Skip to main content

A Python SDK for record the LLM Experiment Execution

Project description

gg_python_sdk

Installation

To install the Trinity package, run the following command:

pip install trinity

Setup the Environment Variable

export TRINITY_SECRET_KEY="your_secret_key"
export TRINITY_PUBLIC_KEY="your_public_key"
export TRINITY_HOST="http://your_trinity_host"

Record the Experiment

To use the record function, ensure that you have properly set up your environment and then call the function as shown below:

# Import the Trinity package
import trinity

# Call the record() function
trinity.record(
    experiment_name=experiment_name,
    questions=questions,
    contexts=contexts,
    generated_prompts=generated_prompts,
    answers=answers,
    ground_truths=ground_truths,
    model_temperature=model_temperature,
    top_k=top_k,
    model_name=model_name,
    prompt_template=prompt_template
)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

trinityml-0.0.2.tar.gz (3.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

trinityml-0.0.2-py3-none-any.whl (4.3 kB view details)

Uploaded Python 3

File details

Details for the file trinityml-0.0.2.tar.gz.

File metadata

  • Download URL: trinityml-0.0.2.tar.gz
  • Upload date:
  • Size: 3.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.10.14

File hashes

Hashes for trinityml-0.0.2.tar.gz
Algorithm Hash digest
SHA256 bf0c2004658c7fec8450ecbede7f31b4d22ebceed9fd1808aeb14e102131bf5d
MD5 621879f5d7155839592c3b8d24742689
BLAKE2b-256 faaff67afc225f753131d69709d519b355f6f13e7ac800263416103a265124bf

See more details on using hashes here.

File details

Details for the file trinityml-0.0.2-py3-none-any.whl.

File metadata

  • Download URL: trinityml-0.0.2-py3-none-any.whl
  • Upload date:
  • Size: 4.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.10.14

File hashes

Hashes for trinityml-0.0.2-py3-none-any.whl
Algorithm Hash digest
SHA256 6b139b0663ef5567ba2bbb74eefcd0e423dbe01185ef92aea55ee46a28953692
MD5 7fda445d44bcd6be7f4c481b6185d05b
BLAKE2b-256 311bf1c73c1499e3dbde5e3f7cb69cde66986e0dd5daf31854281b6af7ed365a

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page