LLMs & Ollama: Building Real World Free AI Apps with Ollama.

Explore building real-world ai apps with Ollama, using CLI, REST API, and Python library; learn retrieval augmented generation with knowledge stacks and private local models.

Connect your llama models to LM Studio on Windows using Golem. Install llama, LM Studio, and Go, then let Golem detect models and link them to LM Studio for use.

Learn to run local llms with Ollama and Open Web UI, delivering private, fast AI interactions on your machine, with multi-model management, offline use, and chat export/import.

Interact with Ollama using its Python library and rest API, installing the library, pulling models such as llama 3.2 or mistral, and generating text and chat with system messages.

Interact with the Ollama rest api from Python by sending post requests to a local server, enabling streaming responses and handling text and chat completions.

Build a retrieval augmented generation app with Ollama, Mistral, and a quadrant vector store by indexing and querying a JSON dataset about Star Trek.

Learn how to build a retrieval augmented generation (RAG) app using Llama index and a vector database, enabling real-time knowledge retrieval, domain expertise, and explainable responses.

Create vector embeddings with a Hugging Face model via Mendix, build a Qdrant-backed vector index, and enable semantic search with persistent storage for production readiness.

Build a Streamlit app that searches sarcastic headlines using Laminex as a vector store with a Hugging Face embedding model and a query engine to return top five similar headlines.

Build an AI powered coding assistant using Streamlit, dotenv, and link chain. Connect to a local Llama model to enable real-time coding help and debugging.

Build an AI code assistant with memory by assigning unique user IDs, creating a memory bank with an SQLite chat history, and retrieving or resetting conversations to personalize interactions.

Build a memory-enabled ai coding assistant by defining a personality, processing user inputs, and delivering context-aware responses, with code suggestions, debugging, and project-specific guidance.

Build an ai code assistant with Ollama and llms by setting up the workspace, loading Streamlit and dotenv, securing api keys, and connecting to a code llama model.

Give our ai coding assistant memory by recognizing users with a user ID and recalling past conversations through a memory bank powered by sqlite and streamlit session state.

Define a helpful ai coding assistant with system and user prompts, manage chat history, process questions, and display responses, enabling code suggestions and debugging in a real world app.

Enhance the AI code assistant by implementing chat history persistence in Streamlit, enabling history viewing, clearing, and optimized prompt processing with a runnable LM pipeline and a sidebar UI.

Explore deep coder v2, a code-focused open source llm with a mixture of experts. Download via Ollama, run with llama run, and consider hardware needs and quantized variants.

Explore building a real world ai data science assistant with Ollama, Streamlit, and multi-model workflows. Set up the environment, load CSVs, analyze images, and perform data cleaning, visualization, and analytics.

Run and test a real-world AI data science assistant app using Streamlit, the Ulama API, and a vision model in a multi-modal setup to analyze images and CSV files.