Skip to main content

Packaging tools for own use

Project description

hwhkit

Main function

  • Connection
    • mqtt
  • llm

Connection

Mqtt

from hwhkit import MQTTAsyncClient, mqtt_subscribe
import asyncio

# Config MQTT Client
client = MQTTAsyncClient(broker="broker.hivemq.com", port=1883, client_id="my_client")
client.start()


@mqtt_subscribe("topic/test1")
async def handle_message_1(message: str):
    print(f"Received message from topic 1: {message}")

@mqtt_subscribe("topic/test2")
async def handle_message_2(message: str):
    print(f"Received message from topic 2: {message}")

async def send_messages():
    while True:
        await asyncio.sleep(2)
        client.publish("topic/test1", "Hello from topic 1!")
        client.publish("topic/test2", "Hello from topic 2!")

async def main():
    await asyncio.gather(
        send_messages(),
        asyncio.sleep(3600) 
    )

if __name__ == '__main__':
    asyncio.run(main())

LLM

Three steps to use models

Step1, llm_config.yaml

matter that needs attention

  1. A_custom_model_name used for models.get_model_instance()
  2. A_custom_model_name.name should specify the name of the model supported by the current company
models:
  openai:
    A_custom_model_name:
      name: "gpt-4o"
      short_name: "OIG4"
      company: "openai"
      max_input_token: 8100
      max_output_token: 2048
      top_p: 0.5
      top_k: 1
      temperature: 0.5
      input_token_fee_pm: 30.0
      output_token_fee_pm: 60.0
      train_token_fee_pm: 0.0
      keys:
        - name: "openai_key1"
        - name: "openai_key2"

  siliconflow:
    qw-72b-p:
      name: "Qwen/QVQ-72B-Preview"
      short_name: "QW-72B-P"
      company: "siliconflow"
      max_input_token: 8100
      max_output_token: 2048
      top_p: 0.5
      top_k: 1
      temperature: 0.5
      input_token_fee_pm: 30.0
      output_token_fee_pm: 60.0
      train_token_fee_pm: 0.0
      keys:
        - name: "siliconflow_1"
Step2, llm_keys.yaml
  1. The keys name of the model in llm_config.yaml corresponds to llm_keys.yaml one by one
keys:
  openai_key1: "xx"
  openai_key2: "xx"
  anthropic_key1: "your_anthropic_api_key_1"
  anthropic_key2: "your_anthropic_api_key_2"
Step3, load models
from hwhkit.llm.config import load_models_from_yaml


async def main():
    models = load_models_from_yaml(config_file="llm_config.yaml", keys_file="llm_keys.yaml")
    print(models.list_models())

    resp = await models.get_model_instance("gpt-4o").chat("who r u?")
    print(resp)


if __name__ == '__main__':
    import asyncio
    asyncio.run(main())

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

hwhkit-1.0.5.tar.gz (8.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

hwhkit-1.0.5-py3-none-any.whl (17.7 kB view details)

Uploaded Python 3

File details

Details for the file hwhkit-1.0.5.tar.gz.

File metadata

  • Download URL: hwhkit-1.0.5.tar.gz
  • Upload date:
  • Size: 8.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.0.1 CPython/3.10.10

File hashes

Hashes for hwhkit-1.0.5.tar.gz
Algorithm Hash digest
SHA256 dc5f847a728f6138a8771f657d1a483d7f37b31c02699c6df6103742e3aed9e6
MD5 8b6f45ab71e66b399d50ab1e4cff2197
BLAKE2b-256 d4bb0d78a95e641c24ab1d6e1930447502276b3377c5dff07330635d5da2d192

See more details on using hashes here.

File details

Details for the file hwhkit-1.0.5-py3-none-any.whl.

File metadata

  • Download URL: hwhkit-1.0.5-py3-none-any.whl
  • Upload date:
  • Size: 17.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.0.1 CPython/3.10.10

File hashes

Hashes for hwhkit-1.0.5-py3-none-any.whl
Algorithm Hash digest
SHA256 b5fa0416cbb249fd05cd8f58c1223e138810227a2ac9ba371f1ddcd9ca6fdbe5
MD5 7809ed1fbc503d30e74583c0b8e9fd64
BLAKE2b-256 818a1cc3420cbd6c9b7404ce2fe86fd96e4633e7225717dd44e9d95e350b8647

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page