prompthub

from prompthub import PromptHub, errors

try:
    prompts = PromptHub('http://localhost:8000', '25cee15690db575d123271ef7f408e6a1f9446b1', category='rmb-prod')
except errors.CategoryNotFoundError:
    print('Category not found')
    # do something
except errors.ConnectionError:
    print('Connection error')
    # do something

# 按照这个顺序来找可以适用的模型
prompts.set_preferred_models(['gpt-3.5', 'gpt-4-turbo', 'any'])

try:
    prompt = prompts.get(
        'MetaName',
        raise_if_missing_variables=True,
        k1='v1',
        k2='v2',
    )
    content = prompt.content
    model = prompt.model

except errors.PromptNotFoundError:
    print('Prompt not found')
    # do something
except errors.PromptMissingVariablesError as e:
    print('Prompt missing variables', e)
    # do something
except errors.NoValidModelError:
    print('No valid model')
    # do something

from client.prompthub.hub import PromptHub, errors

prompts = PromptHub('http://localhost:8000', '25cee15690db575d123271ef7f408e6a1f9446b1', category='rmb-prod')

template = prompts.get_template('MetaName')
# 该Prompt适用的模型有哪些
valid_models = template.models

template = prompts.create_template(
    'MetaN1ame',
    'tex111t',
    output_format='str',
    model_names=['gpt-3.5', 'gpt-4-turbo'],
    label_names=['label1', 'label2'],
)

Metadata

Release files for prompthub 0.1.17

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

Built distribution (wheel)

Table of built distributions (wheels) for prompthub 0.1.17
File	Interpreter	ABI	Platform	Reset
prompthub-0.1.17-py3-none-any.whl 4.5 kB Apr 15, 2024	Python 3	none	any	Details

Release files / prompthub-0.1.17-py3-none-any.whl

Download URL	prompthub-0.1.17-py3-none-any.whl
Size	4.5 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`9da58f7cc507852fc5609e6b6b33ffb8eb245e58e7e11bbd18e2d4813c2da2cc`
BLAKE2b-256 checksum How to use checksums	`a5b6ff6f42a1bf6659b35234258ac3416461af3b96068792955bc370d5ea44b8`
Upload date	Apr 15, 2024
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/4.0.2 CPython/3.11.7`