openai-cost-logger


Nameopenai-cost-logger JSON
Version 0.5.1 PyPI version JSON
download
home_pagehttps://github.com/drudilorenzo/openai-cost-tracker
SummaryOpenAI Cost Logger
upload_time2024-05-28 14:24:13
maintainerNone
docs_urlNone
authorLorenzo Drudi | Mikolaj Boronski | Ivan Zakazov
requires_pythonNone
licenseMIT
keywords openai cost logger tracker viz llms
VCS
bugtrack_url
requirements openai matplotlib pytest
Travis-CI No Travis.
coveralls test coverage No coveralls.
            .. image:: https://img.shields.io/badge/chatGPT-74aa9c.svg?logo=openai
.. image:: https://img.shields.io/pypi/pyversions/setuptools.svg

==================
OpenAI Cost Logger
==================

* Simple **cost logger** for **OpenAI requests**.
* Track the cost of every request you make to OpenAI and visualize them in a user-friendly way.
* Homepage on `PyPI <https://pypi.org/project/openai-cost-logger/>`_.
* `Demo file <https://github.com/drudilorenzo/track-openai-cost/blob/master/demo.ipynb>`_ with a usage example.

How to install:
---------------
* .. code-block:: python

      pip install openai-cost-logger

* .. code-block:: python

      from openai_cost_logger import OpenAICostLogger
      from openai_cost_logger import OpenAICostLoggerViz
      from openai_cost_logger import OpenAICostLoggerUtils
      from openai_cost_logger import OpenAICostLogger_Singleton
      from openai_cost_logger import DEFAULT_LOG_PATH, MODELS_COST

Key Features:
-------------
* Track the cost of every request you make and save them in a JSON file.
* Choose the feature you want to track (prompt_tokens, completion_tokens, completion, prompt, etc.).
* Check the cost of your requests filtering by model or strftime aggregation (see the docs).

Models supported:
-------------------
* The generation of responses is totally up to the user. The library supports every model whose response contains the fields **usage.prompt_tokens** and **usage.total_tokens** (e.g. chat completions, embeddings, etc.).

Multithreading:
---------------
* Be aware that the classic cost logger is not thread-safe.
* If you want to use it in a multithreading environment, you should use the **thread-safe** version of the logger: ``OpenAICostLogger_Singleton``. The interface is the same as the classic logger. This will prevent multiple threads from writing to the same file at the same time.

Note:
-----
* Every cost is specified per **million tokens**.
* If you don't specify the cost, the library will look to the **MODELS_COST** dictionary and get the cost of the model you are using. Be aware that if the model is not in the dictionary, an exception will be raised.

Viz example:
-------------
.. image:: images/example.png
   :alt: Viz example (prints + plot)
   :align: center



            

Raw data

            {
    "_id": null,
    "home_page": "https://github.com/drudilorenzo/openai-cost-tracker",
    "name": "openai-cost-logger",
    "maintainer": null,
    "docs_url": null,
    "requires_python": null,
    "maintainer_email": null,
    "keywords": "openai, cost, logger, tracker, viz, llms",
    "author": "Lorenzo Drudi | Mikolaj Boronski | Ivan Zakazov",
    "author_email": "lorenzodrudi11@gmail.com",
    "download_url": "https://files.pythonhosted.org/packages/1a/7b/539891456e444e4b7bc4370dee4e5e6364687660f4e2ae95d3101969ea36/openai-cost-logger-0.5.1.tar.gz",
    "platform": null,
    "description": ".. image:: https://img.shields.io/badge/chatGPT-74aa9c.svg?logo=openai\n.. image:: https://img.shields.io/pypi/pyversions/setuptools.svg\n\n==================\nOpenAI Cost Logger\n==================\n\n* Simple **cost logger** for **OpenAI requests**.\n* Track the cost of every request you make to OpenAI and visualize them in a user-friendly way.\n* Homepage on `PyPI <https://pypi.org/project/openai-cost-logger/>`_.\n* `Demo file <https://github.com/drudilorenzo/track-openai-cost/blob/master/demo.ipynb>`_ with a usage example.\n\nHow to install:\n---------------\n* .. code-block:: python\n\n      pip install openai-cost-logger\n\n* .. code-block:: python\n\n      from openai_cost_logger import OpenAICostLogger\n      from openai_cost_logger import OpenAICostLoggerViz\n      from openai_cost_logger import OpenAICostLoggerUtils\n      from openai_cost_logger import OpenAICostLogger_Singleton\n      from openai_cost_logger import DEFAULT_LOG_PATH, MODELS_COST\n\nKey Features:\n-------------\n* Track the cost of every request you make and save them in a JSON file.\n* Choose the feature you want to track (prompt_tokens, completion_tokens, completion, prompt, etc.).\n* Check the cost of your requests filtering by model or strftime aggregation (see the docs).\n\nModels supported:\n-------------------\n* The generation of responses is totally up to the user. The library supports every model whose response contains the fields **usage.prompt_tokens** and **usage.total_tokens** (e.g. chat completions, embeddings, etc.).\n\nMultithreading:\n---------------\n* Be aware that the classic cost logger is not thread-safe.\n* If you want to use it in a multithreading environment, you should use the **thread-safe** version of the logger: ``OpenAICostLogger_Singleton``. The interface is the same as the classic logger. This will prevent multiple threads from writing to the same file at the same time.\n\nNote:\n-----\n* Every cost is specified per **million tokens**.\n* If you don't specify the cost, the library will look to the **MODELS_COST** dictionary and get the cost of the model you are using. Be aware that if the model is not in the dictionary, an exception will be raised.\n\nViz example:\n-------------\n.. image:: images/example.png\n   :alt: Viz example (prints + plot)\n   :align: center\n\n\n",
    "bugtrack_url": null,
    "license": "MIT",
    "summary": "OpenAI Cost Logger",
    "version": "0.5.1",
    "project_urls": {
        "Homepage": "https://github.com/drudilorenzo/openai-cost-tracker"
    },
    "split_keywords": [
        "openai",
        " cost",
        " logger",
        " tracker",
        " viz",
        " llms"
    ],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "1a7b539891456e444e4b7bc4370dee4e5e6364687660f4e2ae95d3101969ea36",
                "md5": "adffb3c56c0c548890fa601245b93f13",
                "sha256": "768ed1e7470d4eadff0e75f9a54c82bd7d29521d34ac0a495f4ff193bfbd7b7a"
            },
            "downloads": -1,
            "filename": "openai-cost-logger-0.5.1.tar.gz",
            "has_sig": false,
            "md5_digest": "adffb3c56c0c548890fa601245b93f13",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 7793,
            "upload_time": "2024-05-28T14:24:13",
            "upload_time_iso_8601": "2024-05-28T14:24:13.150494Z",
            "url": "https://files.pythonhosted.org/packages/1a/7b/539891456e444e4b7bc4370dee4e5e6364687660f4e2ae95d3101969ea36/openai-cost-logger-0.5.1.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2024-05-28 14:24:13",
    "github": true,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "github_user": "drudilorenzo",
    "github_project": "openai-cost-tracker",
    "travis_ci": false,
    "coveralls": false,
    "github_actions": true,
    "requirements": [
        {
            "name": "openai",
            "specs": [
                [
                    "==",
                    "1.13.3"
                ]
            ]
        },
        {
            "name": "matplotlib",
            "specs": [
                [
                    "==",
                    "3.6.3"
                ]
            ]
        },
        {
            "name": "pytest",
            "specs": [
                [
                    "==",
                    "7.4.2"
                ]
            ]
        }
    ],
    "lcname": "openai-cost-logger"
}
        
Elapsed time: 0.28370s