Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/promptslab/Promptify

Prompt Engineering | Prompt Versioning | Use GPT or other prompt based models to get structured output. Join our discord for Prompt-Engineering, LLMs and other latest research
https://github.com/promptslab/Promptify

chatgpt chatgpt-api chatgpt-python gpt-3 gpt-3-prompts gpt-4 gpt-4-api gpt3-library large-language-models machine-learning nlp openai prompt-engineering prompt-toolkit prompt-tuning prompt-versioning prompting prompts promptversioning transformers

Last synced: about 1 month ago
JSON representation

Prompt Engineering | Prompt Versioning | Use GPT or other prompt based models to get structured output. Join our discord for Prompt-Engineering, LLMs and other latest research

Awesome Lists containing this project

README 

        




Promptify







  
Prompt Engineering, Solve NLP Problems with LLM's & Easily generate different NLP Task prompts for popular generative models like GPT, PaLM, and more with Promptify




 


  

    Promptify is released under the Apache 2.0 license.

  

  

    PyPI version

  

  

    http://makeapullrequest.com

  

  

    Community

  

  

    colab

  







## Installation



### With pip



This repository is tested on Python 3.7+, openai 0.25+.



You should install Promptify using Pip command



```bash

pip3 install promptify

```



or



```bash

pip3 install git+https://github.com/promptslab/Promptify.git

```



## Quick tour



To immediately use a LLM model for your NLP task, we provide the `Pipeline` API.



```python

from promptify import Prompter,OpenAI, Pipeline



sentence     =  """The patient is a 93-year-old female with a medical  				 

                history of chronic right hip pain, osteoporosis,					

                hypertension, depression, and chronic atrial						

                fibrillation admitted for evaluation and management				

                of severe nausea and vomiting and urinary tract				

                infection"""



model        = OpenAI(api_key) # or `HubModel()` for Huggingface-based inference or 'Azure' etc

prompter     = Prompter('ner.jinja') # select a template or provide custom template

pipe         = Pipeline(prompter , model)



result = pipe.fit(sentence, domain="medical", labels=None)



### Output



[

    {"E": "93-year-old", "T": "Age"},

    {"E": "chronic right hip pain", "T": "Medical Condition"},

    {"E": "osteoporosis", "T": "Medical Condition"},

    {"E": "hypertension", "T": "Medical Condition"},

    {"E": "depression", "T": "Medical Condition"},

    {"E": "chronic atrial fibrillation", "T": "Medical Condition"},

    {"E": "severe nausea and vomiting", "T": "Symptom"},

    {"E": "urinary tract infection", "T": "Medical Condition"},

    {"Branch": "Internal Medicine", "Group": "Geriatrics"},

]

 

```





  

   

  



GPT-3 Example with NER, MultiLabel, Question Generation Task



Features 🎮 


    

      
  •  Perform NLP tasks (such as NER and classification) in just 2 lines of code, with no training data required
    • 

      
  •  Easily add one shot, two shot, or few shot examples to the prompt
    • 

      
  •  Handling out-of-bounds prediction from LLMS (GPT, t5, etc.)
    • 

      
  •  Output always provided as a Python object (e.g. list, dictionary) for easy parsing and filtering. This is a major advantage over LLMs generated output, whose unstructured and raw output makes it difficult to use in business or other applications.
    • 

      
  •  Custom examples and samples can be easily added to the prompt
    • 

      
  •  🤗 Run inference on any model stored on the Huggingface Hub (see notebook guide).
    • 

      
  •  Optimized prompts to reduce OpenAI token costs (coming soon)
    • 




### Supporting wide-range of Prompt-Based NLP tasks :



| Task Name | Colab Notebook | Status |

|-------------|-------|-------|

| Named Entity Recognition | [NER Examples with GPT-3](https://colab.research.google.com/drive/16DUUV72oQPxaZdGMH9xH1WbHYu6Jqk9Q?usp=sharing) | ✅  |

| Multi-Label Text Classification | [Classification Examples with GPT-3](https://colab.research.google.com/drive/1gNqDxNyMMUO67DxigzRAOa7C_Tcr2g6M?usp=sharing) | ✅    |

| Multi-Class Text Classification | [Classification Examples with GPT-3](https://colab.research.google.com/drive/1gNqDxNyMMUO67DxigzRAOa7C_Tcr2g6M?usp=sharing) | ✅    |

| Binary Text Classification  | [Classification Examples with GPT-3](https://colab.research.google.com/drive/1gNqDxNyMMUO67DxigzRAOa7C_Tcr2g6M?usp=sharing) | ✅    |

| Question-Answering | [QA Task Examples with GPT-3](https://colab.research.google.com/drive/1Yhl7iFb7JF0x89r1L3aDuufydVWX_VrL?usp=sharing) | ✅    |

| Question-Answer Generation | [QA Task Examples with GPT-3](https://colab.research.google.com/drive/1Yhl7iFb7JF0x89r1L3aDuufydVWX_VrL?usp=sharing) | ✅    |

| Relation-Extraction | [Relation-Extraction Examples with GPT-3](https://colab.research.google.com/drive/1iW4QNjllc8ktaQBWh3_04340V-tap1co?usp=sharing) | ✅    |

| Summarization  | [Summarization Task Examples with GPT-3](https://colab.research.google.com/drive/1PlXIAMDtrK-RyVdDhiSZy6ztcDWsNPNw?usp=sharing) | ✅    |

| Explanation    | [Explanation Task Examples with GPT-3](https://colab.research.google.com/drive/1PlXIAMDtrK-RyVdDhiSZy6ztcDWsNPNw?usp=sharing) | ✅    |

| SQL Writer    | [SQL Writer Example with GPT-3](https://colab.research.google.com/drive/1JNUYCTdqkdeIAxiX-NzR-4dngdmWj0rV?usp=sharing) | ✅    |

| Tabular Data | |    |

| Image Data | |     |

| More Prompts | |     |



## Docs



[Promptify Docs](https://promptify.readthedocs.io/)



## Community 



If you are interested in Prompt-Engineering, LLMs, ChatGPT and other latest research discussions, please consider joining PromptsLab





Join us on Discord




```



@misc{Promptify2022,

  title = {Promptify: Structured Output from LLMs},

  author = {Pal, Ankit},

  year = {2022},

  howpublished = {\url{https://github.com/promptslab/Promptify}},

  note = {Prompt-Engineering components for NLP tasks in Python}

}



```



## 💁 Contributing



We welcome any contributions to our open source project, including new features, improvements to infrastructure, and more comprehensive documentation. 

Please see the [contributing guidelines](contribute.md)