topic Re: GENERATIVE AI HUB SDK - Python Error in Artificial Intelligence Forum

GENERATIVE AI HUB SDK - Python Error

lnog — Wed, 14 Aug 2024 15:07:16 GMT

Hello,

Looking to deploy a simple model using generative-ai-hub-sdk (using python 3.12) and after setup, I'm finding the following error executing the following script from console (jupyter notebook):

from gen_ai_hub.proxy.langchain.init_models import init_llm

prompt = """Translate to danish: Guten Morgen"""

llm = init_llm('gpt-35-turbo', temperature=0., max_tokens=256)
llm.invoke(prompt).content

-------------------------------------------------------

Error:

ValidationError: 1 validation error for ChatOpenAI

__root__

Parameters {'top_p'} should be specified explicitly. Instead they were passed in as part of `model_kwargs` parameter. (type=value_error)

Any ideas?

Thanks!

Re: GENERATIVE AI HUB SDK - Python Error

MarioDeFelipe — Thu, 15 Aug 2024 11:26:37 GMT

Hi! Since apparently you want to use the Langchain API, the `init_llm` function is likely a wrapper around the `ChatOpenAI` class, which is used to interact with OpenAI. Let me know how this goes

from gen_ai_hub.proxy.langchain.openai import ChatOpenAI from gen_ai_hub.proxy.core.proxy_clients import get_proxy_client from langchain.chains import LLMChain from langchain.prompts import PromptTemplate # Initialize proxy client proxy_client = get_proxy_client('gen-ai-hub') # Set up the chat model chat_llm = ChatOpenAI(proxy_model_name='gpt-35-turbo', proxy_client=proxy_client) # Define the prompt prompt_template = PromptTemplate(input_variables=["text"], template="Translate to Danish: {text}") # Create the LLMChain chain = LLMChain(llm=chat_llm, prompt=prompt_template) # Run the chain with the input text response = chain.run("Guten Morgen") # Print the output print(response)

Re: GENERATIVE AI HUB SDK - Python Error

lnog — Thu, 15 Aug 2024 15:10:31 GMT

Thanks Mario! It worked, but I got the following warnings:

Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/langchain_core/_api/deprecation.py:141: LangChainDeprecationWarning: The class `LLMChain` was deprecated in LangChain 0.1.17 and will be removed in 1.0. Use RunnableSequence, e.g., `prompt | llm` instead.
warn_deprecated(
/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/langchain_core/_api/deprecation.py:141: LangChainDeprecationWarning: The method `Chain.run` was deprecated in langchain 0.1.0 and will be removed in 0.3.0. Use invoke instead.
warn_deprecated(

Any thoughts?

Thanks again!

Leandro

Re: GENERATIVE AI HUB SDK - Python Error

MarioDeFelipe — Mon, 19 Aug 2024 17:58:06 GMT

hi @lnog

so happy to see progress!

Could be the case that your Langchain library got an update, and I might have provided also old instructions, but first make sure you update LangChain Version.

pip install --upgrade langchain

Instead of using the deprecated LLMChain class, the warning suggests using RunnableSequence. 1. Then lets replace the LLMChain usage with the suggested alternative.

# Old deprecated usage

chain = LLMChain(prompt=prompt, llm=llm)

# New recommended usage

chain = prompt | llm

2. Instead of using the deprecated Chain.run method, the warning recommends using invoke.

# Old deprecated usage

output = chain.run(input_data)

# New recommended usage

output = chain.invoke(input_data)

Let me know how it goes

Re: GENERATIVE AI HUB SDK - Python Error

lnog — Mon, 19 Aug 2024 18:43:22 GMT

Thanks, Mario, it worked perfectly

Leo