[LLM] HyDE — Hypothetical Document Embeddings
An overview of HyDE (Hypothetical Document Embeddings), a technique for improving retrieval quality in RAG.
An overview of HyDE (Hypothetical Document Embeddings), a technique for improving retrieval quality in RAG.
An overview of LangChain’s LCEL, prompt templates, message classes, MessagesPlaceholder, and RunnableGenerator.
Using the Ollama Python library to connect to a remote LLM server, with generate, chat, and LangChain integration.
Configuring the OLLAMA_HOST environment variable and Windows Firewall to access a local LLM from other devices on the same network.
A complete guide to installing Ollama and running the Qwen3:8B model locally on Windows 11.