Databricks Certified Generative AI Engineer - Associate
Get started today
Ultimate access to all questions.
Deep dive into the quiz with AI chat providers.
We prepare a focused prompt with your quiz and certificate details so each AI can offer a more tailored, in-depth explanation.
Assuming the API key was properly defined, what change does the Generative AI Engineer need to make to fix their chain?
Real Exam
Community
LLeetQuiz
A
prompt_template = "Tell me a {adjecive} joke"
prompt = PromptTemplate(
input_variables=["adjecive"],
template=prompt_template
)
llm = LLMChain(prompt=prompt)
llm.generate("funny")
prompt_template = "Tell me a {adjecive} joke"
prompt = PromptTemplate(
input_variables=["adjecive"],
template=prompt_template
)
llm = LLMChain(prompt=prompt)
llm.generate("funny")
B
prompt_template = "Tell me a {adjecive} joke"
prompt = PromptTemplate(
input_variables=["adjecive"],
template=prompt_template
)
llm = LLMChain(prompt=prompt.format("funny"))
llm.generate()
prompt_template = "Tell me a {adjecive} joke"
prompt = PromptTemplate(
input_variables=["adjecive"],
template=prompt_template
)
llm = LLMChain(prompt=prompt.format("funny"))
llm.generate()
Explanation:
Explanation
Option A is correct because it properly uses the LLMChain with the PromptTemplate object and passes the input variable "funny" to the generate() method. This is the standard way to use LangChain's LLMChain:
- PromptTemplate is created with input variables and template
- LLMChain is initialized with the prompt template
- generate() method is called with the input values for the template variables
Option B is incorrect because:
- It tries to format the prompt template before passing it to LLMChain (
prompt.format("funny")) - This would result in a formatted string instead of a PromptTemplate object
- The
generate()method is then called without any arguments, but LLMChain expects input values
In LangChain, the correct pattern is to pass the PromptTemplate object to LLMChain and then provide the input variables when calling generate() or invoke() methods.
Comments
Loading comments...