PromptGuru
Modular prompt engineering library for BERT, Mistral, LLaMA, and FLAN-T5 using YAML templates. Includes modes like ELI5, DevMode, Refine, Classification, and QA.
Why
- Lightweight and framework-agnostic
- YAML-first: edit prompts without changing code
- Consistent modes across multiple model families
Install (Local Dev)
pip install PyYAML
For now, clone or copy this repo. PyPI packaging steps are included below.
Usage
from promptguru.engine import PromptEngine
engine = PromptEngine(model_type="mistral", mode="eli5")
prompt = engine.generate_prompt("What is quantum entanglement?")
print(prompt)
Templates
Templates live in promptguru/templates/:
bert.yaml→classification,fill_mask,qamistral.yaml→eli5,devmode,refinellama.yaml→eli5,devmode,refineflan_t5.yaml→eli5,devmode,explain_and_tag
Roadmap
- Add inference adapters (HF Inference API, OpenRouter) behind a common interface
- Add more modes (contrastive QA, chain-of-thought, safety/risk tags)
License
Apache 2.0
Metadata
Release files for promptguru 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| promptguru-0.1.0.tar.gz | 3.3 kB | Without provenance | Details for promptguru-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| promptguru-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for promptguru-0.1.0-py3-none-any.whl |
Total release size: 7.7 kB
Release files / promptguru-0.1.0.tar.gz
| Download URL | promptguru-0.1.0.tar.gz |
|---|---|
| Size | 3.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
bfc384c86f75599ca6f98b97a2c680621eae15f30bf7f07d38eeab049aa20c55
|
|
BLAKE2b-256 checksum How to use checksums |
28673f1b9928336a802ed14085d6b8508bad687b983f0192a34a86fe6a950674
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.13
|
Release files / promptguru-0.1.0-py3-none-any.whl
| Download URL | promptguru-0.1.0-py3-none-any.whl |
|---|---|
| Size | 4.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
78a3497873143f1e00309033bf58e8514b1900f90a4a17c95480979c7b6e644e
|
|
BLAKE2b-256 checksum How to use checksums |
5e1df2513e0a6f18bba91526eb031804cf515a431d0e2f31ca67758fdb5089a1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.13
|
Security for promptguru 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.