Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@

import static org.elasticsearch.xpack.inference.InferencePlugin.UTILITY_THREAD_POOL_NAME;

abstract class BaseRequestManager implements RequestManager {
public abstract class BaseRequestManager implements RequestManager {
private final ThreadPool threadPool;
private final String inferenceEntityId;
// It's possible that two inference endpoints have the same information defining the group but have different
Expand All @@ -24,7 +24,7 @@ abstract class BaseRequestManager implements RequestManager {
private final EndpointGrouping endpointGrouping;
private final RateLimitSettings rateLimitSettings;

BaseRequestManager(ThreadPool threadPool, String inferenceEntityId, Object rateLimitGroup, RateLimitSettings rateLimitSettings) {
public BaseRequestManager(ThreadPool threadPool, String inferenceEntityId, Object rateLimitGroup, RateLimitSettings rateLimitSettings) {
this.threadPool = Objects.requireNonNull(threadPool);
this.inferenceEntityId = Objects.requireNonNull(inferenceEntityId);

Expand All @@ -33,7 +33,7 @@ abstract class BaseRequestManager implements RequestManager {
this.rateLimitSettings = rateLimitSettings;
}

BaseRequestManager(ThreadPool threadPool, RateLimitGroupingModel rateLimitGroupingModel) {
public BaseRequestManager(ThreadPool threadPool, RateLimitGroupingModel rateLimitGroupingModel) {
this.threadPool = Objects.requireNonNull(threadPool);
Objects.requireNonNull(rateLimitGroupingModel);

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@

import java.util.function.Supplier;

record ExecutableInferenceRequest(
public record ExecutableInferenceRequest(
RequestSender requestSender,
Logger logger,
Request request,
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -55,7 +55,7 @@
* attempting to execute a task (aka waiting for the connection manager to lease a connection). See
* {@link org.apache.http.client.config.RequestConfig.Builder#setConnectionRequestTimeout} for more info.
*/
class RequestExecutorService implements RequestExecutor {
public class RequestExecutorService implements RequestExecutor {

/**
* Provides dependency injection mainly for testing
Expand Down Expand Up @@ -123,7 +123,7 @@ interface RateLimiterCreator {
private final AtomicReference<Scheduler.Cancellable> cancellableCleanupTask = new AtomicReference<>();
private final AtomicBoolean started = new AtomicBoolean(false);

RequestExecutorService(
public RequestExecutorService(
ThreadPool threadPool,
@Nullable CountDownLatch startupLatch,
RequestExecutorServiceSettings settings,
Expand All @@ -141,7 +141,7 @@ interface RateLimiterCreator {
);
}

RequestExecutorService(
public RequestExecutorService(
ThreadPool threadPool,
AdjustableCapacityBlockingQueue.QueueCreator<RejectableTask> queueCreator,
@Nullable CountDownLatch startupLatch,
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
* 2.0.
*/

package org.elasticsearch.xpack.inference.external.http.sender;
package org.elasticsearch.xpack.inference.services.alibabacloudsearch;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
Expand All @@ -14,10 +14,11 @@
import org.elasticsearch.threadpool.ThreadPool;
import org.elasticsearch.xpack.inference.external.http.retry.RequestSender;
import org.elasticsearch.xpack.inference.external.http.retry.ResponseHandler;
import org.elasticsearch.xpack.inference.external.http.sender.ChatCompletionInput;
import org.elasticsearch.xpack.inference.external.http.sender.ExecutableInferenceRequest;
import org.elasticsearch.xpack.inference.external.http.sender.InferenceInputs;
import org.elasticsearch.xpack.inference.external.request.alibabacloudsearch.completion.AlibabaCloudSearchCompletionRequest;
import org.elasticsearch.xpack.inference.external.response.alibabacloudsearch.AlibabaCloudSearchCompletionResponseEntity;
import org.elasticsearch.xpack.inference.services.alibabacloudsearch.AlibabaCloudSearchAccount;
import org.elasticsearch.xpack.inference.services.alibabacloudsearch.AlibabaCloudSearchResponseHandler;
import org.elasticsearch.xpack.inference.services.alibabacloudsearch.completion.AlibabaCloudSearchCompletionModel;

import java.util.List;
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
* 2.0.
*/

package org.elasticsearch.xpack.inference.external.http.sender;
package org.elasticsearch.xpack.inference.services.alibabacloudsearch;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
Expand All @@ -15,10 +15,11 @@
import org.elasticsearch.threadpool.ThreadPool;
import org.elasticsearch.xpack.inference.external.http.retry.RequestSender;
import org.elasticsearch.xpack.inference.external.http.retry.ResponseHandler;
import org.elasticsearch.xpack.inference.external.http.sender.EmbeddingsInput;
import org.elasticsearch.xpack.inference.external.http.sender.ExecutableInferenceRequest;
import org.elasticsearch.xpack.inference.external.http.sender.InferenceInputs;
import org.elasticsearch.xpack.inference.external.request.alibabacloudsearch.AlibabaCloudSearchEmbeddingsRequest;
import org.elasticsearch.xpack.inference.external.response.alibabacloudsearch.AlibabaCloudSearchEmbeddingsResponseEntity;
import org.elasticsearch.xpack.inference.services.alibabacloudsearch.AlibabaCloudSearchAccount;
import org.elasticsearch.xpack.inference.services.alibabacloudsearch.AlibabaCloudSearchResponseHandler;
import org.elasticsearch.xpack.inference.services.alibabacloudsearch.embeddings.AlibabaCloudSearchEmbeddingsModel;

import java.util.List;
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -5,10 +5,10 @@
* 2.0.
*/

package org.elasticsearch.xpack.inference.external.http.sender;
package org.elasticsearch.xpack.inference.services.alibabacloudsearch;

import org.elasticsearch.threadpool.ThreadPool;
import org.elasticsearch.xpack.inference.services.alibabacloudsearch.AlibabaCloudSearchModel;
import org.elasticsearch.xpack.inference.external.http.sender.BaseRequestManager;

import java.util.Objects;

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
* 2.0.
*/

package org.elasticsearch.xpack.inference.external.http.sender;
package org.elasticsearch.xpack.inference.services.alibabacloudsearch;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
Expand All @@ -14,10 +14,11 @@
import org.elasticsearch.threadpool.ThreadPool;
import org.elasticsearch.xpack.inference.external.http.retry.RequestSender;
import org.elasticsearch.xpack.inference.external.http.retry.ResponseHandler;
import org.elasticsearch.xpack.inference.external.http.sender.ExecutableInferenceRequest;
import org.elasticsearch.xpack.inference.external.http.sender.InferenceInputs;
import org.elasticsearch.xpack.inference.external.http.sender.QueryAndDocsInputs;
import org.elasticsearch.xpack.inference.external.request.alibabacloudsearch.AlibabaCloudSearchRerankRequest;
import org.elasticsearch.xpack.inference.external.response.alibabacloudsearch.AlibabaCloudSearchRerankResponseEntity;
import org.elasticsearch.xpack.inference.services.alibabacloudsearch.AlibabaCloudSearchAccount;
import org.elasticsearch.xpack.inference.services.alibabacloudsearch.AlibabaCloudSearchResponseHandler;
import org.elasticsearch.xpack.inference.services.alibabacloudsearch.rerank.AlibabaCloudSearchRerankModel;

import java.util.Objects;
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
* 2.0.
*/

package org.elasticsearch.xpack.inference.external.http.sender;
package org.elasticsearch.xpack.inference.services.alibabacloudsearch;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
Expand All @@ -15,10 +15,11 @@
import org.elasticsearch.threadpool.ThreadPool;
import org.elasticsearch.xpack.inference.external.http.retry.RequestSender;
import org.elasticsearch.xpack.inference.external.http.retry.ResponseHandler;
import org.elasticsearch.xpack.inference.external.http.sender.EmbeddingsInput;
import org.elasticsearch.xpack.inference.external.http.sender.ExecutableInferenceRequest;
import org.elasticsearch.xpack.inference.external.http.sender.InferenceInputs;
import org.elasticsearch.xpack.inference.external.request.alibabacloudsearch.AlibabaCloudSearchSparseRequest;
import org.elasticsearch.xpack.inference.external.response.alibabacloudsearch.AlibabaCloudSearchSparseResponseEntity;
import org.elasticsearch.xpack.inference.services.alibabacloudsearch.AlibabaCloudSearchAccount;
import org.elasticsearch.xpack.inference.services.alibabacloudsearch.AlibabaCloudSearchResponseHandler;
import org.elasticsearch.xpack.inference.services.alibabacloudsearch.sparse.AlibabaCloudSearchSparseModel;

import java.util.List;
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -16,12 +16,12 @@
import org.elasticsearch.inference.InferenceServiceResults;
import org.elasticsearch.rest.RestStatus;
import org.elasticsearch.xpack.inference.external.action.ExecutableAction;
import org.elasticsearch.xpack.inference.external.http.sender.AlibabaCloudSearchCompletionRequestManager;
import org.elasticsearch.xpack.inference.external.http.sender.ChatCompletionInput;
import org.elasticsearch.xpack.inference.external.http.sender.InferenceInputs;
import org.elasticsearch.xpack.inference.external.http.sender.Sender;
import org.elasticsearch.xpack.inference.services.ServiceComponents;
import org.elasticsearch.xpack.inference.services.alibabacloudsearch.AlibabaCloudSearchAccount;
import org.elasticsearch.xpack.inference.services.alibabacloudsearch.AlibabaCloudSearchCompletionRequestManager;
import org.elasticsearch.xpack.inference.services.alibabacloudsearch.completion.AlibabaCloudSearchCompletionModel;

import java.util.Objects;
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -12,11 +12,11 @@
import org.elasticsearch.core.TimeValue;
import org.elasticsearch.inference.InferenceServiceResults;
import org.elasticsearch.xpack.inference.external.action.ExecutableAction;
import org.elasticsearch.xpack.inference.external.http.sender.AlibabaCloudSearchEmbeddingsRequestManager;
import org.elasticsearch.xpack.inference.external.http.sender.InferenceInputs;
import org.elasticsearch.xpack.inference.external.http.sender.Sender;
import org.elasticsearch.xpack.inference.services.ServiceComponents;
import org.elasticsearch.xpack.inference.services.alibabacloudsearch.AlibabaCloudSearchAccount;
import org.elasticsearch.xpack.inference.services.alibabacloudsearch.AlibabaCloudSearchEmbeddingsRequestManager;
import org.elasticsearch.xpack.inference.services.alibabacloudsearch.embeddings.AlibabaCloudSearchEmbeddingsModel;

import java.util.Objects;
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -14,11 +14,11 @@
import org.elasticsearch.core.TimeValue;
import org.elasticsearch.inference.InferenceServiceResults;
import org.elasticsearch.xpack.inference.external.action.ExecutableAction;
import org.elasticsearch.xpack.inference.external.http.sender.AlibabaCloudSearchRerankRequestManager;
import org.elasticsearch.xpack.inference.external.http.sender.InferenceInputs;
import org.elasticsearch.xpack.inference.external.http.sender.Sender;
import org.elasticsearch.xpack.inference.services.ServiceComponents;
import org.elasticsearch.xpack.inference.services.alibabacloudsearch.AlibabaCloudSearchAccount;
import org.elasticsearch.xpack.inference.services.alibabacloudsearch.AlibabaCloudSearchRerankRequestManager;
import org.elasticsearch.xpack.inference.services.alibabacloudsearch.rerank.AlibabaCloudSearchRerankModel;

import java.util.Objects;
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -14,11 +14,11 @@
import org.elasticsearch.core.TimeValue;
import org.elasticsearch.inference.InferenceServiceResults;
import org.elasticsearch.xpack.inference.external.action.ExecutableAction;
import org.elasticsearch.xpack.inference.external.http.sender.AlibabaCloudSearchSparseRequestManager;
import org.elasticsearch.xpack.inference.external.http.sender.InferenceInputs;
import org.elasticsearch.xpack.inference.external.http.sender.Sender;
import org.elasticsearch.xpack.inference.services.ServiceComponents;
import org.elasticsearch.xpack.inference.services.alibabacloudsearch.AlibabaCloudSearchAccount;
import org.elasticsearch.xpack.inference.services.alibabacloudsearch.AlibabaCloudSearchSparseRequestManager;
import org.elasticsearch.xpack.inference.services.alibabacloudsearch.sparse.AlibabaCloudSearchSparseModel;

import java.util.Objects;
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
* 2.0.
*/

package org.elasticsearch.xpack.inference.external.http.sender;
package org.elasticsearch.xpack.inference.services.amazonbedrock;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
Expand All @@ -17,6 +17,8 @@
import org.elasticsearch.inference.InferenceServiceResults;
import org.elasticsearch.threadpool.ThreadPool;
import org.elasticsearch.xpack.inference.external.http.retry.RequestSender;
import org.elasticsearch.xpack.inference.external.http.sender.ChatCompletionInput;
import org.elasticsearch.xpack.inference.external.http.sender.InferenceInputs;
import org.elasticsearch.xpack.inference.external.request.amazonbedrock.completion.AmazonBedrockChatCompletionEntityFactory;
import org.elasticsearch.xpack.inference.external.request.amazonbedrock.completion.AmazonBedrockChatCompletionRequest;
import org.elasticsearch.xpack.inference.external.response.amazonbedrock.completion.AmazonBedrockChatCompletionResponseHandler;
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
* 2.0.
*/

package org.elasticsearch.xpack.inference.external.http.sender;
package org.elasticsearch.xpack.inference.services.amazonbedrock;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
Expand All @@ -19,6 +19,8 @@
import org.elasticsearch.threadpool.ThreadPool;
import org.elasticsearch.xpack.inference.common.Truncator;
import org.elasticsearch.xpack.inference.external.http.retry.RequestSender;
import org.elasticsearch.xpack.inference.external.http.sender.EmbeddingsInput;
import org.elasticsearch.xpack.inference.external.http.sender.InferenceInputs;
import org.elasticsearch.xpack.inference.external.request.amazonbedrock.embeddings.AmazonBedrockEmbeddingsEntityFactory;
import org.elasticsearch.xpack.inference.external.request.amazonbedrock.embeddings.AmazonBedrockEmbeddingsRequest;
import org.elasticsearch.xpack.inference.external.response.amazonbedrock.embeddings.AmazonBedrockEmbeddingsResponseHandler;
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -5,9 +5,11 @@
* 2.0.
*/

package org.elasticsearch.xpack.inference.external.http.sender;
package org.elasticsearch.xpack.inference.services.amazonbedrock;

import org.elasticsearch.threadpool.ThreadPool;
import org.elasticsearch.xpack.inference.external.http.sender.RequestExecutorService;
import org.elasticsearch.xpack.inference.external.http.sender.RequestExecutorServiceSettings;
import org.elasticsearch.xpack.inference.services.amazonbedrock.client.AmazonBedrockExecuteOnlyRequestSender;

import java.io.IOException;
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -5,12 +5,12 @@
* 2.0.
*/

package org.elasticsearch.xpack.inference.external.http.sender;
package org.elasticsearch.xpack.inference.services.amazonbedrock;

import org.elasticsearch.core.Nullable;
import org.elasticsearch.core.TimeValue;
import org.elasticsearch.threadpool.ThreadPool;
import org.elasticsearch.xpack.inference.services.amazonbedrock.AmazonBedrockModel;
import org.elasticsearch.xpack.inference.external.http.sender.RequestManager;
import org.elasticsearch.xpack.inference.services.settings.RateLimitSettings;

import java.util.Objects;
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -11,10 +11,10 @@
import org.elasticsearch.core.TimeValue;
import org.elasticsearch.xpack.inference.external.action.ExecutableAction;
import org.elasticsearch.xpack.inference.external.action.SenderExecutableAction;
import org.elasticsearch.xpack.inference.external.http.sender.AmazonBedrockChatCompletionRequestManager;
import org.elasticsearch.xpack.inference.external.http.sender.AmazonBedrockEmbeddingsRequestManager;
import org.elasticsearch.xpack.inference.external.http.sender.Sender;
import org.elasticsearch.xpack.inference.services.ServiceComponents;
import org.elasticsearch.xpack.inference.services.amazonbedrock.AmazonBedrockChatCompletionRequestManager;
import org.elasticsearch.xpack.inference.services.amazonbedrock.AmazonBedrockEmbeddingsRequestManager;
import org.elasticsearch.xpack.inference.services.amazonbedrock.completion.AmazonBedrockChatCompletionModel;
import org.elasticsearch.xpack.inference.services.amazonbedrock.embeddings.AmazonBedrockEmbeddingsModel;

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -16,14 +16,14 @@
import org.elasticsearch.inference.InferenceServiceResults;
import org.elasticsearch.threadpool.ThreadPool;
import org.elasticsearch.xpack.inference.external.http.retry.ResponseHandler;
import org.elasticsearch.xpack.inference.external.http.sender.AmazonBedrockRequestExecutorService;
import org.elasticsearch.xpack.inference.external.http.sender.AmazonBedrockRequestManager;
import org.elasticsearch.xpack.inference.external.http.sender.InferenceInputs;
import org.elasticsearch.xpack.inference.external.http.sender.RequestExecutorServiceSettings;
import org.elasticsearch.xpack.inference.external.http.sender.RequestManager;
import org.elasticsearch.xpack.inference.external.http.sender.Sender;
import org.elasticsearch.xpack.inference.external.request.Request;
import org.elasticsearch.xpack.inference.services.ServiceComponents;
import org.elasticsearch.xpack.inference.services.amazonbedrock.AmazonBedrockRequestExecutorService;
import org.elasticsearch.xpack.inference.services.amazonbedrock.AmazonBedrockRequestManager;

import java.io.IOException;
import java.time.Clock;
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
* 2.0.
*/

package org.elasticsearch.xpack.inference.external.http.sender;
package org.elasticsearch.xpack.inference.services.anthropic;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
Expand All @@ -14,9 +14,11 @@
import org.elasticsearch.threadpool.ThreadPool;
import org.elasticsearch.xpack.inference.external.http.retry.RequestSender;
import org.elasticsearch.xpack.inference.external.http.retry.ResponseHandler;
import org.elasticsearch.xpack.inference.external.http.sender.ChatCompletionInput;
import org.elasticsearch.xpack.inference.external.http.sender.ExecutableInferenceRequest;
import org.elasticsearch.xpack.inference.external.http.sender.InferenceInputs;
import org.elasticsearch.xpack.inference.external.request.anthropic.AnthropicChatCompletionRequest;
import org.elasticsearch.xpack.inference.external.response.anthropic.AnthropicChatCompletionResponseEntity;
import org.elasticsearch.xpack.inference.services.anthropic.AnthropicResponseHandler;
import org.elasticsearch.xpack.inference.services.anthropic.completion.AnthropicChatCompletionModel;

import java.util.Objects;
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -5,11 +5,10 @@
* 2.0.
*/

package org.elasticsearch.xpack.inference.external.http.sender;
package org.elasticsearch.xpack.inference.services.anthropic;

import org.elasticsearch.threadpool.ThreadPool;
import org.elasticsearch.xpack.inference.services.anthropic.AnthropicAccount;
import org.elasticsearch.xpack.inference.services.anthropic.AnthropicModel;
import org.elasticsearch.xpack.inference.external.http.sender.BaseRequestManager;

import java.util.Objects;

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -9,9 +9,9 @@

import org.elasticsearch.xpack.inference.external.action.ExecutableAction;
import org.elasticsearch.xpack.inference.external.action.SingleInputSenderExecutableAction;
import org.elasticsearch.xpack.inference.external.http.sender.AnthropicCompletionRequestManager;
import org.elasticsearch.xpack.inference.external.http.sender.Sender;
import org.elasticsearch.xpack.inference.services.ServiceComponents;
import org.elasticsearch.xpack.inference.services.anthropic.AnthropicCompletionRequestManager;
import org.elasticsearch.xpack.inference.services.anthropic.completion.AnthropicChatCompletionModel;

import java.util.Map;
Expand Down
Loading