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 - Client

The KISS AI Stack Client provides an easy-to-use interface for interacting with the KISS AI Stack Server, supporting RESTful and WebSocket APIs to manage AI-agent session lifecycle and execute tasks.


Features

  • REST client for session management, query execution, and document storage.
  • WebSocket client for real-time interactions with the AI agent.

Getting Started

Requirements

  • Python 3.12

Installation

  1. Install the kiss-ai-stack-client package:
pip install kiss-ai-stack-client
  1. Initialize the REST client:
from kiss_ai_stack_client import RestEvent

client = RestEvent(hostname="your-server-hostname", secure_protocol=True)

Usage

1. Authorize an Agent Session

Create or refresh an agent session:

session = await client.authorize_agent(scope="temporary")
# or
session = await client.authorize_agent(client_id="your-client-id", client_secret="your-client-secret")

2. Bootstrap the Agent

Initialize the agent session for task execution:

response = await client.bootstrap_agent(data="Hello, Agent!")

3. Generate an Answer

Send a query and receive the agent's response:

response = await client.generate_answer(data="What is the weather today?")

4. Store Documents

Upload files with optional metadata for storage:

files = ["path/to/document1.txt", "path/to/document2.pdf"]
metadata = {"category": "example"}
response = await client.store_data(files=files, metadata=metadata)

5. Destroy the Agent Session

Close the current session and clean up resources:

response = await client.destroy_agent(data="Goodbye!")

License

This project is licensed under the MIT License.

Metadata

Release files for kiss-ai-stack-client 0.1.0a2

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-client 0.1.0a2
File Size Uploaded Provenance Actions
kiss_ai_stack_client-0.1.0a2.tar.gz 8.7 kB Without provenance Details for kiss_ai_stack_client-0.1.0a2.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for kiss-ai-stack-client 0.1.0a2
File Interpreter ABI Platform Actions
kiss_ai_stack_client-0.1.0a2-py3-none-any.whl Python 3 none any Details for kiss_ai_stack_client-0.1.0a2-py3-none-any.whl

Total release size: 19.6 kB

Release files / kiss_ai_stack_client-0.1.0a2.tar.gz

Download URL kiss_ai_stack_client-0.1.0a2.tar.gz
Size 8.7 kB
Tags Source
SHA-256 checksum
How to use checksums
d12756d25988c7b464c409d5742ee7d747f91756a021b8aa8913fce754b188fd
BLAKE2b-256 checksum
How to use checksums
549078b04c1774f069461aa21b0385d63a33396d3b31a0f3954c938f6c387e90
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_client-0.1.0a2-py3-none-any.whl

Download URL kiss_ai_stack_client-0.1.0a2-py3-none-any.whl
Size 11.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
58a77c02816726a87d93ec7a8fb18407fb1a578d458ef0ae9f810d6647857b51
BLAKE2b-256 checksum
How to use checksums
6b547215559e92d2145a2e200a02b5057727a7d8e29b521071fc65a2a2d86ed3
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-client 0.1.0a2

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