quality-prompts 0.0.2

No project description provided

Write Quality Prompts

Use and evaluate prompting techniques surveyed by Openai and Microsoft quickly.

1. Install Quality Prompts:

pip install quality-prompts

2. Write down few-shot examples:

from quality_prompts.prompt import QualityPrompt
from quality_prompts.exemplars import ExemplarStore, Exemplar
from quality_prompts.utils.llm import get_embedding

exemplars = [Exemplar(input="Cardiovascular disease (CVD) encompasses..."
                      label="[{"entity": "cardiovascular disease (cvd)..."
                      input_embedding=[-0.008424, 0.097374, ...]
                     ),
                     ...
            ]
exemplar_store = ExemplarStore(exemplars=exemplars)

3. Write the components of your prompt

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

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

4. Effortlessly add few-shot examples to your prompt.

input_text = "list the disorders included in cvd"
prompt.few_shot(input_text=input_text, n_shots=2)

5. Simply call a prompting technique to your prompt

prompt.system2attention(input_text)

6. Compile your prompt to use it

print(prompt.compile())

>> You are given a document and your task is to create a knowledge graph from it.
        
In the knowledge graph, entities such as people, places, objects, institutions, topics, ideas, etc. are represented as nodes.
Whereas the relationships and actions between them are represented as edges.

Example input: Cardiovascular disease (CVD) encompasses a spectrum of...
Example output: [{'entity': 'cardiovascular disease (cvd)', 'connections': ...

Example input: The epidemiological burden of cardiovascular disease underscores ...
You will respond with a knowledge graph in the given JSON format:

[
    {"entity" : "Entity_name", "connections" : [
        {"entity" : "Connected_entity_1", "relationship" : "Relationship_with_connected_entity_1},
        {"entity" : "Connected_entity_2", "relationship" : "Relationship_with_connected_entity_2},
        ]
    },
]