openai-node-cli v1.1.1

OpenAI Node.js CLI

Command Line Interface

The openai-node-cli package is a command line interface (CLI) for interacting with the OpenAI API. It allows you to perform various operations using the OpenAI API, such as creating completions, images, and embeddings, uploading and downloading files, and managing fine-tune jobs and models.

Overview

• Installation
• Usage
• Commands
  • cancelFineTune
  • createCompletion
  • createEdit
  • createEmbedding
  • createFile
  • createFineTune
  • createImage
  • createImageEdit
  • createImageVariation
  • createModeration
  • deleteFile
  • deleteModel
  • downloadFile
  • listEngines
  • listFiles
  • listFineTuneEvents
  • listFineTunes
  • listModels
  • retrieveEngine
  • retrieveFile
  • retrieveFineTune
  • retrieveModel

Installation

Use Node Package Manager (NPM) to install the package globally.

npm install -g openai-node-cli

Usage

To use the openai api, you will need to create an api key from beta.openai.com/account/api-keys. It is recommended to setup the api key as an enviroment variable.

export OPENAI_API_KEY="YOUR_API_KEY_HERE"

Commands:

cancelFineTune

Immediately cancel a fine-tune job.

Options:

Example:

openai cancelFineTune --fine-tune-id "ft-AF1WoRqd3aJAHsqc9NY7iL8F"

Output:

{
  "id": "ft-xhrpBbvVUzYGo8oUO1FY4nI7",
  "object": "fine-tune",
  "model": "curie",
  "created_at": 1614807770,
  "events": [
    {
      "object": "fine-tune-event",
      "created_at": 1614807352,
      "level": "info",
      "message": "Job enqueued. Waiting for jobs ahead to complete. Queue number: 0."
    }
  ],
  "fine_tuned_model": null,
  "hyperparams": {
    "batch_size": 4,
    "learning_rate_multiplier": 0.1,
    "n_epochs": 4,
    "prompt_loss_weight": 0.1,
  },
  "organization_id": "org-uik025NZM3fVwbeO4wTFb645",
  "result_files": [],
  "status": "cancelled",
  "validation_files": [],
  "training_files": [
    {
      "id": "file-XGinujblHPwGLSztz8cPS8XY",
      "object": "file",
      "bytes": 1547276,
      "created_at": 1610062281,
      "filename": "training.jsonl",
      "purpose": "fine-tune-train"
    }
  ],
  "updated_at": 1614807789,
}

createCompletion

Creates a completion for the provided prompt and parameters.

Options:

Example:

openai createCompletion --prompt "The quick brown fox jumps over the lazy" --model "text-davinci-003"

Output:

{
  "id": "cmpl-6S7aM5kBKFfolZdClsBFW1HOinnHg",
  "object": "text_completion",
  "created": 1672158750,
  "model": "text-davinci-003",
  "choices": [
    {
      "text": " dog\n\nThe quick brown fox jumped over the lazy dog.",
      "index": 0,
      "logprobs": null,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 8,
    "completion_tokens": 13,
    "total_tokens": 21
  }
}

createEdit

Creates a new edit for the provided input, instruction, and parameters.

Options:

Example:

openai createEdit --input "The quick brown fox jumps over the lazy dog." --instruction "Make the sentence more interesting" --model "text-davinci-edit-001"

Output:

{
  "object": "edit",
  "created": 1672159258,
  "choices": [
    {
      "text": "The quick brown fox jumps over the lazy dog. She sells sea shells on the sea shore.\n",
      "index": 0
    }
  ],
  "usage": {
    "prompt_tokens": 27,
    "completion_tokens": 40,
    "total_tokens": 67
  }
}

createEmbedding

Creates an embedding vector representing the input text.

Options:

Example:

openai createEmbedding --input "The quick brown fox jumps over the lazy dog." --model "text-embedding-ada-002"

Output:

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [
        -0.029333716,
        0.023189154,
        -0.044676352
      ]
    }
  ],
  "model": "text-embedding-ada-002-v2",
  "usage": {
    "prompt_tokens": 10,
    "total_tokens": 10
  }
}

createFile

Upload a file that contains document(s) to be used across various endpoints/features. Currently, the size of all the files uploaded by one organization can be up to 1 GB.

Options:

Example:

openai createFile --file "/path/to/training.jsonl" --purpose "fine-tune"

Output:

{
  "id": "file-XjGxS3KTG0uNmNOK362iJua3",
  "object": "file",
  "bytes": 140,
  "created_at": 1613779121,
  "filename": "training.jsonl",
  "purpose": "fine-tune"
}

createFineTune

Creates a job that fine-tunes a specified model from a given dataset.

Options:

Example:

openai createFineTune --model "davinci" --training-file file-i8DZk4twt8dbNezMYtPf1LCN

Output:

{
  "id": "ft-AF1WoRqd3aJAHsqc9NY7iL8F",
  "object": "fine-tune",
  "model": "davinci",
  "created_at": 1614807352,
  "events": [
    {
      "object": "fine-tune-event",
      "created_at": 1614807352,
      "level": "info",
      "message": "Job enqueued. Waiting for jobs ahead to complete. Queue number: 0."
    }
  ],
  "fine_tuned_model": null,
  "hyperparams": {
    "batch_size": 4,
    "learning_rate_multiplier": 0.1,
    "n_epochs": 4,
    "prompt_loss_weight": 0.1,
  },
  "organization_id": "org-uik025NZM3fVwbeO4wTFb645",
  "result_files": [],
  "status": "pending",
  "validation_files": [],
  "training_files": [
    {
      "id": "file-XGinujblHPwGLSztz8cPS8XY",
      "object": "file",
      "bytes": 1547276,
      "created_at": 1610062281,
      "filename": "training.jsonl",
      "purpose": "fine-tune-train"
    }
  ],
  "updated_at": 1614807352,
}

createImage

Creates an image given a prompt.

Options:

Example:

openai createImage --prompt "A dog playing fetch" --size "512x512"

Output:

{
  "created": 1672160804,
  "data": [
    {
      "url": "https://oaidalleapiprodscus.blob.core.windows.net/private/org-uij025NZM3fVwbLT4wTFb6k6/user-1x2xoypsFdo1223Vb4Pfh105/img-kAjByWUFwan5ScQEUq1GTrnr.png?st=2022-12-27T16%3A06%3A44Z&se=2022-12-27T18%3A06%3A44Z&sp=r&sv=2021-08-06&sr=b&rscd=inline&rsct=image/png&skoid=6aaadede-4fb3-4698-a8f6-684d7786b067&sktid=a48cca56-e6da-484e-a814-9c849652bcb3&skt=2022-12-27T13%3A20%3A02Z&ske=2022-12-28T13%3A20%3A02Z&sks=b&skv=2021-08-06&sig=RRWZ/TWWmR3wouWXK7Gg3%2BqTehKhR5pnDwt5z/34eGU%3D"
    }
  ]
}

createImageEdit

Creates an edited or extended image given an original image and a prompt.

Options:

Example:

openai createImageEdit --prompt "Add a cat to the image" --image "photo.png" --mask "photo-mask.png"

Output:

{
  "created": 1589478378,
  "data": [
    {
      "url": "https://oaidalleapiprodscus.blob.core.windows.net/private/org-uij025NZM3fVwbLT4wTFb6k6/user-1x2xoypsFdo1223Vb4Pfh105/img-kAjByWUFwan5ScQEUq1GTrnr.png?st=2022-12-27T16%3A06%3A44Z&se=2022-12-27T18%3A06%3A44Z&sp=r&sv=2021-08-06&sr=b&rscd=inline&rsct=image/png&skoid=6aaadede-4fb3-4698-a8f6-684d7786b067&sktid=a48cca56-e6da-484e-a814-9c849652bcb3&skt=2022-12-27T13%3A20%3A02Z&ske=2022-12-28T13%3A20%3A02Z&sks=b&skv=2021-08-06&sig=RRWZ/TWWmR3wouWXK7Gg3%2BqTehKhR5pnDwt5z/34eGU%3D"
    }
  ]
}

createImageVariation

Creates a variation of a given image.

Options:

Example:

openai createImageVariation --image "fox.png" --response-format "b64_json"

Output:

{
  "created": 1589478378,
  "data": [
    {
      "url": "https://oaidalleapiprodscus.blob.core.windows.net/private/org-uij025NZM3fVwbLT4wTFb6k6/user-1x2xoypsFdo1223Vb4Pfh105/img-kAjByWUFwan5ScQEUq1GTrnr.png?st=2022-12-27T16%3A06%3A44Z&se=2022-12-27T18%3A06%3A44Z&sp=r&sv=2021-08-06&sr=b&rscd=inline&rsct=image/png&skoid=6aaadede-4fb3-4698-a8f6-684d7786b067&sktid=a48cca56-e6da-484e-a814-9c849652bcb3&skt=2022-12-27T13%3A20%3A02Z&ske=2022-12-28T13%3A20%3A02Z&sks=b&skv=2021-08-06&sig=RRWZ/TWWmR3wouWXK7Gg3%2BqTehKhR5pnDwt5z/34eGU%3D"
    }
  ]
}

createModeration

Classifies if text violates OpenAI's Content Policy

Options:

Example:

openai createModeration --input "I want to kill them."

Output:

{
  "id": "modr-5MWoLO",
  "model": "text-moderation-001",
  "results": [
    {
      "categories": {
        "hate": false,
        "hate/threatening": true,
        "self-harm": false,
        "sexual": false,
        "sexual/minors": false,
        "violence": true,
        "violence/graphic": false
      },
      "category_scores": {
        "hate": 0.22714105248451233,
        "hate/threatening": 0.4132447838783264,
        "self-harm": 0.005232391878962517,
        "sexual": 0.01407341007143259,
        "sexual/minors": 0.0038522258400917053,
        "violence": 0.9223177433013916,
        "violence/graphic": 0.036865197122097015
      },
      "flagged": true
    }
  ]
}

deleteFile

Delete a file.

Options:

Example:

openai deleteFile --file-id "file-XjGxS3KTG0uNmNOK362iJua3"

Output:

{
  "id": "file-XjGxS3KTG0uNmNOK362iJua3",
  "object": "file",
  "deleted": true
}

deleteModel

Delete a fine-tuned model. You must have the Owner role in your organization.

Options:

Example:

openai deleteModel --model "davinci:ft-org-domain-2022-12-22-07-26-01"

Output:

{
  "id": "davinci:ft-org-domain-2022-12-22-07-26-01",
  "object": "model",
  "deleted": true
}

downloadFile

Returns the contents of the specified file.

Options:

Example:

openai downloadFile --file "file-i9DZk2twt4deNezMYtPf1LCN"

Output:

{"prompt": "10 + 9", "completion": "21"}
{"prompt": "what is 10 + 9 =", "completion": "21"}
{"prompt": "what is 10 plus 9 equal to", "completion": "21"}

listEngines

Lists the currently available (non-finetuned) models, and provides basic information about each one such as the owner and availability.

Example:

openai listEngines

Output:

{
  "object": "list"
  "data": [
    {
      "object": "engine",
      "id": "babbage",
      "ready": true,
      "owner": "openai",
      "permissions": null,
      "created": null
    },
    {
      "object": "engine",
      "id": "ada",
      "ready": true,
      "owner": "openai",
      "permissions": null,
      "created": null
    }
  ]
}

listFiles

Returns a list of files that belong to the user's organization.

Example:

openai listFiles

Output:

{
  "object": "list",
  "data": [
    {
      "object": "file",
      "id": "file-rph3Zutld7ImjVXN9hQhHjc",
      "purpose": "fine-tune-results",
      "filename": "compiled_results.csv",
      "bytes": 1790,
      "created_at": 1671693962,
      "status": "processed",
      "status_details": null
    },
    {
      "object": "file",
      "id": "file-e8DZk4twt8dbNezMYtPf1LCN",
      "purpose": "fine-tune",
      "filename": "twenty-one.jsonl",
      "bytes": 519,
      "created_at": 1671690297,
      "status": "processed",
      "status_details": null
    }
  ]
}

listFineTuneEvents

Get fine-grained status updates for a fine-tune job.

Options:

Example:

openai listFineTuneEvents --fine-tune-id "ft-vMYr5UujI7bKEHmObuHXbtB"

Output:

{
  "object": "list",
  "data": [
    {
      "object": "fine-tune-event",
      "created_at": 1614807352,
      "level": "info",
      "message": "Job enqueued. Waiting for jobs ahead to complete. Queue number: 0."
    },
    {
      "object": "fine-tune-event",
      "created_at": 1614807356,
      "level": "info",
      "message": "Job started."
    }
  ]
}

listFineTunes

List your organization's fine-tuning jobs.

Example:

openai listFineTunes

Output:

{
  "object": "list",
  "data": [
    {
      "object": "fine-tune",
      "id": "ft-XuYr4UujI7bKEHmXb9vHXbtB",
      "hyperparams": {
        "n_epochs": 4,
        "batch_size": 1,
        "prompt_loss_weight": 0.01,
        "learning_rate_multiplier": 0.1
      },
      "organization_id": "org-uik025NZM3fVwbeO4wTFb645",
      "model": "curie",
      "training_files": [
        {
          "object": "file",
          "id": "file-dtIeV15XKVQI80qyMK2pOI7t",
          "purpose": "fine-tune",
          "filename": "training.jsonl",
          "bytes": 501,
          "created_at": 1671655748,
          "status": "deleted",
          "status_details": null
        }
      ],
      "validation_files": [],
      "result_files": [
        {
          "object": "file",
          "id": "file-fQRWLGltMGsRWzsHqO7Krl0m",
          "purpose": "fine-tune-results",
          "filename": "compiled_results.csv",
          "bytes": 1458,
          "created_at": 1671657273,
          "status": "deleted",
          "status_details": null
        }
      ],
      "created_at": 1671656382,
      "updated_at": 1671657273,
      "status": "succeeded",
      "fine_tuned_model": "curie:ft-org-name-2022-12-21-21-14-32"
    }
  ]
}   

listModels

Lists the currently available models, and provides basic information about each one such as the owner and availability.

Example:

openai listModels

Output:

{
  "object": "list",
  "data": [
    {
      "id": "davinci:ft-org-name-2022-12-22-07-26-01",
      "object": "model",
      "created": 1671693961,
      "owned_by": "org-name",
      "permission": [
        {
          "id": "snapperm-eZpZLBCmKmXs2ccdRtUsmxFV",
          "object": "model_permission",
          "created": 1671693961,
          "allow_create_engine": true,
          "allow_sampling": true,
          "allow_logprobs": true,
          "allow_search_indices": false,
          "allow_view": true,
          "allow_fine_tuning": true,
          "organization": "org-uiEo25NZM3fVwbLT4wTFb456",
          "group": null,
          "is_blocking": false
        }
      ],
      "root": "davinci:2020-05-03",
      "parent": "davinci:2020-05-03"
    }
  ]
}

retrieveEngine

Retrieves a model instance, providing basic information about it such as the owner and availability.

Options:

Example:

openai retrieveEngine --engine-id "text-search-babbage-query-001"

Output:

{
  "object": "list",
  "data": [
    {
      "object": "engine",
      "id": "audio-transcribe-001",
      "ready": true,
      "owner": "openai",
      "permissions": null,
      "created": null
    },
    {
      "object": "engine",
      "id": "davinci-similarity",
      "ready": true,
      "owner": "openai-dev",
      "permissions": null,
      "created": null
    }
  ]
}

retrieveFile

Returns information about a specific file.

Options:

Example:

openai retrieveFile --file-id "file-i9DZk2twt4deNezMYtPf1LCN"

Output:

{
  "object": "file",
  "id": "file-e8DZk4twt8dbNezMYtPf1vCN",
  "purpose": "fine-tune",
  "filename": "prompts.jsonl",
  "bytes": 519,
  "created_at": 1671690297,
  "status": "processed",
  "status_details": null
}

retrieveFineTune

Gets info about the fine-tune job.

Options:

Example:

openai retrieveFineTune --fine-tune-id "ft-vMYr5UujI7bKEHmObuHXbtB"

Output:

{
  "object": "fine-tune",
  "id": "ft-ufGTYcH6ofN0mce9xGQeTXE9",
  "hyperparams": {
    "n_epochs": 4,
    "batch_size": 1,
    "prompt_loss_weight": 0.01,
    "learning_rate_multiplier": 0.1
  },
  "organization_id": "org-oij025NZw3fVwbiT4wTFb6k6",
  "model": "davinci",
  "training_files": [
    {
      "object": "file",
      "id": "file-e8DZk4tvt8dbNezMYtPf1LCN",
      "purpose": "fine-tune",
      "filename": "twenty-one.jsonl",
      "bytes": 519,
      "created_at": 1671690297,
      "status": "processed",
      "status_details": null
    }
  ],
  "validation_files": [],
  "result_files": [
    {
      "object": "file",
      "id": "file-Kqpe3Zutld7ImjVXN9hQhHjc",
      "purpose": "fine-tune-results",
      "filename": "compiled_results.csv",
      "bytes": 1790,
      "created_at": 1671693962,
      "status": "processed",
      "status_details": null
    }
  ],
  "created_at": 1671690698,
  "updated_at": 1671693963,
  "status": "succeeded",
  "fine_tuned_model": "davinci:ft-org-name-2022-12-22-07-26-01",
  "events": [
    {
      "object": "fine-tune-event",
      "level": "info",
      "message": "Created fine-tune: ft-rVGTuCH6ofN0mce9xGQeTXE9",
      "created_at": 1671690698
    },
    {
      "object": "fine-tune-event",
      "level": "info",
      "message": "Fine-tune costs $0.01",
      "created_at": 1671690710
    }
  ]
}

retrieveModel

Retrieves a model instance, providing basic information about the model such as the owner and permissioning.

Options:

Example:

openai retrieveModel --model "text-davinci-003"

Output:

{
  "id": "text-davinci-003",
  "object": "model",
  "created": 1669599635,
  "owned_by": "openai-internal",
  "permission": [
    {
      "id": "modelperm-avGyoQNQYTDulwkeSa6n60ry",
      "object": "model_permission",
      "created": 1671910080,
      "allow_create_engine": false,
      "allow_sampling": true,
      "allow_logprobs": true,
      "allow_search_indices": false,
      "allow_view": true,
      "allow_fine_tuning": false,
      "organization": "*",
      "group": null,
      "is_blocking": false
    }
  ],
  "root": "text-davinci-003",
  "parent": null
}