Loading…
Browse by type
Tutorial reads
Tutorial posts on Yomu, summarised newest first.
- 630 posts
- 20 companies
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
Tutorial posts
High-Throughput Structure Prediction with BioNeMo Inference Runtime
Proteome-scale biomolecular structure prediction requires moving large worklists efficiently, and NVIDIA BioNeMo Inference Runtime (BioIR) accelerates supported models on NVIDIA GPUs while retaining a PyTorch workflow. Its end-to-end processor passes InputRequest objects through parsing, tokenization, feature generation, GPU inference, and PDB or mmCIF writing; a Ray backend places complete model replicas on GPUs for concurrent independent inputs, while direct PyTorch integration supports custom code. In a matched 1,000-target human-dimer benchmark, BioIR completed all targets at 58.5K successfully folded residues per allocated GPU-hour versus 20.2K for the tested public implementation, a 2.90× improvement, which ran out of memory on 29 targets. Rated-power-equivalent estimates for one million comparable targets were 11 versus 35 MWh at 8-GPU TDP and 21 versus 64 MWh at full-node maximum power, excluding data-center overhead and several pipeline costs.
Loading Parquet data into MySQL with ClickHouse
The post demonstrates how to move Parquet data into MySQL and query the resulting table using ClickHouse table functions. It sets up MySQL 8.4 in Docker, runs clickhouse-local with a configuration file and named collection, and inspects StackOverflow votes stored in a 2024 Parquet file on S3. An INSERT INTO FUNCTION mysql statement loads the file into a MySQL InnoDB table with 12,296,977 rows, while subsequent examples query MySQL from ClickHouse using either translated ClickHouse syntax or an opaque MySQL SQL string. The post also shows named-collection credentials and a query that identifies posts with both upvotes and downvotes, returning ten ranked results. It concludes that this workflow stays within ClickHouse and notes that table functions also support Postgres, SQLite, and MongoDB.
How to Build a Voice AI Agent with OpenAI's GPT-Live, Twilio Agent Connect, and Python
This tutorial shows how to build a phone-based voice AI agent with OpenAI's GPT-Live, Twilio Agent Connect, and Python. It configures TAC's GPTLiveProvider to bridge Twilio Programmable Voice Media Streams to GPT-Live-1 in the OpenAI API, using 8kHz mu-law audio and avoiding custom WebSocket plumbing. The tutorial sets a proactive greeting, exposes a Python weather function through Responses delegation, and runs the function outside the real-time voice loop so a simulated three-second backend delay does not block the conversation. The resulting setup handles inbound calls through a Twilio webhook and outbound calls with an E.164 number, while the tutorial also notes per-call customization and alternative voice providers.
121+ Cyber Monday email subject line examples in 2026
Cyber Monday email marketing depends on subject lines to help messages stand out in a crowded inbox, even when designs and discounts are strong. The guide recommends pairing subject lines with preview text, emphasizing exclusivity and urgency, stating discount amounts, using emojis selectively, and keeping copy concise. It also covers personalization, segmentation, pre-event notices, abandoned-cart messages, and reminders. More than 121 examples and templates are organized into Cyber Monday, pre-event, FOMO, abandoned-cart, and emoji-heavy categories, with additional seasonal resources. The post positions Twilio SendGrid for campaign execution and reports 75.1 billion emails processed during Cyber Week in 2025, a 14.6% increase over the previous record-breaking sending, but provides no comparative performance results for the example lines.
Build an AI Voice Assistant with Twilio Voice and Media Streams, OpenAI's GPT-Live API, and Node.js
This tutorial shows how to build an AI voice assistant that answers phone calls using Twilio Programmable Voice, Twilio Media Streams, OpenAI's GPT-Live-1, and Node.js. GPT-Live-1 acts as the speech-to-speech model for listening, talking, and handling interruptions, while the delegated gpt-5.6-terra model handles deeper reasoning and tool use. The implementation uses a Fastify server with WebSocket support, dotenv configuration, a marin voice, and separate prompts for the voice and backend roles. Callers can request a city's top headline through the custom get_top_headline function or ask factual questions through OpenAI's hosted web_search tool. The guide exposes port 5050 with ngrok, points a Twilio number at an /incoming-call webhook, and concludes that the working example fits in under 200 lines.
Make Outbound Calls with Twilio Voice and Media Streams, GPT-Live-1 in the OpenAI API, and Node.js
This tutorial shows how to build an outbound AI voice agent that uses Twilio Programmable Voice and Media Streams to call a permitted phone number, rather than waiting for inbound calls. It connects the call to GPT-Live-1 in the OpenAI API through a Node.js server, with Fastify, ws, dotenv, and the Twilio helper library handling the application and relay. The implementation reads the destination from a --call flag, validates E.164 formatting, exposes the server through a public tunnel, and uses environment variables for credentials and the calling number. Owlie identifies itself as an AI assistant, retrieves a callback note with get_callback_reason, delegates factual questions to hosted web_search, and can be interrupted during speech. The completed demo rings the chosen number, explains why it is calling, and can return random callback notes or web-searched answers, while the tutorial stresses verified numbers, model access, and outbound-calling compliance.
Rebuilding AUTOMATIC1111 with Gradio Workflow
Workflow1111 rebuilds most of AUTOMATIC1111’s stable-diffusion-webui feature set as a single Gradio Workflow canvas. It combines eleven media pipelines and 73 nodes for text-to-image, refinement, image-to-image, prompting, interrogation, detection masks, annotators, upscaling, background removal, PNG metadata, and image-to-video. The implementation uses four operator kinds—Python fn functions, model calls through InferenceClient, Space calls, and Hub dataset rows—with parallel branches for independent work; 32 of 36 operator nodes are fn nodes, and 22 run in-process without network calls. Models can run through Inference Providers, Spaces, or a local GPU, while output nodes automatically become REST endpoints and MCP tools. The result is a browser-accessible, OAuth-enabled workflow that can also be duplicated, rewired, deployed, and called from code.
Testing application resilience with Amazon SQS and AWS Fault Injection Service
The post presents a resilience-testing tutorial for applications that depend on Amazon Simple Queue Service (Amazon SQS), where failed queue operations can stall downstream processing and trigger cascading outages. It uses AWS Fault Injection Service (AWS FIS) and AWS Systems Manager (SSM) Automation to apply a scoped deny resource policy that blocks data-plane actions, including sending, receiving, deleting, changing visibility, and purging, while preserving queue management. The experiment increases disruption across four phases, then observes producer-side and consumer-side behavior through application and Amazon CloudWatch metrics, including circuit-breaker state, failed sends, backlog, message age, duplicates, and dead-letter-queue effects. The guidance emphasizes hypotheses with measurable success criteria, non-production guardrails, tagged target queues, and a stop condition based on customer impact. It also describes consumer-only, partial, and compound-failure extensions, warning that concurrent experiments on one queue can leave a stale deny policy.
Validating multi-Region DR for Terraform Enterprise with AWS FIS
Athenahealth’s single-Region Terraform Enterprise deployment became inaccessible to developers during an October 2025 AWS regional service event, exposing missing regional failover capabilities. The post describes a customer-operated active-passive design spanning us-east-1 and us-west-2, using Aurora PostgreSQL-Compatible global databases, bidirectional S3 cross-Region replication, Route 53 health checks, and compute scaled to zero in the DR Region. AWS Fault Injection Service experiments validate three phases of recovery, including failover, failback, and disruptions that can reveal dependencies such as state-file lookups or S3 connectivity. The resulting architecture achieved a validated 12–14 minute RTO and less than one minute RPO, while costing approximately 30–40% more than the single-Region deployment. The design is presented as an option for critical workloads rather than a supported multi-Region TFE product configuration.
Deploy NeMo Guardrails on Red Hat OpenShift AI
This article shows how to deploy an evaluated NeMo Guardrails configuration on a Red Hat OpenShift AI cluster, continuing a series on local development and dataset-based evaluation. It requires OpenShift AI 3.5 or later and namespace write access, while OpenShift AI 3.2 or newer can be configured to use the 3.5 NeMo Guardrails image through TrustyAI service-operator changes. Deployment uses a ConfigMap for the configuration, a NemoGuardrails custom resource, and an authentication annotation that protects the server route; an empty rails.co file is sufficient when no custom algorithms are defined. The deployed server accepts v1/guardrail/checks requests with a bearer token, and the demonstrated classifier permits a benign prompt, blocks a prompt injection, and rejects an invalid token. The article notes that LLM proxying and LLM-based guardrailing are outside its scope.
Use a local and open source code assistant
Closed or cloud-based coding assistants can expose work to external services, so the article presents a local, open-source alternative built around OpenCode. OpenCode is an AI coding agent—not an LLM—that runs as a terminal interface, desktop application, or IDE extension and connects to models through the Model Context Protocol (MCP). The setup installs OpenCode, selects a local model runtime such as Ollama for AMD/NVIDIA GPUs or OpenVINO Model Server with INT4 Qwen3-8B for Intel integrated graphics, then configures opencode.jsonc and an editor plug-in. Examples cover Qwen3:14b with Ollama, Podman-based OpenVINO serving, and NetBeans integration; the resulting assistant can answer queries and edit files after permission is granted, although local inference may be slow and generated advice can be unreliable.
Personalize your product's text-to-speech voice for any language: Fine-tuning with Kubeflow Trainer on Red Hat OpenShift AI
Training an English-centered text-to-speech model for Turkish can produce fluent but hard-to-understand pronunciation for native speakers. This tutorial fine-tunes unsloth/orpheus-3b-0.1-pretrained with about 81,000 Turkish text-audio pairs on Red Hat OpenShift AI using a Kubeflow Trainer TrainJob distributed across two nodes with two A100 GPUs each. LoRA freezes the 3-billion-parameter base and trains 97.3M adapter parameters, while preprocessing converts text to Llama-3 tokenizer tokens and audio to three-layer SNAC codes, masking text labels during scoring. The merged model is evaluated against the base on ten Turkish sentences using Whisper transcription and WER/CER metrics. Mean WER falls from 2.44 to 0.35 and CER from 1.59 to 0.09, though the authors describe the small test as directional.
Build a Fraud Review Agent with MongoDB Atlas and Claude Managed Agents
Claude Managed Agents runs Anthropic’s Claude as a hosted agent without managing inference infrastructure. Pairing it with MongoDB Atlas provides fast access to operational and vector data through a single pymongo connection, eliminating the need for separate vector, full-text, and graph stores. This tutorial builds a human-in-the-loop fraud review agent that retrieves flagged transactions, runs four retrieval patterns (vector, full-text, hybrid, and graph) against one collection, and escalates risky cases to a human reviewer using Managed Agents’ native pause. The credential-safe integration uses host-side custom tools so the MongoDB connection string never enters the agent sandbox, keeping secrets on your side. The agent verifies a signed authorization mandate, uses $graphLookup to detect mule chains and $rankFusion for hybrid search, writes immutable verdicts and audit events back to the same cluster, and triggers durable human pauses on structuring deposits just under $5,000, wires over $50,000, and ring signals from graph traversal.
10+ best practices to improve your email deliverability
Email deliverability determines whether messages reach inboxes rather than merely being accepted by recipient mail servers, and the guide distinguishes delivery rate from inbox placement. It recommends authenticating domains with SPF and DKIM, using appropriate IP allocation and warm-up, applying double opt-in, writing genuine subject lines, offering preference controls, cleaning lists, avoiding purchased addresses and spam traps, sending valuable content, and monitoring metrics. The stated benchmark for good deliverability is at least 95%, while the excerpt cites Twilio SendGrid's 99% API rate and warns that changing providers does not repair domain or IP reputation. Case studies report Shopify at 99.5% overall delivered and 91.3% inbox placement, and Klaviyo at 99.94% average delivery, with the latter also reporting 1.9-second median delivery speed.
From AI Agent to Human Agent: ElevenLabs Call Handoffs with Twilio
This reference integration connects an ElevenLabs voice agent to Twilio Programmable Voice, enabling escalation from automated support to a human when a conversation becomes complex, sensitive, or unresolved. Twilio retains ownership of the original inbound call while ElevenLabs conducts the real-time conversation; an escalate_to_human webhook tells Twilio to update that parent Call SID with new TwiML. In the Flex example, Enqueue sends the caller into a TaskRouter workflow, creating a voice task with intent and summary context, while the Call SID and metadata such as direction and phone numbers travel into ElevenLabs as dynamic variables for the handoff. The blueprint describes Studio-owned routing, direct TaskRouter or Flex routing, and custom TwiML destinations; Conversation Memory and Conversation Intelligence are optional additions, and the implementation is explicitly a proof of concept rather than a production drop-in.
Optimize vLLM speculative decoding with FastMTP heads
Autoregressive LLM inference is memory-bandwidth bound because each token requires a full pass over billions of parameters, while speculative decoding can verify several drafted tokens in one pass. Speculators 0.6.0 adapts a single native MTP head with FastMTP-style recursive fine-tuning, addressing the mismatch between teacher-forced training and vLLM’s autoregressive reuse of the head. The training loop fuses each next-token embedding with the current hidden state, predicts the following token, feeds the resulting hidden state back, and weights three steps with normalized exponential decay using β = 0.6. Native mtp.* weights extraction, shared full-vocabulary embeddings and output head, and vLLM-compatible stitching support deployment; on Qwen3-Next-80B-A3B-Instruct evaluated on GSM8K, mean accepted length improved at positions 0–2 from 0.897, 0.719, 0.476 to 0.912, 0.776, 0.616.
Integrate Deepgram Flux with Twilio's Conversation Relay
Twilio's ConversationRelay connects phone calls to an AI stack while handling speech-to-text, text-to-speech, and the WebSocket session, leaving application code focused on the LLM and conversation logic. This tutorial updates a Node.js ConversationRelay application to use Deepgram Flux, which combines transcription and turn detection and is described as reducing response latency by up to 200–600 milliseconds and false interruptions by around 30 percent. It walks through cloning a Fastify demo, exposing it with ngrok, configuring environment variables, and adding Flux settings to the ConversationRelay TwiML, including eotThreshold, speechTimeout, and ignoreBackchannel. The supplied configuration uses an end-of-turn threshold of 0.8, a 3,000-millisecond speech timeout, and enabled backchannel ignoring, while the tutorial also explains partial prompts, smart formatting, and recognition hints.
Holiday email marketing best practices for 2026 (and beyond)
Holiday email marketing carries higher volume and stakes during the seasonal shopping period, making planning, deliverability, personalization, and post-holiday retention central concerns. The guide recommends warming sending volume before Black Friday and Cyber Monday, increasing it by only 25–40% at a time to avoid sudden mailbox-provider signals. It also calls for a calendar with one or two lower-volume days each week, list hygiene, segmentation, testing, and journey-driven campaigns that account for shipping and fulfillment constraints. For holiday-season signups, the post-holiday process uses sign-up date or source cohorts, monitors open and click rates, and can reduce frequency, run re-engagement campaigns, or suppress addresses after 30–60 days without engagement. Examples and templates emphasize concise, value-driven content, specific offers, and personalization such as location or past purchases.
How MCP Toolbox turns agent text into ClickHouse vectors
MCP Toolbox for Databases addresses the gap between an AI agent’s text queries and ClickHouse’s SQL and vector interfaces by translating text into embeddings for both ingestion and search. A flat YAML configuration declares a Gemini embedding model, associates parameters with it through embeddedBy, inserts content and vectors, and ranks matches with ClickHouse’s cosineDistance function; the agent receives ranked rows without handling vectors. The post walks through installation, prebuilt ClickHouse tools, custom tools, toolsets, and an end-to-end synthetic-corpus run using Toolbox 1.9.0 and ClickHouse Cloud 26.4.1. At the demonstrated 57-row scale, search uses exact O(n) brute force because the HNSW index adds overhead, while larger datasets can use approximate search. Limitations include Gemini-only embeddings, a hardcoded SEMANTIC_SIMILARITY task type, opt-in REST endpoints, and restart-required configuration changes.
Understanding W8A8 INT8 LLM quantization: Half the size, better performance, same accuracy
Serving Llama 3.1 8B in BF16 requires roughly 14.9 GB for weights, leaving little VRAM on a 16 GB GPU for KV cache and activations, which limits practical deployment. The workflow benchmarks the base model, applies INT8 W8A8 quantization with llm-compressor, then repeats accuracy and performance tests under identical hardware and load conditions. SmoothQuant modifies weights to reduce activation outliers, while GPTQ uses calibration data and error compensation before rounding weights to INT8; the experiment used 512 WikiText-2 samples and targeted deployment with vLLM. On the Llama 3.1 8B Instruct model, compression reduced storage from 14.9 GB to 8.0 GB, a 46% reduction, and accuracy was preserved across MMLU, ARC, HellaSwag, and IFeval; generation-speed results are reserved for part 2.
Top topics
- Architecture834
- Performance817
- LLMs673
- Machine Learning622
- Open Source568
- AI Agents564
- AI483
- Developer Experience448
Weekly digest
The best engineering reads, once a week.