Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add OpenAI models from Jan 25th #150

Merged
merged 4 commits into from
Feb 2, 2024
Merged

Add OpenAI models from Jan 25th #150

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
8a86a59
Add OpenAI models from Jan 25th
philippzagar Jan 28, 2024
c99de7b
Fix tests data
Feb 2, 2024
4ac97f5
Incorporate feedback from review
philippzagar Feb 2, 2024
f0eea34
Merge branch 'feat/update-available-models' of github.com:philippzaga…
philippzagar Feb 2, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
31 changes: 22 additions & 9 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -785,16 +785,24 @@ Models are represented as a typealias `typealias Model = String`.

```swift
public extension Model {
static let gpt4_1106_preview = "gpt-4-1106-preview"
static let gpt4_vision_preview = "gpt-4-vision-preview"
static let gpt4_turbo_preview = "gpt-4-turbo-preview"
static let gpt4_vision_preview = "gpt-4-vision-preview"
static let gpt4_0125_preview = "gpt-4-0125-preview"
static let gpt4_1106_preview = "gpt-4-1106-preview"
static let gpt4 = "gpt-4"
static let gpt4_0613 = "gpt-4-0613"
static let gpt4_0314 = "gpt-4-0314"
static let gpt4_32k = "gpt-4-32k"
static let gpt4_32k_0613 = "gpt-4-32k-0613"
static let gpt4_32k_0314 = "gpt-4-32k-0314"

static let gpt3_5Turbo = "gpt-3.5-turbo"
static let gpt3_5Turbo_0125 = "gpt-3.5-turbo-0125"
static let gpt3_5Turbo_1106 = "gpt-3.5-turbo-1106"
static let gpt3_5Turbo0613 = "gpt-3.5-turbo-0613"
static let gpt3_5Turbo0301 = "gpt-3.5-turbo-0301"
philippzagar marked this conversation as resolved.
Show resolved Hide resolved

static let gpt3_5Turbo_16k = "gpt-3.5-turbo-16k"
static let gpt3_5Turbo_16k_0613 = "gpt-3.5-turbo-16k-0613"

static let textDavinci_003 = "text-davinci-003"
static let textDavinci_002 = "text-davinci-002"
Expand All @@ -805,7 +813,13 @@ public extension Model {
static let textDavinci_001 = "text-davinci-001"
static let codeDavinciEdit_001 = "code-davinci-edit-001"

static let tts_1 = "tts-1"
static let tts_1_hd = "tts-1-hd"

static let whisper_1 = "whisper-1"

static let dall_e_2 = "dall-e-2"
static let dall_e_3 = "dall-e-3"

static let davinci = "davinci"
static let curie = "curie"
Expand All @@ -816,22 +830,21 @@ public extension Model {
static let textSearchAda = "text-search-ada-doc-001"
static let textSearchBabbageDoc = "text-search-babbage-doc-001"
static let textSearchBabbageQuery001 = "text-search-babbage-query-001"
static let textEmbedding3 = "text-embedding-3-small"
static let textEmbedding3Large = "text-embedding-3-large"

static let textModerationStable = "text-moderation-stable"
static let textModerationLatest = "text-moderation-latest"
static let moderation = "text-moderation-001"

static let dall_e_2 = "dall-e-2"
static let dall_e_3 = "dall-e-3"
static let moderation = "text-moderation-007"
}
```

GPT-4 models are supported.

For example to use basic GPT-4 8K model pass `.gpt4` as a parameter.
As an example: To use the `gpt-4-turbo-preview` model, pass `.gpt4_turbo_preview` as the parameter to the `ChatQuery` init.

```swift
let query = ChatQuery(model: .gpt4, messages: [
let query = ChatQuery(model: .gpt4_turbo_preview, messages: [
.init(role: .system, content: "You are Librarian-GPT. You know everything about the books."),
.init(role: .user, content: "Who wrote Harry Potter?")
])
Expand Down
80 changes: 51 additions & 29 deletions Sources/OpenAI/Public/Models/Models/Models.swift
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,50 +5,70 @@
// Created by Sergii Kryvoblotskyi on 12/19/22.
//

import Foundation

/// Defines all available OpenAI models supported by the library.
public typealias Model = String

public extension Model {

// Chat Completions

/// More capable than any GPT-3.5 model, able to do more complex tasks, and optimized for chat. Will be updated with our latest model iteration 2 weeks after it is released.
static let gpt4 = "gpt-4"
// Chat Completion
// GPT-4

/// GPT-4 Turbo, teh latest gpt-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling and more.
/// Maximum of 4096 output tokens
static let gpt4_1106_preview = "gpt-4-1106-preview"
/// `gpt-4-turbo`, the latest gpt-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling and more. Maximum of 4096 output tokens
static let gpt4_turbo_preview = "gpt-4-turbo-preview"

/// Ability to understand images, in addition to all other GPT-4 Turbo capabilities.
/// `gpt-4-vision-preview`, able to understand images, in addition to all other GPT-4 Turbo capabilities.
static let gpt4_vision_preview = "gpt-4-vision-preview"

/// Snapshot of gpt-4 from March 14th 2023. Unlike gpt-4, this model will not receive updates, and will only be supported for a three month period ending on June 14th 2023.

/// Snapshot of `gpt-4-turbo-preview` from January 25th 2024. This model reduces cases of “laziness” where the model doesn’t complete a task. Also fixes the bug impacting non-English UTF-8 generations. Maximum of 4096 output tokens
static let gpt4_0125_preview = "gpt-4-0125-preview"

/// Snapshot of `gpt-4-turbo-preview` from November 6th 2023. Improved instruction following, JSON mode, reproducible outputs, parallel function calling and more. Maximum of 4096 output tokens
@available(*, deprecated, message: "Please upgrade to the newer model")
static let gpt4_0314 = "gpt-4-0314"
/// Snapshot of gpt-4 from June 13th 2023 with function calling data. Unlike gpt-4, this model will not receive updates, and will be deprecated 3 months after a new version is released.
static let gpt4_1106_preview = "gpt-4-1106-preview"

/// Most capable `gpt-4` model, outperforms any GPT-3.5 model, able to do more complex tasks, and optimized for chat.
static let gpt4 = "gpt-4"

/// Snapshot of `gpt-4` from June 13th 2023 with function calling data. Unlike `gpt-4`, this model will not receive updates, and will be deprecated 3 months after a new version is released.
static let gpt4_0613 = "gpt-4-0613"
/// Same capabilities as the base gpt-4 mode but with 4x the context length. Will be updated with our latest model iteration.

/// Snapshot of `gpt-4` from March 14th 2023. Unlike gpt-4, this model will not receive updates, and will only be supported for a three month period ending on June 14th 2023.
@available(*, deprecated, message: "Please upgrade to the newer model")
static let gpt4_0314 = "gpt-4-0314"

/// Same capabilities as the base `gpt-4` model but with 4x the context length. Will be updated with our latest model iteration.
static let gpt4_32k = "gpt-4-32k"
/// Snapshot of gpt-4-32 from March 14th 2023. Unlike gpt-4-32k, this model will not receive updates, and will only be supported for a three month period ending on June 14th 2023.

/// Snapshot of `gpt-4-32k` from June 13th 2023. Unlike `gpt-4-32k`, this model will not receive updates, and will be deprecated 3 months after a new version is released.
static let gpt4_32k_0613 = "gpt-4-32k-0613"

/// Snapshot of `gpt-4-32k` from March 14th 2023. Unlike `gpt-4-32k`, this model will not receive updates, and will only be supported for a three month period ending on June 14th 2023.
@available(*, deprecated, message: "Please upgrade to the newer model")
static let gpt4_32k_0314 = "gpt-4-32k-0314"
/// Snapshot of gpt-4-32 from June 13th 2023. Unlike gpt-4-32k, this model will not receive updates, and will be deprecated 3 months after a new version is released.
static let gpt4_32k_0613 = "gpt-4-32k-0613"

/// The latest GPT-3.5 Turbo model with improved instruction following, JSON mode, reproducible outputs, parallel function calling and more.
static let gpt3_5Turbo_1106 = "gpt-3.5-turbo-1106"

/// Most capable GPT-3.5 model and optimized for chat at 1/10th the cost of text-davinci-003. Will be updated with our latest model iteration.
// GPT-3.5

/// Most capable `gpt-3.5-turbo` model and optimized for chat. Will be updated with our latest model iteration.
static let gpt3_5Turbo = "gpt-3.5-turbo"
/// Snapshot of gpt-3.5-turbo from March 1st 2023. Unlike gpt-3.5-turbo, this model will not receive updates, and will only be supported for a three month period ending on June 1st 2023.

/// Snapshot of `gpt-3.5-turbo` from January 25th 2024. Decreased prices by 50%. Various improvements including higher accuracy at responding in requested formats and a fix for a bug which caused a text encoding issue for non-English language function calls.
static let gpt3_5Turbo_0125 = "gpt-3.5-turbo-0125"

/// Snapshot of `gpt-3.5-turbo` from November 6th 2023. The latest `gpt-3.5-turbo` model with improved instruction following, JSON mode, reproducible outputs, parallel function calling and more.
@available(*, deprecated, message: "Please upgrade to the newer model")
static let gpt3_5Turbo0301 = "gpt-3.5-turbo-0301"
/// Snapshot of gpt-3.5-turbo from June 13th 2023 with function calling data. Unlike gpt-3.5-turbo, this model will not receive updates, and will be deprecated 3 months after a new version is released.
static let gpt3_5Turbo_1106 = "gpt-3.5-turbo-1106"

/// Snapshot of `gpt-3.5-turbo` from June 13th 2023 with function calling data. Unlike `gpt-3.5-turbo`, this model will not receive updates, and will be deprecated 3 months after a new version is released.
@available(*, deprecated, message: "Please upgrade to the newer model")
static let gpt3_5Turbo0613 = "gpt-3.5-turbo-0613"
/// Same capabilities as the standard gpt-3.5-turbo model but with 4 times the context.

/// Snapshot of `gpt-3.5-turbo` from March 1st 2023. Unlike `gpt-3.5-turbo`, this model will not receive updates, and will only be supported for a three month period ending on June 1st 2023.
@available(*, deprecated, message: "Please upgrade to the newer model")
static let gpt3_5Turbo0301 = "gpt-3.5-turbo-0301"

/// Same capabilities as the standard `gpt-3.5-turbo` model but with 4 times the context.
static let gpt3_5Turbo_16k = "gpt-3.5-turbo-16k"
/// Snapshot of gpt-3.5-turbo-16k from June 13th 2023. Unlike gpt-3.5-turbo-16k, this model will not receive updates, and will be deprecated 3 months after a new version is released.

/// Snapshot of `gpt-3.5-turbo-16k` from June 13th 2023. Unlike `gpt-3.5-turbo-16k`, this model will not receive updates, and will be deprecated 3 months after a new version is released.
static let gpt3_5Turbo_16k_0613 = "gpt-3.5-turbo-16k-0613"

// Completions
Expand Down Expand Up @@ -101,12 +121,14 @@ public extension Model {
static let textSearchAda = "text-search-ada-doc-001"
static let textSearchBabbageDoc = "text-search-babbage-doc-001"
static let textSearchBabbageQuery001 = "text-search-babbage-query-001"
static let textEmbedding3 = "text-embedding-3-small"
static let textEmbedding3Large = "text-embedding-3-large"

// Moderations

/// Almost as capable as the latest model, but slightly older.
static let textModerationStable = "text-moderation-stable"
/// Most capable moderation model. Accuracy will be slightly higher than the stable model.
static let textModerationLatest = "text-moderation-latest"
static let moderation = "text-moderation-001"
static let moderation = "text-moderation-007"
}
2 changes: 1 addition & 1 deletion Tests/OpenAITests/OpenAITests.swift
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -117,7 +117,7 @@ class OpenAITests: XCTestCase {
}

func testChatsFunction() async throws {
let query = ChatQuery(model: .gpt3_5Turbo_1106, messages: [
let query = ChatQuery(model: .gpt3_5Turbo_0125, messages: [
.init(role: .system, content: "You are Weather-GPT. You know everything about the weather."),
.init(role: .user, content: "What's the weather like in Boston?"),
], functions: [
Expand Down
2 changes: 1 addition & 1 deletion Tests/OpenAITests/OpenAITestsDecoder.swift
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -347,7 +347,7 @@ class OpenAITestsDecoder: XCTestCase {
let data = """
{
"id": "modr-5MWoLO",
"model": "text-moderation-001",
"model": "text-moderation-007",
"results": [
{
"categories": {
Expand Down
Loading