Ollama Projects | AI Final Year Project Report

Complete Technical Paper Content — Ollama Projects

1. Executive Abstract, Problem Formulation & Background

MLX is an open-source machine learning framework developed by Apple and designed primarily for Apple silicon. It is used for training and running machine learning models and is optimized for Apple silicon's unified memory architecture, allowing the CPU and GPU to work with the same data without copying it between separate memory pools. MLX can be used for applications including large language model training and inference, image generation, and speech recognition.

These lists include projects which release their software under open-source licenses and are related to artificial intelligence projects. These include software libraries, frameworks, platforms, and tools used for machine learning, deep learning, natural language processing, computer vision, reinforcement learning, artificial general intelligence, and more.

Auto-GPT — experimental open-source autonomous GPT-based agent OpenClaw — autonomous task-executing AI agent CrewAI — framework for building and orchestrating multi-agent AI systems LangChain — framework for building applications and agents powered by large language models Theia AI — framework for integrating AI capabilities and agents into integrated development environments (IDEs).

Codex CLI – AI coding agent and command-line interface developed by OpenAI. Cline – AI coding agent for IDEs and the command line. Command Code — CLI and desktop AI agent DeepSeek Coder – large language model designed for code generation and AI-assisted software development. goose – AI coding agent for the desktop and command line. Grok Build – SpaceXAI's terminal-based AI coding agent. Hermes Agent – AI coding agent for the command line and IDE extensions. Kilo Code — CLI and IDE extension developed by Anaconda OpenCode — CLI, desktop app, web app, and IDE extensions OpenHands — AI software development agent Oh My Pi – terminal-based AI coding agent developed as a fork of Pi. Pi – terminal-based AI coding agent. Warp – agentic development environment combining a terminal, integrated coding agent, and CLI. Zed – source-code editor with integrated AI-assisted development and agentic coding features.

EDLUT – event-driven neural network simulator for large-scale spiking networks Emergent – cognitive modeling platform implementing neural networks Encog – machine learning framework for Java and C# supporting neural networks JOONE – Java-based neural network framework with modular architecture for learning tasks Nengo – Python library for building and simulating large-scale neural systems Neuroph – lightweight Java framework for creating neural networks OpenNN – C++ library for designing, training, and deploying neural networks SNNS – Stuttgart Neural Network Simulator, supports feedforward and recurrent neural networks

ACT-R – cognitive architecture for modeling human cognition and developing cognitive agents. CLARION – Connectionist Learning with Adaptive Rule Induction On-line, hybrid connectionist/symbolic cognitive architecture. OpenCog – project that aims to build an open source artificial intelligence framework Soar – cognitive architecture for decision-making and learning in intelligent agents

AForge.NET – computer vision, artificial intelligence, and robotics library for the .NET framework Dlib – C++ library for computer vision and image processing OpenCV — library of programming functions mainly for real-time computer vision Point Cloud Library – library for point cloud processing Tesseract – optical character recognition

2. Related Work, Literature Survey & Algorithmic Foundations

BigDL – distributed deep learning library for Apache Spark Caffe – deep learning framework focused on speed and modularity Deeplearning4j – Java library for deep learning algorithms on the Java virtual machine DeepSpeed – deep learning optimization library developed by Microsoft fastai – deep learning library built on top of PyTorch Fast Artificial Neural Network (FANN) – C library for feedforward neural networks Horovod – distributed deep learning framework for TensorFlow, Keras, and PyTorch Hugging Face Transformers — open-source deep learning library developed by Hugging Face Keras – Python library for artificial neural networks Microsoft Cognitive Toolkit – deep learning framework developed by Microsoft Research MXNet – deep learning framework for training and deploying deep neural networks Neuroph – object-oriented artificial neural network framework written in Java OpenNN – artificial neural network library written in C++ PlaidML – deep learning backend for neural networks and tensor computations PyTorch – deep learning framework developed by Meta AI PyTorch Lightning – high-level framework built on top of PyTorch for organizing and scaling deep learning models TensorFlow – end-to-end open-source platform for machine learning and deep learning developed by Google Brain Torch – scientific computing framework with support for machine learning and deep learning algorithms

Accord.NET — C# framework for machine learning, statistics, computer vision, and signal processing Apache Mahout — scalable machine learning library for big data built on Hadoop and Spark Apache SINGA — distributed deep learning and machine learning software Apache SystemDS — ML system for the end-to-end data science lifecycle CatBoost — machine learning library for gradient boosting on decision trees Caffe — Image classification and image segmentation Dlib — C++ machine learning and computer vision library ELKI — data mining and unsupervised learning software fastText — Word embeddings developed by Meta AI Flux — machine learning library for the Julia programming language Gensim — topic modelling and vector space model toolkit JAX — machine learning library for numerical computing and automatic differentiation H2O — machine learning and predictive analytics platform Infer.NET — probabilistic programming framework for Bayesian inference Jubatus — online machine learning and distributed computing framework KNIME — modular data pipelining LIBSVM — library for support vector machines LightGBM — machine learning framework for gradient boosting Massive Online Analysis — framework for machine learning and data mining on evolving data streams Microsoft Cognitive Toolkit — deep learning framework developed by Microsoft Research MindSpore — machine learning and deep learning framework ML.NET — machine learning framework for .NET mlpack — C++ header-only machine learning library MLX — machine learning framework for Apple silicon supporting model training, inference, and fine-tuning MXNet — deep learning framework Orange — machine learning, data mining, data visualization, and data analysis PyMC — Python framework for Bayesian modeling and probabilistic programming Scikit-learn — library built on top of NumPy, SciPy, and matplotlib Scikit-multiflow — Python framework for online and stream machine learning Shogun — C++ library for large-scale machine learning Spark MLlib — machine learning library for Apache Spark TensorFlow — machine learning and deep learning platform Theano — numerical computation library for machine learning Vowpal Wabbit — machine learning system for fast online learning Weka — collection of machine learning algorithms for data mining tasks XGBoost — machine learning library for gradient boosting

TPOT – tree-based pipeline optimization tool using genetic programming Neural Network Intelligence – Microsoft toolkit for hyperparameter tuning and neural architecture search MindsDB – AutoML platform that embeds machine learning into SQL databases and applications

Apertus – Swiss National AI Initiative LLM BERT – Google LLM BLOOM – BigScience multilingual LLM Cerebras-GPT – Cerebras Systems LLMs DeepSeek – R1 and V3 models Gemma 4 – Google LLM GLM-4.5 and later versions – Z.ai LLMs GPT-1, GPT-2, and GPT-OSS – OpenAI LLMs GPT-J, GPT-Neo, and GPT-NeoX – EleutherAI LLMs Hy – Tencent open-weight LLM Granite – IBM LLMs Grok-1 – xAI LLM Inkling – Thinking Machines Kimi (some versions) – Moonshot AI LLMs MiMo (some versions) – Xiaomi LLMs Mistral (some versions) Muse Glimmer — Meta Superintelligence Labs LLM Nemotron 3 – Nvidia open-weight models OLMo – Allen Institute for AI LLM Phi – Microsoft LLMs Qwen (some versions) – Alibaba Cloud LLMs Sarvam-M, Sarvam-105B and Sarvam-30B – Sarvam AI LLMs SmolLM – Hugging Face small language models (SLMs) Step-3.7Flash – StepFun LLM T5 – Google LLM XLNet – Google LLM

Apache OpenNLP Apertium – rule-based machine translation platform. ChatScript – natural language engine and dialog management system General Architecture for Text Engineering – information extraction Gensim – topic modeling and document similarity analysis library GloVe – unsupervised learning algorithm for obtaining vector representations of words Mallet – Java "Machine Learning for Language Toolkit" MontyLingua – libraries and programs for symbolic and statistical NLP for both Python and Java Moses – statistical machine translation engine to train statistical models of text from a source language to a target language NiuTrans – statistical machine translation NLTK – natural Language toolkit for symbolic and statistical NLP Probabilistic Action Cores – interpreter for natural-language instructions for robotic applications spaCy – Python library Spark NLP – text processing library for advanced NLP for Python, Java, and Scala. Word2vec – obtaining vector representations of words

GOLOG – logic programming language, situation calculus, first-order logical language for reasoning about action and change.

AlphaTensor – DeepMind reinforcement-learning system for discovering efficient matrix multiplication algorithms

3. Dataset Ingestion, Preprocessing & Stochastic Augmentations

ConceptNet – multilingual commonsense knowledge graph used in natural-language processing and artificial-intelligence applications. DBpedia – project that extracts structured knowledge from Wikipedia using an open-source extraction framework.

Open-source artificial intelligence List of artificial intelligence algorithms List of artificial intelligence journals and List of artificial intelligence books List of artificial intelligence projects List of free and open-source software packages for artificial intelligence List of proprietary artificial intelligence software Open weights Common Crawl – nonprofit that crawls the web and freely provides its archives and datasets to the public under an MIT License Google Colab – an O-IDE Jupyter notebook environment with free access to GPUs and TPUs for machine learning and deep learning development Applications of artificial intelligence

Learning Ollama with Projects A comprehensive collection of 30 Python scripts using Ollama and its Python SDK, organized by difficulty level. Learn to build AI-powered applications with local LLMs through practical, hands-on projects. Each script comes with detailed requirements documentation (Pflichtenheft) describing functionality, inputs, outputs, and tests. 📚 Project Structure This repository contains 30 Ollama projects divided into three difficulty levels: Beginner (10 projects): Fundamental Ollama concepts and basic LLM interactions Advanced (10 projects): Real-world applications and advanced features Expert (10 projects): Complex AI patterns and architectures Each project is contained in its own directory with: script.py - The Python implementation using Ollama SDK Pflichtenheft.md - Requirements document with functionality, I/O specs, and test cases 🎯 Beginner Level Perfect for those starting their Ollama journey. Learn basic LLM interactions and foundational concepts. # Project Description 01 Hello LLM Basic LLM interaction and model communication 02 Simple Chat Simple chat interface with a model 03 Prompt Templates Working with prompt templates 04 Model Info Getting model information and details 05 Text Completion Text completion tasks 06 Streaming Response Streaming responses for real-time output 07 Temperature Control Parameter control and model behavior 08 System Prompts Using system prompts for model behavior 09 Conversation History Maintaining conversation context 10 List Models Listing and managing available models 🚀 Advanced Level Build real-world AI applications with advanced Ollama features. # Project Description 01 Code Assistant Code generation and programming assistance 02 Summarization Tool Text summarization with LLMs 03 Sentiment Analyzer Sentiment analysis of text 04 Translation Service Multi-language translation 05 QA System Question-answering system 06 Content Generator Content generation tool 07 Data Extractor Extract structured data from text 08 Chat with Context Context-aware chatbot 09 Few-Shot Learning Few-shot learning examples 10 JSON Mode Structured JSON responses 💎 Expert Level Master advanced AI patterns and build sophisticated applications. # Project Description 01 RAG System Retrieval Augmented Generation 02 Function Calling Function/tool calling patterns 03 Multi-Model Ensemble Using multiple models together 04 Embedding Search Semantic search with embeddings 05 Async Processing Asynchronous/concurrent processing 06 Custom Model Adapter Custom model configuration 07 Conversation Manager Advanced conversation management 08 Prompt Optimizer Prompt optimization framework 09 Model Evaluator Model performance evaluation 10 AI Agent Framework Autonomous AI agent system 🛠️ Getting Started Prerequisites Python 3.8 or higher pip (Python package manager) Ollama installed and running ( Installation Guide ) At least one model pulled (e.g., ollama pull llama3 ) Installation Clone the repository: git clone https://github.com/r14r/Learning_Ollama_with-Projects.git cd Learning_Ollama_with-Projects Create a virtual environment (recommended): python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate Install dependencies: pip install -r requirements.txt Ensure Ollama is running and pull a model: # Check if Ollama is running ollama list # Pull a model if needed (e.g., llama3) ollama pull llama3 Running a Script Navigate to any project directory and run the script: cd beginner/01_hello_llm python script.py Each script is self-contained and can be run independently. 📖 Learning Path Recommended Order: Start with Beginner : Complete all 10 beginner projects to understand Ollama basics Move to Advanced : Build practical AI applications Challenge with Expert : Master advanced patterns and architectures How to Use Each Project: Read the Pflichtenheft.md - Understand the requirements and what the script should do Study the script.py - Analyze the implementation and code patterns Run the script - See it in action and observe the output Modify it - Experiment with changes and parameters Try the tests - Verify functionality works as expected 🎓 What You'll Learn Beginner Level Basic Ollama SDK usage Model interaction and communication Prompt engineering fundamentals Response handling and streaming Parameter tuning (temperature, top_p, etc.) System prompts and conversation history Model management Advanced Level Code generation and assistance Text analysis and transformation Natural language processing tasks Context management Few-shot learning techniques Structured output generation Building practical AI tools Expert Level Retrieval Augmented Generation (RAG) Function calling and tool use Multi-model architectures Semantic search with embeddings Asynchronous processing Custom model configurations AI agent patterns Prompt optimization Model evaluation and benchmarking 📝 Documentation Format Each Pflichtenheft.md includes: Expected Functionality : What the script does Input : What data/parameters it accepts Expected Output : What results it produces Tests : Sample test cases with expected results Dependencies : Required Python packages Usage : How to run the script 🔧 Common Ollama Models Popular models to use with these projects: llama3 - Meta's Llama 3 model (recommended for beginners) mistral - Mistral AI's efficient model codellama - Specialized for code tasks phi3 - Microsoft's compact model gemma2 - Google's Gemma model Pull a model: ollama pull <model-name> 🤝 Contributing Contributions are welcome! Feel free to: Report bugs Suggest new projects Improve existing code Add more test cases Enhance documentation 📄 License This project is open source and available for educational purposes. 🙏 Acknowledgments Built with Ollama and the Ollama Python SDK Inspired by practical, hands-on learning approaches Created as a comprehensive learning resource for AI developers at all levels Happy Learning with Ollama! 🤖

A comprehensive collection of 30 Python scripts using Ollama and its Python SDK, organized by difficulty level. Learn to build AI-powered applications with local LLMs through practical, hands-on projects. Each script comes with detailed requirements documentation (Pflichtenheft) describing functionality, inputs, outputs, and tests.

Perfect for those starting their Ollama journey. Learn basic LLM interactions and foundational concepts.

git clone https://github.com/r14r/Learning_Ollama_with-Projects.git cd Learning_Ollama_with-Projects

# Check if Ollama is running ollama list # Pull a model if needed (e.g., llama3) ollama pull llama3

4. Neural Network Backbone, Layer Specifications & Loss Formulations

This project is licensed under the MIT License - see the LICENSE file for more details.

Interesting LLM projects that I created for my YouTube channel using Ollama's open-source models.

Lab 1 introduces local LLM execution using Ollama, demonstrating both interactive CLI and API-based interaction.

graph TB subgraph "Local Machine" subgraph "Ollama Service :11434" OllamaServer[Ollama Server HTTP API] ModelStore[Model Storage llama3.2] end subgraph "User Interactions" CLI[CLI Interface ollama run] Python[Python Program simple_ollama.py] CURL[API Client curl/HTTP] end subgraph "Python Stack" LangChain[LangChain-Ollama Library] ChatOllama[ChatOllama Class] Python --> LangChain LangChain --> ChatOllama end OllamaServer --> ModelStore CLI --> OllamaServer CURL --> OllamaServer ChatOllama -->|HTTP POST :11434/api/chat| OllamaServer end Internet[Internet ollama.com] -.->|Pull Models| ModelStore style OllamaServer fill:#e1f5ff style ModelStore fill:#fff4e1 style CLI fill:#e8f5e9 style Python fill:#e8f5e9 style LangChain fill:#fff4e1 style ChatOllama fill:#ffe8e8

sequenceDiagram participant User participant Python as Python Program participant ChatOllama as ChatOllama Class participant HTTP as HTTP Client participant Ollama as Ollama Server :11434 participant Model as llama3.2 Model User->>Python: Run simple_ollama.py Python->>User: Prompt for input User->>Python: "What is the capital of France?" Note over Python,ChatOllama: LangChain Wrapper Python->>ChatOllama: llm.invoke("What is...") ChatOllama->>ChatOllama: Format as chat message Note over ChatOllama,Ollama: HTTP API Call ChatOllama->>HTTP: POST /api/chat HTTP->>Ollama: {"model": "llama3.2", "messages": [...]} Note over Ollama,Model: Local Inference Ollama->>Model: Load model if needed Model->>Model: Generate response Model->>Ollama: "The capital of France is Paris." Note over Ollama,Python: Response Flow Ollama->>HTTP: JSON response HTTP->>ChatOllama: Response data ChatOllama->>Python: AIMessage object Python->>User: Print response.content

import requests import json response = requests . post ( "http://localhost:11434/api/chat" , json = { "model" : "llama3.2" , "messages" : [{ "role" : "user" , "content" : "What is AI?" }], "stream" : False } ) data = response . json () print ( data [ "message" ][ "content" ])

5. Training Protocol, Convergence Behavior & Experimental Evaluation

from langchain_ollama import ChatOllama llm = ChatOllama ( model = "llama3.2" ) response = llm . invoke ( "What is AI?" ) print ( response . content )

LangChain is a framework for building applications with Large Language Models (LLMs). It provides:

In Lab 1, we use the langchain-ollama package, which is LangChain's official integration for Ollama.

graph TB subgraph "Your Python Code" Code[simple_ollama.py] end subgraph "LangChain Layer" ChatOllama[ChatOllama Class] Formatter[Message Formatter] HTTPClient[HTTP Client] ChatOllama --> Formatter Formatter --> HTTPClient end subgraph "Ollama Server" API[REST API :11434] Router[Endpoint Router] Inference[Inference Engine] API --> Router Router --> Inference end subgraph "Model Layer" ModelFile[llama3.2 GGUF] end Code -->|1. llm.invoke| ChatOllama HTTPClient -->|2. HTTP POST| API Inference -->|3. Load| ModelFile ModelFile -->|4. Generate| Inference Inference -->|5. JSON| API API -->|6. Response| HTTPClient HTTPClient -->|7. AIMessage| Code style ChatOllama fill:#e1f5ff style API fill:#fff4e1 style Code fill:#e8f5e9 style ModelFile fill:#ffe8e8

# simple_ollama.py - Basic Ollama interaction # Step 1: Import LangChain's Ollama integration from langchain_ollama import ChatOllama # Step 2: Create ChatOllama instance # This establishes the connection parameters but doesn't connect yet llm = ChatOllama ( model = "llama3.2" , # Which Ollama model to use base_url = "http://localhost:11434" , # Ollama server (default) temperature = 0.7 # Controls randomness (0=deterministic, 1=creative) ) # Step 3: Get user input user_prompt = input ( "Enter your prompt: " ) # Step 4: Send to Ollama and get response # invoke() does the following: # a. Formats prompt as {"role": "user", "content": "..."} # b. POSTs to http://localhost:11434/api/chat # c. Waits for response # d. Returns AIMessage object response = llm . invoke ( user_prompt ) # Step 5: Display result # response.content contains the LLM's text response print ( f" \n Response: { response . content } " )

flowchart TD Start([invoke called]) --> Format[Format prompt as chat message] Format --> Build[Build HTTP request JSON] Build --> Post[POST to :11434/api/chat] Post --> Wait[Wait for Ollama response] Wait --> Parse[Parse JSON response] Parse --> Create[Create AIMessage object] Create --> Return([Return AIMessage]) style Start fill:#e8f5e9 style Post fill:#e1f5ff style Return fill:#fff4e1

POST http://localhost:11434/api/chat { "model" : " llama3.2 " , "messages" : [ { "role" : " user " , "content" : " What is the capital of France? " } ], "stream" : false }