Elixir Wizards

• LangChain: LLM Integration for Elixir Apps with Mark Ericksen

  Mark Ericksen, creator of the Elixir LangChain framework, joins the Elixir Wizards to talk about LLM integration in Elixir apps. He explains how LangChain abstracts away the quirks of different AI providers (OpenAI, Anthropic’s Claude, Google’s Gemini) so you can work with any LLM in one more consistent API. We dig into core features like conversation chaining, tool execution, automatic retries, and production-grade fallback strategies. Mark shares his experiences maintaining LangChain in a fast-moving AI world: how it shields developers from API drift, manages token budgets, and handles rate limits and outages. He also reveals testing tactics for non-deterministic AI outputs, configuration tips for custom authentication, and the highlights of the new v0.4 release, including “content parts” support for thinking-style models. Key topics discussed in this episode: • Abstracting LLM APIs behind a unified Elixir interface • Building and managing conversation chains across multiple models • Exposing application functionality to LLMs through tool integrations • Automatic retries and fallback chains for production resilience • Supporting a variety of LLM providers • Tracking and optimizing token usage for cost control • Configuring API keys, authentication, and provider-specific settings • Handling rate limits and service outages with degradation • Processing multimodal inputs (text, images) in Langchain workflows • Extracting structured data from unstructured LLM responses • Leveraging “content parts” in v0.4 for advanced thinking-model support • Debugging LLM interactions using verbose logging and telemetry • Kickstarting experiments in LiveBook notebooks and demos • Comparing Elixir LangChain to the original Python implementation • Crafting human-in-the-loop workflows for interactive AI features • Integrating Langchain with the Ash framework for chat-driven interfaces • Contributing to open-source LLM adapters and staying ahead of API changes • Building fallback chains (e.g., OpenAI → Azure) for seamless continuity • Embedding business logic decisions directly into AI-powered tools • Summarization techniques for token efficiency in ongoing conversations • Batch processing tactics to leverage lower-cost API rate tiers • Real-world lessons on maintaining uptime amid LLM service disruptions Links mentioned: https://rubyonrails.org/ https://fly.io/ https://zionnationalpark.com/ https://podcast.thinkingelixir.com/ https://github.com/brainlid/langchain https://openai.com/ https://claude.ai/ https://gemini.google.com/ https://www.anthropic.com/ Vertex AI Studio https://cloud.google.com/generative-ai-studio https://www.perplexity.ai/ https://azure.microsoft.com/ https://hexdocs.pm/ecto/Ecto.html https://oban.pro/ Chris McCord’s ElixirConf EU 2025 Talk https://www.youtube.com/watch?v=ojL_VHc4gLk Getting started: https://hexdocs.pm/langchain/gettingstarted.html https://ash-hq.org/ https://hex.pm/packages/langchain https://hexdocs.pm/igniter/readme.html https://www.youtube.com/watch?v=WM9iQlQSFg @brainlid on Twitter and BlueSky Special Guest: Mark Ericksen.

  --------  

  38:18
• Blue Heron: Bluetooth Low Energy (BLE) for Elixir & Nerves with Connor Rigby

  Connor Rigby joins the Elixir Wizards to talk about Blue Heron BLE (Bluetooth Low Energy) support for Elixir apps. Blue Heron implements the BLE specs in pure Elixir, leveraging binary pattern matching and concurrent message processing to handle Bluetooth protocols. Unlike most solutions that require C ports or NIFs, Blue Heron runs entirely in user space, so it works seamlessly in both Nerves-based embedded projects and (eventually) desktop Elixir applications. We discuss how Nerves development differs from building Phoenix apps. Connor shares challenges he's experienced with hardware compatibility, where some chips only partially implement the spec, and he discusses the surprisingly deep (but sometimes incomplete) world of BLE device profiles. His tip for anyone entering the BLE space: read the official spec instead of trusting secondhand blog posts. Tools like Nerves LiveBook give you hands-on examples, so you can get a BLE prototype running on a Raspberry Pi and your phone in no time. Key topics discussed in this episode: Blue Heron origins and “bird” naming convention BLE vs. Bluetooth Classic: core differences Pure Elixir implementation—no C dependencies Binary pattern matching for packet parsing Hardware transport options: UART, SPI, USB, SDIO GenServer patterns in Nerves vs. Phoenix Linux requirement and power-consumption trade-offs GATT (Generic Attribute Table) implementation patterns SQLite integration for Nerves apps Hardware chip quirks and spec compliance Manufacturer-specific commands and workarounds BLE device profiles and spec gaps Security Management Profile (SMP) for encryption Device connection and pairing workflows Web vs. embedded development differences Where to get started: hardware recommendations and docs Links mentioned: https://github.com/ConnorRigby/ https://github.com/blue-heron/ https://nerves-project.org/ BLE (Bluetooth Low Energy) https://en.wikipedia.org/wiki/BluetoothLowEnergy https://developer.apple.com/ibeacon/ https://learnyousomeerlang.com/building-otp-applications Linux https://www.linux.org/ HCI (Host Controller Interface) https://en.wikipedia.org/wiki/Hostcontrollerinterface Circuits UART Library https://hexdocs.pm/circuitsuart/readme.html SPI (Serial Peripheral Interface) https://github.com/elixir-circuits/circuitsspi SDIO (Secure Digital Input Output https://en.wikipedia.org/wiki/SDIO Raspberry Pi https://www.raspberrypi.com/ Coral SoM Dev Board https://coral.ai/products/dev-board/ BeagleBone Single-Board Linux Computer https://www.beagleboard.org/boards/beaglebone-black https://www.bluetooth.com/bluetooth-resources/intro-to-bluetooth-gap-gatt/ Genservers https://hexdocs.pm/elixir/1.12/GenServer.html https://hexdocs.pm/ecto/Ecto.html https://github.com/elixir-sqlite/ectosqlite3 https://github.com/nerves-livebook/nerveslivebook Special Guest: Connor Rigby.

  --------  

  46:16
• Zigler: Zig NIFs for Elixir with Isaac Yonemoto

  In the Season 14 premiere, hosts Dan Ivovich and Sundi Myint chat with Isaac Yonemoto, creator of the Zigler library, to explore how Zigler brings Zig’s performance and safety to Elixir through Native Implemented Functions (NIFs). Isaac walks through the core design of Zigler and how it auto-generates the Elixir-to-Zig bridge, enforces type safety, and exposes multiple execution modes (normal, dirty, threaded). The conversation covers real-world applications, from SIMD-powered token selection for LLM hardware acceleration to OTP-style fault tolerance in low-level code. Isaac shares his own journey: stepping back from professional software work to launch a biotech startup focused on reducing drug manufacturing costs while continuing to maintain Zigler and even leveraging Elixir for bioinformatics pipelines. Topics discussed in this episode: What is the Zigler library and what does it do? What does it mean to run a "dirty NIF"? Async mode is temporarily removed from Zig (therefore, yielding NIFs is temporarily deprecated in Zigler) Zigler’s three execution modes (normal, dirty, and threaded) and how you switch modes with a single config change Isaac’s journey from professional software work to launching a biotech startup How Isaac leverages Elixir in bioinformatics pipelines at his startup LLM hardware acceleration using Zigler NIFs and SIMD-powered token picking Fault-tolerant load balancing of NIF workloads via OTP principles Transparent handling and recovery from hardware failures through monitoring Potential future memory-safety features in Zig and their implications The Elixir-based borrow-checker prototype: purpose and design Unit-checking for scientific computations to enforce correctness New OS support in Zigler 0.14: macOS, Windows, and FreeBSD Inline Zig code authoring directly within Elixir modules Isaac's commitment to maintain Zigler through its 1.0 release (...and beyond?) Links mentioned: https://github.com/E-xyza/zigler https://github.com/ziglang/zig https://vidalalabs.com/ Zig Programming Language: https://ziglang.org/ https://obsidian.md/ https://hexdocs.pm/elixir/macros.html https://erlang.org/documentation/doc-4.7.3/doc/extensions/macros.html A Deep Dive Into the Elixir AST: https://dorgan.ar/posts/2021/04/theelixirast/ https://www.erlang.org/doc/system/nif.html https://nodejs.org/en Llama Open-Source LLM: https://www.llama.com/ Mixtral Open-Source LLM: https://mistral.ai/news/mixtral-of-experts https://Fly.io SIMD: https://en.wikipedia.org/wiki/Singleinstruction,multiple_data https://opentrons.com/ CI/CD: https://en.wikipedia.org/wiki/CI/CD https://hexdocs.pm/zigler/Zig.html http://www.x.com/DNAutics https://bsky.app/profile/dnautics.bsky.social

  --------  

  43:00
• Building an Open Vehicle Control System using Elixir and Nerves with Marc, Thibault, and Loïc

  For the Season 13 finale, Elixir Wizards Dan and Charles are joined by Spin42 Engineers Marc Lainez, Thibault Poncelet, and Loïc Vigneron to discuss their work retrofitting a 2007 VW Polo and creating an Open Vehicle Control System (OVCS). Using Elixir, Nerves, and Raspberry Pis, the team is reimagining vehicle technology to extend the lifespan of older cars and reduce waste—all while making the process approachable and open source. The Spin42 team shares the technical details behind OVCS and how they use Elixir and Nerves to interact with the CAN bus and build a Vehicle Management System (VMS) to coordinate various vehicle components. They dive into the challenges of reverse engineering CAN messages, designing a distributed architecture with Elixir processes, and ensuring safety with fail-safe modes and emergency shutoffs. Beyond the technical, the team discusses their motivation for the project—upgrading older vehicles with modern features to keep them on the road, building an open-source platform to share their findings with others, and above all-- to just have fun. They explore potential applications for OVCS in boats, construction equipment, and other vehicles, while reflecting on the hurdles of certifying the system for road use. If you’ve ever wondered how Elixir and Nerves can drive innovation beyond software, this episode is packed with insights into automotive computing, hardware development, and the collaborative potential of open-source projects. Topics Discussed in this Episode: Retrofitting a 2007 VW Polo with electric engines and modern tech Building an open-source Vehicle Control System (OVCS) using Elixir and Nerves Leveraging Elixir to interact with the CAN bus and parse proprietary messages Designing a Vehicle Management System (VMS) to coordinate vehicle components Developing custom hardware for CAN communication Creating a YAML-based DSL for CAN message and frame descriptions Building a distributed architecture using Elixir processes Ensuring safety with fail-safe modes and emergency shutoffs Using Flutter and Nerves to build a custom infotainment system Exploring autonomous driving features with a ROS2 bridge Developing remote control functionality with a Mavlink transmitter Testing OVCS features at scale with a Traxxas RC car (OVCS Mini) Challenges of certifying OVCS for road use and meeting regulatory requirements Encouraging community contributions to expand OVCS functionality Balancing open-source projects with contract work to sustain development The fun and fulfillment of experimenting with Elixir beyond traditional applications Links mentioned: https://www.spin42.com/ https://nerves-project.org/ Quadcopter https://github.com/Spin42/elicopter https://github.com/linux-can/can-utils https://docs.kernel.org/networking/can.html https://github.com/open-vehicle-control-system/cantastic https://github.com/commaai/opendbc https://en.wikipedia.org/wiki/CANbus#CANFD https://comma.ai/ https://en.wikipedia.org/wiki/CANFD https://webkit.org/wpe/ https://docs.nvidia.com/jetson/archives/r35.4.1/DeveloperGuide/text/SD/WindowingSystems/WestonWayland.html https://buildroot.org/ https://vuejs.org/ https://flutter.dev/ https://github.com/smartrent/elixirflutterembedder https://www.raspberrypi.com/products/raspberry-pi-5/ The Rabbit Pickup https://www.hemmings.com/stories/value-guide-1980-83-volkswagen-pickup https://www.expresslrs.org/software/mavlink https://industrial-training-master.readthedocs.io/en/melodic/source/session7/ROS1-ROS2-bridge.html https://github.com/ros2/rcl https://github.com/open-vehicle-control-system/traxxas Contact Marc, Thibault, and Loïc: [email protected] Special Guests: Loïc Vigneron, Marc Lainez, and Thibault Poncelet.

  --------  

  54:19
• Creating Horizon: Deploy Elixir Phoenix Apps on FreeBSD with Jim Freeze

  The Elixir Wizards welcome Jim Freeze, organizer of ElixirConf and creator of the Horizon library. Jim shares his journey from organizing Ruby conferences to founding and growing ElixirConf into the community cornerstone it is today. He reflects on the challenges of running a major conference, how COVID-19 shaped the event, and why the talks remain an evergreen resource for the Elixir ecosystem. We discuss Horizon, Jim’s deployment library for Elixir and Phoenix applications with Postgres on FreeBSD. Driven by a need for simplicity and cost-effectiveness, Jim explains how Horizon minimizes external dependencies while delivering fault-tolerant and streamlined setups. He compares it to tools like Fly, Terraform, and Ansible, highlighting its low cognitive load and flexibility—key benefits for developers seeking more control over their deployment environments. Jim also unpacks the broader value of understanding and customizing your deployment stack rather than relying solely on managed services. He discusses the benefits of using FreeBSD, including its stability, security, and performance advantages, as well as its robust ZFS file system. Jim emphasizes the importance of coherent deployment workflows, community collaboration, and contributions to open-source projects like Horizon. He invites listeners to explore Horizon, share feedback, and own their deployments. Topics discussed in this episode: Jim Freeze’s background organizing RubyConf and founding ElixirConf Reducing reliance on managed services and external dependencies Simplifying deployments with minimal tools and lower cognitive overhead The trade-offs of cutting-edge tools vs. stable, well-documented solutions The importance of customizing deployment tools to meet specific needs Addressing challenges with Tailwind compatibility Streamlining the FreeBSD installation process for Horizon users Community collaboration: contributing to open-source tools Jim’s vision for Horizon: PKI support, hot standby features, and serverless potential Links mentioned Nine Minutes of Elixir (https://youtu.be/hht9s6nAAx8?si=ocrk1wQtGplSGL0B) https://www.youtube.com/@ElixirConf https://github.com/liveview-native https://github.com/elixir-nx/nx https://2024.elixirconf.com/ https://github.com/jfreeze/horizon https://hexdocs.pm/horizon/deploying-with-horizon.html#web-cluster-topology https://kamal-deploy.org/ https://fly.io/ https://aws.amazon.com/console/ https://www.digitalocean.com/ https://cloud.google.com/ https://www.cloudflare.com/ https://www.hetzner.com/ https://www.proxmox.com/en/ https://nginx.org/ https://github.com/openzfs/zfs Zettabyte File System https://en.wikipedia.org/wiki/ZFS https://www.postgresql.org/ https://www.terraform.io/ https://www.ansible.com/ https://docs.freebsd.org/ https://www.redhat.com/ https://ubuntu.com/ https://esbuild.github.io/ Listener's Survey: https://smr.tl/EWS13 Special Guest: Jim Freeze.

  --------  

  44:48

More Technology podcasts

Trending Technology podcasts

About Elixir Wizards