Upgrade SDK to support v0.1.2

README.md

@@ -8,7 +8,7 @@ Features:
 - Remote Inferencing: Perform inferencing tasks remotely with Llama models hosted on a remote connection (or serverless localhost).
 - Simple Integration: With easy-to-use APIs, a developer can quickly integrate Llama Stack in their Android app. The difference with local vs remote inferencing is also minimal.
 
-Latest Release Notes: [v0.1.0](https://github.com/meta-llama/llama-stack-client-kotlin/releases/tag/v0.1.0) 
+Latest Release Notes: [v0.1.2](https://github.com/meta-llama/llama-stack-client-kotlin/releases/tag/v0.1.2) 
 
 *Tagged releases are stable versions of the project. While we strive to maintain a stable main branch, it's not guaranteed to be free of bugs or issues.*
 
@@ -24,7 +24,7 @@ The key files in the app are `ExampleLlamaStackLocalInference.kt`, `ExampleLlama
 Add the following dependency in your `build.gradle.kts` file:
 ```
 dependencies {
- implementation("com.llama.llamastack:llama-stack-client-kotlin:0.1.0")
+ implementation("com.llama.llamastack:llama-stack-client-kotlin:0.1.2")
 }
 ```
 This will download jar files in your gradle cache in a directory like `~/.gradle/caches/modules-2/files-2.1/com.llama.llamastack/` 
@@ -60,7 +60,7 @@ Start a Llama Stack server on localhost. Here is an example of how you can do th
 ```
 conda create -n stack-fireworks python=3.10 
 conda activate stack-fireworks
-pip install llama-stack=0.1.0
+pip install llama-stack=0.1.2
 llama stack build --template fireworks --image-type conda
 export FIREWORKS_API_KEY=<SOME_KEY>
 llama stack run /Users/<your_username>/.llama/distributions/llamastack-fireworks/fireworks-run.yaml --port=5050
@@ -99,7 +99,7 @@ client = LlamaStackClientLocalClient
 client = LlamaStackClientOkHttpClient
                 .builder()
                 .baseUrl(remoteURL)
-                .headers(mapOf("x-llamastack-client-version" to listOf("0.1.0")))
+                .headers(mapOf("x-llamastack-client-version" to listOf("0.1.2")))
                 .build()
 ```
 </td>
@@ -258,7 +258,7 @@ val result = client!!.inference().chatCompletion(
         )
 
 // response contains string with response from model
-var response = result.asChatCompletionResponse().completionMessage().content().string();
+var response = result.completionMessage().content().string();
 ```
 
 [Remote only] For inference with a streaming response:
@@ -286,7 +286,7 @@ The purpose of this section is to share more details with users that would like
 ### Prerequisite
 
 You must complete the following steps:
-1. Clone the repo (`git clone https://github.com/meta-llama/llama-stack-client-kotlin.git -b release/0.1.0`)
+1. Clone the repo (`git clone https://github.com/meta-llama/llama-stack-client-kotlin.git -b release/0.1.2`)
 2. Port the appropriate ExecuTorch libraries over into your Llama Stack Kotlin library environment.
 ```
 cd llama-stack-client-kotlin-client-local
@@ -309,7 +309,7 @@ Copy the .jar files over to the lib directory in your Android app. At the same t
 ### Additional Options for Local Inferencing
 Currently we provide additional properties support with local inferencing. In order to get the tokens/sec metric for each inference call, add the following code in your Android app after you run your chatCompletion inference function. The Reference app has this implementation as well:
 ```
-var tps = (result.asChatCompletionResponse()._additionalProperties()["tps"] as JsonNumber).value as Float
+var tps = (result._additionalProperties()["tps"] as JsonNumber).value as Float
 ```
 We will be adding more properties in the future.
 

build.gradle.kts

@@ -4,5 +4,5 @@ plugins {
 
 allprojects {
     group = "com.llama.llamastack"
-    version = "0.1.0"
+    version = "0.1.2"
 }

llama-stack-client-kotlin-client-local/src/main/kotlin/com/llama/llamastack/client/local/InferenceServiceLocalImpl.kt

@@ -8,11 +8,12 @@ import com.llama.llamastack.client.local.util.buildInferenceChatCompletionRespon
 import com.llama.llamastack.client.local.util.buildLastInferenceChatCompletionResponsesFromStream
 import com.llama.llamastack.core.RequestOptions
 import com.llama.llamastack.core.http.StreamResponse
+import com.llama.llamastack.models.ChatCompletionResponse
+import com.llama.llamastack.models.ChatCompletionResponseStreamChunk
+import com.llama.llamastack.models.CompletionResponse
 import com.llama.llamastack.models.EmbeddingsResponse
 import com.llama.llamastack.models.InferenceChatCompletionParams
-import com.llama.llamastack.models.InferenceChatCompletionResponse
 import com.llama.llamastack.models.InferenceCompletionParams
-import com.llama.llamastack.models.InferenceCompletionResponse
 import com.llama.llamastack.models.InferenceEmbeddingsParams
 import com.llama.llamastack.services.blocking.InferenceService
 import org.pytorch.executorch.LlamaCallback
@@ -31,7 +32,7 @@ constructor(
     private var sequenceLengthKey: String = "seq_len"
     private var stopToken: String = ""
 
-    private val streamingResponseList = mutableListOf<InferenceChatCompletionResponse>()
+    private val streamingResponseList = mutableListOf<ChatCompletionResponseStreamChunk>()
     private var isStreaming: Boolean = false
 
     private val waitTime: Long = 100
@@ -69,7 +70,7 @@ constructor(
     override fun chatCompletion(
         params: InferenceChatCompletionParams,
         requestOptions: RequestOptions
-    ): InferenceChatCompletionResponse {
+    ): ChatCompletionResponse {
         isStreaming = false
         clearElements()
         val mModule = clientOptions.llamaModule
@@ -99,8 +100,8 @@ constructor(
     }
 
     private val streamResponse =
-        object : StreamResponse<InferenceChatCompletionResponse> {
-            override fun asSequence(): Sequence<InferenceChatCompletionResponse> {
+        object : StreamResponse<ChatCompletionResponseStreamChunk> {
+            override fun asSequence(): Sequence<ChatCompletionResponseStreamChunk> {
                 return sequence {
                     while (!onResultComplete || streamingResponseList.isNotEmpty()) {
                         if (streamingResponseList.isNotEmpty()) {
@@ -132,7 +133,7 @@ constructor(
     override fun chatCompletionStreaming(
         params: InferenceChatCompletionParams,
         requestOptions: RequestOptions
-    ): StreamResponse<InferenceChatCompletionResponse> {
+    ): StreamResponse<ChatCompletionResponseStreamChunk> {
         isStreaming = true
         streamingResponseList.clear()
         resultMessage = ""
@@ -156,14 +157,14 @@ constructor(
     override fun completion(
         params: InferenceCompletionParams,
         requestOptions: RequestOptions
-    ): InferenceCompletionResponse {
+    ): CompletionResponse {
         TODO("Not yet implemented")
     }
 
     override fun completionStreaming(
         params: InferenceCompletionParams,
         requestOptions: RequestOptions
-    ): StreamResponse<InferenceCompletionResponse> {
+    ): StreamResponse<CompletionResponse> {
         TODO("Not yet implemented")
     }
 

llama-stack-client-kotlin-client-local/src/main/kotlin/com/llama/llamastack/client/local/LlamaStackClientClientLocalImpl.kt

@@ -60,6 +60,10 @@ constructor(
         TODO("Not yet implemented")
     }
 
+    override fun close() {
+        TODO("Not yet implemented")
+    }
+
     override fun agents(): AgentService {
         TODO("Not yet implemented")
     }

llama-stack-client-kotlin-client-local/src/main/kotlin/com/llama/llamastack/client/local/util/ResponseUtil.kt

@@ -1,17 +1,19 @@
 package com.llama.llamastack.client.local.util
 
 import com.llama.llamastack.core.JsonValue
+import com.llama.llamastack.models.ChatCompletionResponse
+import com.llama.llamastack.models.ChatCompletionResponseStreamChunk
 import com.llama.llamastack.models.CompletionMessage
 import com.llama.llamastack.models.ContentDelta
-import com.llama.llamastack.models.InferenceChatCompletionResponse
 import com.llama.llamastack.models.InterleavedContent
+import com.llama.llamastack.models.ToolCall
 import java.util.UUID
 
 fun buildInferenceChatCompletionResponse(
     response: String,
     stats: Float,
     stopToken: String
-): InferenceChatCompletionResponse {
+): ChatCompletionResponse {
     // check for prefix [ and suffix ] if so then tool call.
     // parse for "toolName", "additionalProperties"
     var completionMessage =
@@ -30,41 +32,33 @@ fun buildInferenceChatCompletionResponse(
                 .build()
         }
 
-    var inferenceChatCompletionResponse =
-        InferenceChatCompletionResponse.ofChatCompletionResponse(
-            InferenceChatCompletionResponse.ChatCompletionResponse.builder()
-                .completionMessage(completionMessage)
-                .putAdditionalProperty("tps", JsonValue.from(stats))
-                .build()
-        )
+    val inferenceChatCompletionResponse =
+        ChatCompletionResponse.builder()
+            .completionMessage(completionMessage)
+            .putAdditionalProperty("tps", JsonValue.from(stats))
+            .build()
     return inferenceChatCompletionResponse
 }
 
 fun buildInferenceChatCompletionResponseFromStream(
     response: String,
-): InferenceChatCompletionResponse {
-    return InferenceChatCompletionResponse.ofChatCompletionResponseStreamChunk(
-        InferenceChatCompletionResponse.ChatCompletionResponseStreamChunk.builder()
-            .event(
-                InferenceChatCompletionResponse.ChatCompletionResponseStreamChunk.Event.builder()
-                    .delta(ContentDelta.TextDelta.builder().text(response).build())
-                    .eventType(
-                        InferenceChatCompletionResponse.ChatCompletionResponseStreamChunk.Event
-                            .EventType
-                            .PROGRESS
-                    )
-                    .build()
-            )
-            .build()
-    )
+): ChatCompletionResponseStreamChunk {
+    return ChatCompletionResponseStreamChunk.builder()
+        .event(
+            ChatCompletionResponseStreamChunk.Event.builder()
+                .delta(ContentDelta.TextDelta.builder().text(response).build())
+                .eventType(ChatCompletionResponseStreamChunk.Event.EventType.PROGRESS)
+                .build()
+        )
+        .build()
 }
 
 fun buildLastInferenceChatCompletionResponsesFromStream(
     resultMessage: String,
     stats: Float,
     stopToken: String,
-): List<InferenceChatCompletionResponse> {
-    val listOfResponses: MutableList<InferenceChatCompletionResponse> = mutableListOf()
+): List<ChatCompletionResponseStreamChunk> {
+    val listOfResponses: MutableList<ChatCompletionResponseStreamChunk> = mutableListOf()
     if (isResponseAToolCall(resultMessage)) {
         val toolCalls = createCustomToolCalls(resultMessage)
         for (toolCall in toolCalls) {
@@ -83,73 +77,51 @@ fun buildLastInferenceChatCompletionResponsesFromStream(
 }
 
 fun buildInferenceChatCompletionResponseForCustomToolCallStream(
-    toolCall: CompletionMessage.ToolCall,
+    toolCall: ToolCall,
     stopToken: String,
     stats: Float
-): InferenceChatCompletionResponse {
+): ChatCompletionResponseStreamChunk {
     val delta =
         ContentDelta.ToolCallDelta.builder()
             .parseStatus(ContentDelta.ToolCallDelta.ParseStatus.SUCCEEDED)
-            .toolCall(
-                ContentDelta.ToolCallDelta.ToolCall.InnerToolCall.builder()
-                    .toolName(toolCall.toolName().toString())
-                    .arguments(
-                        ContentDelta.ToolCallDelta.ToolCall.InnerToolCall.Arguments.builder()
-                            .additionalProperties(toolCall.arguments()._additionalProperties())
-                            .build()
-                    )
-                    .callId(toolCall.callId())
-                    .build()
-            )
+            .toolCall(toolCall)
             .build()
-    return InferenceChatCompletionResponse.ofChatCompletionResponseStreamChunk(
-        InferenceChatCompletionResponse.ChatCompletionResponseStreamChunk.builder()
-            .event(
-                InferenceChatCompletionResponse.ChatCompletionResponseStreamChunk.Event.builder()
-                    .delta(delta)
-                    .stopReason(mapStopTokenToReasonForStream(stopToken))
-                    .eventType(
-                        InferenceChatCompletionResponse.ChatCompletionResponseStreamChunk.Event
-                            .EventType
-                            .PROGRESS
-                    )
-                    .build()
-            )
-            .putAdditionalProperty("tps", JsonValue.from(stats))
-            .build()
-    )
+    return ChatCompletionResponseStreamChunk.builder()
+        .event(
+            ChatCompletionResponseStreamChunk.Event.builder()
+                .delta(delta)
+                .stopReason(mapStopTokenToReasonForStream(stopToken))
+                .eventType(ChatCompletionResponseStreamChunk.Event.EventType.PROGRESS)
+                .build()
+        )
+        .putAdditionalProperty("tps", JsonValue.from(stats))
+        .build()
 }
 
 fun buildInferenceChatCompletionResponseForStringStream(
     str: String,
     stopToken: String,
     stats: Float
-): InferenceChatCompletionResponse {
+): ChatCompletionResponseStreamChunk {
 
-    return InferenceChatCompletionResponse.ofChatCompletionResponseStreamChunk(
-        InferenceChatCompletionResponse.ChatCompletionResponseStreamChunk.builder()
-            .event(
-                InferenceChatCompletionResponse.ChatCompletionResponseStreamChunk.Event.builder()
-                    .delta(ContentDelta.TextDelta.builder().text(str).build())
-                    .stopReason(mapStopTokenToReasonForStream(stopToken))
-                    .eventType(
-                        InferenceChatCompletionResponse.ChatCompletionResponseStreamChunk.Event
-                            .EventType
-                            .PROGRESS
-                    )
-                    .putAdditionalProperty("tps", JsonValue.from(stats))
-                    .build()
-            )
-            .build()
-    )
+    return ChatCompletionResponseStreamChunk.builder()
+        .event(
+            ChatCompletionResponseStreamChunk.Event.builder()
+                .delta(ContentDelta.TextDelta.builder().text(str).build())
+                .stopReason(mapStopTokenToReasonForStream(stopToken))
+                .eventType(ChatCompletionResponseStreamChunk.Event.EventType.PROGRESS)
+                .putAdditionalProperty("tps", JsonValue.from(stats))
+                .build()
+        )
+        .build()
 }
 
 fun isResponseAToolCall(response: String): Boolean {
     return response.startsWith("[") && response.endsWith("]")
 }
 
-fun createCustomToolCalls(response: String): List<CompletionMessage.ToolCall> {
-    val toolCalls: MutableList<CompletionMessage.ToolCall> = mutableListOf()
+fun createCustomToolCalls(response: String): List<ToolCall> {
+    val toolCalls: MutableList<ToolCall> = mutableListOf()
 
     val splitsResponse = response.split("),")
     for (split in splitsResponse) {
@@ -170,13 +142,9 @@ fun createCustomToolCalls(response: String): List<CompletionMessage.ToolCall> {
             }
         }
         toolCalls.add(
-            CompletionMessage.ToolCall.builder()
-                .toolName(CompletionMessage.ToolCall.ToolName.of(toolName))
-                .arguments(
-                    CompletionMessage.ToolCall.Arguments.builder()
-                        .additionalProperties(paramsJson)
-                        .build()
-                )
+            ToolCall.builder()
+                .toolName(toolName)
+                .arguments(ToolCall.Arguments.builder().additionalProperties(paramsJson).build())
                 .callId(UUID.randomUUID().toString())
                 .build()
         )
@@ -194,15 +162,9 @@ fun mapStopTokenToReason(stopToken: String): CompletionMessage.StopReason =
 
 fun mapStopTokenToReasonForStream(
     stopToken: String
-): InferenceChatCompletionResponse.ChatCompletionResponseStreamChunk.Event.StopReason =
+): ChatCompletionResponseStreamChunk.Event.StopReason =
     when (stopToken) {
-        "<|eot_id|>" ->
-            InferenceChatCompletionResponse.ChatCompletionResponseStreamChunk.Event.StopReason
-                .END_OF_TURN
-        "<|eom_id|>" ->
-            InferenceChatCompletionResponse.ChatCompletionResponseStreamChunk.Event.StopReason
-                .END_OF_MESSAGE
-        else ->
-            InferenceChatCompletionResponse.ChatCompletionResponseStreamChunk.Event.StopReason
-                .OUT_OF_TOKENS
+        "<|eot_id|>" -> ChatCompletionResponseStreamChunk.Event.StopReason.END_OF_TURN
+        "<|eom_id|>" -> ChatCompletionResponseStreamChunk.Event.StopReason.END_OF_MESSAGE
+        else -> ChatCompletionResponseStreamChunk.Event.StopReason.OUT_OF_TOKENS
     }

llama-stack-client-kotlin-client-okhttp/src/main/kotlin/com/llama/llamastack/client/okhttp/LlamaStackClientOkHttpClient.kt

@@ -21,7 +21,8 @@ class LlamaStackClientOkHttpClient private constructor() {
         fun fromEnv(): LlamaStackClientClient = builder().fromEnv().build()
     }
 
-    class Builder {
+    /** A builder for [LlamaStackClientOkHttpClient]. */
+    class Builder internal constructor() {
 
         private var clientOptions: ClientOptions.Builder = ClientOptions.builder()
         private var baseUrl: String = ClientOptions.PRODUCTION_URL
@@ -128,6 +129,8 @@ class LlamaStackClientOkHttpClient private constructor() {
             clientOptions.responseValidation(responseValidation)
         }
 
+        fun apiKey(apiKey: String?) = apply { clientOptions.apiKey(apiKey) }
+
         fun fromEnv() = apply { clientOptions.fromEnv() }
 
         fun build(): LlamaStackClientClient =