Tuning Local LLMs With RAG Using Ollama and Langchain

import os from datetime import datetime from werkzeug.utils import secure_filename from langchain_community.document_loaders import UnstructuredPDFLoader from langchain_text_splitters import RecursiveCharacterTextSplitter from get_vector_db import get_vector_db TEMP_FOLDER = os.getenv(‘TEMP_FOLDER’, ‘./_temp’) def allowed_file(filename): return filename.lower().endswith(‘.pdf’)…

Setting Up Ollama With Docker

Setting Up Ollama With Docker

docker ps Method 2: Running Ollama with Docker compose Ollama exposes an API on http://localhost:11434, allowing other tools to connect and interact with it. That was when I got hooked…