trulens-apps-gepa
TruLens adapter for GEPA (Genetic/Evolutionary Prompt Adaptation).
GEPA optimizes prompts using evolutionary algorithms. This package provides
TruGEPA, a thin adapter that wraps any TruLens feedback callable as a
GEPA-compatible fitness function and automatically logs every evaluation as a
TruVirtual record for dashboard visibility, plus a simple run_evolution
helper that implements the evolutionary loop.
Installation
pip install trulens-apps-gepa
Quick start
from trulens.apps.gepa import TruGEPA, run_evolution
def my_relevance(prompt: str) -> float:
return len(prompt) / 200 # replace with a real TruLens provider method
# Without logging:
fitness = TruGEPA(my_relevance, optimize_key="prompt")
# With logging — supply both app_name and app_version (omit both to disable;
# supplying only one raises a ValueError immediately):
from trulens.core import TruSession
session = TruSession()
fitness = TruGEPA(
my_relevance,
optimize_key="prompt",
app_name="my_optimizer",
app_version="v1",
)
# Works with any feedback signature — e.g. context_relevance(question, context):
# fitness = TruGEPA(
# provider.context_relevance,
# optimize_key="question",
# feedback_args={"context": REFERENCE_CONTEXT},
# )
best_prompt, best_score, history = run_evolution(
base_prompt="Summarize the document.",
fitness_fn=fitness,
mutate_fn=lambda p: p + " Be concise.",
n_generations=5,
population_size=4,
)
print(f"Best prompt ({best_score:.3f}): {best_prompt}")
When both app_name and app_version are provided, a TruVirtual recorder
is created automatically and every evaluation is logged. Omit both to run
without any logging.
Metadata
Release files for trulens-apps-gepa 2.16.0
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 |
|---|---|---|---|---|
| trulens_apps_gepa-2.16.0.tar.gz | 4.4 kB | Without provenance | Details for trulens_apps_gepa-2.16.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| trulens_apps_gepa-2.16.0-py3-none-any.whl | Python 3 | none | any | Details for trulens_apps_gepa-2.16.0-py3-none-any.whl |
Total release size: 10.0 kB
Release files / trulens_apps_gepa-2.16.0.tar.gz
| Download URL | trulens_apps_gepa-2.16.0.tar.gz |
|---|---|
| Size | 4.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
b750450c80aed85b63bc8e3b5d7669904b40a033295336b3ce0752ec24da1e60
|
|
BLAKE2b-256 checksum How to use checksums |
07e9e709c30c1523d569d01a882014825f86626d2237965ea04fb40754ec141b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.17
|
Release files / trulens_apps_gepa-2.16.0-py3-none-any.whl
| Download URL | trulens_apps_gepa-2.16.0-py3-none-any.whl |
|---|---|
| Size | 5.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
5af2817b2affc7a1ae868470e8074726579aa544b448f060f1aab90bfeba3045
|
|
BLAKE2b-256 checksum How to use checksums |
847e20f6829f24444f1552610464757f1dbdbda2bfd53655ec62b1ffa86ab221
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.17
|
Security for trulens-apps-gepa 2.16.0
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.