mcolomerc commented on code in PR #250: URL: https://github.com/apache/flink-agents/pull/250#discussion_r2447059769
########## api/src/main/java/org/apache/flink/agents/api/embedding/model/BaseEmbeddingModelConnection.java: ########## @@ -0,0 +1,82 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.flink.agents.api.embedding.model; + +import org.apache.flink.agents.api.resource.Resource; +import org.apache.flink.agents.api.resource.ResourceDescriptor; +import org.apache.flink.agents.api.resource.ResourceType; + +import java.util.List; +import java.util.Map; +import java.util.function.BiFunction; + +/** + * Abstraction of embedding model connection. + * + * <p>Responsible for managing embedding model service connection configurations, such as Service + * address, API key, Connection timeout, Model name, Authentication information, etc. + * + * <p>This class follows the parameter pattern where additional configuration options can be passed + * through a Map<String, Object> parameters argument. Common parameters include: + * + * <ul> + * <li>model - The model name to use for embeddings + * <li>encoding_format - The format for encoding (e.g., "float", "base64") + * <li>timeout - Request timeout in milliseconds + * <li>batch_size - Maximum number of texts to process in a single request + * </ul> + */ +public abstract class BaseEmbeddingModelConnection extends Resource { + + public BaseEmbeddingModelConnection( + ResourceDescriptor descriptor, BiFunction<String, ResourceType, Resource> getResource) { + super(descriptor, getResource); + } + + @Override + public ResourceType getResourceType() { + return ResourceType.EMBEDDING_MODEL_CONNECTION; + } + + /** + * Generate embeddings for a single text input. + * + * @param text The input text to generate embeddings for + * @param parameters Additional parameters to configure the embedding request + * @return An array of floating-point values representing the text embeddings + */ + public abstract float[] embed(String text, Map<String, Object> parameters); + + /** + * Generate embeddings for multiple text inputs. + * + * @param texts The list of input texts to generate embeddings for + * @param parameters Additional parameters to configure the embedding request + * @return A list of arrays, each containing floating-point values representing the text + * embeddings + */ + public abstract List<float[]> embed(List<String> texts, Map<String, Object> parameters); + + /** + * Get the dimension of the embeddings produced by this model. + * + * @return The embedding dimension + */ + public abstract int getEmbeddingDimension(); Review Comment: Removed. Provides a fallback dimension that the model supports by default -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
