NORMA’s Post

Blog #22: Deploying a Python Application : Azure vs Nimbuz Platform   A quick comparison on deployment speed, flexibility and cost for Python workloads.   Click here to read: https://lnkd.in/gGWkdGDE   Explore: https://nimbuz.tech/   #nimbuzplatform #cloud #PaaS #appdeployment #Python #DevOps  #CloudComputing

Next article in my cross cloud Agent series - this installment covers building ADK agents and then deploying the complete solution to an Amazon cluster running AKS. A whole cluster just for one Agent? Probably overkill- but I wanted to start with the most basic approach before tackling more complex scenarios with multiple pods, agents, gateways, and proxies. The code base is virtually unchanged across clouds and is a building block to validate the approach. The Cross Cloud Series is here: https://lnkd.in/eHYsbUhH The Medium Article is here: https://lnkd.in/evpaZ8HY dev.to is here: https://lnkd.in/eJ_icFWJ #GDE #MCP #Python #GooogleCloud #AWScommunity #AWS #AWSCommunityBuilders

Most transcription APIs fall apart during a 60-minute enterprise audit. They lose context, hallucinate timestamps, or simply time out. We recently tackled this for a client who needed 100% accurate, word-level timestamps for multi-hour compliance calls. We engineered a custom pipeline using Google Cloud’s Chirp-3. By automating the chunking and merging logic through Python scripts, we bypassed the standard 20-minute constraints. Now, they get searchable, perfectly synced transcripts for audits that used to take days to review manually. #GoogleCloud #Transcription #MultimodalAI #ViMaxTech #SoftwareEngineering #chirp

Turn PDFs, markdown, and raw text into lineage-aware knowledge graphs. Query with local, global, hybrid, naive, mix, and graph-aware retrieval. Run the full stack in Rust on PostgreSQL. Built for teams that want Graph-RAG quality without Python pipeline fragility, cloud lock-in, or opaque retrieval behavior. https://edgequake.com/ #KnowledgeGraphs #GraphRAG

Next article in my cross cloud Agent series - this installment covers building ADK agents and then deploying the complete solution to an Amazon ECS cluster running ECS Express. A whole cluster just for an Agent? Probably overkill- but I wanted to start with the most basic approach before tackling more complex scenarios with multiple agents, gateways, and proxies. The code base is virtually unchanged across clouds and is a building block to validate the approach. The Cross Cloud Series is here: https://lnkd.in/eHYsbUhH The Medium Article is here: https://lnkd.in/ebjqBYfu dev.to is here: https://lnkd.in/er9ZFcSw #GDE #MCP #Python #GooogleCloud #AWScommunity #AWS #AWSCommunityBuilders

GC Magic Experiment: 0 to Production in < 4 hours. ⏱️ Just deployed my Python API on Google Cloud Run first time! The Setup: Python + Docker + Cloud Run. The Timeline: Under 4 hours to a live URL. I'm a fan of the serverless life. No servers to manage, no "it works on my machine" excuses—just code that runs. #GoogleCloud #Python #SoftwareEngineering #CloudRun #CodingLife

I have been posting non-stop from Google Cloud Next- but also made the latest AWS community builders list!! My article covered a multi-agent pipeline with an image generation model- all deployed to AWS ECS Express. ECS express gives you a lot of the benefits of Kubernates but without the management complexity. Article is here: https://lnkd.in/er9ZFcSw #MCP #Python #GoogleCloud #AWScommunity #AWS #AWSCommunityBuilders

🐍📰 AI Coding Agents Guide: A Map of the Four Workflow Types AI coding agents come in four types: IDE, terminal, PR, and cloud. Learn how each workflow fits into modern Python development https://lnkd.in/gGnXwxjk

Launch Week - Day 3: Custom Eval Support! Most teams default to LLM-as-a-Judge because it feels like the only option. But half your evals don't need an LLM. They need a function. With AgentMark, any function your engineers write can now be registered as an eval. Exact match, regex, JSON schema, custom business logic — if you can write it, the platform can run it. Same function, whether you're running experiments/evals locally or in the cloud. Define once, run everywhere. Works with TS and Python.

VoxCPM is a 2B parameter open-source TTS model that generates expressive, natural speech from text no API keys, no cloud, no per-character billing. Here's how to wrap it in a REST API and use it in your own projects. Read the full article: https://lnkd.in/gpxRFdCi #Text-to-Speech #VoxCPM #Python #FastAPI #OpenSource #VoiceAI #TTS