Yeah. Agree with Vikram here. We had many things "open" and one of those things is how we treat providers. so we will likely have time (and mental capacity) to discuss this after 3.1 is out :)
On Tue, Sep 16, 2025 at 9:47 AM Vikram Koka via dev <dev@airflow.apache.org> wrote: > Hey Arthur, > > Thank you for reaching out and definitely appreciate the interest. > Can you give us a little bit of time to get back to you? > > We are in the midst of the Airflow 3.1 release this week, so please don't > mistake the lack of response as a lack of interest. > > Best regards, > Vikram > > > On Mon, Sep 15, 2025 at 7:49 AM Arthur Raulino Kretzer <a...@certi.org.br> > wrote: > > > Hello Airflow Community, > > > > I am starting this discussion to propose the addition of a new community > > provider for *Voyage AI*. > > > > Voyage AI is a service that specializes in high-performance vector > > embeddings for AI applications, offering state-of-the-art models for text > > representation. This provider aims to integrate Voyage AI's capabilities > > directly into Airflow DAGs, making it easy for users to build powerful AI > > and RAG (Retrieval-Augmented Generation) pipelines. > > > > The initial Pull Request with the implementation, tests, and > documentation > > can be found here: https://github.com/apache/airflow/pull/55671 > > > > *Provider Details:* > > > > The initial version of the provider includes the following components: > > > > - > > > > *VoyageAiEmbeddingOperator:* An operator to generate text embeddings > > using the Voyage AI API. > > - > > > > *VoyageAiHook:* A hook to manage the connection and authentication > with > > the Voyage AI service. > > > > > > *Justification:* > > > > As AI-native workflows become more common, integrating with specialized > > services like Voyage AI is crucial. This provider will enable data > > engineers and ML practitioners to: > > > > - > > > > Easily vectorize large datasets as part of their ETL/ELT processes. > > - > > > > Build and automate RAG pipelines that require up-to-date vector > > embeddings. > > - > > > > Leverage Airflow's orchestration capabilities for complex AI workflows > > without writing extensive boilerplate code. > > > > *Community Provider Checklist:* > > > > I have reviewed the criteria for new community providers and believe this > > submission complies with them: > > > > - > > > > *Relevant:* The provider integrates a relevant service for the data > and > > AI community. > > - > > > > *License:* All dependencies have licenses compatible with the Apache > > License 2.0. The main dependency is voyageai which is licensed under > > Apache 2.0. > > - > > > > *Mature:* Voyage AI is a stable and publicly available service. > > - > > > > *No new core dependencies:* The provider does not add new dependencies > > to the core Airflow package. > > - > > > > *Naming:* The provider package will be named > > apache-airflow-providers-voyageai. > > - > > > > *Documentation & Tests:* The PR includes documentation, usage > examples, > > and unit tests for the new components. > > > > I am looking forward to hearing your feedback, thoughts, and suggestions > on > > this proposal. > > > > Thank you! > > -- > > *Arthur Raulino Kretzer* > > Desenv De Software | Sw > > CDM | Centro de Convergência Digital e Mecatrônica > > Fundação CERTI a...@certi.org.br > > (48) 9926-3500 > > > > www.certi.org.br <https://www.certi.org.br/> > > <https://www.facebook.com/FundacaoCerti> > > <https://www.instagram.com/fundacaocerti/> > > <https://www.youtube.com/user/FundacaoCERTI> > > <https://www.linkedin.com/company/fundacao-certi/> > > Esta mensagem (incluindo arquivos anexos) contém informações > confidenciais > > e é dirigida exclusivamente ao seu destinatário, sendo proibido e > sujeito a > > sanções penais qualquer ato de divulgação, utilização, ou reprodução > (total > > ou parcial) das informações nela contidas, caso não seja seu > destinatário. > > >
