Skip to main content

Send prompts and model responses to the Argilla A/B testing platform for annotations

Project description

prompt-sender

A tool for sending JSON files of prompts and model responses to the Argilla A/B testing platform for human annotations.

How to use

Simply install the package using pip:

pip install prompt-sender

Run prompt-sender --help for the required arguments:

$ prompt-sender --help
                                                                                                                                                                                  
 Usage: prompt-sender [OPTIONS]                                                                                                                                                   
                                                                                                                                                                                  
 Send prompts that need annotations to the A/B testing platform. Make sure WORKSPACE_NAME and DATASET_NAME already exist on the platform!                                         
                                                                                                                                                                                  
╭─ Options ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ *  --api-url                   TEXT  A/B testing platform URL [default: None] [required]                                                                                       │
│ *  --api-key                   TEXT  API key for testing platform [default: None] [required]                                                                                   │
│ *  --prompt-file               TEXT  The name of the file of prompts to send to the A/B testing platform [default: None] [required]                                            │
│ *  --workspace-name            TEXT  The name of the workspace in the Argilla A/B testing platform [default: None] [required]                                                  │
│ *  --dataset-name              TEXT  The dataset to add prompts to [default: None] [required]                                                                                  │
│    --install-completion              Install completion for the current shell.                                                                                                 │
│    --show-completion                 Show completion for the current shell, to copy it or customize the installation.                                                          │
│    --help                            Show this message and exit.                                                                                                               │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯

How to develop

  1. Clone the repo: git clone git@github.com:langtech-bsc/prompt-sender.git.

  2. If poetry is not installed on your system, follow the instructions to install it:

  3. cd prompt-sender/ and create a virtual environment, either by using something like venv or by using poetry's built-in virtual environment, which can be created and activated by running poetry shell (run exit to deactivate).

  4. Run poetry install to install project dependencies.

  5. Run pre-commit install to set up the git pre-commit hook scripts

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

prompt_sender-0.2.2.tar.gz (6.7 kB view details)

Uploaded Source

Built Distribution

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

prompt_sender-0.2.2-py3-none-any.whl (7.5 kB view details)

Uploaded Python 3

File details

Details for the file prompt_sender-0.2.2.tar.gz.

File metadata

  • Download URL: prompt_sender-0.2.2.tar.gz
  • Upload date:
  • Size: 6.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.10.12 Linux/6.5.0-1025-azure

File hashes

Hashes for prompt_sender-0.2.2.tar.gz
Algorithm Hash digest
SHA256 2d7e317f5a20e7a7164dcee6be5ac12e29fb1933cf9bdd10e8f45e82db05995e
MD5 627d8842384b2c8463d5ccf0b1295a2a
BLAKE2b-256 6d48323e45e1813d7d82ece9decb79d93cc3aa5912a317ed418191ad41ef6146

See more details on using hashes here.

File details

Details for the file prompt_sender-0.2.2-py3-none-any.whl.

File metadata

  • Download URL: prompt_sender-0.2.2-py3-none-any.whl
  • Upload date:
  • Size: 7.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.10.12 Linux/6.5.0-1025-azure

File hashes

Hashes for prompt_sender-0.2.2-py3-none-any.whl
Algorithm Hash digest
SHA256 38c7b97549465d6023361de1bd93d4a4714814a1ce7c95c7d22096ff9a1a6fb2
MD5 0a07c52fc5ffb5a71d8f72f25f92bcf0
BLAKE2b-256 547445ff36b0323d944d98cef4fbc82dd24add1d424d771524471f0a5fd35d86

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