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
- custom_model_name used for models.get_model_instance()
- 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
- 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 Distributions
No source distribution files available for this release.See tutorial on generating distribution archives.
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file descartcan-2025.4.2.1-py3-none-any.whl.
File metadata
- Download URL: descartcan-2025.4.2.1-py3-none-any.whl
- Upload date:
- Size: 50.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.0.1 CPython/3.10.10
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
1bbd77ea7c70c2437c6c59eb390c5d68e599fe85f00f9d427b90bbd384a683e5
|
|
| MD5 |
3ff3884491d6a5d27e90ecfc8b3bccb3
|
|
| BLAKE2b-256 |
0cbf0adcfee5a3f730010299704175ae317da858c8298d9fab54027603028310
|