Electronic Data Interchange (EDI) underpins the flow of information in numerous industries. From healthcare, retail, and aviation, to finance, manufacturing, and logistics, EDI is the workhorse carrying billions of transactions across applications in these industries. Historically viewed as a long, complex and costly journey, connecting EDI to the enterprise is traditionally thought to belong in the realm of expensive proprietary software or organisations with sizeable in-house IT teams. The goal of this blog post is to dispel this perception.

Continue reading ❯

USECASESHOWTOSCAMELJBANGTRANSFORMATION

Introduction This has been several blog posts now where we have learned about how to use generative AI for data extraction from a Camel route. Starting from the initial inception, we have then focused a lot on how to best combine Camel and Quarkus LangChain4j. In this blog post, we will reap the benefit of this great combination to improve the accuracy of our data extraction almost for free. Almost for free really?

Continue reading ❯

CAMELAI

Introduction In the just released Apache Camel 4.10 LTS, AI-related components have been further enhanced. Among others, three new components related to AI model serving have been added. 1 TorchServe component TensorFlow Serving component KServe component My previous article Apache Camel AI: Leverage power of AI with DJL component demonstrated how the DJL component can be used to perform AI model inference within the Camel routes. Starting from 4.10, in addition to the in-route inference by DJL, these new components will allow the Camel routes to invoke external model servers to perform inference.

Continue reading ❯

CAMELAI