🚀 Level Up Your Data Processing with Bytewax v0.20! Bytewax v0.20 brings critical updates to improve your workflow. The newly added Dataflow Visualizer provides a graphical representation of your data pipelines, making them easier to navigate and optimize. 🐝 We've also restructured our core operators to boost data handling efficiency, ensuring smoother operations within your applications. Ready to upgrade your data streams? ➡️ https://lnkd.in/e-WQPyxk
Bytewax
Software Development
A Real-Time Data Streaming Processor. Cloud native, highly scalable, open source, engineered for #Python developers.
About us
Open source framework and distributed stream processing engine. Build streaming data pipelines and real-time apps with everything you need: recovery, scalability, windowing, aggregations, and connectors! Bytewax's mission is to transform stream processing, making it faster, more accessible, and flexible for all users. #StreamProcessing #Python #DataStreaming #OpenSource #DataScience #PredictiveAnalytics #AnomalyDetection #StreamingInfrastructure #EventDrivenArchitecture
- Website
-
https://www.bytewax.io
External link for Bytewax
- Industry
- Software Development
- Company size
- 2-10 employees
- Headquarters
- Santa Cruz
- Type
- Privately Held
Locations
-
Primary
Get directions
Santa Cruz, US
Employees at Bytewax
-
Jonas Best
Chief of Staff @ Bytewax 🐝 | Bringing real-time data streams to the Python ecosystem
-
Doug Cohen
Sales and GTM Leader for Enterprise Data and AI Solutions | Culture & Team Builder | Results-Driven Executive in SaaS, IaaS, Cloud, and Streaming…
-
Srini Kadamati
Synthetic Data @ Datacebo
-
Anna Filippova
Streamlit Community Growth @ Snowflake
Updates
-
🐝 Our Bytewax MAD Map has grown with your support! We received many comments and messages about what tools to add and are now working on an update. Now, we need your help to make it even more comprehensive. 💡From data acquisition to GenAI, our map features many Python tools, but we want to know what we’re missing. 👉Drop a comment with your favorite tools that aren’t on the map yet. Let’s add more great resources together! ➡️ https://lnkd.in/eGdW7w9W
-
-
🚀 Excited to share Paul Iusztin’s fantastic free lessons on building real-world LLM systems! A big shoutout to the Decoding ML team, Alex Vesa, Rares Istoc, and Alex Razvant, for their incredible efforts. Bytewax is thrilled to contribute to this course along with Superlinked, Qdrant, Qwak, Comet! 💛
Architect and build a real-world LLM system 🌍 Paul Iusztin explains how to build and design high-performance RAG inference pipelines in lesson 9 of the free LLM Twin course. He walks us through: ☑ Microservice vs monolithic LLM architectures ☑ Building a production-grade RAG business module with #Qdrant and Superlinked ☑ Deploying LLM microservices on Qwak ☑ Implementing prompt monitoring with Comet ML 👉 Read the article: https://lnkd.in/gEPv2d2T 👉 See all 11 lessons of the LLM Twin course: https://lnkd.in/gXFE4ezv Thank you to Paul and the whole Decoding ML team, Alex Vesa, Rares Istoc, and Alex Razvant, for their amazing work in this course!
-
-
✨ Fresh Guide Alert! ✨ We’re excited to share our updated guide on maintaining a real-time limit order book using Bytewax! This tutorial covers everything from connecting to Coinbase via WebSockets to processing and analyzing live financial data. 🔧 Skill Level: Intermediate ⏳ Time to Complete: Approx. 25 Min What You’ll Learn: - Connect to Coinbase for live order book updates. - Initialize and manage order books for major cryptocurrencies. - Update order books in real-time with market changes. - Utilize advanced data structures for efficient management. - Process live data with Bytewax. - Filter significant market movements based on the spread. Check out the full guide and code here ➡️ https://lnkd.in/efsxVmbp
-
-
💛🐝
Developer Advocate at Bytewax - I talk about stream analytics, LLM prompting, model tuning, ML Engineering and Data engineering.
Bytewax goes to the SciPy Conference! Zander Matheson and I shared with the community our most recent work on real time retrieval augmented generation, joint work with unstructured.io and Microsoft Azure. We chatted with folks what stream processing is, its applications in data operations and an application in AI through financial news real time indexing pipelines as part of a RAG system. I look forward to continuing chats with folks from MongoDB Jib Adegunloye, Coiled Sarah Johnson, Streamlit and MotherDuck Guen Prawiroatmodjo Thank you for having us! #dataops #llmops #RAG #streaming
-
-
🚀 New Blog Alert! Discover how Retrieval Augmented Generation (RAG) transforms NLP by combining retrieval-based methods with generative models. Our latest blog covers: 🔍 RAG Basics: Learn how RAG uses a vector database and LLM for context-aware answers. 📈 Key Processes: Understand data extraction, wrangling, chunking, embedding, retrieval, query encoding, and LLM generation. ⏱️ Real-Time vs. Batch: Explore the pros and cons of each and how micro-batching offers the best of both worlds. 💻 Building with Bytewax: See how Bytewax enables scalable RAG systems with real-time processing of financial news and public filings. 🌐 Advanced Architecture: Check out our streamlined setup using Bytewax dataflows and Haystack by deepset pipelines for real-time indexing and embedding. 📊 Future Work: Preview our upcoming Streamlit report generator, delivering LLM-generated reports with real-time data. Read the full blog here: https://lnkd.in/eb2gn4cD Laura Funderburk unstructured.io
-
-
Bytewax reposted this
Super happy with the OSS4AI July event yesterday made possible by Bytewax and Microsoft Reactor! We had 79 signups for a day reaching 97 degrees. Both less signups than usual and higher temps - yet we ended up with a great turnout! Nearly 50 people came out to learn about #AI. Laura Funderburk from Bytewax came all the way from Canada and talked to us about Real Time RAG, and Andrew Hoh from LastMile AI came all the way from NYC to come talk to us about specific evals and how to put LLMs into production. Also it was great seeing Oli Makhasoeva again, her commitment to the AI community is incredible. See you at the next one Seattle!
-
-
🎉 Yesterday's OSS4AI meetup hosted by Yujian Tang was absolutely fantastic! We were so excited to have the chance to speak and present on setting up real-time RAG pipelines with Bytewax. And your enthusiasm and great questions made the event extra special—thank you! 💛 Laura Funderburk has put together all the key findings from her presentation. Make sure to visit her page to check them out. 🙌 Another confirmation of our team's friendliness and passion for their work is that our own Oli Makhasoeva came to the meetup during her maternity leave to support Laura. 👶❤️ Thanks again for joining us, and we can't wait for more amazing discussions in the future.
-
😎 Today’s the day, Seattle! Everyone is invited to the #AI Tech Talk Meetup to learn about real-time LLM applications. Laura Funderburk will share insights on Real-Time RAG and bring some of our 🐝 awesome swag. We’re also excited to have Andrew Hoh speak about evaluating and debugging LLM applications. The amazing host and organizer, Yujian Tang, will guide the event. 📍 Microsoft Reactor Redmond 🕔 Starts at 5 PM See you there! 💛 P.S. This is your moment for those looking to catch the final chance to register ➡️ https://lu.ma/wkzc09nz
-
🚀 Today's all about event invitations! Right after the #AI tech talk meetup on July 9th, join Bytewax at the SciPy Conference to engage with open-source Python! 🎓 🐝 Zander Matheson and Laura Funderburk will present on July 10th from 6-7 PM in the Ballroom during our Poster session on Real-time RAG. This is the perfect opportunity to meet us in person and get answers to all your questions. Find more details here ➡️ https://lnkd.in/e-GQETTT Let’s discuss how we can innovate together!
-