spring-ai

Files

Soby Chacko 949f1ed4e8 Add Batching strategy for embedding documents

- When embedding documents, allow batching the documents using some criteria.
 - `BatchingStrategy` interface with a `TokenCountBatchingStrategy` implementation that uses
   the openai max input token size of 8191 as the default.
 - Add a default method in EmbeddingModel to embed document using this new batching strategy.
 - Change `MilvusVectorStore` to make use of this new batching API.
 - Adding unit tests for `TokenCountBatchingStrategy`.
 - Adding openai integration test to call the embed API that uses batching.

Resolves https://github.com/spring-projects/spring-ai/issues/1214

Other vector stores will be updated seperately

2024-08-20 14:08:06 -04:00

spring-ai-anthropic

Model observability for Anthropic

2024-08-20 01:13:43 -04:00

spring-ai-azure-openai

Replace the Embedding format from List<Double> to float[]

2024-08-13 11:53:08 -04:00

spring-ai-bedrock

Replace the Embedding format from List<Double> to float[]

2024-08-13 11:53:08 -04:00

spring-ai-huggingface

Improve Hugging Face ITs