| Name | taskara JSON |
| Version |
0.1.181
JSON |
| download |
| home_page | None |
| Summary | Task management for AI agents |
| upload_time | 2024-12-20 03:53:52 |
| maintainer | None |
| docs_url | None |
| author | Patrick Barker |
| requires_python | <4.0,>=3.10 |
| license | MIT |
| keywords |
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
<!-- PROJECT LOGO -->
<br />
<p align="center">
<!-- <a href="https://github.com/agentsea/skillpacks">
<img src="https://project-logo.png" alt="Logo" width="80">
</a> -->
<h1 align="center">Taskara</h1>
<p align="center">
Task management for AI agents
<br />
<a href="https://docs.hub.agentsea.ai/taskara/intro"><strong>Explore the docs »</strong></a>
<br />
<br />
<a href="https://youtu.be/exoOUUwFRB8">View Demo</a>
·
<a href="https://github.com/agentsea/taskara/issues">Report Bug</a>
·
<a href="https://github.com/agentsea/taskara/issues">Request Feature</a>
</p>
<br>
</p>
## Installation
```sh
pip install taskara
```
## Usage
Create a task
```python
from taskara import Task
task = Task(
description="Search for the most common varieties of french ducks",
owner_id="delores@agentsea.ai"
)
```
Assign the task to an agent
```python
task.assigned_to = "roko@agentsea.ai"
```
Post a message to the task thread
```python
task.post_message("assistant", "Getting started working on this")
task.status = "in progress"
```
Create a custom thread for the task
```python
task.create_thread("debug")
task.post_message("assistant", "I'll post debug messages to this thread", thread="debug")
task.post_message("assistant", 'My current screenshot', images=["b64img"], thread="debug")
```
Store prompts used to accomplish the task
```python
from mllm import RoleThread, RoleMessage
thread = RoleThread()
thread.post(role="system", msg="I am a helpful assistant")
response = RoleMessage(
role="assistant",
text="How can I help?"
)
task.store_prompt(thread, response, namespace="actions")
```
Store the result
```python
task.output = "The most common type of french duck is the Rouen"
task.status = "success"
```
Save the task
```python
task.save()
```
## Tracker
Taskara comes with a task tracker server which can be run on docker or kubernetes.
Install surfkit to create a tracker
```
pip install surfkit
```
Create a tracker
```
surfkit create tracker
```
List trackers
```
surfkit list trackers
```
Get tracker logs
```
surfkit logs tracker <name>
```
Create a task
```
surfkit create task --description "Search for french ducks"
```
List tasks
```
surfkit list tasks
```
Get a task
```
surfkit get task <id>
```
## Integrations
Taskara is integrated with:
- [Surfkit](https://github.com/agentsea/surfkit) A platform for AI agents
- [MLLM](https://github.com/agentsea/mllm) A prompt management, routing, and schema validation library for multimodal LLMs
- [Skillpacks](https://github.com/agentsea/skillpacks) A library to fine tune AI agents on tasks.
- [Threadmem](https://github.com/agentsea/threadmem) A thread management library for AI agents
## Community
Come join us on [Discord](https://discord.gg/hhaq7XYPS6).
## Backends
Thread and prompt storage can be backed by:
- Sqlite
- Postgresql
Sqlite will be used by default. To use postgres simply configure the env vars:
```sh
DB_TYPE=postgres
DB_NAME=tasks
DB_HOST=localhost
DB_USER=postgres
DB_PASS=abc123
```
Thread image storage by default will utilize the db, to configure bucket storage using GCS:
- Create a bucket with fine grained permissions
- Create a GCP service account JSON with permissions to write to the bucket
```sh
export THREAD_STORAGE_SA_JSON='{
"type": "service_account",
...
}'
export THREAD_STORAGE_BUCKET=my-bucket
```
Raw data
{
"_id": null,
"home_page": null,
"name": "taskara",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.10",
"maintainer_email": null,
"keywords": null,
"author": "Patrick Barker",
"author_email": "patrickbarkerco@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/19/d5/379e18917aac054442ad8a50ceac144d61e6a9673edd2ff80f2bf260b1a2/taskara-0.1.181.tar.gz",
"platform": null,
"description": "<!-- PROJECT LOGO -->\n<br />\n<p align=\"center\">\n <!-- <a href=\"https://github.com/agentsea/skillpacks\">\n <img src=\"https://project-logo.png\" alt=\"Logo\" width=\"80\">\n </a> -->\n\n <h1 align=\"center\">Taskara</h1>\n\n <p align=\"center\">\n Task management for AI agents\n <br />\n <a href=\"https://docs.hub.agentsea.ai/taskara/intro\"><strong>Explore the docs \u00bb</strong></a>\n <br />\n <br />\n <a href=\"https://youtu.be/exoOUUwFRB8\">View Demo</a>\n \u00b7\n <a href=\"https://github.com/agentsea/taskara/issues\">Report Bug</a>\n \u00b7\n <a href=\"https://github.com/agentsea/taskara/issues\">Request Feature</a>\n </p>\n <br>\n</p>\n\n## Installation\n\n```sh\npip install taskara\n```\n\n## Usage\n\nCreate a task\n\n```python\nfrom taskara import Task\n\ntask = Task(\n description=\"Search for the most common varieties of french ducks\",\n owner_id=\"delores@agentsea.ai\"\n)\n```\n\nAssign the task to an agent\n\n```python\ntask.assigned_to = \"roko@agentsea.ai\"\n```\n\nPost a message to the task thread\n\n```python\ntask.post_message(\"assistant\", \"Getting started working on this\")\ntask.status = \"in progress\"\n```\n\nCreate a custom thread for the task\n\n```python\ntask.create_thread(\"debug\")\ntask.post_message(\"assistant\", \"I'll post debug messages to this thread\", thread=\"debug\")\ntask.post_message(\"assistant\", 'My current screenshot', images=[\"b64img\"], thread=\"debug\")\n```\n\nStore prompts used to accomplish the task\n\n```python\nfrom mllm import RoleThread, RoleMessage\n\nthread = RoleThread()\nthread.post(role=\"system\", msg=\"I am a helpful assistant\")\n\nresponse = RoleMessage(\n role=\"assistant\",\n text=\"How can I help?\"\n)\ntask.store_prompt(thread, response, namespace=\"actions\")\n```\n\nStore the result\n\n```python\ntask.output = \"The most common type of french duck is the Rouen\"\ntask.status = \"success\"\n```\n\nSave the task\n\n```python\ntask.save()\n```\n\n## Tracker\n\nTaskara comes with a task tracker server which can be run on docker or kubernetes.\n\nInstall surfkit to create a tracker\n\n```\npip install surfkit\n```\n\nCreate a tracker\n\n```\nsurfkit create tracker\n```\n\nList trackers\n\n```\nsurfkit list trackers\n```\n\nGet tracker logs\n\n```\nsurfkit logs tracker <name>\n```\n\nCreate a task\n\n```\nsurfkit create task --description \"Search for french ducks\"\n```\n\nList tasks\n\n```\nsurfkit list tasks\n```\n\nGet a task\n\n```\nsurfkit get task <id>\n```\n\n## Integrations\n\nTaskara is integrated with:\n\n- [Surfkit](https://github.com/agentsea/surfkit) A platform for AI agents\n- [MLLM](https://github.com/agentsea/mllm) A prompt management, routing, and schema validation library for multimodal LLMs\n- [Skillpacks](https://github.com/agentsea/skillpacks) A library to fine tune AI agents on tasks.\n- [Threadmem](https://github.com/agentsea/threadmem) A thread management library for AI agents\n\n## Community\n\nCome join us on [Discord](https://discord.gg/hhaq7XYPS6).\n\n## Backends\n\nThread and prompt storage can be backed by:\n\n- Sqlite\n- Postgresql\n\nSqlite will be used by default. To use postgres simply configure the env vars:\n\n```sh\nDB_TYPE=postgres\nDB_NAME=tasks\nDB_HOST=localhost\nDB_USER=postgres\nDB_PASS=abc123\n```\n\nThread image storage by default will utilize the db, to configure bucket storage using GCS:\n\n- Create a bucket with fine grained permissions\n- Create a GCP service account JSON with permissions to write to the bucket\n\n```sh\nexport THREAD_STORAGE_SA_JSON='{\n \"type\": \"service_account\",\n ...\n}'\nexport THREAD_STORAGE_BUCKET=my-bucket\n```\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Task management for AI agents",
"version": "0.1.181",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "a2082f939df75c70c3f0a8d9d287381ded30de2dd74e667a9838480b2323c517",
"md5": "2687234dc9fd84d76353ab68c5e047c0",
"sha256": "c541a417311bbfb18460e88741fb141d54bfb5feb4e8338736da39b8bc459b06"
},
"downloads": -1,
"filename": "taskara-0.1.181-py3-none-any.whl",
"has_sig": false,
"md5_digest": "2687234dc9fd84d76353ab68c5e047c0",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.10",
"size": 62107,
"upload_time": "2024-12-20T03:53:50",
"upload_time_iso_8601": "2024-12-20T03:53:50.799533Z",
"url": "https://files.pythonhosted.org/packages/a2/08/2f939df75c70c3f0a8d9d287381ded30de2dd74e667a9838480b2323c517/taskara-0.1.181-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "19d5379e18917aac054442ad8a50ceac144d61e6a9673edd2ff80f2bf260b1a2",
"md5": "7c21655bffd8f49af5abe93dbf742994",
"sha256": "2dc0e2f76651c14776a1b41299fd3da26827dd693f9912125c8f97deff6db19b"
},
"downloads": -1,
"filename": "taskara-0.1.181.tar.gz",
"has_sig": false,
"md5_digest": "7c21655bffd8f49af5abe93dbf742994",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.10",
"size": 51688,
"upload_time": "2024-12-20T03:53:52",
"upload_time_iso_8601": "2024-12-20T03:53:52.159187Z",
"url": "https://files.pythonhosted.org/packages/19/d5/379e18917aac054442ad8a50ceac144d61e6a9673edd2ff80f2bf260b1a2/taskara-0.1.181.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-12-20 03:53:52",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "taskara"
}
