PyLand Team
PyLand Team
Author's articles
All publications PyLand Team
Document Chunking Strategies for RAG
Embedding a long document averages out its meanings β a specific question won't find the right paragraph. The solution is...
Pydantic v2: Data Validation in Python
Pydantic validates and converts data through type annotations. It is commonly used in APIs and LLM applications when an external...
asyncio in Python: Asynchronous Programming
asyncio is Python's standard library for asynchronous code. It lets you execute multiple tasks "simultaneously" within a single thread.
AsyncAnthropic: Async Client for the Claude API
AsyncAnthropic is the asynchronous version of the Anthropic client. It uses async/await and integrates with the asyncio event loop.
RAG: Chatting with Documents via Vector Search
RAG (Retrieval-Augmented Generation) is a pattern for working with your own documents. Instead of fine-tuning the model, you find the...
Prompt Caching in the Claude API: Saving on Tokens
Every request to Claude costs money. inputtokens includes everything: the system prompt, conversation history, and the current question. If you...
Embeddings: Coordinates of Text in Semantic Space
An embedding is a numerical vector that represents a piece of text. Texts that are similar in meaning get vectors...
JSON Schema: Describing Data Structures
JSON Schema is a standard for describing the structure of JSON. In the Claude API it is used to define...
Tool Use in the Claude API: Agents with Tools
Tool use lets Claude call functions in your code β fetching weather, reading files, running searches. Claude decides when to...
ChromaDB: Vector Database for RAG
ChromaDB is an embeddable vector database. It stores texts and their embeddings, and can search by semantic meaning. No separate...
SQLite in Python: Persistent Memory for Agents
SQLite is a relational database built into Python. It stores data in a single file and requires no server. It...
Health Checks: Liveness and Readiness in Kubernetes
A container is running β that does not mean the application is working. There might be a deadlock, memory overflow,...
Statistics by categories
Author's article distribution by topics
Django
63 articles
Python
54 articles
Git ΠΈ GitHub
32 articles
Html Css
23 articles
LLM ΠΈ AI
21 articles