Skip to main content
Pre-release

This release is a pre-release and may not be stable for production use.

KISS AI Stack Banner

KISS AI Stack - Server

The KISS AI Stack Server is an server stub designed to support RESTful and WebSocket APIs for handling AI-agent sessions with kiss-ai-stack-core tasks like agent lifecycle management, query execution, and document storage.

Features

  • REST API for authentication, session actions, queries, and document storage.
  • WebSocket API for real-time, event-driven interactions.
  • Built-in persistent and temporary session management.
  • Flexible architecture to handle server events though AI agent's lifecycle events.

Agent's session lifecycle Events

  • ON_AUTH: Authenticate a session.
  • ON_INIT: Initialize a session.
  • ON_CLOSE: Close a session.
  • ON_QUERY: Execute a query.
  • ON_STORE: Store documents.

Getting Started

Requirements

  • Python 3.12

Installation

  1. Install kiss-ai-stack-server package:

    pip install kiss-ai-stack-server
    
  2. Set environment variables file

    # .env
     ACCESS_TOKEN_SECRET_KEY = "your-secure-random-secret-key"
     ACCESS_TOKEN_ALGORITHM = "HS256"
     ACCESS_TOKEN_EXPIRE_MINUTES = 30
    
     SESSION_DB_URL="sqlite://sessions.db"
    
  3. Run the server:

    from kiss_ai_stack_server import bootstrap_session_schema, agent_server
    

REST API Endpoints

1. Authentication

Endpoint: /auth
Method: POST
Request Body:

{
  "client_id": "string",
  "client_secret": "string"
}

Response:

{
  "session_id": "string",
  "access_token": "string",
  "expires_in": 3600
}

2. Session Actions

Endpoint: /sessions?action={init|close}
Method: POST
Query Parameter:

  • action (required): Action to perform on the session (init or close).

Request Body:

{
  "session_id": "string"
}

Response: Session-related details or status.


3. Query Execution

Endpoint: /queries
Method: POST
Request Body:

{
  "query": "string",
  "parameters": {
    "key": "value"
  }
}

Response: Query results.


4. Document Storage

Endpoint: /documents
Method: POST
Request Body:

{
  "documents": [
    {
      "id": "string",
      "content": "string",
      "metadata": {}
    }
  ]
}

Response: Document storage confirmation.


WebSocket API

Endpoint: /ws

Workflow

  1. Establish a WebSocket connection:

    ws://localhost:8080/ws
    
  2. Send a message:

    {
      "event": "ON_QUERY",
      "data": {
        "query": "example query",
        "parameters": {
          "key": "value"
        }
      }
    }
    
  3. Receive a response:

    {
      "event": "ON_QUERY",
      "result": {
        "response_key": "response_value"
      }
    }
    

Contributing

Contributions are welcome! Feel free to fork the repository and submit a pull request.


License

This project is licensed under the MIT License.

Metadata

Release files for kiss-ai-stack-server 0.1.0a17

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for kiss-ai-stack-server 0.1.0a17
File Size Uploaded Provenance Actions
kiss_ai_stack_server-0.1.0a17.tar.gz 13.1 kB Without provenance Details for kiss_ai_stack_server-0.1.0a17.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for kiss-ai-stack-server 0.1.0a17
File Interpreter ABI Platform Actions
kiss_ai_stack_server-0.1.0a17-py3-none-any.whl Python 3 none any Details for kiss_ai_stack_server-0.1.0a17-py3-none-any.whl

Total release size: 30.9 kB

Release files / kiss_ai_stack_server-0.1.0a17.tar.gz

Download URL kiss_ai_stack_server-0.1.0a17.tar.gz
Size 13.1 kB
Tags Source
SHA-256 checksum
How to use checksums
2a4fd53577d9f7c337c1c552c57ae8af546de8ebe67633e7c448de0b863e4a7a
BLAKE2b-256 checksum
How to use checksums
275ae033d0fab88227012bb299b86ea072eec4fdd162c7edee1ea5d6e886130d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.0.1 CPython/3.12.7

Release files / kiss_ai_stack_server-0.1.0a17-py3-none-any.whl

Download URL kiss_ai_stack_server-0.1.0a17-py3-none-any.whl
Size 17.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
3e923823f4e4f3feb3cae467e018d95e0e4f059f61902fbf9ca9535a224d8a61
BLAKE2b-256 checksum
How to use checksums
ea7e138644af8a99da572ffec0c76708df225f643a6fe88f1614b6ffaeab4f12
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.0.1 CPython/3.12.7

Security for kiss-ai-stack-server 0.1.0a17

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page