{"podcast":{"title":"Elixir Wizards","slug":"elixir-wizards","podcast_index_feed_id":674321,"rss_url":"https://feeds.fireside.fm/smartlogic/rss","website_url":"https://smartlogic.fireside.fm","image_url":"https://media24.fireside.fm/file/fireside-images-2024/podcasts/images/0/03a50f66-dc5e-4da4-ab6e-31895b6d4c9e/cover.jpg?v=3","author":"SmartLogic LLC","episode_count":201,"summary":"Elixir Wizards is an interview-style podcast from SmartLogic featuring conversations with developers, engineers, and industry leaders about the Elixir programming language and the broader software development landscape. Each episode explores how modern systems are built, from distributed architectures and infrastructure to developer workflows, security, and emerging technologies like AI. While rooted in the Elixir ecosystem, the show often branches out to compare approaches across languages, platforms, and disciplines. Whether you’re working in Elixir or just interested in how software is evolving, Elixir Wizards offers practical insights and thoughtful perspectives from the people building today’s systems.","last_synced_at":null,"page_url":"https://stenobird.com/podcast/elixir-wizards"},"episode":{"title":"LangChain: LLM Integration for Elixir Apps with Mark Ericksen","slug":"langchain-llm-integration-for-elixir-apps-with-mark-ericksen","published_at":"2025-06-12T10:30:00+00:00","page_url":"https://stenobird.com/podcast/elixir-wizards/langchain-llm-integration-for-elixir-apps-with-mark-ericksen","show_page_url":"https://stenobird.com/podcast/elixir-wizards","url":"https://smartlogic.fireside.fm/s14-e03-langchain-llm-integration-elixir","audio_url":"https://aphid.fireside.fm/d/1437767933/03a50f66-dc5e-4da4-ab6e-31895b6d4c9e/8707c422-2959-4052-a493-ba96183ba07e.mp3","summary":"Learn how to unify disparate AI providers like OpenAI, Anthropic, and Google Gemini under a single, consistent Elixir API. This episode explores building resilient, production-grade LLM workflows using the Elixir LangChain framework.","meta_description":"Master LLM integration in Elixir. Discover how Elixir LangChain abstracts APIs, manages token usage, and implements robust fallback strategies for AI apps.","key_points":["Main idea: Elixir LangChain provides a unified interface to shield developers from the rapid API drift and breaking changes of various LLM providers","Practical takeaway: Implement fallback chains (e.g., OpenAI to Azure) to maintain application uptime during provider outages or rate limits","Practical takeaway: Use the framework to track token usage per customer to manage costs and implement usage-based billing","Failure mode: Be wary of high-concurrency request spikes in Elixir that can quickly exhaust your LLM API rate limits and inflate costs","Technical detail: The v0.4 release introduces 'content parts' to support advanced reasoning and thinking-style models"],"chapters":[{"start_ms":60000,"title":"Introduction and Background","summary":"Mark Ericksen discusses his transition from Ruby on Rails to Elixir and his motivation for creating Elixir LangChain."},{"start_ms":235000,"title":"The Core Value of Abstraction","summary":"An exploration of how LangChain abstracts the complexities of different LLM request/response formats into a consistent API."},{"start_ms":580000,"title":"Extending Provider Support","summary":"How the framework evolves to support new features from providers like Gemini and the importance of community contributions."},{"start_ms":760000,"title":"Tool Integration and Structured Data","summary":"Using LLMs to extract structured data and trigger application-level functions through tool calling."},{"start_ms":930000,"title":"Resilience and Fallback Strategies","summary":"Implementing multi-region Azure or OpenAI-to-Azure fallback chains to ensure service continuity."},{"start_ms":1090000,"title":"Managing API Configuration and Tokens","summary":"Strategies for managing API keys, handling customer-provided keys, and tracking token usage for cost control."},{"start_ms":1785000,"title":"The Future of Thinking Models","summary":"A look at the v0.4 release and how 'content parts' enable support for next-generation reasoning models."}],"topics":["Elixir","LangChain","Large Language Models","API Abstraction","Software Resilience","Token Management","Open Source","AI Integration"],"duration_seconds":2298,"processing_state":"processed","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/elixir-wizards/episodes/langchain-llm-integration-for-elixir-apps-with-mark-ericksen/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/elixir-wizards/langchain-llm-integration-for-elixir-apps-with-mark-ericksen.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}