-        Build an agent and assign it a task, then return a list of Member connecting the agent created and the task given.
-        """
-
-        from versionhq.agent.model import Agent
-        from versionhq.task.model import Task, ResponseField
-        from versionhq.team.model import Member
-
-        new_member_list: List[Member] = []
-        agent_creator = Agent(
-            role="agent_creator",
-            goal="build an ai agent that can competitively handle the task given",
-            llm=self.planner_llm,
-        )
-
-        for unassgined_task in unassigned_tasks:
-            task = Task(
-                description=f"""
-                    Based on the following task summary, draft a AI agent's role and goal in concise manner.
-                    Task summary: {unassgined_task.summary}
-                """,
-                response_fields=[
-                    ResponseField(title="goal", data_type=str, required=True),
-                    ResponseField(title="role", data_type=str, required=True),
-                ],
-            )
-            res = task.execute(agent=agent_creator)
-            agent = Agent(
-                role=res.json_dict["role"] if "role" in res.json_dict else res.raw,
-                goal=res.json_dict["goal"] if "goal" in res.json_dict else task.description
-            )
-            if agent.id:
-                team_member = Member(agent=agent, tasks=[unassgined_task], is_manager=False)
-                new_member_list.append(team_member)
-
-        return new_member_list
-
-
-    def _handle_task_planning(self, context: Optional[str] = None, tools: Optional[str] = None) -> TaskOutput:
-        """
-        Handles the team planning by creating detailed step-by-step plans for each task.
-        """
-
-        from versionhq.agent.model import Agent
-        from versionhq.task.model import Task
-
-        team_planner = Agent(
-            role="team planner",
-            goal="Plan extremely detailed, step-by-step plan based on the tasks and tools available to each agent so that they can perform the tasks in an exemplary manner and assign a task to each agent.",
-            llm=self.planner_llm,
-        )
-
-        task_summary_list = [task.summary for task in self.tasks]
-
-        class TeamPlanIdea(BaseModel):
-            plan: str | Dict[str, Any] = Field(default=None, description="a decriptive plan to be executed by the team")
-
-
-        task = Task(
-            description=f"""
-                Based on the following task summaries, create the most descriptive plan that the team can execute most efficiently. Take all the task summaries - task's description and tools available - into consideration. Your answer only contains a dictionary.
-
-                Task summaries: {" ".join(task_summary_list)}
-            """,
-            pydantic_output=TeamPlanIdea
-        )
-        output = task.execute(agent=team_planner, context=context, tools=tools)
-        return output