Community

Blog

Tune Studio Docs

Studio

Chat

Cookbooks

API Reference

Events

Tune Studio

Support

Tune Chat

List base models

State of the model. This is used to track the model's lifecycle.
The state is updated by the model controller.

State of the model.

 - UNSPECIFIED: Model in unknown state.
 - PROVISIONING: model is being created on the cluster.
 - ENV_SETUP: running initilization steps.
 - AWAITING_STARTUP: starting model container.
 - LIVENESS_CHECK: checking model liveness.
 - READY: model is ready.
 - FAILED: model is in error state.
 - TERMINATED: model is terminated can be restarted.

`Any` contains an arbitrary serialized protocol buffer message along with a
URL that describes the type of the serialized message.

Protobuf library provides support to pack/unpack Any values in the form
of utility functions or additional generated methods of the Any type.

Example 1: Pack and unpack a message in C++.

    Foo foo = ...;
    Any any;
    any.PackFrom(foo);
    ...
    if (any.UnpackTo(&foo)) {
      ...
    }

Example 2: Pack and unpack a message in Java.

    Foo foo = ...;
    Any any = Any.pack(foo);
    ...
    if (any.is(Foo.class)) {
      foo = any.unpack(Foo.class);
    }
    // or ...
    if (any.isSameTypeAs(Foo.getDefaultInstance())) {
      foo = any.unpack(Foo.getDefaultInstance());
    }

 Example 3: Pack and unpack a message in Python.

    foo = Foo(...)
    any = Any()
    any.Pack(foo)
    ...
    if any.Is(Foo.DESCRIPTOR):
      any.Unpack(foo)
      ...

 Example 4: Pack and unpack a message in Go

     foo := &pb.Foo{...}
     any, err := anypb.New(foo)
     if err != nil {
       ...
     }
     ...
     foo := &pb.Foo{}
     if err := any.UnmarshalTo(foo); err != nil {
       ...
     }

The pack methods provided by protobuf library will by default use
'type.googleapis.com/full.type.name' as the type URL and the unpack
methods only use the fully qualified type name after the last '/'
in the type URL, for example "foo.bar.com/x/y.z" will yield type
name "y.z".

JSON
====
The JSON representation of an `Any` value uses the regular
representation of the deserialized, embedded message, with an
additional field `@type` which contains the type URL. Example:

    package google.profile;
    message Person {
      string first_name = 1;
      string last_name = 2;
    }

    {
      "@type": "type.googleapis.com/google.profile.Person",
      "firstName": <string>,
      "lastName": <string>
    }

If the embedded message type is well-known and has a custom JSON
representation, that representation will be embedded adding a field
`value` which holds the custom JSON in addition to the `@type`
field. Example (for message [google.protobuf.Duration][]):

    {
      "@type": "type.googleapis.com/google.protobuf.Duration",
      "value": "1.212s"
    }

A URL/resource name that uniquely identifies the type of the serialized
protocol buffer message. This string must contain at least
one "/" character. The last segment of the URL's path must represent
the fully qualified name of the type (as in
`path/google.protobuf.Duration`). The name should be in a canonical form
(e.g., leading "." is not accepted).

In practice, teams usually precompile into the binary all types that they
expect it to use in the context of Any. However, for URLs which use the
scheme `http`, `https`, or no scheme, one can optionally set up a type
server that maps type URLs to message definitions as follows:

* If no scheme is provided, `https` is assumed.
* An HTTP GET on the URL must yield a [google.protobuf.Type][]
  value in binary format, or produce an error.
* Applications are allowed to cache lookup results based on the
  URL, or have them precompiled into a binary to avoid any
  lookup. Therefore, binary compatibility needs to be preserved
  on changes to types. (Use versioned type names to manage
  breaking changes.)

Note: this functionality is not currently available in the official
protobuf release, and it is not used for type URLs beginning with
type.googleapis.com. As of May 2023, there are no widely used type server
implementations and no plans to implement one.

Schemes other than `http`, `https` (or the empty scheme) might be
used with implementation specific semantics.

The organization ID for request, it override the x-org-id header if set.

access_key is used to authenticate requests to the endpoint.
It is used in the following ways:
curl -H "x-tune-key:  $access_key" https://proxy.tune.app/ |  $url

URL to access the model or serving group.

 - MODALITY_TEXT: Text.
 - MODALITY_IMAGE: Image.
 - MODALITY_AUDIO: Audio.
 - MODALITY_VIDEO: Video.
 - MODALITY_IMAGE_TEXT: Image and Text.

LLM model id which is supported by tune.Studio or any huggingface model.

feature gates for the model (internal use).

true if model have public endpoint else false.

server type of the model, if empty used from DB.

uri of the model in the form of username/model_name.

 - QUANTIZATION_AWQ: Aware Quantization.
 - QUANTIZATION_GPTQ: GPT Quantization.
 - QUANTIZATION_SQUEEZELLM: SqueezeLLM Quantization.
 - QUANTIZATION_FP16: FP16 Quantization.

Used to specify the resource requirement for a
(job, model).

in GiBs

in seconds. Note this is inclusive of jobs and init containers,
enforced by k8s, regardless of `max_retries` set.
Not supported for models.

Resource Requirements

Return list of all supported model for deployment and finetuning

Logging

How to deploy a custom model on Tune Studio.

Deploy Custom Models

This guide will help you get started quickly with creating and using AI assistants.

Assistant in Action

Tune Assistant in Action

Learn about the different concepts in Tune Studio

Overview

Pricing information for various resources on Tune Studio

Pricing and Model Support

Fine-tune a large language model for solving a specific problem and optimizing cost.

Fine-tuning

Deploy and manage your models in Tune Studio

Models

Generate completions for a prompt in a chat or text context.

Completions API

Connect your favorite tools to Tune Studio

Integrations

Store conversation logs of your app in Tune Studio.

Threads

Function Calling

Blob is an AI agent model that uses the internet and multiple tools to help solve your problems.

Tune Blob

Generate Vision Completions for a prompt in a chat or text context.

Vision Completion

Adding a custom model. Integrate your self-hosted or custom-built LLMs with Tune Studio.

Custom Models

A guide to understand, create AI assistant, adding tools, and implementing actions using the Assistant API.

Assistant

Tune Assistant

Run tune studio on your own cloud (BYOC) - self host the compute.

My Cloud

Integrate your cloud provider with Tune Studio to bring your own cloud (BYOC) and self-host the compute.

My Cloud Integrations

Learn how to authenticate with the Tune API

Authentication

Glossary

Changelog

FAQs

Frequently asked questions for Tune Chat.

Frequently Asked Questions

See Tune Studio in action. Explore real-world examples and build practical AI applications"

Tune Studio Cookbook

Use Tune Studio to integrate LangChain with the Mistral AI API to translate user-provided input to a given language, and build the frontend with Streamlit.

Build a translator app using Tune Studio, LangChain, and Streamlit

Create a RAG (retrieval-augmented generation) agent using Python, Tune Studio, OpenAI, and Supabase for data storage.

Creating an Internet Scraping RAG Agent With Python and Supabase

A chat app for playing with TuneStudio APIs

Web assistant with function calling using Next JS

Using LlamaIndex

In a chat application, the "threads" API is commonly used to manage and organize conversations.

Your own chat app with threads API and Next JS

Create a dynamic recipe generator using Tune Studio and Notion.

Notion Recipe Generator

Here are some potential issues you can run into while working with LLMs

Edge Cases and Potential Pitfalls

Join Tune AI at PennApps XXV! Compete in our epic challenge to create groundbreaking LLM-powered applications using Tune Studio.

Completions

Tune Studio

List base models

Body

Response