Announcing Jina 0.7.0
We are excited to release Jina v0.7.0! Jina is an easier way to do a neural search on the cloud.
Highlights of this release include:
- Support for preventing duplicates Documents in the index
In this post we'll highlight some of the key new features. For full release notes, including bug fixes, breaking changes, and sample code, please check our GitHub repo
⬆️ Major Features and Improvements
Evaluation is fully supported by Jina.
jina.drivers.evaluatehave been introduced to make this happen. Now you can use different metrics to evaluate the Flow. No matter whether you want to evaluate the whole Flow or just part of it, the evaluation can be done smoothly without stopping the running Flow.
To prevent duplicates in the index,
UniqueVectorIndexerare introduced together with the corresponding drivers in
jina.drivers.cache. Please refer to docs.jina.ai for more details.
- Add visualization for Flow. Calling
Flowgives a better view of how the Flow looks.
🙏 Thanks to our Contributors
This release contains contributions from Alex C-G, Alex McKenzie, CatStark, Christopher Lennan, Deepankar Mahapatro, Fernanda Kawasaki, Han Xiao, Joan Fontanals Martinez, Ján Jendrušák, Maximilian Werk, Nan Wang, Oleh Yaroshchuk, Pratik Bhavsar, RenrakuRunrat, Rutuja Surve, Sai Sandeep Mutyala, Sergei Averkiev, Susana Guzman, Wang Bo, jancijen, pswu11
🙏 Thanks to our Community
And thanks to all of you out there as well! Without you, Jina couldn't do what we do. Your support means a lot to us.
🤝 Work with Jina
Want to work with Jina full-time? Check out our openings on our website.