- Notifications
You must be signed in to change notification settings - Fork359
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
License
promptslab/Promptify
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
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
This repository is tested on Python 3.7+, openai 0.25+.
You should install Promptify using Pip command
pip3 install promptify
or
pip3 install git+https://github.com/promptslab/Promptify.git
To immediately use a LLM model for your NLP task, we provide thePipeline API.
frompromptifyimportPrompter,OpenAI,Pipelinesentence="""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' etcprompter=Prompter('ner.jinja')# select a template or provide custom templatepipe=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"},]
- 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 (seenotebook guide).
- Optimized prompts to reduce OpenAI token costs (coming soon)
| Task Name | Colab Notebook | Status |
|---|---|---|
| Named Entity Recognition | NER Examples with GPT-3 | ✅ |
| Multi-Label Text Classification | Classification Examples with GPT-3 | ✅ |
| Multi-Class Text Classification | Classification Examples with GPT-3 | ✅ |
| Binary Text Classification | Classification Examples with GPT-3 | ✅ |
| Question-Answering | QA Task Examples with GPT-3 | ✅ |
| Question-Answer Generation | QA Task Examples with GPT-3 | ✅ |
| Relation-Extraction | Relation-Extraction Examples with GPT-3 | ✅ |
| Summarization | Summarization Task Examples with GPT-3 | ✅ |
| Explanation | Explanation Task Examples with GPT-3 | ✅ |
| SQL Writer | SQL Writer Example with GPT-3 | ✅ |
| Tabular Data | ||
| Image Data | ||
| More Prompts |
@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}}We welcome any contributions to our open source project, including new features, improvements to infrastructure, and more comprehensive documentation.Please see thecontributing guidelines
About
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
Topics
Resources
License
Uh oh!
There was an error while loading.Please reload this page.
Stars
Watchers
Forks
Packages0
Uh oh!
There was an error while loading.Please reload this page.




