README.MD

Quality Prompts

Use and evaluate prompting techniques quickly.

Quality Prompts implements 58 prompting techniques explained in this survey from the University of Maryland in collaboration with researchers from Learn Prompting, OpenAI, Microsoft, etc.

1. Install Quality Prompts:

pip install quality-prompts

2. Write the components of your prompt

from quality_prompts.prompt import QualityPrompt

directive = "You are given a document and your task..."
additional_information = "In the knowledge graph, ..."
output_formatting = "You will respond with a ..."

prompt = QualityPrompt(
                        directive,
                        additional_information,
                        output_formatting,
                        exemplar_store
                       )

3. Quality Prompts searches and uses only the few-shot examples that are relevant to the user's query

input_text = "list the disorders included in cvd"
prompt.few_shot(input_text=input_text, n_shots=1)

4. Simply call one of several prompting techniques to your prompt

System2Attention

Helps clarify the given context as an additinoal step before it's used to answer the question

prompt.system2attention(input_text)

Tabular Chain of Thought

Prompts the LLM to think step by step and write the step, process and result of each step in a markdown table. Significantly boosts accuracy in solving math problems.

prompt.tabular_chain_of_thought_prompting(input_text)

6. Upcoming: Easily evaluate different prompting techniques

Star History

To stay updated on the latest evaluation features and prompting techniques added to the library, you can star this repo.