# Praison AI
Praison AI, leveraging both AutoGen and CrewAI or any other agent framework, represents a low-code, centralised framework designed to simplify the creation and orchestration of multi-agent systems for various LLM applications, emphasizing ease of use, customization, and human-agent interaction.
## TL;DR
```bash
pip install praisonai
export OPENAI_API_KEY="Enter your API key"
praisonai --init create a movie script about dog in moon
praisonai
```
## Installation
```bash
pip install praisonai
```
## Initialise
```bash
export OPENAI_API_KEY="Enter your API key"
```
Generate your OPENAI API KEY from here: https://platform.openai.com/api-keys
Note: You can use other providers such as Ollama, Mistral ... etc. Details are provided at the bottom.
```bash
praisonai --init create a movie script about dog in moon
```
This will automatically create agents.yaml file in the current directory.
### To initialse with a specific agent framework (Optional):
```bash
praisonai --framework autogen --init create movie script about cat in mars
```
## Run
```bash
praisonai
```
or
```bash
python -m praisonai
```
### Specify the agent framework (Optional):
```bash
praisonai --framework autogen
```
### Full Automatic Mode
```bash
praisonai --auto create a movie script about Dog in Moon
```
## Create Custom Tools
### TL;DR to Create a Custom Tool
```bash
pip install praisonai duckduckgo-search
export OPENAI_API_KEY="Enter your API key"
praisonai --init research about the latest AI News and prepare a detailed report
```
- Add `- InternetSearchTool` in the agents.yaml file in the tools section.
- Create a file called tools.py and add this code [tools.py](./tools.py)
```bash
praisonai
```
### Pre-requisite to Create a Custom Tool
`agents.yaml` file should be present in the current directory.
If it doesn't exist, create it by running the command `praisonai --init research about the latest AI News and prepare a detailed report`.
### Step 1 to Create a Custom Tool
Create a file called tools.py in the same directory as the agents.yaml file.
```python
# example tools.py
from duckduckgo_search import DDGS
from praisonai_tools import BaseTool
class InternetSearchTool(BaseTool):
name: str = "InternetSearchTool"
description: str = "Search Internet for relevant information based on a query or latest news"
def _run(self, query: str):
ddgs = DDGS()
results = ddgs.text(keywords=query, region='wt-wt', safesearch='moderate', max_results=5)
return results
```
### Step 2 to Create a Custom Tool
Add the tool to the agents.yaml file as show below under the tools section `- InternetSearchTool`.
```yaml
framework: crewai
topic: research about the latest AI News and prepare a detailed report
roles:
research_analyst:
backstory: Experienced in gathering and analyzing data related to AI news trends.
goal: Analyze AI News trends
role: Research Analyst
tasks:
gather_data:
description: Conduct in-depth research on the latest AI News trends from reputable
sources.
expected_output: Comprehensive report on current AI News trends.
tools:
- InternetSearchTool
```
## Test
```bash
python -m unittest tests.test
```
## Agents Playbook
### Simple Playbook Example
```yaml
framework: crewai
topic: Artificial Intelligence
roles:
screenwriter:
backstory: 'Skilled in crafting scripts with engaging dialogue about {topic}.'
goal: Create scripts from concepts.
role: Screenwriter
tasks:
scriptwriting_task:
description: 'Develop scripts with compelling characters and dialogue about {topic}.'
expected_output: 'Complete script ready for production.'
```
### Detailed Playbook Example
```yaml
framework: crewai
topic: Artificial Intelligence
roles:
movie_concept_creator:
backstory: 'Creative thinker with a deep understanding of cinematic storytelling,
capable of using AI-generated storylines to create unique and compelling movie
ideas.'
goal: Generate engaging movie concepts using AI storylines
role: Movie Concept Creator
tasks:
movie_concept_development:
description: 'Develop movie concepts from AI-generated storylines, ensuring
they are engaging and have strong narrative arcs.'
expected_output: 'Well-structured movie concept document with character
bios, settings, and plot outlines.'
screenwriter:
backstory: 'Expert in writing engaging dialogue and script structure, able to
turn movie concepts into production-ready scripts.'
goal: Write compelling scripts based on movie concepts
role: Screenwriter
tasks:
scriptwriting_task:
description: 'Turn movie concepts into polished scripts with well-developed
characters, strong dialogue, and effective scene transitions.'
expected_output: 'Production-ready script with a beginning, middle, and
end, along with character development and engaging dialogues.'
editor:
backstory: 'Adept at identifying inconsistencies, improving language usage,
and maintaining the overall flow of the script.'
goal: Refine the scripts and ensure continuity of the movie storyline
role: Editor
tasks:
editing_task:
description: 'Review, edit, and refine the scripts to ensure they are cohesive
and follow a well-structured narrative.'
expected_output: 'A polished final draft of the script with no inconsistencies,
strong character development, and effective dialogue.'
dependencies: []
```
## Include praisonai package in your project
```python
from praisonai import PraisonAI
def basic(): # Basic Mode
praison_ai = PraisonAI(agent_file="agents.yaml")
praison_ai.main()
def advanced(): # Advanced Mode with options
praison_ai = PraisonAI(
agent_file="agents.yaml",
framework="autogen",
)
praison_ai.main()
def auto(): # Full Automatic Mode
praison_ai = PraisonAI(
auto="Create a movie script about car in mars",
framework="autogen"
)
print(praison_ai.framework)
praison_ai.main()
if __name__ == "__main__":
basic()
advanced()
auto()
```
## Deploy
```bash
gcloud init
gcloud services enable run.googleapis.com
gcloud services enable containerregistry.googleapis.com
gcloud services enable cloudbuild.googleapis.com
export OPENAI_MODEL_NAME="gpt-4-turbo-preview"
export OPENAI_API_KEY="Enter your API key"
export OPENAI_API_BASE="https://api.openai.com/v1"
yes | gcloud auth configure-docker us-central1-docker.pkg.dev
gcloud artifacts repositories create praisonai-repository --repository-format=docker --location=us-central1
PROJECT_ID=$(gcloud config get-value project)
TAG="latest"
docker build --platform linux/amd64 -t gcr.io/${PROJECT_ID}/praisonai-app:${TAG} .
docker tag gcr.io/${PROJECT_ID}/praisonai-app:${TAG} us-central1-docker.pkg.dev/${PROJECT_ID}/praisonai-repository/praisonai-app:${TAG}
docker push us-central1-docker.pkg.dev/${PROJECT_ID}/praisonai-repository/praisonai-app:${TAG}
gcloud run deploy praisonai-service \
--image us-central1-docker.pkg.dev/${PROJECT_ID}/praisonai-repository/praisonai-app:${TAG} \
--platform managed \
--region us-central1 \
--allow-unauthenticated \
--set-env-vars OPENAI_MODEL_NAME=${OPENAI_MODEL_NAME},OPENAI_API_KEY=${OPENAI_API_KEY},OPENAI_API_BASE=${OPENAI_API_BASE}
```
## Other Models
```bash
Ollama
OPENAI_API_BASE='http://localhost:11434/v1'
OPENAI_MODEL_NAME='mistral'
OPENAI_API_KEY='NA'
FastChat¶
OPENAI_API_BASE="http://localhost:8001/v1"
OPENAI_MODEL_NAME='oh-2.5m7b-q51'
OPENAI_API_KEY=NA
LM Studio¶
OPENAI_API_BASE="http://localhost:8000/v1"
OPENAI_MODEL_NAME=NA
OPENAI_API_KEY=NA
Mistral API¶
OPENAI_API_BASE=https://api.mistral.ai/v1
OPENAI_MODEL_NAME="mistral-small"
OPENAI_API_KEY=your-mistral-api-key
```
## Contributing
- Fork on GitHub: Use the "Fork" button on the repository page.
- Clone your fork: `git clone https://github.com/yourusername/praisonAI.git`
- Create a branch: `git checkout -b new-feature`
- Make changes and commit: `git commit -am "Add some feature"`
- Push to your fork: `git push origin new-feature`
- Submit a pull request via GitHub's web interface.
- Await feedback from project maintainers.
Raw data
{
"_id": null,
"home_page": null,
"name": "praisonAI",
"maintainer": null,
"docs_url": null,
"requires_python": "<3.13,>=3.10",
"maintainer_email": null,
"keywords": null,
"author": "Mervin Praison",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/fd/82/4c1d8a6984016a9d7678dd575977d3a1b0562319963eab80825dbc82f5d6/praisonai-0.0.21.tar.gz",
"platform": null,
"description": "# Praison AI\n\nPraison AI, leveraging both AutoGen and CrewAI or any other agent framework, represents a low-code, centralised framework designed to simplify the creation and orchestration of multi-agent systems for various LLM applications, emphasizing ease of use, customization, and human-agent interaction.\n\n## TL;DR\n```bash\npip install praisonai\nexport OPENAI_API_KEY=\"Enter your API key\"\npraisonai --init create a movie script about dog in moon\npraisonai\n```\n\n## Installation\n\n```bash\npip install praisonai\n```\n\n## Initialise\n\n```bash\nexport OPENAI_API_KEY=\"Enter your API key\"\n```\n\nGenerate your OPENAI API KEY from here: https://platform.openai.com/api-keys\n\nNote: You can use other providers such as Ollama, Mistral ... etc. Details are provided at the bottom.\n \n```bash\npraisonai --init create a movie script about dog in moon\n```\nThis will automatically create agents.yaml file in the current directory.\n\n### To initialse with a specific agent framework (Optional):\n\n```bash\npraisonai --framework autogen --init create movie script about cat in mars\n```\n\n## Run\n\n```bash\npraisonai\n```\n\nor \n \n```bash\npython -m praisonai\n```\n\n### Specify the agent framework (Optional):\n\n```bash\npraisonai --framework autogen\n```\n\n### Full Automatic Mode\n\n```bash\npraisonai --auto create a movie script about Dog in Moon\n```\n\n## Create Custom Tools\n\n### TL;DR to Create a Custom Tool\n\n```bash\npip install praisonai duckduckgo-search\nexport OPENAI_API_KEY=\"Enter your API key\"\npraisonai --init research about the latest AI News and prepare a detailed report\n```\n\n- Add `- InternetSearchTool` in the agents.yaml file in the tools section. \n- Create a file called tools.py and add this code [tools.py](./tools.py)\n\n```bash\npraisonai\n```\n\n### Pre-requisite to Create a Custom Tool\n`agents.yaml` file should be present in the current directory. \n\nIf it doesn't exist, create it by running the command `praisonai --init research about the latest AI News and prepare a detailed report`.\n\n### Step 1 to Create a Custom Tool\n\nCreate a file called tools.py in the same directory as the agents.yaml file.\n\n```python\n# example tools.py\nfrom duckduckgo_search import DDGS\nfrom praisonai_tools import BaseTool\n\nclass InternetSearchTool(BaseTool):\n name: str = \"InternetSearchTool\"\n description: str = \"Search Internet for relevant information based on a query or latest news\"\n\n def _run(self, query: str):\n ddgs = DDGS()\n results = ddgs.text(keywords=query, region='wt-wt', safesearch='moderate', max_results=5)\n return results\n```\n\n### Step 2 to Create a Custom Tool\n\nAdd the tool to the agents.yaml file as show below under the tools section `- InternetSearchTool`.\n\n```yaml\nframework: crewai\ntopic: research about the latest AI News and prepare a detailed report\nroles:\n research_analyst:\n backstory: Experienced in gathering and analyzing data related to AI news trends.\n goal: Analyze AI News trends\n role: Research Analyst\n tasks:\n gather_data:\n description: Conduct in-depth research on the latest AI News trends from reputable\n sources.\n expected_output: Comprehensive report on current AI News trends.\n tools:\n - InternetSearchTool\n```\n\n## Test\n \n```bash\npython -m unittest tests.test \n```\n\n## Agents Playbook \n\n### Simple Playbook Example\n\n```yaml\nframework: crewai\ntopic: Artificial Intelligence\nroles:\n screenwriter:\n backstory: 'Skilled in crafting scripts with engaging dialogue about {topic}.'\n goal: Create scripts from concepts.\n role: Screenwriter\n tasks:\n scriptwriting_task:\n description: 'Develop scripts with compelling characters and dialogue about {topic}.'\n expected_output: 'Complete script ready for production.'\n```\n\n### Detailed Playbook Example\n\n```yaml\nframework: crewai\ntopic: Artificial Intelligence\nroles:\n movie_concept_creator:\n backstory: 'Creative thinker with a deep understanding of cinematic storytelling,\n capable of using AI-generated storylines to create unique and compelling movie\n ideas.'\n goal: Generate engaging movie concepts using AI storylines\n role: Movie Concept Creator\n tasks:\n movie_concept_development:\n description: 'Develop movie concepts from AI-generated storylines, ensuring\n they are engaging and have strong narrative arcs.'\n expected_output: 'Well-structured movie concept document with character\n bios, settings, and plot outlines.'\n screenwriter:\n backstory: 'Expert in writing engaging dialogue and script structure, able to\n turn movie concepts into production-ready scripts.'\n goal: Write compelling scripts based on movie concepts\n role: Screenwriter\n tasks:\n scriptwriting_task:\n description: 'Turn movie concepts into polished scripts with well-developed\n characters, strong dialogue, and effective scene transitions.'\n expected_output: 'Production-ready script with a beginning, middle, and\n end, along with character development and engaging dialogues.'\n editor:\n backstory: 'Adept at identifying inconsistencies, improving language usage,\n and maintaining the overall flow of the script.'\n goal: Refine the scripts and ensure continuity of the movie storyline\n role: Editor\n tasks:\n editing_task:\n description: 'Review, edit, and refine the scripts to ensure they are cohesive\n and follow a well-structured narrative.'\n expected_output: 'A polished final draft of the script with no inconsistencies,\n strong character development, and effective dialogue.'\ndependencies: []\n```\n\n## Include praisonai package in your project\n\n```python\nfrom praisonai import PraisonAI\n\ndef basic(): # Basic Mode\n praison_ai = PraisonAI(agent_file=\"agents.yaml\")\n praison_ai.main()\n \ndef advanced(): # Advanced Mode with options\n praison_ai = PraisonAI(\n agent_file=\"agents.yaml\",\n framework=\"autogen\",\n )\n praison_ai.main()\n \ndef auto(): # Full Automatic Mode\n praison_ai = PraisonAI(\n auto=\"Create a movie script about car in mars\",\n framework=\"autogen\"\n )\n print(praison_ai.framework)\n praison_ai.main()\n\nif __name__ == \"__main__\":\n basic()\n advanced()\n auto()\n```\n\n## Deploy \n \n```bash\ngcloud init\ngcloud services enable run.googleapis.com\ngcloud services enable containerregistry.googleapis.com\ngcloud services enable cloudbuild.googleapis.com\n\nexport OPENAI_MODEL_NAME=\"gpt-4-turbo-preview\"\nexport OPENAI_API_KEY=\"Enter your API key\"\nexport OPENAI_API_BASE=\"https://api.openai.com/v1\"\n\nyes | gcloud auth configure-docker us-central1-docker.pkg.dev \ngcloud artifacts repositories create praisonai-repository --repository-format=docker --location=us-central1\n\nPROJECT_ID=$(gcloud config get-value project)\nTAG=\"latest\"\ndocker build --platform linux/amd64 -t gcr.io/${PROJECT_ID}/praisonai-app:${TAG} .\ndocker tag gcr.io/${PROJECT_ID}/praisonai-app:${TAG} us-central1-docker.pkg.dev/${PROJECT_ID}/praisonai-repository/praisonai-app:${TAG}\ndocker push us-central1-docker.pkg.dev/${PROJECT_ID}/praisonai-repository/praisonai-app:${TAG}\n\ngcloud run deploy praisonai-service \\\n --image us-central1-docker.pkg.dev/${PROJECT_ID}/praisonai-repository/praisonai-app:${TAG} \\\n --platform managed \\\n --region us-central1 \\\n --allow-unauthenticated \\\n --set-env-vars OPENAI_MODEL_NAME=${OPENAI_MODEL_NAME},OPENAI_API_KEY=${OPENAI_API_KEY},OPENAI_API_BASE=${OPENAI_API_BASE}\n```\n\n## Other Models\n\n```bash\nOllama\nOPENAI_API_BASE='http://localhost:11434/v1'\nOPENAI_MODEL_NAME='mistral'\nOPENAI_API_KEY='NA'\n\nFastChat\u00b6\nOPENAI_API_BASE=\"http://localhost:8001/v1\"\nOPENAI_MODEL_NAME='oh-2.5m7b-q51'\nOPENAI_API_KEY=NA\n\nLM Studio\u00b6\nOPENAI_API_BASE=\"http://localhost:8000/v1\"\nOPENAI_MODEL_NAME=NA\nOPENAI_API_KEY=NA\n\nMistral API\u00b6\nOPENAI_API_BASE=https://api.mistral.ai/v1\nOPENAI_MODEL_NAME=\"mistral-small\"\nOPENAI_API_KEY=your-mistral-api-key\n```\n\n## Contributing\n\n- Fork on GitHub: Use the \"Fork\" button on the repository page.\n- Clone your fork: `git clone https://github.com/yourusername/praisonAI.git`\n- Create a branch: `git checkout -b new-feature`\n- Make changes and commit: `git commit -am \"Add some feature\"`\n- Push to your fork: `git push origin new-feature`\n- Submit a pull request via GitHub's web interface.\n- Await feedback from project maintainers.\n",
"bugtrack_url": null,
"license": null,
"summary": "praisonAI application combines AutoGen and CrewAI or similar frameworks into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customization, and efficient human-agent collaboration.",
"version": "0.0.21",
"project_urls": {
"Homepage": "https://github.com/mervinpraison/praisonAI",
"Repository": "https://github.com/mervinpraison/praisonAI"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "21f0da6ea420cc3fea0344e4e1e1af7cba833b1737f7f3119fe18998089b0bdd",
"md5": "57f426e119cffc9906f00bceb5bfa915",
"sha256": "6af82b9469ebfe0bfd153329fc57400d0aea331cb6c8106508c344306a5c6a63"
},
"downloads": -1,
"filename": "praisonai-0.0.21-py3-none-any.whl",
"has_sig": false,
"md5_digest": "57f426e119cffc9906f00bceb5bfa915",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<3.13,>=3.10",
"size": 16453,
"upload_time": "2024-05-14T07:21:07",
"upload_time_iso_8601": "2024-05-14T07:21:07.646121Z",
"url": "https://files.pythonhosted.org/packages/21/f0/da6ea420cc3fea0344e4e1e1af7cba833b1737f7f3119fe18998089b0bdd/praisonai-0.0.21-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "fd824c1d8a6984016a9d7678dd575977d3a1b0562319963eab80825dbc82f5d6",
"md5": "f566163edffb24d5ee63e7001a2c5492",
"sha256": "bb87650a3459134bcc7d8877e67c8bf2fb3a7f0d3e1137ee634e15c6ef499df5"
},
"downloads": -1,
"filename": "praisonai-0.0.21.tar.gz",
"has_sig": false,
"md5_digest": "f566163edffb24d5ee63e7001a2c5492",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<3.13,>=3.10",
"size": 15584,
"upload_time": "2024-05-14T07:21:10",
"upload_time_iso_8601": "2024-05-14T07:21:10.275242Z",
"url": "https://files.pythonhosted.org/packages/fd/82/4c1d8a6984016a9d7678dd575977d3a1b0562319963eab80825dbc82f5d6/praisonai-0.0.21.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-05-14 07:21:10",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "mervinpraison",
"github_project": "praisonAI",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [
{
"name": "rich",
"specs": [
[
">=",
"13.7"
]
]
},
{
"name": "pyautogen",
"specs": [
[
">=",
"0.2.19"
]
]
},
{
"name": "crewai",
"specs": [
[
">=",
"0.22.5"
]
]
},
{
"name": "gradio",
"specs": [
[
">=",
"4.20.0"
]
]
},
{
"name": "crewai_tools",
"specs": []
},
{
"name": "duckduckgo_search",
"specs": []
},
{
"name": "praisonai_tools",
"specs": []
}
],
"lcname": "praisonai"
}
JSON
