SpeziLLMOpenAI: Replace MacPaw/OpenAI With Generated API Calls #64

paulhdk · 2024-08-27T10:09:23Z

SpeziLLMOpenAI: Replace MacPaw/OpenAI With Generated API Calls

♻️ Current situation & Problem

This PR replaces the MacPaw/OpenAI package with generated API calls by the swift-openapi-generator package.
Calls are generated from OpenAI's official OpenAPI spec.
Closes: #49

This PR does not add any new features but simply replicates the existing feature set with the generated API calls.

I've tried my best to keep track of any known issues in-code with FIXMEs as well as in the following list.

Current Issues

Sources/SpeziLLMOpenAI/LLMOpenAISession+Generation.swift does not handle the "[DONE]" message sent by the API to conclude a stream. There is currently a hacky workaround that catches the error that is thrown in that case. I'm not quite sure yet how to handle that case elegantly.
There are several do ... catch blocks that catch OpenAI package-specific errors, which I had to commented out. I have not found a semantically equivalent solution for the generated API calls yet.
The LLMFunctionParameterItemSchema type does not use a generated type yet.
The convenience initialisers in SpeziLLMOpenAI/FunctionCalling should be, if possible, refactored, as they currently have a lot of optional bindings.
Correct error handling
Currently, openapi-generator-swift expects and an openapi.yaml and a configuration file in the TestApp, which is why there are duplicate openapi specs and configuration files in this PR. I'm not quite sure why it's expecting them in the TestApp, but I suspect it has something to do with the generated types being used in the TestApp's model selection mechanism.
The SpeziLLMTests are currently not passing. Because the test errors are realted to the above issues, I’ll update the tests once I’ve addressed all of the issues above.

⚙️ Release Notes

Replace the MacPaw/OpenAI package with Apple/swift-openapi-generator, which is able to generate API calls directly from OpenAI's official OpenAPI spec.

📚 Documentation

As no new functionality is added, nothing should change here (unless I missed something).

✅ Testing

This PR passes the existing tests. Since no new functionality has been added, I believe this should suffice.

📝 Code of Conduct & Contributing Guidelines

By submitting creating this pull request, you agree to follow our Code of Conduct and Contributing Guidelines:

I agree to follow the Code of Conduct and Contributing Guidelines.

codecov · 2024-10-04T22:03:05Z

Codecov Report

Attention: Patch coverage is 54.38596% with 260 lines in your changes missing coverage. Please review.

Project coverage is 38.58%. Comparing base (fd9f1ca) to head (42f9079).
Report is 1 commits behind head on main.

Files with missing lines	Patch %	Lines
...peziLLMOpenAI/LLMOpenAISession+Configuration.swift	0.00%	80 Missing ⚠️
...ources/SpeziLLMOpenAI/LLMOpenAISession+Setup.swift	0.00%	47 Missing ⚠️
...s/SpeziLLMOpenAI/LLMOpenAISession+Generation.swift	0.00%	27 Missing ⚠️
Sources/SpeziLLMOpenAI/LLMOpenAIError.swift	0.00%	22 Missing ⚠️
...ng/LLMFunctionParameterWrapper+OptionalTypes.swift	86.56%	16 Missing ⚠️
...SpeziLLMOpenAI/Helpers/LLMOpenAIStreamResult.swift	0.00%	16 Missing ⚠️
...nCalling/LLMFunctionParameterSchemaCollector.swift	0.00%	11 Missing ⚠️
...lling/LLMFunctionParameterWrapper+ArrayTypes.swift	88.74%	8 Missing ⚠️
...tionCalling/LLMFunctionParameterWrapper+Enum.swift	85.72%	8 Missing ⚠️
...g/LLMFunctionParameterWrapper+PrimitiveTypes.swift	83.68%	8 Missing ⚠️
... and 4 more

Additional details and impacted files

@@            Coverage Diff             @@
##             main      #64      +/-   ##
==========================================
+ Coverage   38.52%   38.58%   +0.07%     
==========================================
  Files          65       65              
  Lines        2355     2517     +162     
==========================================
+ Hits          907      971      +64     
- Misses       1448     1546      +98

Files with missing lines	Coverage Δ
...penAI/Configuration/LLMOpenAIModelParameters.swift	`100.00% <100.00%> (ø)`
...iLLMOpenAI/Configuration/LLMOpenAIParameters.swift	`100.00% <ø> (ø)`
Sources/SpeziLLMOpenAI/Helpers/Chat+OpenAI.swift	`0.00% <ø> (ø)`
...I/Onboarding/LLMOpenAIAPITokenOnboardingStep.swift	`100.00% <ø> (ø)`
...enAI/Onboarding/LLMOpenAIModelOnboardingStep.swift	`97.88% <100.00%> (+0.10%)`	⬆️
.../FunctionCalling/LLMFunctionParameterWrapper.swift	`61.54% <50.00%> (+24.04%)`	⬆️
...ling/LLMFunctionParameterWrapper+CustomTypes.swift	`92.00% <91.31%> (-8.00%)`	⬇️
Sources/SpeziLLMOpenAI/LLMOpenAISession.swift	`22.86% <0.00%> (ø)`
...urces/SpeziLLMOpenAI/LLMOpenAIAuthMiddleware.swift	`0.00% <0.00%> (ø)`
...lling/LLMFunctionParameterWrapper+ArrayTypes.swift	`89.88% <88.74%> (-10.12%)`	⬇️
... and 9 more

... and 7 files with indirect coverage changes

Continue to review full report in Codecov by Sentry.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update fd9f1ca...42f9079. Read the comment docs.

PSchmiedmayer

Thank you for all the work here @paulhdk; very important to improve this setup and build on the OpenAPI specification!

It would be amazing to get a first insight from @philippzagar to get a good round of feedback.

Package.swift

PSchmiedmayer · 2024-10-15T14:14:17Z

Sources/SpeziLLMOpenAI/Configuration/LLMOpenAIModelParameters.swift

@@ -51,7 +50,7 @@ public struct LLMOpenAIModelParameters: Sendable {
    ///   - logitBias: Alters specific token's likelihood in completion.
    ///   - user: Unique identifier for the end-user, aiding in abuse monitoring.
    public init(
-        responseFormat: ChatQuery.ResponseFormat? = nil,
+        responseFormat: Components.Schemas.CreateChatCompletionRequest.response_formatPayload? = nil,


I am wondering if we should add compact type aliases for this?

I’ve added an LLMOpenAIRequestType alias. Does that work for you?

Should we also introduce an alias for Components.Schemas in general? This won’t make the types shorter, but something like LLMOpenAIGeneratedTypes could improve readability, maybe?

I think we can introduce well defined and named typealias for the specific types that we use in our API surface; we should see if we can make them compact and focus on them.

PSchmiedmayer · 2024-10-15T14:15:31Z

Sources/SpeziLLMOpenAI/FunctionCalling/LLMFunctionParameterArray.swift

+///                 "firstName": [
+///                     "type": "string",
+///                     "description": "The first name of the person")
+///                 ],


I am wondering if we can add a nicely typed type for this instead of a dictionary; it can always map to a dictionary under the hood. Would be cool to avoid loosing that type-safe element?

Previously, SpeziLLMOpenAI wrapped around the Swift types provided by the OpenAI package, which would then eventually be passed to the API.
With the OpenAI OpenAPI spec, such types aren't generated, but the JSON schemas are instead validated for correctness as they're being encoded in the OpenAPIObjectContainer type.

Introducing such wrapper types again would require precise alignment with the OpenAI, which would make it, I could imagine, harder to maintain over time.
I could imagine that’s one reason why the official OpenAI Python package, which is also generated from the OpenAI OpenAPI specification, does not offer wrapper types either, AFAICT.

What do you think?

I think adding an extension initializer/function that takes the well-typed arguments of one wants to use them would be beneficial and would avoid issues with string keys that are not correct or malformatted. Still allowing to pass in a dictionary might be an escape hatch that we can still provide. The OpenAPI surface is quite stable and if we use e.g. an enum for the type of the parameter can also have an other case with an associated string value.

I most definitely agree with @PSchmiedmayer here, I would follow the typical Swift paradigm and provide as much type safety as possible.
As mentioned by @PSchmiedmayer, I would implement well-typed inits / functions etc. that then map to the underlying String dictionary. And yes, an escape hatch that passes the raw dictionary might be beneficial!

Just to be clear and because I'm a little clueless about how to implement this easily: the only way I'm seeing here is to re-implement these two types from the MacPaw OpenAI package that SpeziLLM was using previously, and then reverting the changes around the initialisers accordingly.

SpeziLLM/Sources/SpeziLLMOpenAI/FunctionCalling/LLMFunctionParameterWrapper.swift

Lines 12 to 15 in 26b1e07

/// Alias of the OpenAI `JSONSchema/Property` type, describing properties within an object schema.

public typealias LLMFunctionParameterPropertySchema = ChatQuery.ChatCompletionToolParam.FunctionDefinition.FunctionParameters.Property

/// Alias of the OpenAI `JSONSchema/Item` type, describing array items within an array schema.

public typealias LLMFunctionParameterItemSchema = ChatQuery.ChatCompletionToolParam.FunctionDefinition.FunctionParameters.Property.Items

I was not able to find a definitive documentation for the fileds that the OpenAI API accepts here, including the ones that are currently support by SpeziLLM, e.g., minItems, maxItems, uniqueItems.

The function calling documentation mentions none of them: https://platform.openai.com/docs/guides/function-calling

What do you think?

Sources/SpeziLLMOpenAI/FunctionCalling/LLMFunctionParameterSchemaCollector.swift

Sources/SpeziLLMOpenAI/LLMOpenAIError.swift

Sources/SpeziLLMOpenAI/LLMOpenAISession.swift

PSchmiedmayer

Thank you for continuing to work on this @paulhdk!

I had a quick sync with @philippzagar and he will take a closer look at the PR to provide insights on the different changes; would be great to update the PR to the latest version of main to resolve the conflicts; I think after the feedback from @philippzagar we should be ready to get this merged 🚀

PSchmiedmayer · 2024-10-28T17:54:54Z

Sources/SpeziLLMOpenAI/LLMOpenAISession+Configuration.swift

+                .Input(body: .json(LLMOpenAIRequestType(
+                    messages: openAIContext,
+                    model: schema.parameters.modelType,
+                    frequency_penalty: schema.modelParameters.frequencyPenalty,
+                    logit_bias: schema.modelParameters.logitBias.additionalProperties.isEmpty ? nil : schema
+                        .modelParameters
+                        .logitBias,
+                    max_tokens: schema.modelParameters.maxOutputLength,
+                    n: schema.modelParameters.completionsPerOutput,
+                    presence_penalty: schema.modelParameters.presencePenalty,
+                    response_format: schema.modelParameters.responseFormat,
+                    seed: schema.modelParameters.seed,
+                    stop: LLMOpenAIRequestType.stopPayload.case2(schema.modelParameters.stopSequence),
+                    stream: true,
+                    temperature: schema.modelParameters.temperature,
+                    top_p: schema.modelParameters.topP,
+                    tools: functions.isEmpty ? nil : functions,
+                    user: schema.modelParameters.user
+                )))


Might be nice to format this similar to our other code bases; might be applicable to other parts as well:

Suggested change

.Input(body: .json(LLMOpenAIRequestType(

messages: openAIContext,

model: schema.parameters.modelType,

frequency_penalty: schema.modelParameters.frequencyPenalty,

logit_bias: schema.modelParameters.logitBias.additionalProperties.isEmpty ? nil : schema

.modelParameters

.logitBias,

max_tokens: schema.modelParameters.maxOutputLength,

n: schema.modelParameters.completionsPerOutput,

presence_penalty: schema.modelParameters.presencePenalty,

response_format: schema.modelParameters.responseFormat,

seed: schema.modelParameters.seed,

stop: LLMOpenAIRequestType.stopPayload.case2(schema.modelParameters.stopSequence),

stream: true,

temperature: schema.modelParameters.temperature,

top_p: schema.modelParameters.topP,

tools: functions.isEmpty ? nil : functions,

user: schema.modelParameters.user

)))

.Input(body:

.json(

LLMOpenAIRequestType(

messages: openAIContext,

model: schema.parameters.modelType,

frequency_penalty: schema.modelParameters.frequencyPenalty,

logit_bias: schema.modelParameters.logitBias.additionalProperties.isEmpty ? nil : schema

.modelParameters

.logitBias,

max_tokens: schema.modelParameters.maxOutputLength,

n: schema.modelParameters.completionsPerOutput,

presence_penalty: schema.modelParameters.presencePenalty,

response_format: schema.modelParameters.responseFormat,

seed: schema.modelParameters.seed,

stop: LLMOpenAIRequestType.stopPayload.case2(schema.modelParameters.stopSequence),

stream: true,

temperature: schema.modelParameters.temperature,

top_p: schema.modelParameters.topP,

tools: functions.isEmpty ? nil : functions,

user: schema.modelParameters.user

)

)

)

Agree with @PSchmiedmayer here!

Is this coding style being enforced in the other code bases?

I played around with some Swiftformat rules yesterday while trying to make it produce the example above. But I was unsuccessful and had to update it manually. Is there a better way to catch all the remaining examples in the PR?

philippzagar

Thanks for the great PR @paulhdk, it's great to move away from the OpenAI package! 🚀
Had some feedback on some parts of the PR, please also clean up the leftover compile errors in the testing code as well as possible linter issues.
Also, it would be great to get rid of some Swift warnings / deprecations that are tagged via the CI!

One more thing: Please add a small documentation (in the README and DocC) on how to (re-)generate the client (needed if the API changes at some point).

Sources/SpeziLLM/Models/LLMContextEntity.swift

Sources/SpeziLLMOpenAI/FunctionCalling/LLMFunctionParameter.swift

philippzagar · 2024-11-12T09:15:10Z

Sources/SpeziLLMOpenAI/FunctionCalling/LLMFunctionParameterArray.swift

+///                 "firstName": [
+///                     "type": "string",
+///                     "description": "The first name of the person")
+///                 ],


I most definitely agree with @PSchmiedmayer here, I would follow the typical Swift paradigm and provide as much type safety as possible.
As mentioned by @PSchmiedmayer, I would implement well-typed inits / functions etc. that then map to the underlying String dictionary. And yes, an escape hatch that passes the raw dictionary might be beneficial!

philippzagar · 2024-11-12T09:16:17Z

Sources/SpeziLLMOpenAI/FunctionCalling/LLMFunctionParameterSchemaCollector.swift

+                "required": requiredPropertyNames
+            ])
+        } catch {
+            logger.error("Error creating OpenAPIObjectContainer.")


Is a fallthrough error handeling really beneficial here?
To be fair, errors should be very rare here, only when the validated container cannot be created

fatalError(), then? Or can you think of a nicer way to handle this?

Sources/SpeziLLMOpenAI/FunctionCalling/LLMFunctionParameterWrapper+ArrayTypes.swift

Sources/SpeziLLMOpenAI/openapi-generator-config.yaml

Tests/SpeziLLMTests/LLMOpenAIParameterTests+Array.swift

philippzagar · 2024-11-12T09:39:33Z

Tests/SpeziLLMTests/LLMOpenAIParameterTests+Array.swift

-        XCTAssertEqual(schemaArrayBool.schema.items?.type, .boolean)
-        XCTAssertEqual(schemaArrayBool.schema.items?.const, "true")
+        schema = schemaArrayBool.schema.value
+        items = schema["items"] as? [String: Any]


It's a bit ugly that we loose all underlying type information of the respective properties of the schema here.. Mabye some computed properties on the schema with a specific type would make sense?

I agree. The problem is that the underlying type for the schema is the generated OpenAPIRuntime.OpenAPIObjectContainer type, which boils down to a [String: (any Sendable)?] type and is what we get back from the API / generated calls.

Which schema are you referring to here? I don't think I'm following where you would want that computed property to be.

philippzagar · 2024-11-12T09:40:15Z

Tests/SpeziLLMTests/LLMOpenAIParameterTests+CustomTypes.swift

+                ])
+            } catch {
+                print("unable to initialse schema in LLMOpenAIParameterCustomTypesTets")
+                return .init()


What happens down the line if the validation fails and an empty schema is created?

Shouldn't something like this do the trick?

diff --git a/Tests/SpeziLLMTests/LLMOpenAIParameterTests+CustomTypes.swift b/Tests/SpeziLLMTests/LLMOpenAIParameterTests+CustomTypes.swift index ca262bd..3bbce43 100644 --- a/Tests/SpeziLLMTests/LLMOpenAIParameterTests+CustomTypes.swift +++ b/Tests/SpeziLLMTests/LLMOpenAIParameterTests+CustomTypes.swift @@ -11,6 +11,10 @@ import XCTest final class LLMOpenAIParameterCustomTypesTests: XCTestCase { + override func setUp() { + continueAfterFailure = false + } + struct CustomType: LLMFunctionParameterArrayElement, Encodable, Equatable { static var itemSchema: LLMFunctionParameterItemSchema = { do { @@ -28,8 +32,7 @@ final class LLMOpenAIParameterCustomTypesTests: XCTestCase { ] ]) } catch { - print("unable to initialse schema in LLMOpenAIParameterCustomTypesTets") - return .init() + XCTFail("Unable to initialse schema in LLMOpenAIParameterCustomTypesTets") } }()

The compiler is still expecting a return after the XCTFail(). Do you have another suggestion?

Tests/UITests/TestApp/LLMOpenAI/Functions/LLMOpenAIFunctionPerson.swift

PSchmiedmayer · 2024-12-05T23:01:56Z

@paulhdk A short ping on the state of this PR; would be amazing to get it merged before we tag a new 0.X version tag in combination with the MLX changes 🚀

paulhdk · 2024-12-06T09:17:51Z

First of all, thank you @philippzagar for the review!

@paulhdk A short ping on the state of this PR; would be amazing to get it merged before we tag a new 0.X version tag in combination with the MLX changes 🚀

I"m OOF until the end of the week. Will be able to address all the feedback here with full force starting next week Monday.

I'm sorry for letting this sit so long, thaz wasn't my plan either ..

PSchmiedmayer · 2024-12-09T00:52:02Z

Thank you @paulhdk! 🚀

paulhdk · 2024-12-16T10:30:13Z

StanfordSpezi/SpeziAccount#82, StanfordSpezi/SpeziViews#49

code

endpoint This enables swift-openapi-generator to generate streamed responses. See: openai/openai-openapi#311

See: apple/swift-openapi-runtime#115

…olCall`

Modifier was mistakenly removed in 99e0e6d

Reverts: 239aff5

philippzagar · 2024-12-18T10:22:57Z

@paulhdk Great to see tons of progress on the PR! 🥳
Let me know as soon as you're ready for another review, would be great to get all of these changes in soon! 🚀

philippzagar · 2024-12-21T11:54:05Z

Hey @paulhdk,
just following up here: Can you give us an estimate when you will be able to finish the PR? I guess there shouldn't be too much missing?
It would be great to get all of these changes in soon, also in order to unblock other related issues / PRs 🚀

paulhdk · 2024-12-21T12:28:37Z

Hey @paulhdk, just following up here: Can you give us an estimate when you will be able to finish the PR? I guess there shouldn't be too much missing? It would be great to get all of these changes in soon, also in order to unblock other related issues / PRs 🚀

I've been sick all week; today is the first day where I feel ready to do some work.
My personal goal would be to address all the review comments before Christmas.

The wrapper types suggested by you and @PSchmiedmayer are still missing and will require some thinking on my part. Doing my best to get all of this done ASAP.

…eterWrapper.swift

This reverts commit 1a6cc12.

Co-authored-by: Paul Schmiedmayer <[email protected]>

paulhdk · 2024-12-22T17:51:04Z

@paulhdk Great to see tons of progress on the PR! 🥳 Let me know as soon as you're ready for another review, would be great to get all of these changes in soon! 🚀

@philippzagar I've left questions for the remaining comments above where I need your help. Thank you for taking another look!

paulhdk requested a review from PSchmiedmayer August 27, 2024 10:09

PSchmiedmayer removed their request for review August 30, 2024 18:51

PSchmiedmayer assigned paulhdk Aug 30, 2024

PSchmiedmayer added the enhancement New feature or request label Aug 30, 2024

paulhdk force-pushed the generate-api-calls branch 2 times, most recently from d5a4eb3 to 3ded304 Compare September 13, 2024 16:33

paulhdk marked this pull request as ready for review September 13, 2024 17:49

paulhdk force-pushed the generate-api-calls branch 3 times, most recently from 48f3c0b to 974449b Compare October 4, 2024 21:20

PSchmiedmayer requested a review from philippzagar October 15, 2024 14:11

PSchmiedmayer reviewed Oct 15, 2024

View reviewed changes

paulhdk changed the title ~~SpeziLLMOpenAI: Repalce MacPaw/OpenAI With Generated API Calls~~ S Oct 24, 2024

paulhdk changed the title S SpeziLLMOpenAI: Repalce MacPaw/OpenAI With Generated API Calls Oct 24, 2024

paulhdk force-pushed the generate-api-calls branch from bdd7127 to 1f52a7f Compare October 28, 2024 08:54

PSchmiedmayer reviewed Nov 5, 2024

View reviewed changes

philippzagar requested changes Nov 12, 2024

View reviewed changes

philippzagar mentioned this pull request Nov 13, 2024

Maintenance: iOS 18.1 / Swift 6 compatibility, Fix Deprecations, Rudimentary Fog Node CI testing, Bump Fog Node JS Dependencies #74

Merged

1 task

vishnuravi changed the title ~~SpeziLLMOpenAI: Repalce MacPaw/OpenAI With Generated API Calls~~ SpeziLLMOpenAI: Replace MacPaw/OpenAI With Generated API Calls Nov 22, 2024

philippzagar mentioned this pull request Dec 12, 2024

Fix Download and Mocking LLMLocalSession #81

Merged

1 task

paulhdk force-pushed the generate-api-calls branch from 4a70bb7 to 0c5505d Compare December 16, 2024 10:37

paulhdk added 3 commits December 16, 2024 13:16

SpeziLLMOpenAI: openapi-generator infrastructure

0cfbf29

SpeziLLMOpenAI: set "public" as the default access modifier generated

d340a10

code

SpeziLLMOpenAI: set a text/event-stream schema for the chat/completions

ce640b4

endpoint This enables swift-openapi-generator to generate streamed responses. See: openai/openai-openapi#311

paulhdk added 16 commits December 16, 2024 13:20

Remove redundant closing brackets

b1b95b5

Swiftlint

95c2979

Fix tests

0a789e6

Remove OpenAI dependency from SpeziLLMOpenAI in Package.swift

0ad1776

Rename local var in LLMFunctionParameterSchemaCollector.swift

48c3aab

Introduce LLMOpenAIRequestType type alias

6471784

LLMOpenAI: refactor generation call to OpenAI API

91b3f8d

See: apple/swift-openapi-runtime#115

LLMOPenAI: Remove redundant OpenAI package imports

e39d202

SpeziLLM: remove unnecessary type property in `LLMContextEntity::To…

3a994ee

…olCall`

SpeziLLMOpenAI: add public modifier to convenience init

7fea2b4

Modifier was mistakenly removed in 99e0e6d

SpeziLLMOpenAI: replace use of _LLMFunctionParameterWrapper

fd524b0

SpeziLLMOpenAI: Replace deprecated Servers.server1()

80e133f

LLMOpenAIParameterTests: don't initialise modelType's value1

5a19c35

SpeziLLMOpenAI: remove trailing whitespace

13b7bd2

SpeziLLMTests: set LLMOpenAISchema's value1 correctly

16644d0

Reverts: 239aff5

fixup! SpeziLLMOpenAI: replace use of _LLMFunctionParameterWrapper

3ded7a0

paulhdk force-pushed the generate-api-calls branch from 0e1eb92 to 3ded7a0 Compare December 16, 2024 13:09

Xcode: remove dangling references from project.pbxproj

2a5269b

This was referenced Dec 18, 2024

Complete Concurrency Checking #54

Open

Complete automated testing for all inference layers #84

Open

jdisho mentioned this pull request Dec 20, 2024

Swift 6 Complete Concurrency Checking #85

Draft

1 task

paulhdk and others added 5 commits December 21, 2024 14:30

SpeziLLMOpenAI: update swiftlint:disable syntax in LLMFunctionParam…

271b255

…eterWrapper.swift

SpeziLLMOpenAI: add docs for AuthMiddleware

55897f8

SpeziLLMOpenAI: Move global logger into local scope

10fcb63

This reverts commit 1a6cc12.

Update Sources/SpeziLLMOpenAI/LLMOpenAISession+Configuration.swift

37b2b60

Co-authored-by: Paul Schmiedmayer <[email protected]>

swiftlint

42f9079

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

SpeziLLMOpenAI: Replace MacPaw/OpenAI With Generated API Calls #64

SpeziLLMOpenAI: Replace MacPaw/OpenAI With Generated API Calls #64

paulhdk commented Aug 27, 2024 •

edited by vishnuravi

Loading

codecov bot commented Oct 4, 2024 •

edited

Loading

PSchmiedmayer left a comment

PSchmiedmayer Oct 15, 2024

paulhdk Oct 28, 2024

PSchmiedmayer Nov 6, 2024

PSchmiedmayer Oct 15, 2024

paulhdk Nov 5, 2024

PSchmiedmayer Nov 6, 2024

philippzagar Nov 12, 2024

paulhdk Dec 22, 2024

PSchmiedmayer left a comment

PSchmiedmayer Oct 28, 2024

philippzagar Nov 12, 2024

paulhdk Dec 22, 2024

philippzagar left a comment

philippzagar Nov 12, 2024

philippzagar Nov 12, 2024

paulhdk Dec 21, 2024

philippzagar Nov 12, 2024

paulhdk Dec 22, 2024

philippzagar Nov 12, 2024

paulhdk Dec 21, 2024 •

edited

Loading

PSchmiedmayer commented Dec 5, 2024

paulhdk commented Dec 6, 2024

PSchmiedmayer commented Dec 9, 2024

paulhdk commented Dec 16, 2024

philippzagar commented Dec 18, 2024

philippzagar commented Dec 21, 2024

paulhdk commented Dec 21, 2024

paulhdk commented Dec 22, 2024

	/// Alias of the OpenAI `JSONSchema/Property` type, describing properties within an object schema.
	public typealias LLMFunctionParameterPropertySchema = ChatQuery.ChatCompletionToolParam.FunctionDefinition.FunctionParameters.Property
	/// Alias of the OpenAI `JSONSchema/Item` type, describing array items within an array schema.
	public typealias LLMFunctionParameterItemSchema = ChatQuery.ChatCompletionToolParam.FunctionDefinition.FunctionParameters.Property.Items

SpeziLLMOpenAI: Replace MacPaw/OpenAI With Generated API Calls #64

Are you sure you want to change the base?

SpeziLLMOpenAI: Replace MacPaw/OpenAI With Generated API Calls #64

Conversation

paulhdk commented Aug 27, 2024 • edited by vishnuravi Loading

SpeziLLMOpenAI: Replace MacPaw/OpenAI With Generated API Calls

♻️ Current situation & Problem

Current Issues

⚙️ Release Notes

📚 Documentation

✅ Testing

📝 Code of Conduct & Contributing Guidelines

codecov bot commented Oct 4, 2024 • edited Loading

Codecov Report

PSchmiedmayer left a comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

PSchmiedmayer left a comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

philippzagar left a comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

paulhdk Dec 21, 2024 • edited Loading

Choose a reason for hiding this comment

PSchmiedmayer commented Dec 5, 2024

paulhdk commented Dec 6, 2024

PSchmiedmayer commented Dec 9, 2024

paulhdk commented Dec 16, 2024

philippzagar commented Dec 18, 2024

philippzagar commented Dec 21, 2024

paulhdk commented Dec 21, 2024

paulhdk commented Dec 22, 2024

paulhdk commented Aug 27, 2024 •

edited by vishnuravi

Loading

codecov bot commented Oct 4, 2024 •

edited

Loading

paulhdk Dec 21, 2024 •

edited

Loading