diff --git a/spring-ai-docs/src/main/antora/modules/ROOT/images/spring-ai-document1-api.jpg b/spring-ai-docs/src/main/antora/modules/ROOT/images/spring-ai-document1-api.jpg new file mode 100644 index 000000000..12e51d9d7 Binary files /dev/null and b/spring-ai-docs/src/main/antora/modules/ROOT/images/spring-ai-document1-api.jpg differ diff --git a/spring-ai-docs/src/main/antora/modules/ROOT/images/spring-ai-message-api.jpg b/spring-ai-docs/src/main/antora/modules/ROOT/images/spring-ai-message-api.jpg index ce4f0e72f..7f8a39657 100644 Binary files a/spring-ai-docs/src/main/antora/modules/ROOT/images/spring-ai-message-api.jpg and b/spring-ai-docs/src/main/antora/modules/ROOT/images/spring-ai-message-api.jpg differ diff --git a/spring-ai-docs/src/main/antora/modules/ROOT/pages/api/etl-pipeline.adoc b/spring-ai-docs/src/main/antora/modules/ROOT/pages/api/etl-pipeline.adoc index 55e33b50e..0235c9fcd 100644 --- a/spring-ai-docs/src/main/antora/modules/ROOT/pages/api/etl-pipeline.adoc +++ b/spring-ai-docs/src/main/antora/modules/ROOT/pages/api/etl-pipeline.adoc @@ -8,13 +8,19 @@ The RAG use case is text to augment the capabilities of generative models by ret == API Overview +The ETL pipelines creates, transforms and stores `Document` instances. + +image::spring-ai-document1-api.jpg[Spring AI Message API, width=400, align="center"] + +The `Document` class contains text, metadata and optionally additionall media types like images, audio and video. + There are three main components of the ETL pipeline, * `DocumentReader` that implements `Supplier>` * `DocumentTransformer` that implements `Function, List>` * `DocumentWriter` that implements `Consumer>` -The `Document` class contains text and metadata and is created from PDFs, text files and other document types via the `DocumentReader`. +The `Document` class content is created from PDFs, text files and other document types throught the help of `DocumentReader`. To construct a simple ETL pipeline, you can chain together an instance of each type.