Pondhouse Data Blog
Artikel auf EnglischDeepSeek 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.
Artikel auf EnglischBuilding 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.
Artikel auf EnglischEnhancing Self-Made Agent with Memory: Keeping Context for Better Conversations
Add PostgreSQL-backed memory to a self-made Python AI agent: store every interaction, summarize long histories with GPT-4o and feed context into the prompt.
Artikel auf EnglischAdvanced Self-Made Agent: Building a Smarter, Multi-Step AI Agent
Extend a framework-free Python AI agent with an AgentState enum, a multi-step reasoning loop and clarifying questions to the user. Full code included.
Artikel auf EnglischHow to Build AI Agents Without Frameworks: A Step-by-Step Guide
Build an AI agent in plain Python with GPT-4o function calling: a PostgreSQL tool, a Wikipedia tool, a tool-call loop and PostgreSQL memory.
Artikel auf EnglischLate Chunking: Improving RAG Performance with Context-Aware Embeddings
Late chunking embeds the whole document first, then pools token embeddings into chunks. Python code with jina-embeddings-v3 and a similarity comparison.
Artikel auf EnglischDSPy Tutorial: Build Better AI Systems with Automated Prompt Optimization
A hands-on DSPy tutorial: the 8-step workflow, metrics and optimizers, and a summarization example where optimization lifted the score from 42% to 68%.
Artikel auf EnglischHow to create LLM tools from any Python SDK using langchain-autotools
langchain-autotools turns a Python SDK client into LangChain agent tools. Covers setup, CrudControls for picking functions and an Azure Blob Storage example.
Artikel auf EnglischHow to crawl websites for LLMs - using Firecrawl
Firecrawl turns websites into LLM-ready markdown. Python examples for scraping, crawling, Pydantic-based extraction, LangChain and self-hosting with Docker.
Artikel auf EnglischAzure AI Studio: How to evaluate and upgrade your models, using the Prompt Flow SDK
Check a new Azure OpenAI model against your current one before upgrading, using the Prompt Flow evaluation SDK, a GPT-4o judge and Azure AI Studio.









