Just released Swiftide 0.31 A Rust library for building LLM applications. From performing a simple prompt completion, to building fast, streaming indexing and querying pipelines, to building agents that can use tools and call other agents.
The release is absolutely packed:
- Graph like workflows with tasks
- Langfuse integration via tracing
- Ground-work for multi-modal pipelines
- Structured prompts with SchemaRs
... and a lot more, shout-out to all our contributors and users for making it possible <3
Just shipped a major release for Swiftide. Swiftide provides the building blocks to build composable agentic and RAG applications.
Shoutout to wulawulu for contributing a Kafka integration! <3
A major new staple is a straight-forward way for human-in-the-loop interaction. Human-in-the-loop pattern is a common solution for GenAI agents to provide them with feedback and some measure of safety.
Additionally there's a host of new features, improvements, and fixes. You can find the project on [github](https://github.com/bosun-ai/swiftide).
I've worked with C++ in the past, it's subject to taste. I like how Rust's rigidness empowers rapid change _without_ breaking things.
Besides, the ML ecosystem is also very mature. llama.cpp has native bindings (which Swiftide supports), onnx bindings, ndarray (numpy in Rust) works great, Candle, lots of processing utilities. Additionally, many languages are rewriting parts in Rust, more often than not, these are available in Rust as well.
Core maintainer of Swiftide here. That's a fair comment! Additionially, it's interesting to note that almost all the time is spend in FastEmbed / onxx in the Swiftide benchmark. A more involved follow up with chunking and transformation could be very interesting, and anecdotally shows far bigger differences. We did not have the time yet to fully dive into this.
Personally, I just love code being fast, and Rust is incredible to work with. Exceptions granted, I'm more productive with Rust than any other language. And it's fun.
Excited to announce that Swiftide, a Rust library for building RAG applications, can now do hybrid search with Qdrant, supports filters in search, load parquet files for indexing (i.e. from HuggingFace) and is a lot faster.
Salonized is the Benelux' leading software provider for Salons to manage their appointments, customers, checkouts and online presence. Delighting our users is our prime directive. And looking for a challenge? Scheduling at scale is awesome.
We're skyrocketing in Salons and users and we've grown in the past 5 years from 5 employees to almost 40 now. We're looking to expand our development team of 8 to at least double the size by the end of next year.
Very social, slightly crazy company in a beautiful office in the heart of Amsterdam.
Relocation is possible.
Interested? We're looking for medior and senior engineers and also SRE. Check out https://jobs.salonized.com to apply.
We help making running a salon easy. Sounds boring? Heck no! We have the happiest customers, fantastisc design challenges, high quality demands, a development first company and amazing colleagues.
We are looking for self managing full stack and frontend developers of all levels to support our fast growing company.
Our stack is Rails, Ember.js, lots of internal tools, kubernetes, and ever growing.
We offer a competetive salary, benefits, frequent beers and wines, room to grow and a weekly hackday.
The release is absolutely packed:
- Graph like workflows with tasks
- Langfuse integration via tracing
- Ground-work for multi-modal pipelines
- Structured prompts with SchemaRs
... and a lot more, shout-out to all our contributors and users for making it possible <3
Even went wild with my drawing skills.
Full write up on all the things in this release at our https://blog.bosun.ai/swiftide-0-31/ and on https://github.com/bosun-ai/swiftide.
edit: fmt