Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/microsoft/sammo
A library for prompt engineering and optimization (SAMMO = Structure-aware Multi-Objective Metaprompt Optimization)
https://github.com/microsoft/sammo
llms prompt-engineering prompt-tuning
Last synced: 4 days ago
JSON representation
A library for prompt engineering and optimization (SAMMO = Structure-aware Multi-Objective Metaprompt Optimization)
- Host: GitHub
- URL: https://github.com/microsoft/sammo
- Owner: microsoft
- License: mit
- Created: 2023-12-04T22:49:34.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2024-12-19T10:44:21.000Z (12 days ago)
- Last Synced: 2024-12-20T02:02:43.931Z (11 days ago)
- Topics: llms, prompt-engineering, prompt-tuning
- Language: Python
- Homepage:
- Size: 2.96 MB
- Stars: 608
- Watchers: 10
- Forks: 27
- Open Issues: 4
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md
- Codeowners: .github/CODEOWNERS
- Security: SECURITY.md
- Support: SUPPORT.md
Awesome Lists containing this project
README
# SAMMO ([📘User Guide](https://microsoft.github.io/sammo/))
[](https://pypi.python.org/pypi/sammo)
[](https://opensource.org/licenses/MIT)
[](https://mybinder.org/v2/gh/microsoft/sammo/main?urlpath=tree/docs/tutorials/quickstart.ipynb)
A flexible, easy-to-use library for running and optimizing prompts for Large Language Models (LLMs).
## 🎉 News
- Nov 13, 2024: Turn Markdown into prompt programs: First version of SAMMO express released
- Nov 1, 2024: Use CSS selectors to query and modify prompt programs!
- Oct 15, 2024: SAMMO now supports structured outputs!
## How to Get Started
Go to the [user guide](https://microsoft.github.io/sammo/) for examples, how-tos, and API reference.
Just want to have a quick look? Try the [live demo on Binder](https://mybinder.org/v2/gh/microsoft/sammo/main?urlpath=tree/docs/tutorials/quickstart.ipynb).
### Install library only
```bash
pip install sammo
```
### Install and run tutorials
***Prerequisites***
* Python 3.9+
The following commands will install sammo and jupyter and launch jupyter notebook. It's recommended that you create and activate a virtualenv prior to installing packages.
```bash
pip install sammo jupyter
# clone sammo to a local directory
git clone https://github.com/microsoft/sammo.git
cd sammo
# launch jupyter notebook and open tutorials directory
jupyter notebook --notebook-dir docs/tutorials
```
## Example
This example shows how easy it is to optimize a prompt with SAMMO. The full example is in the [user guide](https://microsoft.github.io/sammo/).
```python
runner = OpenAIChat(model_id="gpt-3.5-turbo", api_config=API_CONFIG)
PROMPT_IN_MARKDOWN = """
# Instructions
Convert the following user queries into a SQL query.
# Table
Users:
- user_id (INTEGER, PRIMARY KEY)
- name (TEXT)
- age (INTEGER)
- city (TEXT)
# Complete this
Input: {{{input}}}
Output:
"""
spp = MarkdownParser(PROMPT_IN_MARKDOWN).get_sammo_program()
mutation_operators = BagOfMutators(
Output(GenerateText(spp)),
Paraphrase("#instr"),
Rewrite("#instr", "Make this more verbose.\n\n {{{{text}}}}")
)
prompt_optimizer = BeamSearch(runner, mutation_operators, accuracy)
prompt_optimizer.fit(d_train)
prompt_optimizer.show_report()
```
## Use Cases
SAMMO is designed to support
- **Efficient data labeling**: Supports minibatching by packing and parsing multiple datapoints into a single prompt.
- **Prompt prototyping and engineering**: Re-usable components and prompt structures to quickly build and test new prompts.
- **Instruction optimization**: Optimize instructions to do better on a given task.
- **Prompt compression**: Compress prompts while maintaining performance.
- **Large-scale prompt execution**: parallelization
and rate-limiting out-of-the-box so you can run many queries in parallel and at scale without overwhelming the LLM API.
It is less useful if you want to build
- Interactive, agent-based LLM applications (→ check out [AutoGen](https://microsoft.github.io/autogen/))
- Interactive, production-ready LLM applications (→ check out [LangChain](https://www.langchain.com/))
## Licence
This project is licensed under [MIT](https://choosealicense.com/licenses/mit/).
To cite this paper, you can use the following BibTeX entry:
```bibtex
@inproceedings{schnabel-neville-2024-symbolic,
title = "Symbolic Prompt Program Search: A Structure-Aware Approach to Efficient Compile-Time Prompt Optimization",
author = "Schnabel, Tobias and Neville, Jennifer",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
year = "2024",
url = "https://aclanthology.org/2024.findings-emnlp.37",
pages = "670--686"
}
```
## Authors
`SAMMO` was written by [Tobias Schnabel](mailto:[email protected]).
## Contributing
This project welcomes contributions and suggestions. Most contributions require you to agree to a
Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us
the rights to use your contribution. For details, visit .
When you submit a pull request, a CLA bot will automatically determine whether you need to provide
a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions
provided by the bot. You will only need to do this once across all repos using our CLA.
This project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/).
For more information see the [Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/) or
contact [[email protected]](mailto:[email protected]>) with any additional questions or comments.