Implementing few-shot prompting
Time to combine your components together into a chain! The few-shot prompt you created in the previous exercise is still available for you to use, along with examples and example_prompt.
All of the LangChain classes necessary for completing this exercise have been pre-loaded for you.
This exercise is part of the course
Developing LLM Applications with LangChain
Exercise instructions
- Instantiate an OpenAI chat LLM.
- Create a chain from the LLM and prompt template, and invoke it on the input provided.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
prompt_template = FewShotPromptTemplate(
examples=examples,
example_prompt=example_prompt,
suffix="Question: {input}",
input_variables=["input"],
)
# Create an OpenAI chat LLM
llm = ____(model="gpt-4o-mini", api_key='')
# Create and invoke the chain
llm_chain = ____
print(____({"input": "What is Jack's favorite technology on DataCamp?"}))