Skip to main content

A Python toolkit for advanced data processing and API interactions

Project description

descartkit

LLM

Three steps to use models

Step1, llm_config.yaml

matter that needs attention

  1. custom_model_name used for models.get_model_instance()
  2. custom_model_name.name should specify the name of the model supported by the current company
models:
  openai:
    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 descartcan.llm.config import load_models_from_yaml
from descartcan.llm import LLMClient


async def main():
    # The first method
    models = load_models_from_yaml(config_file="examples/llm_config.yaml", keys_file="examples/llm_keys.yaml")
    print(models.list_models())

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

    # The second method
    client = LLMClient(config_file="llm_config.yaml", keys_file="llm_keys.yaml")
    print(client.list_models())
    resp = await client.chat("qw-72b-p", "who r u?", system_prompt="")
    print(resp)
    async for chunk in client.chat_stream("qw-72b-p", "who r u?", system_prompt=""):
        print(chunk)


if __name__ == '__main__':
    import asyncio

    asyncio.run(main())

Project details


Release history Release notifications | RSS feed

Download files

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

Source Distribution

descartcan-2025.4.3.1.tar.gz (12.8 kB view details)

Uploaded Source

Built Distribution

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

descartcan-2025.4.3.1-py3-none-any.whl (26.9 kB view details)

Uploaded Python 3

File details

Details for the file descartcan-2025.4.3.1.tar.gz.

File metadata

  • Download URL: descartcan-2025.4.3.1.tar.gz
  • Upload date:
  • Size: 12.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.0.1 CPython/3.10.10

File hashes

Hashes for descartcan-2025.4.3.1.tar.gz
Algorithm Hash digest
SHA256 2a814a92c755e24ae467ec72bd05ea525d3075b4bd1c99f0221b151f34cd51d4
MD5 e64883f5f1b068226260c01f9bf76a81
BLAKE2b-256 7de5a5420e82743d04203fec7aae8512344b0c27cbdb542428079934accc25bd

See more details on using hashes here.

File details

Details for the file descartcan-2025.4.3.1-py3-none-any.whl.

File metadata

File hashes

Hashes for descartcan-2025.4.3.1-py3-none-any.whl
Algorithm Hash digest
SHA256 24c332bfba4350a8fe81029ac8b6d4440bd51179272191dfab544e3c9491a8d9
MD5 415e4edd644e7d085a3686e8c329a872
BLAKE2b-256 bc7e4f7a8648e9889530d4e74713dbbba4d61a22b3edb7a1cedebe396eeadd1e

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