Pondhouse Data Blog

blog preview

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.

4 min read
Read Post
blog preview

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.

6 min read
Read Post
blog preview

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.

12 min read
Read Post
blog preview

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.

13 min read
Read Post
blog preview

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.

10 min read
Read Post
blog preview

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.

22 min read
Read Post
blog preview

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.

7 min read
Read Post
blog preview

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.

5 min read
Read Post
blog preview

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.

9 min read
Read Post
blog preview

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.

17 min read
Read Post