Archive

Collaborative Robot.

Intro video - Industrial Robots vs. Collaborative Robots | A Clear Winner? - YouTube

low skilled tasks like:

• macine tending
• pick and place
• finishing
• quality inspection
• end of line palletizing

Features:

• handle light payloads
• easy to program by operators
• zero coding
• require no guarding

Major Players:

• Kawasaki
• Universal Robots
• productive robotics?

Cobot consultation: Neff automation based in Indianapolis.

SendCutSend - How They Became America’s #1 Manufacturer - YouTube

• 4x8 CNC Plasma Cutting table, Cherry-EagleTec Plasma and Laser Cutting
• 2x2 Versa Cut by Eastwood Company. Laser is more precise than plasma.
• Omada ENSIS 3015 AJ
• 200,000 sqft under roof
• 100kw of cutting power
• 10 fiber lasers
• CNC routers

Manufacturers:

• OKUMA
  • Twin spindle lathe 2SP-2500H with Okuma Gantry Loader - YouTube
• FANUC
  • MetalQuest - Robotic Automation of a Machine Shop | Machine Shop Tour - YouTube LR Mate 200
    • 3d printed fixtures
• Snapmaker for 3d printing
• Brother Mill via This Isn’t Your Typical Machine Shop! | PTP Manufacturing Machine Shop Tour - YouTube, TC-234
• Tormach A Tormach Unlike Any Other - YouTube 1500MX - $32k

Concepts:

• CNC Machining and 3d Printing - Where Ideas Become Reality - YouTube

Scripts I wrote that I use all the time -- This is a neat page, and a concept worth copying (ie., make this page into that).

In the meantime, my scripts are over at GitHub - btbytes/scripts and also see my gist page.

Hyperflask is built on top of Flask, introduces component-driven architecture to Flask apps. Seamlessly create frontend (web components, react, etc...) and backend components and use them in your jinja templates. Use HTMX to create server-backed interactive components...  file-based routing using a new file format that combines python code and a jinja template (inspired by Astro pages). Uses DaisyUI.

See also Litestar

Notes on RAG from the creator of GitHub - agentset-ai/agentset --  open-source platform to build, evaluate, and ship production-ready RAG and agentic applications. It provides end-to-end tooling: ingestion, vector indexing, evaluation/benchmarks, chat playground, hosting, and a clean API with first-class developer experience.

What made the difference

• Query Generation -- review the thread and generate a number of semantic + keyword queries. We processed all of those queries in parallel, and passed them to a reranker. This made us cover a larger surface area and not be dependent on a computed score for hybrid search.
• Reranking -- "the highest value 5 lines of code you'll add. The chunk ranking shifted a lot. More than you'd expect. Reranking can many times make up for a bad setup if you pass in enough chunks."
• Chunking Strategy -- * this takes a lot of effort, you'll probably be spending most of your time on it.*
• Metadata to LLM -- Injecting metadata (title, author, etc.) improves context and answers by a lot.
• Query routing: many users asked questions that can't be answered by RAG (e.g. summarize the article, who wrote this). We created a small router that detects these questions and answers them using an API call + LLM instead of the full-blown RAG set-ups.

Stack

• turbopuffer for vector-databases
• UnstructuredIO for chunking
• Zerank by ZeroEntropy - Smarter, Faster Models for Search for Reranking
• GPT-4.1

Collaborative robot automation | Productive Robotics is an American Industrial cobot manufacturer. Heard via - He Makes High-End Film Gear in the Tiniest CNC Machine Shop Ever | Possum Solutions Shop Tour - YouTube