Pondhouse Data Blog
LLM Sampling with FastMCP: Using Client LLMs for Scalable AI Workflows in your MCP
How MCP sampling lets a FastMCP server hand its LLM calls to the client: ctx.sample on the server, a sampling handler on the client, with code.
Automating MCP Server Creation from OpenAPI and FastAPI
Generate an MCP server from an existing OpenAPI spec or FastAPI app with FastMCP: route mapping, timeouts, parameter handling and code examples.
FastMCP Tutorial: Build an MCP Server in Python, Step by Step
What an MCP server is, how it differs from an API, and how to build one in Python with FastMCP: resources, templates, tools, progress reporting and a client.
What Is Langfuse? Open-Source LLM Observability, Self-Hosted
Self-host Langfuse with Docker Compose and use it to trace OpenAI calls, group them into sessions, score outputs and version your prompts.
Integrating n8n with Open WebUI: Building advanced AI chatbots and workflows
Connect Open WebUI to n8n with a webhook workflow and a Python pipe function, so chat messages trigger n8n workflows. Setup steps and full code.
Building High-Quality AI Agent Systems: Best Practices
Why multi-agent LLM systems fail, based on a study of 14 failure modes, and the design practices that make AI agent systems more reliable.
Building Powerful AI Agents with smolagents: A Minimalist Approach
smolagents is Hugging Face's minimal agent library: code agents that act in Python, sandboxed execution, support for any LLM and tips for better agents.
DeepSeek R1 On-Prem Setup: Run Advanced AI Models on Your Hardware with SGLang
Run DeepSeek-R1-Distill-Qwen-32B on two 24GB GPUs with SGLang: install, model download, Docker setup and OpenAI-compatible API calls in Python.
Building Better AI Applications with LLM Tracing using Opik
Self-host Opik, Comet's open-source LLM tracing tool, trace OpenAI, PydanticAI and LangChain calls, track costs and score traces with an LLM judge.
Building AI Agents with n8n: Postgres Tools, Memory and Human Approval
Build a self-hosted AI agent in n8n 2.46: order lookups in Postgres, chat memory, email drafts behind human approval. With screenshots, costs and pitfalls.









