# Agential
## Features
Our primary goal is to provide easy-to-use and clean functions for natural language processing tasks, enabling developers to build robust and efficient applications with ease.
- Easy-to-Use Interface: Provides intuitive and user-friendly functions for rapid prototyping and development.
- Clean Functions: Offers clean and well-structured functions, promoting readability and maintainability of code.
- Modularized Implementations: Includes modularized implementations of popular LLM-based agents and agent-related methods, allowing users to leverage cutting-edge innovations from the literature.
## Getting Started
```python
question = 'Who was once considered the best kick boxer in the world, however he has been involved in a number of controversies relating to his "unsportsmanlike conducts" in the sport and crimes of violence outside of the ring?'
llm = ChatOpenAI(openai_api_key="YOUR_API_KEY")
agent = ReActAgent(llm=llm)
out = agent.generate(question=question)
```
Here's what the output would look like!
```
Thought : I need to search for the best kick boxer in the world, and then find any controversies or crimes they have been involved in.
Action : Search[best kick boxer in the world]
Observation : (Result 1/1) Ramon Dekkers is considered by many to be the best kickboxer in the world.
Thought : It mentions "unsportsmanlike conducts" and crimes of violence. I need to find more information about Ramon Dekkers.
Action : Lookup[crimes]
Observation: (Result 1/1) Dekkers was involved in a number of controversies relating to his "unsportsmanlike conducts" in the sport and crimes of violence outside of the ring.
Thought: Ramon Dekkers has been involved in controversies and crimes. I need to find more information about them.
...
```
## Project Organization
------------
├── data
│ ├── external <- Data from third party sources.
│ ├── interim <- Intermediate data that has been transformed.
│ ├── processed <- The final, canonical data sets for modeling.
│ └── raw <- The original, immutable data dump.
│
├── agential <- Source code for this project.
│ ├── cog
│ │ ├── agent <- Model/agent-related modules.
│ │ │
│ │ ├── eval <- Agent core modules.
│ │ │
│ │ ├── functional
│ │ │
│ │ ├── modules
│ │ │ ├── memory <- Memory-related modules.
│ │ │ ├── plan <- Planning-related modules.
│ │ │ ├── reflect <- Reflecting-related modules.
│ │ │ └── score <- Scoring-related modules.
│ │ │
│ │ ├── persona
│ │ │
│ │ └── prompts
│ │
│ └── utils <- Utility methods.
│
├── docs <- An mkdocs project.
│
├── models <- Trained and serialized models, model predictions,
│ or model summaries.
│
├── notebooks <- Jupyter notebooks. Naming convention is a number
│ (for ordering), the creator's initials, and a short `-` delimited │ description, e.g. `1.0-jqp-initial-data-exploration`.
│
│
├── references <- Data dictionaries, manuals, and all other explanatory materials.
│
├── reports <- Generated analysis as HTML, PDF, LaTeX, etc.
│ └── figures <- Generated graphics and figures to be used in reporting.
│
└── tests <- Tests.
---------
## Contributing
If you want to contribute, please check the [contributing.md](https://github.com/alckasoc/agential/blob/main/CONTRIBUTING.md) for guidelines!
Raw data
{
"_id": null,
"home_page": "https://github.com/alckasoc/agential",
"name": "agential",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.11",
"maintainer_email": null,
"keywords": "agent, LLM, poetry",
"author": "Vincent Tu",
"author_email": "tuvincent0106@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/3d/75/f941158053ec594e5e611034bf1da5f4f9dec097bf6607fdbfa78f634938/agential-0.0.1.tar.gz",
"platform": null,
"description": "\n# Agential\n\n\n## Features\n\n\n Our primary goal is to provide easy-to-use and clean functions for natural language processing tasks, enabling developers to build robust and efficient applications with ease.\n\n- Easy-to-Use Interface: Provides intuitive and user-friendly functions for rapid prototyping and development.\n\n- Clean Functions: Offers clean and well-structured functions, promoting readability and maintainability of code.\n\n- Modularized Implementations: Includes modularized implementations of popular LLM-based agents and agent-related methods, allowing users to leverage cutting-edge innovations from the literature.\n\n\n## Getting Started \n\n```python\nquestion = 'Who was once considered the best kick boxer in the world, however he has been involved in a number of controversies relating to his \"unsportsmanlike conducts\" in the sport and crimes of violence outside of the ring?'\n\nllm = ChatOpenAI(openai_api_key=\"YOUR_API_KEY\")\nagent = ReActAgent(llm=llm)\nout = agent.generate(question=question)\n```\n\n\nHere's what the output would look like!\n```\nThought : I need to search for the best kick boxer in the world, and then find any controversies or crimes they have been involved in.\nAction : Search[best kick boxer in the world]\nObservation : (Result 1/1) Ramon Dekkers is considered by many to be the best kickboxer in the world.\nThought : It mentions \"unsportsmanlike conducts\" and crimes of violence. I need to find more information about Ramon Dekkers.\nAction : Lookup[crimes]\nObservation: (Result 1/1) Dekkers was involved in a number of controversies relating to his \"unsportsmanlike conducts\" in the sport and crimes of violence outside of the ring.\nThought: Ramon Dekkers has been involved in controversies and crimes. I need to find more information about them.\n...\n```\n\n\n## Project Organization\n\n------------\n\n \n\n \u251c\u2500\u2500 data\n \u2502\u00a0\u00a0 \u251c\u2500\u2500 external <- Data from third party sources.\n \u2502\u00a0\u00a0 \u251c\u2500\u2500 interim <- Intermediate data that has been transformed.\n \u2502\u00a0\u00a0 \u251c\u2500\u2500 processed <- The final, canonical data sets for modeling.\n \u2502\u00a0\u00a0 \u2514\u2500\u2500 raw <- The original, immutable data dump.\n \u2502\n \u251c\u2500\u2500 agential <- Source code for this project.\n \u2502\u00a0\u00a0 \u251c\u2500\u2500 cog \n \u2502 \u2502 \u251c\u2500\u2500 agent <- Model/agent-related modules.\n \u2502 \u2502 \u2502 \n \u2502 \u2502 \u251c\u2500\u2500 eval <- Agent core modules.\n \u2502 \u2502 \u2502 \n \u2502 \u2502 \u251c\u2500\u2500 functional \n \u2502 \u2502 \u2502\n \u2502 \u2502 \u251c\u2500\u2500 modules \n \u2502 \u2502 \u2502 \u251c\u2500\u2500 memory <- Memory-related modules.\n \u2502 \u2502 \u2502 \u251c\u2500\u2500 plan <- Planning-related modules.\n \u2502 \u2502 \u2502 \u251c\u2500\u2500 reflect <- Reflecting-related modules.\n \u2502 \u2502 \u2502 \u2514\u2500\u2500 score <- Scoring-related modules.\n \u2502 \u2502 \u2502\n \u2502 \u2502 \u251c\u2500\u2500 persona \n \u2502 \u2502 \u2502\n \u2502 \u2502 \u2514\u2500\u2500 prompts \n \u2502 \u2502\n \u2502 \u2514\u2500\u2500 utils <- Utility methods.\n \u2502 \n \u251c\u2500\u2500 docs <- An mkdocs project.\n \u2502\n \u251c\u2500\u2500 models <- Trained and serialized models, model predictions,\n \u2502 or model summaries.\n \u2502 \n \u251c\u2500\u2500 notebooks <- Jupyter notebooks. Naming convention is a number \n \u2502 (for ordering), the creator's initials, and a short `-` delimited \u2502 description, e.g. `1.0-jqp-initial-data-exploration`.\n \u2502 \n \u2502\n \u251c\u2500\u2500 references <- Data dictionaries, manuals, and all other explanatory materials.\n \u2502\n \u251c\u2500\u2500 reports <- Generated analysis as HTML, PDF, LaTeX, etc.\n \u2502\u00a0\u00a0 \u2514\u2500\u2500 figures <- Generated graphics and figures to be used in reporting.\n \u2502\n \u2514\u2500\u2500 tests <- Tests.\n\n---------\n\n\n## Contributing\n\nIf you want to contribute, please check the [contributing.md](https://github.com/alckasoc/agential/blob/main/CONTRIBUTING.md) for guidelines!\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "A flexible agent library.",
"version": "0.0.1",
"project_urls": {
"Homepage": "https://github.com/alckasoc/agential",
"Repository": "https://github.com/alckasoc/agential"
},
"split_keywords": [
"agent",
" llm",
" poetry"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "3c7e49760b1bd3ff55fb438523b9acf73bbdfe284623835a69bf5823a8e1c652",
"md5": "9ea0e645777fb33843dc1f1b46801e9c",
"sha256": "1dd280b56c43f93fb6af9dc81d4ebe51f09e8e909de4eb39d19555c679c0066f"
},
"downloads": -1,
"filename": "agential-0.0.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "9ea0e645777fb33843dc1f1b46801e9c",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.11",
"size": 92649,
"upload_time": "2024-04-23T09:25:47",
"upload_time_iso_8601": "2024-04-23T09:25:47.829356Z",
"url": "https://files.pythonhosted.org/packages/3c/7e/49760b1bd3ff55fb438523b9acf73bbdfe284623835a69bf5823a8e1c652/agential-0.0.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "3d75f941158053ec594e5e611034bf1da5f4f9dec097bf6607fdbfa78f634938",
"md5": "d6e1570380378e1806199f8739881f0a",
"sha256": "dd37c0836c43a3deeed6bdf5b87cf92a1caeafc3ae8b2b1a525c24fdf3380944"
},
"downloads": -1,
"filename": "agential-0.0.1.tar.gz",
"has_sig": false,
"md5_digest": "d6e1570380378e1806199f8739881f0a",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.11",
"size": 71492,
"upload_time": "2024-04-23T09:25:50",
"upload_time_iso_8601": "2024-04-23T09:25:50.163481Z",
"url": "https://files.pythonhosted.org/packages/3d/75/f941158053ec594e5e611034bf1da5f4f9dec097bf6607fdbfa78f634938/agential-0.0.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-04-23 09:25:50",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "alckasoc",
"github_project": "agential",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "agential"
}
JSON
