Free Preparation Discussions
MENU
Databricks Certified Generative AI Engineer Associate Exam - Topic 6 Question 35 Discussion
Topic #: 6
A Generative AI Engineer is testing a simple prompt template in LangChain using the code below, but is getting an error:
Python
from langchain.chains import LLMChain
from langchain_community.llms import OpenAI
from langchain_core.prompts import PromptTemplate
prompt_template = "Tell me a {adjective} joke"
prompt = PromptTemplate(input_variables=["adjective"], template=prompt_template)
# ... (Error-prone section)
Assuming the API key was properly defined, what change does the Generative AI Engineer need to make to fix their chain?
The error in the original snippet usually stems from the improper instantiation of the LLMChain or the incorrect call to the .generate() method. In LangChain, an LLMChain requires two primary components: an LLM (the engine) and a Prompt (the template). Option C provides the correct syntax: first, the PromptTemplate is defined with the correct input_variables. Second, the OpenAI model is instantiated. Third, the LLMChain binds the model and the prompt together. Finally, the .generate() method expects a list of dictionaries, where each dictionary represents a set of inputs for the prompt variables. Options A, B, and D in the original image contain syntax errors such as passing the variable directly into the chain initialization or missing the dictionary list format required by the standard LangChain API for batch-like generation.
Currently there are no comments in this discussion, be the first to comment!