bamaer opened a new pull request, #8454: URL: https://github.com/apache/hop/pull/8454
… vectors Completes the retrieval chain: chunk, embed, store. Nothing in Hop could call an embedding model, so #8415 and #8422 had no middle step. AI provider gains model roles. One provider can now serve a chat model, an embedding model and a reranker from the same endpoint and credentials, with a models table in its editor. A transform resolves the role it needs rather than asking the user to pick one. - AiModelRole, AiProviderModel and AiProvider.resolveModelName(role) - AiEmbeddingFactory alongside AiChatFactory, for Ollama and OpenAI compatible providers - AiChatFactory honours a CHAT row, still falling back to modelName - Embed text, in plugins/tech/ai next to the metadata type it needs, the way pgvector, parquet and avro carry their transforms - a dependencies.xml so the langchain4j libraries are on the class loader before the first row rather than once another plugin happens to load - an AI transform category, which did not exist Fully backward compatible. modelName and temperature keep their meaning, a provider with no rows behaves exactly as before, and AiChatFactory was the only production consumer of either field. Adds an integration test project for the transforms that call an AI model. They share one Ollama container, and are disabled by default because the image and model pulls are too expensive for every run. **Please** add a meaningful description for your change here ------------------------ Thank you for your contribution! Follow this checklist to help us incorporate your contribution quickly and easily: - [x] Run `mvn clean install apache-rat:check` to make sure basic checks pass. A more thorough check will be performed on your pull request automatically. - [x] If you have a group of commits related to the same change, please squash your commits into one and force push your branch using `git rebase -i`. - [x] Mention the appropriate issue in your description (for example: `addresses #123`), if applicable. To make clear that you license your contribution under the [Apache License Version 2.0, January 2004](http://www.apache.org/licenses/LICENSE-2.0) you have to acknowledge this by using the following check-box. - [x] I hereby declare this contribution to be licensed under the [Apache License Version 2.0, January 2004](http://www.apache.org/licenses/LICENSE-2.0) - [ ] In any other case, please file an [Apache Individual Contributor License Agreement](https://www.apache.org/licenses/icla.pdf). -- 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]
