RAG

Token optimization is the critical skill separating cost-effective LLM applications from budget-draining experiments.

Converting HTML to Markdown is a fundamental task in modern development workflows, particularly when preparing web content for Large Language Models (LLMs), documentation systems, or static site generators like Hugo.

This guide provides a comprehensive overview of available Go SDKs for Ollama and compares their feature sets.

Here is a comparison between Qwen3:30b and GPT-OSS:20b focusing on instruction following and performance parameters, specs and speed.

In this post, we’ll explore two ways to connect your Python application to Ollama: 1. Via HTTP REST API; 2. Via the official Ollama Python library.

Here’s a side-by-side support comparison of structured output (getting reliable JSON back) across popular LLM providers, plus minimal Python examples

Large Language Models (LLMs) are powerful, but in production we rarely want free-form paragraphs. Instead, we want predictable data: attributes, facts, or structured objects you can feed into an app. That’s LLM Structured Output.

Since standard Ollama doesn’t have a direct rerank API, you’ll need to implement reranking using Qwen3 Reranker in GO by generating embeddings for query-document pairs and scoring them.

This little Reranking Go code example is calling Ollama to generate embeddings for the query and for eache candidate document, then sorting descending by cosine similarity.

The Qwen3 Embedding and Reranker models are the latest releases in the Qwen family, specifically designed for advanced text embedding, retrieval, and reranking tasks.

• For a direct Beautiful Soup analogue in Go, use soup.
• For CSS selector support, consider goquery.
• For XPath queries, use htmlquery.
• For another Beautiful Soup-inspired option, look at Node.

If you’re looking for a Beautiful Soup equivalent in Go, several libraries offer similar HTML parsing and scraping functionality:

In the Ollama models library there are models that able convert HTML content to Markdown, which is useful for content conversion tasks.

Using LLMs is not very expensive, might be no need to buy new awesome GPU. Here is a list if LLM providers in the cloud with LLMs they host.

This guide explains how Ollama handles parallel requests (concurrency, queuing, and resource limits), and how to tune it using the OLLAMA_NUM_PARALLEL environment variable (and related knobs).

DeepSeek’s first-generation of reasoning models with comparable performance to OpenAI-o1, including six dense models distilled from DeepSeek-R1 based on Llama and Qwen.

Reranking is a second step in Retrieval Augmented Generation (RAG) systems, right between Retrieving and Generating.