Azure AI Services: Azureopenai
APIs for fine-tuning and managing deployments of OpenAI models.
Fork copies the collection into your workspace, without the publisher's secrets, so you can add your own key and send requests. Star saves it to your starred APIs (Account › Marketplace) and helps others find it.
Overview
APIs for fine-tuning and managing deployments of OpenAI models.
Endpoints 23
Batch:
- GETGets a list of all batches owned by the Azure OpenAI resource.
/batches?after=string&limit=20&api-version=string - POSTCreates and executes a batch from an uploaded file of requests.
Response includes details of the enqueued job including job status.
The ID of the result file is added to the response once complete.
/batches?api-version=string - GETGets details for a single batch specified by the given batch-id.
/batches/:batch-id?api-version=string - POSTCancels the processing of the batch specified by the given batch-id.
/batches/:batch-id/cancel?api-version=string
Files:
- GETGets a list of all files owned by the Azure OpenAI resource.
These include user uploaded content like files with purpose "fine-tune" for training or validation of fine-tunes models
as well as files that are generated by the service such as "fine-tune-results" which contains various metrics for the corresponding fine-tune job.
/files?purpose=fine-tune&api-version=string - POSTCreates a new file entity by uploading data from a local machine. Uploaded files can, for example, be used for training or evaluating fine-tuned models.
/files?api-version=string - GETGets details for a single file specified by the given file-id including status, size, purpose, etc.
/files/:file-id?api-version=string - DELETEDeletes the file with the given file-id.
Deletion is also allowed if a file was used, e.g., as training file in a fine-tune job.
/files/:file-id?api-version=string - GETGets the content of the file specified by the given file-id.
Files can be user uploaded content or generated by the service like result metrics of a fine-tune job.
/files/:file-id/content?api-version=string - POSTCreates a new file entity by importing data from a provided url. Uploaded files can, for example, be used for training or evaluating fine-tuned models.
/files/import?api-version=string
Fine-tuning:
- GETGets a list of all fine-tune jobs owned by the Azure OpenAI resource.
The details that are returned for each fine-tune job contain besides its identifier
the base model, training and validation files, hyper parameters, time stamps, status and events.
Events are created when the job status changes, e.g. running or complete, and when results are uploaded.
/fine_tuning/jobs?after=string&limit=20&api-version=string - POSTCreates a job that fine-tunes a specified model from a given training file.
Response includes details of the enqueued job including job status and hyper parameters.
The name of the fine-tuned model is added to the response once complete.
/fine_tuning/jobs?api-version=string - GETGets details for a single fine-tune job specified by the given fine-tune-id.
The details contain the base model, training and validation files, hyper parameters, time stamps, status and events.
Events are created when the job status changes, e.g. running or complete, and when results are uploaded.
/fine_tuning/jobs/:fine-tuning-job-id?api-version=string - DELETEDeletes the fine-tune job specified by the given fine-tune-id.
/fine_tuning/jobs/:fine-tuning-job-id?api-version=string - GETGets the events for the fine-tune job specified by the given fine-tune-id.
Events are created when the job status changes, e.g. running or complete, and when results are uploaded.
/fine_tuning/jobs/:fine-tuning-job-id/events?after=string&limit=20&api-version=string - GETGets the checkpoints for the fine-tune job specified by the given fine-tune-id.
Checkpoints are created at the end of successful epochs during training.
/fine_tuning/jobs/:fine-tuning-job-id/checkpoints?after=string&limit=10&api-version=string - POSTCancels the processing of the fine-tune job specified by the given fine-tune-id.
/fine_tuning/jobs/:fine-tuning-job-id/cancel?api-version=string
Models:
- GETGets a list of all models that are accessible by the Azure OpenAI resource.
These include base models as well as all successfully completed fine-tuned models owned by the Azure OpenAI resource.
/models?api-version=string - GETGets details for the model specified by the given modelId.
/models/:model-id?api-version=string
UploadFile:
- POSTAn intermediate Upload object is created, allowing you to add Parts to it. Currently, an Upload size can be a maximum of 9 GB in total and will expire two hours after being created.
After the Upload is completed a File object will be generated, containing all the uploaded parts. This File object can then be used across our platform just like any other file.
/uploads?api-version=string - POSTAdds a Part to an Upload object, where each Part represents a segment of the file you are uploading.
Each Part can be up to the standard size limit for file upload, based on the File Purpose. You can continue adding Parts until reaching the Upload size limit of 9 GB.
/uploads/:upload-id/parts?api-version=string - POSTThis completes the Upload, and the returned Upload object contains a nested File object that is ready for use across the platform.
You can define the order of the Parts by providing an ordered list of Part IDs.
The total number of bytes uploaded must match the size originally specified when creating the Upload object.
After this operation no additional Parts can be added once the Upload is completed.
/uploads/:upload-id/complete?api-version=string - POSTCancels the Upload, and will lead to all uploaded parts to be deleted asynchronously.
No Parts may be added after an Upload is cancelled.
/uploads/:upload-id/cancel?api-version=string
API details
- Authentication
- An API key in the api-key header
- Operations
- 23 operations on 18 pathsGET 11POST 10DELETE 2
- Main resources
- Fine-tuning: 7Files: 6Batch: 4UploadFile: 4Models: 2
- Description format
- Swagger 2.0, API version
2024-10-21 - Links
- OpenAPI document
How to test the Azure AI Services: Azureopenai in Swastik Codes
- Open the APISelect “Fork & run in Swastik Codes” on this page. Sign in or create a free account if asked.
- Fork it into your workspaceChoose a workspace. You get your own copy of the Azure AI Services: Azureopenai collection, without the publisher's secrets.
- Add your credentialsThis API uses an API key in the api-key header. Add yours in the collection's variables or an environment; the requests already reference it.
- Send a requestPick an endpoint, for example “Gets a list of all batches owned by the Azure OpenAI resource.” (GET /batches?after=string&limit=20&api-version=string), and press Send. Check the response, add tests and run the whole collection with the runner.
Frequently asked questions
What is the Azure AI Services: Azureopenai?
APIs for fine-tuning and managing deployments of OpenAI models. It is listed under AI & machine learning and has 23 endpoints.
Who publishes the Azure AI Services: Azureopenai?
It is listed from Microsoft Azure's public API description (an OpenAPI document), not published by Microsoft Azure on Swastik Codes. Anyone who controls azure.com can claim the profile by adding a DNS TXT record.
How do I authenticate with the Azure AI Services: Azureopenai?
With an API key in the api-key header.
How many endpoints does the Azure AI Services: Azureopenai have?
23 operations on 18 paths (11 GET, 10 POST, 2 DELETE). The largest groups are Fine-tuning:, Files:, Batch:, UploadFile:.
Is forking the Azure AI Services: Azureopenai free?
Yes. Forking copies the collection into your workspace for free. It has been starred 0 times and forked 0 times.