<div style="text-align: left; margin-bottom: 20px;">
<img src="https://kiss-ai-stack.github.io/kissaistack.svg" alt="KISS AI Stack Banner" style="max-width: auto; height: 250px">
</div>
# KISS AI Stack - Core
**Effortless AI Agent Building**
Welcome to the core of the **KISS AI Stack**! This module helps you build an AI agent effortlessly using a simple YAML configuration file. Say goodbye to boilerplate code and embrace minimalism with the **KISS principle** (Keep It Simple, Stupid).
---
## Features
- **Centralized Agent Management**: Manage multiple session-based AI agents with lifecycle support.
- **Minimal Dependencies**: Built using simple, vanilla vendor libraries.
- **Tool Classification**: Configure tools for your agent to handle specific tasks easily.
- **Supports RAG and Prompt-Based Models**: Choose the model type that suits your needs.
- **Thread-Safe**: Reliable operation in multi-threaded environments.
---
## Installation
Install the core module using pip:
```bash
pip install kiss-ai-stack-core
```
---
## Example Configuration
Here’s an example YAML configuration to set up an AI agent with different tools:
```yaml
agent:
decision_maker: # Required for tool classification
name: decision_maker
role: classify tools for given queries
kind: prompt # Choose from 'rag' or 'prompt'
ai_client:
provider: openai
model: gpt-4
api_key: <your-api-key>
tools:
- name: general_queries
role: process other queries if no suitable tool is found.
kind: prompt
ai_client:
provider: openai
model: gpt-4
api_key: <your-api-key>
- name: document_tool
role: process documents and provide answers based on them.
kind: rag # Retrieval-Augmented Generation
embeddings: text-embedding-ada-002
ai_client:
provider: openai
model: gpt-4
api_key: <your-api-key>
vector_db:
provider: chroma
kind: remote # Choose in-memory, storage or remote options.
host: 0.0.0.0
port: 8000
secure: false
```
---
## Example Python Usage
Use the core module to build and interact with your AI agent:
```python
from kiss_ai_stack import AgentStack
async def main():
try:
# Initialize an agent in the stack
await AgentStack.bootstrap_agent(agent_id="my_agent", temporary=True)
# Process a query
response = await AgentStack.generate_answer(agent_id="my_agent", query="What is KISS AI Stack?")
print(response.answer)
except Exception as ex:
print(f"An error occurred: {ex}")
# Run the example
import asyncio
asyncio.run(main())
```
---
## How It Works
1. **Agent Initialization**: Use `AgentStack.bootstrap_agent` to initialize agents with their configuration and resources.
2. **Query Processing**: Process queries with `AgentStack.generate_answer`, leveraging tools and AI clients defined in the YAML configuration.
3. **Tool Management**: Define tools to handle specific tasks like document processing or query classification.
4. **Vector Database**: Use the `vector_db` section to define how document embeddings are stored and retrieved for RAG-based tasks. Currently, `Chroma` is supported.
---
## Documentation
### Key Methods
- `bootstrap_agent(agent_id: str, temporary: bool)`: Initialize a new agent session.
- `generate_answer(agent_id: str, query: Union[str, Dict, List])`: Process a query and return a response.
### Configuration Highlights
- **AI Client**: Configure the provider, model, and API key for supported services like OpenAI.
- **Tools**: Define tools such as general-purpose query handlers or document processors.
- **Vector Database**: Set up in-memory or persistent storage for RAG-based tasks.
---
## Contributing
We welcome contributions! Submit pull requests or open issues to improve this stack.
---
## License
This project is licensed under the MIT License. See the [LICENSE](./LICENSE) file for details.
Raw data
{
"_id": null,
"home_page": null,
"name": "kiss-ai-stack-core",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.12",
"maintainer_email": null,
"keywords": "ai, agent, machine-learning, llm, document-processing",
"author": "KISS AI Stack, Lahiru Pathirage",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/3f/14/f1655a9a361fb03ad9420544a06ef4071ab10e206b655bb82ebf3715a036/kiss_ai_stack_core-0.1.0a14.tar.gz",
"platform": null,
"description": "<div style=\"text-align: left; margin-bottom: 20px;\">\n <img src=\"https://kiss-ai-stack.github.io/kissaistack.svg\" alt=\"KISS AI Stack Banner\" style=\"max-width: auto; height: 250px\">\n</div>\n\n# KISS AI Stack - Core\n\n**Effortless AI Agent Building**\n\nWelcome to the core of the **KISS AI Stack**! This module helps you build an AI agent effortlessly using a simple YAML configuration file. Say goodbye to boilerplate code and embrace minimalism with the **KISS principle** (Keep It Simple, Stupid).\n\n---\n\n## Features\n\n- **Centralized Agent Management**: Manage multiple session-based AI agents with lifecycle support.\n- **Minimal Dependencies**: Built using simple, vanilla vendor libraries.\n- **Tool Classification**: Configure tools for your agent to handle specific tasks easily.\n- **Supports RAG and Prompt-Based Models**: Choose the model type that suits your needs.\n- **Thread-Safe**: Reliable operation in multi-threaded environments.\n\n---\n\n## Installation\n\nInstall the core module using pip:\n\n```bash\npip install kiss-ai-stack-core\n```\n\n---\n\n## Example Configuration\n\nHere\u2019s an example YAML configuration to set up an AI agent with different tools:\n\n```yaml\nagent:\n decision_maker: # Required for tool classification\n name: decision_maker\n role: classify tools for given queries\n kind: prompt # Choose from 'rag' or 'prompt'\n ai_client:\n provider: openai\n model: gpt-4\n api_key: <your-api-key>\n\n tools:\n - name: general_queries\n role: process other queries if no suitable tool is found.\n kind: prompt\n ai_client:\n provider: openai\n model: gpt-4\n api_key: <your-api-key>\n\n - name: document_tool\n role: process documents and provide answers based on them.\n kind: rag # Retrieval-Augmented Generation\n embeddings: text-embedding-ada-002\n ai_client:\n provider: openai\n model: gpt-4\n api_key: <your-api-key>\n\n vector_db:\n provider: chroma\n kind: remote # Choose in-memory, storage or remote options.\n host: 0.0.0.0\n port: 8000\n secure: false\n```\n\n---\n\n## Example Python Usage\n\nUse the core module to build and interact with your AI agent:\n\n```python\nfrom kiss_ai_stack import AgentStack\n\nasync def main():\n try:\n # Initialize an agent in the stack\n await AgentStack.bootstrap_agent(agent_id=\"my_agent\", temporary=True)\n\n # Process a query\n response = await AgentStack.generate_answer(agent_id=\"my_agent\", query=\"What is KISS AI Stack?\")\n print(response.answer)\n\n except Exception as ex:\n print(f\"An error occurred: {ex}\")\n\n# Run the example\nimport asyncio\nasyncio.run(main())\n```\n\n---\n\n## How It Works\n\n1. **Agent Initialization**: Use `AgentStack.bootstrap_agent` to initialize agents with their configuration and resources.\n2. **Query Processing**: Process queries with `AgentStack.generate_answer`, leveraging tools and AI clients defined in the YAML configuration.\n3. **Tool Management**: Define tools to handle specific tasks like document processing or query classification.\n4. **Vector Database**: Use the `vector_db` section to define how document embeddings are stored and retrieved for RAG-based tasks. Currently, `Chroma` is supported.\n\n---\n\n## Documentation\n\n### Key Methods\n\n- `bootstrap_agent(agent_id: str, temporary: bool)`: Initialize a new agent session.\n- `generate_answer(agent_id: str, query: Union[str, Dict, List])`: Process a query and return a response.\n\n### Configuration Highlights\n\n- **AI Client**: Configure the provider, model, and API key for supported services like OpenAI.\n- **Tools**: Define tools such as general-purpose query handlers or document processors.\n- **Vector Database**: Set up in-memory or persistent storage for RAG-based tasks.\n\n---\n\n## Contributing\n\nWe welcome contributions! Submit pull requests or open issues to improve this stack.\n\n---\n\n## License\n\nThis project is licensed under the MIT License. See the [LICENSE](./LICENSE) file for details.\n\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "KISS AI Stack's AI Agent Builder - Simplify AI Agent Development",
"version": "0.1.0a14",
"project_urls": {
"Documentation": "https://github.com/kiss-ai-stack/kiss-ai-stack-core/main/README.md",
"Homepage": "https://github.com/kiss-ai-stack",
"Repository": "https://github.com/kiss-ai-stack"
},
"split_keywords": [
"ai",
" agent",
" machine-learning",
" llm",
" document-processing"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "5e9cdf754ba227034953cc00848204a4f4f44207c983378a8f6e8a4cd7f6f581",
"md5": "dbe4938894fd263e3847c05a09b13d21",
"sha256": "63c9bd6e76912554cd445a4e6616a9423ce2f3997f7495e950a6e934538ee451"
},
"downloads": -1,
"filename": "kiss_ai_stack_core-0.1.0a14-py3-none-any.whl",
"has_sig": false,
"md5_digest": "dbe4938894fd263e3847c05a09b13d21",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.12",
"size": 32919,
"upload_time": "2024-12-16T06:33:17",
"upload_time_iso_8601": "2024-12-16T06:33:17.644219Z",
"url": "https://files.pythonhosted.org/packages/5e/9c/df754ba227034953cc00848204a4f4f44207c983378a8f6e8a4cd7f6f581/kiss_ai_stack_core-0.1.0a14-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "3f14f1655a9a361fb03ad9420544a06ef4071ab10e206b655bb82ebf3715a036",
"md5": "f1b05143361049352a0114250124439e",
"sha256": "b4c586bb6d239147cc14fcea96b32c85c734bab9494788fae6e81064c004ec12"
},
"downloads": -1,
"filename": "kiss_ai_stack_core-0.1.0a14.tar.gz",
"has_sig": false,
"md5_digest": "f1b05143361049352a0114250124439e",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.12",
"size": 24428,
"upload_time": "2024-12-16T06:33:22",
"upload_time_iso_8601": "2024-12-16T06:33:22.768420Z",
"url": "https://files.pythonhosted.org/packages/3f/14/f1655a9a361fb03ad9420544a06ef4071ab10e206b655bb82ebf3715a036/kiss_ai_stack_core-0.1.0a14.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-12-16 06:33:22",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "kiss-ai-stack",
"github_project": "kiss-ai-stack-core",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [
{
"name": "aiofiles",
"specs": [
[
"~=",
"24.1.0"
]
]
},
{
"name": "asyncio",
"specs": [
[
"~=",
"3.4.3"
]
]
},
{
"name": "PyYAML",
"specs": [
[
"~=",
"6.0.2"
]
]
},
{
"name": "pydantic",
"specs": [
[
"~=",
"2.10.3"
]
]
},
{
"name": "setuptools",
"specs": [
[
"~=",
"75.6.0"
]
]
},
{
"name": "unstructured",
"specs": [
[
"~=",
"0.16.8"
]
]
},
{
"name": "unstructured",
"specs": [
[
"~=",
"0.16.8"
]
]
},
{
"name": "unstructured",
"specs": [
[
"~=",
"0.16.8"
]
]
},
{
"name": "unstructured",
"specs": [
[
"~=",
"0.16.8"
]
]
},
{
"name": "unstructured",
"specs": [
[
"~=",
"0.16.8"
]
]
},
{
"name": "tiktoken",
"specs": [
[
"~=",
"0.8.0"
]
]
},
{
"name": "tokenizers",
"specs": [
[
"~=",
"0.20.3"
]
]
},
{
"name": "pandas",
"specs": [
[
"~=",
"2.2.3"
]
]
}
],
"lcname": "kiss-ai-stack-core"
}
JSON
