HigherU

HigherU Document API

The HigherU REST API. Please see https://platform.higheru.ai/docs/api-reference for more details.

API Reference

Given a list of messages comprising a conversation, the model will return a response.

Chat

Creates a model response for the given chat conversation.

Given a prompt and an instruction, the model will return an edited version of the prompt.

Edits

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

Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms.

Embeddings

Creates an embedding vector representing the input text.

Audio

Transcribes audio into the input language.

Translates audio into english.

Files are used to upload documents that can be used with features like fine-tuning.

Files

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

Upload a file that can be used across various endpoints/features. currently, the size of all the files uploaded by one organization can be up to 1 gb. please [contact us](https://help.higheru.ai/) if you need to increase the storage limit.

Delete a file.

Returns information about a specific file.

Returns the contents of the specified file.

Manage fine-tuning jobs to tailor a model to your specific training data.

Fine-tuning

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

response includes details of the enqueued job including job status and the name of the fine-tuned models once complete.

[learn more about fine-tuning](/docs/guides/fine-tuning)

List your organization's fine-tuning jobs

Get info about a fine-tuning job.

[learn more about fine-tuning](/docs/guides/fine-tuning)

Get status updates for a fine-tuning job.

Immediately cancel a fine-tune job.

Manage legacy fine-tuning jobs to tailor a model to your specific training data.

Fine-tunes

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

response includes details of the enqueued job including job status and the name of the fine-tuned models once complete.

[learn more about fine-tuning](/docs/guides/legacy-fine-tuning)

Gets info about the fine-tune job.

[learn more about fine-tuning](/docs/guides/legacy-fine-tuning)

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

HigherU API

Default

The Defaul API section provides a comprehensive set of functionalities for integrating with the HigherU REST API. This API allows you to interact with various resources and perform actions such as retrieving data, creating new records, updating existing ones, and deleting information.

By leveraging the Defaul API, you can seamlessly integrate the HigherU platform into your own applications or systems. This integration opens up opportunities to automate processes, extract valuable insights, and enhance user experiences.

Whether you are a developer looking to incorporate HigherU functionality into your software solution or a non-technical professional seeking to understand the capabilities of the API, this section provides clear and concise documentation to guide you throughout the integration process.

To get started, refer to the detailed API reference available at https://platform.higheru.ai/docs/api-reference. The API reference provides in-depth information about each endpoint, including the required parameters, expected responses, and any additional considerations for successful integration.

By following the guidelines and examples provided in the API reference, you can easily utilize the Defaul API to harness the power of HigherU and enhance your application with seamless access to critical resources and functionality.

The Chat API endpoint allows you to retrieve a response based on a list of messages comprising a conversation. This functionality is particularly useful for applications where you need to generate automated replies or provide intelligent conversational interfaces. By passing in the conversation messages, the Chat API will analyze the content and provide you with a response. This API endpoint empowers developers to seamlessly integrate conversational capabilities into their applications, enhancing user experiences and enabling efficient communication.

The `post /chat/completions` API endpoint allows you to create a model response for a given chat conversation. This endpoint is designed to make API integration straightforward and is suitable for both developers and non-technical roles.

To use this endpoint, you need to provide the contents of the messages in the chat conversation. The `content` parameter is required for all messages, and it may be null for assistant messages with function calls. Additionally, you need to specify the name of the author of each message using the `name` parameter. The role of the author should be one of `system`, `user`, `assistant`, or `function`.

You can also include function calls in the chat conversation by providing the name and arguments of the function using the `messages.function_call.name` and `messages.function_call.arguments` parameters. The model will call the specified function based on the provided information.

In addition to the main parameters, there are several optional parameters that you can use to customize the behavior of the API. For example, you can modify the likelihood of specific tokens appearing in the completion using the `logit_bias` parameter. You can also control the temperature of the sampling process using the `temperature` parameter. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

After making a request to the API, you will receive a response with the generated chat completion choices. Each choice includes information such as the contents of the message, the function call details, and the role of the author. The response may contain multiple choices if the `n` parameter is greater than 1.

Overall, the `post /chat/completions` endpoint provides a straightforward way to generate model responses for chat conversations, making it easy to integrate with your application.

A list of messages that comprise the conversation history. Refer to the provided [Example Python code](https://cookbook.higheru.ai/examples/how_to_format_inputs_to_chatgpt_models) for formatting inputs to ChatGPT models.

messages

model

A number between -2.0 and 2.0 that penalizes new tokens

frequency_penalty

The name and arguments of the function to be called, as generated by the model.

function_call

An array of functions to be used in the response

functions

logit_bias

The maximum number of tokens to be generated in the chat completion. The total length of both input and generated tokens is determined by the model's context length. Refer to the provided [Example Python code](https://cookbook.higheru.ai/examples/how_to_count_tokens_with_tiktoken) for counting tokens.

max_tokens

The number of chat completion choices to be generated for each input message.

presence_penalty

Up to 4 sequences where the API should stop generating further tokens.

stop

Specifies whether the chat conversation should be closed or not

stream

temperature

top_p

user

Authorization

A list of chat completion choices. If `n` is greater than 1, there may be more than one choice.

choices

The Unix timestamp (in seconds) indicating the time when the chat completion was created.

created

The model utilized for the chat completion.

The object type, which is always `chat.completion`.

object

usage

Project Name: Defaul
API Endpoint: Edits

Description:
The Edits API endpoint allows you to retrieve an edited version of a given prompt and instruction. This API is designed to assist with refining and enhancing text content by generating suggested edits based on the provided input.

By making a request to this endpoint, you can obtain a modified version of the prompt that incorporates revisions and improvements recommended by our language model.

Whether you are looking to fine-tune an email, 

Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms. This API endpoint, Embeddings, allows you to retrieve a vector representation of your input that is suitable for integration with various machine learning models and algorithms. By leveraging this functionality, you can enhance the capabilities of your applications by incorporating the power of machine learning. The retrieved vector can be used for a wide range of use cases, includ

This section of the Defaul API documentation covers the functionality of the GET method for the Audio endpoint. The Audio endpoint allows you to convert audio files into text format. With this API, you can easily transcribe speech, interviews, recordings, or any other audio content into written text. This feature is particularly useful for applications that require text-based analysis or accessibility features. The API provides efficient and accurate transcription capabilities, saving you time a

Files are a crucial part of the Defaul project, allowing users to upload and manage documents for various features and purposes. By utilizing this API endpoint, you gain the ability to seamlessly integrate file uploading and retrieval functionality within your application. Whether it's for fine-tuning or other related tasks, this endpoint ensures that you can easily handle the transfer and storage of important documents. With its straightforward implementation, you can effortlessly incorporate f