Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/kiss-ai-stack/kiss-ai-stack-core
KISS AI Stack's AI Agent builder
https://github.com/kiss-ai-stack/kiss-ai-stack-core
ai ai-agent ai-agents-framework artificial-intelligence boilerplate-application chromadb gen-ai openai python3
Last synced: 8 days ago
JSON representation
KISS AI Stack's AI Agent builder
- Host: GitHub
- URL: https://github.com/kiss-ai-stack/kiss-ai-stack-core
- Owner: kiss-ai-stack
- License: mit
- Created: 2024-11-24T07:37:14.000Z (about 1 month ago)
- Default Branch: main
- Last Pushed: 2024-12-16T06:36:25.000Z (18 days ago)
- Last Synced: 2024-12-20T08:14:41.782Z (14 days ago)
- Topics: ai, ai-agent, ai-agents-framework, artificial-intelligence, boilerplate-application, chromadb, gen-ai, openai, python3
- Language: Python
- Homepage: https://kiss-ai-stack.github.io/
- Size: 81.1 KB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# KISS AI Stack - Core
**Effortless AI Stack Building**
Welcome to the core of the **KISS AI Stack**! This module helps you build a stack 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 Stack Management**: Manage multiple session-based AI stacks with lifecycle support.
- **Minimal Dependencies**: Built using simple, vanilla vendor libraries.
- **Tool Classification**: Configure tools for your stack 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~=0.1.0a28
```
---
## Example Configuration
Here’s an example YAML configuration to set up an AI stack with different tools:
```yaml
stack:
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:
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:
- 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:
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 stack:
```python
from kiss_ai_stack import Stacks
async def main():
try:
# Initialize a stack in the stack
await Stacks.bootstrap_stack(stack_id="my_stack", temporary=True)
# Process a query
response = await Stacks.generate_answer(stack_id="my_stack", query="What is Retrieval-Augmented Generation?")
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. **Stack Initialization**: Use `Stack.bootstrap_stack` to initialize stacks with their configuration and resources.
2. **Query Processing**: Process queries with `Stack.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, only `Chroma` is supported.
---
For more information please refer: [Core documentation](https://kiss-ai-stack.github.io/docs/ai-stack-core/)
## 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.