└── README.md /README.md: -------------------------------------------------------------------------------- 1 | # AI Engineering Roadmap (Crash Course) 2 | 3 | ### **Level 1 (Beginner)** 4 | 5 | 1. Understand the basics of LLM - you should just know how ChatGPT works at a high level 6 | - Article: [What is an LLM?](https://www.datacamp.com/blog/what-is-an-llm-a-guide-on-large-language-models) 7 | - Video: [Intro to Large Language Models](https://www.youtube.com/watch?v=zjkBMFhNj_g) 8 | 2. Learn Prompt Engineering for Developers. How to write prompts to improve the response of an LLM. 9 | - Articles 10 | - [Introduction to prompt engineering](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/prompt-engineering) 11 | - [Prompt engineering guide](https://platform.openai.com/docs/guides/prompt-engineering) 12 | - Video: 13 | - [https://www.promptingguide.ai/techniques/zeroshot](https://www.promptingguide.ai/techniques/zeroshot) 14 | - [ChatGPT Prompt Engineering for Developers](https://www.deeplearning.ai/short-courses/chatgpt-prompt-engineering-for-developers/) 15 | 3. Learn to call closed and open-source LLM models, function calling, passing prompts, and parsing responses 16 | - Articles 17 | - [Using GPT-3.5 and GPT-4 via the OpenAI API in Python](https://www.datacamp.com/tutorial/using-gpt-models-via-the-openai-api-in-python) 18 | - [Cracking Open the OpenAI (Python) API](https://towardsdatascience.com/cracking-open-the-openai-python-api-230e4cae7971) 19 | - [Developer quickstart from OpenAI](https://platform.openai.com/docs/quickstart) 20 | - Video: [Building Systems with the ChatGPT API](https://www.deeplearning.ai/short-courses/building-systems-with-chatgpt/) 21 | 4. Learn to create and automate a sequence of operations - Chains using langchain. 22 | - Articles 23 | - [LangChain: Introduction and Getting Started](https://www.pinecone.io/learn/series/langchain/langchain-intro/) 24 | - [Getting started with LangChain](https://www.pluralsight.com/resources/blog/data/getting-started-langchain) 25 | - [How to Build LLM Applications with LangChain Tutorial](https://www.datacamp.com/tutorial/how-to-build-llm-applications-with-langchain) 26 | - Video: [LangChain for LLM Application Development](https://www.deeplearning.ai/short-courses/langchain-for-llm-application-development/) 27 | 5. Basic app development using Streamlit or Gradio for POCs and demos. 28 | - Articles 29 | - [Streamlit tutorial](https://www.datacamp.com/tutorial/streamlit) 30 | - [Streamlit getting started](https://docs.streamlit.io/get-started/tutorials/create-an-app) 31 | - [Build an LLM app using LangChain](https://docs.streamlit.io/develop/tutorials/llms/llm-quickstart) 32 | - Video: [Streamlit: The Fastest Way To Build Python Apps?](https://www.youtube.com/watch?v=D0D4Pa22iG0) 33 | 34 | ### **Level 2 (Intermediate)** 35 | 36 | 1. Understanding vector embeddings and vector databases 37 | - Articles 38 | - [What are Vector Embeddings?](https://qdrant.tech/articles/what-are-embeddings/) 39 | - [An Intuitive 101 Guide to Vector Embeddings](https://medium.com/@2twitme/an-intuitive-101-guide-to-vector-embeddings-ffde295c3558) 40 | - [A Gentle Introduction to Vector Databases](https://weaviate.io/blog/what-is-a-vector-database) 41 | - Video: [Vector Databases: from Embeddings to Applications](https://www.deeplearning.ai/short-courses/vector-databases-embeddings-applications/) 42 | 2. Learning how to use vector databases for your application 43 | - Articles 44 | - [Mastering Vector Databases with Pinecone Tutorial](https://www.datacamp.com/tutorial/mastering-vector-databases-with-pinecone-tutorial) 45 | - [Build a Question Answering App Using Pinecone And Python](https://betterprogramming.pub/build-a-question-answering-app-using-pinecone-and-python-1d624c5818bf) 46 | - Video: [Building Applications with Vector Databases](https://www.deeplearning.ai/short-courses/building-applications-vector-databases/) 47 | 3. Building retrieval-augmented Generation (RAG) - chat with your knowledge base 48 | - Articles 49 | - [What is Retrieval Augmented Generation (RAG)?](https://www.datacamp.com/blog/what-is-retrieval-augmented-generation-rag) 50 | - [Build a Retrieval Augmented Generation (RAG) App](https://python.langchain.com/v0.2/docs/tutorials/rag/) 51 | - [Hands-On with RAG: Step-by-Step Guide to Integrating Retrieval Augmented Generation in LLMs](https://blog.demir.io/hands-on-with-rag-step-by-step-guide-to-integrating-retrieval-augmented-generation-in-llms-ac3cb075ab6f) 52 | - Video: [LangChain: Chat with Your Data](https://www.deeplearning.ai/short-courses/langchain-chat-with-your-data/) 53 | 54 | ### **Level 3 (Advanced)** 55 | 56 | 1. Understanding hybrid search 57 | - Articles 58 | - [The Basics of AI-Powered (Vector) Search](https://cameronrwolfe.substack.com/p/the-basics-of-ai-powered-vector-search) 59 | - [On Hybrid Search](https://qdrant.tech/articles/hybrid-search/) 60 | - Video: [Large Language Models with Semantic Search](https://www.deeplearning.ai/short-courses/large-language-models-semantic-search/) 61 | 2. Evaluating RAG 62 | - Articles 63 | - [Evaluating Retrieval Augmented Generation](https://superlinked.com/vectorhub/articles/evaluating-retrieval-augmented-generation-framework) 64 | - [RAG Evaluation: Don’t let customers tell you first](https://www.pinecone.io/learn/series/vector-databases-in-production-for-busy-engineers/rag-evaluation/) 65 | - Video: [Building and Evaluating Advanced RAG Applications](https://www.deeplearning.ai/short-courses/building-evaluating-advanced-rag/) 66 | 3. Build multi-modal applications - hybrid semantic search with text and image 67 | - Articles 68 | - [What is Multimodal Search](https://cloud.google.com/blog/products/ai-machine-learning/multimodal-generative-ai-search) 69 | - [Multi-modal Image Search with Embeddings & Vector DBs](https://medium.com/@tenyks_blogger/multi-modal-image-search-with-embeddings-vector-dbs-cee61c70a88a) 70 | - Video: [Building Multimodal Search and RAG](https://www.deeplearning.ai/short-courses/building-multimodal-search-and-rag/) 71 | 4. Building agents - iterative workflows to finish off a big task 72 | - Articles 73 | - [What is Agent](https://docs.deepwisdom.ai/main/en/guide/tutorials/concepts.html#agent) 74 | - [Agentic Design Patterns](https://www.deeplearning.ai/the-batch/how-agents-can-improve-llm-performance/) 75 | - [The Future of Generative AI is Agentic: What You Need to Know](https://towardsdatascience.com/the-future-of-generative-ai-is-agentic-what-you-need-to-know-01b7e801fa69) 76 | - [Agentic RAG](https://www.leewayhertz.com/agentic-rag/#Types-of-agentic-RAG-based-on-function) 77 | - Videos 78 | - [What's next for AI agentic workflows ft. Andrew Ng of AI Fund](https://www.youtube.com/watch?v=sal78ACtGTc) 79 | - [Functions, Tools and Agents with LangChain](https://www.deeplearning.ai/short-courses/functions-tools-agents-langchain/) 80 | - [Building Agentic RAG with LlamaIndex](https://www.deeplearning.ai/short-courses/building-agentic-rag-with-llamaindex/) 81 | 5. Building multi-agent applications where more than one agent works together to provide a better solution 82 | - Articles 83 | - [Agentic Design Patterns Part 5, Multi-Agent Collaboration](https://www.deeplearning.ai/the-batch/agentic-design-patterns-part-5-multi-agent-collaboration/) 84 | - [Multi-Agent System](https://abvijaykumar.medium.com/multi-agent-architectures-e09c53c7fe0d) 85 | - Video: [Multi AI Agent Systems with crewAI](https://www.deeplearning.ai/short-courses/multi-ai-agent-systems-with-crewai/) 86 | 87 | ### **Level 4 (Expert)** 88 | 89 | 1. Evaluate and benchmark the model performance 90 | - Video: [Evaluating and Debugging Generative AI Models Using Weights and Biases](https://www.deeplearning.ai/short-courses/evaluating-debugging-generative-ai/) 91 | 2. LLMOps - build complete e2e pipelines with model registry, observability and automated testing 92 | - Videos 93 | - [LLMOps](https://www.deeplearning.ai/short-courses/llmops/) 94 | - [Automated Testing for LLMOps](https://www.deeplearning.ai/short-courses/automated-testing-llmops/) 95 | 3. Secure your AI applications using techniques like prompt hacking and incorporating defensive measures by checking against vulnerabilities and potential risks 96 | - Videos 97 | - [Quality and Safety for LLM Applications](https://www.deeplearning.ai/short-courses/quality-safety-llm-applications/) 98 | - [Red Teaming LLM Applications](https://www.deeplearning.ai/short-courses/red-teaming-llm-applications/) 99 | 4. Fine-tuning pre-trained LLMs for domain-specific knowledge 100 | - Video: [Finetuning Large Language Models](https://www.deeplearning.ai/short-courses/finetuning-large-language-models/) 101 | 102 | ### ps: I am making youtube videos to share the similar content.Check that out too. [BlogYourCode](https://www.youtube.com/watch?v=U93RWtA5cCo) 103 | --------------------------------------------------------------------------------