promptslab / Promptify

Prompt Engineering | Prompt Versioning | Use GPT or other prompt based models to get structured output. Join our discord for Prompt-Engineering, LLMs and other latest research
https://discord.gg/m88xfYMbK6
Apache License 2.0
3.2k stars 238 forks source link

Error in generating prompt: Model not found. (gpt-35-turbo-16k) #98

Open hv129 opened 11 months ago

hv129 commented 11 months ago
from promptify import Prompter, Pipeline, Azure

llm = Azure(engine=engine, api_base=api_base, api_version="2023-05-15", 
            api_key=api_key, api_type="azure", model="gpt-35-turbo-16k")
prompter = Prompter('ner.jinja')
pipe = Pipeline(prompter, llm)

result = pipe.fit(text, domain=domain, labels=labels, description=description, examples=examples)
result

Getting error:

Error in generating prompt: Model not found. Please choose the model from : ['text-davinci-003', 'gpt-3.5-turbo', 'gpt-35-turbo', 'claude-instant-1', 'claude-2', 'command', 'command-light', 'command-medium-beta', 'command-nightly', 'command-xlarge-beta']

hv129 commented 11 months ago

Inside prompts/text2text for each task (such as ner, qa, explain etc.), metadata.json needs to be updated, models should include gpt-35-turbo-16k.

Vigneswaran-M97 commented 11 months ago

Hi, I think you chose the wrong model, kindly try this one 'gpt-3.5-turbo-16k' link is here - https://platform.openai.com/docs/models/gpt-3-5