Building LLMs with Hugging Face and LangChain

Edureka via Coursera Specialization

Go to class Write review

Details

Go to class

Provider

Coursera Specialization
Pricing

Paid Course
Languages

English
Certificate

Certificate Available
Duration & workload

8 weeks, 7 hours a week

Found in

Overview

Coursera Flash Sale

40% Off Coursera Plus for 3 Months!

Grab it

The Building LLMs with Hugging Face and LangChain Specialization teaches you how to create modern LLM applications from core concepts to real-world deployment. You will learn how LLMs work, how to build applications with LangChain, and how to optimize and deploy systems using industry tools. In Course 1, you’ll explore the foundations of LLMs, including tokenization, embeddings, transformer architecture, and attention. You’ll work with the Hugging Face Hub, Datasets, and Transformers pipelines, experiment with models like BERT, GPT, and T5, and build simple NLP workflows. In Course 2, you’ll build real LLM applications using LangChain and LCEL. You’ll create prompts, chains, memory, and RAG pipelines with FAISS, process documents, and integrate agents, tools, APIs, LangServe, LangSmith, and LangGraph. In Course 3, you’ll optimize and deploy LLM systems. You’ll improve latency and token usage, integrate structured and multimodal data, orchestrate workflows with LlamaIndex and LangGraph, build FastAPI services, add security, containerize with Docker, and deploy with monitoring and CI/CD. By the end, you’ll be able to create and deploy production-ready LLM applications using modern tools and MLOps practices.

Syllabus

Course 1: Introduction to LLMs and Hugging Face
Course 2: Developing LLM Applications with LangChain
Course 3: Optimizing and Deploying LLM Systems

Courses

0 reviews
10 hours 21 minutes
View details

This course introduces the concepts, tools, and practical techniques behind LangChain, the leading framework for building intelligent applications powered by Large Language Models (LLMs). It blends conceptual understanding with hands-on implementation to help you design, build, and deploy context-aware, tool-using AI systems. Whether you’re a developer, data scientist, or AI practitioner, this course provides a clear roadmap for transforming LLMs into dynamic, reasoning-driven applications that interact with real-world data and APIs. Through guided lessons, structured demonstrations, and project-based learning, you’ll explore how LangChain connects prompts, models, memory, and tools into composable workflows. You’ll learn to build Retrieval-Augmented Generation (RAG) pipelines, integrate LangServe for deployment, and implement LangSmith for observability and evaluation. The course culminates with a capstone Knowledge Assistant project, where you’ll combine RAG, multi-agent systems, and secure API integrations into a fully functional, deployable AI assistant. By the end of this course, you will be able to: • Understand the architecture and components of LangChain for LLM development. • Build multi-step reasoning pipelines and retrieval-augmented generation (RAG) workflows. • Implement memory, tools, and agents to enable contextual, goal-oriented behavior. • Evaluate and optimize LLM applications for performance, safety, and scalability. This course is ideal for AI developers, data scientists, and software engineers seeking to go beyond prompt-based experimentation and build real-world, production-ready LLM applications. A working knowledge of Python and APIs is recommended, but the course provides guided support to help learners of all backgrounds master the LangChain ecosystem. Join us to master the framework that powers today’s most advanced generative AI applications.
0 reviews
10 hours 34 minutes
View details

This course introduces the Large Language Models (LLMs) and the Hugging Face ecosystem, combining conceptual understanding with hands-on implementation to help you build intelligent, language-driven systems. Whether you’re exploring AI for the first time or looking to deepen your understanding of modern NLP architectures, this course provides a clear and practical path into the world of transformer-based models and open-source innovation. Through guided lessons and real-world demonstrations, you’ll explore how LLMs process language, learn from massive datasets, and generate context-aware responses. You’ll also gain hands-on experience using Hugging Face tools to load, evaluate, and fine-tune models, prepare datasets for NLP tasks, and build pipelines for classification, sentiment analysis, and question answering. The course culminates with a project that integrates fine-tuned models, external APIs, and a user interface to create a fully functional knowledge assistant. By the end of this course, you will be able to: • Understand transformer architecture and attention mechanisms that power modern LLMs. • Differentiate between pre-training and fine-tuning approaches and apply them using Hugging Face tools. • Compare open-source and proprietary LLMs, evaluating trade-offs in performance and accessibility. • Prepare and tokenize datasets for efficient model training and evaluation. • Build, test, and deploy NLP pipelines for real-world applications. • Extend agents with external data sources and integrate APIs securely. • Develop and test an end-to-end intelligent assistant powered by fine-tuned models. This course is ideal for AI developers, data scientists, and ML enthusiasts who want to understand and apply LLMs using open-source frameworks. A basic understanding of Python and machine learning will be helpful, but not required. Join us to explore the Introduction of large language models, master the Hugging Face ecosystem, and gain the practical skills to fine-tune, connect, and deploy intelligent systems that power the future of AI.
0 reviews
10 hours 7 minutes
View details

This course advances your skills from building working LLM prototypes to scaling, integrating, and deploying production-grade AI systems. You’ll blend system-level concepts with hands-on engineering to profile performance, integrate real-time data and multimodal sources, and ship secure, cloud-deployed applications. Whether you’re a developer, data scientist, or AI practitioner, this course gives you a clear roadmap to transform optimized LangChain workflows into reliable, observable services that interact with live APIs, structured data, and orchestration frameworks. Through guided lessons, structured demonstrations, and project-based learning, you’ll learn how to profile latency and token usage, design efficient prompts and chains, and evaluate pipelines with LLMOps metrics. You’ll connect external APIs, build hybrid retrieval across text, tables, and images, and orchestrate complex data flows using LlamaIndex and LangGraph. Finally, you’ll containerize and deploy a FastAPI service with authentication, monitoring, and CI/CD, culminating in an end-to-end capstone deployment. By the end of this course, you will be able to: • Profile and optimize LLM pipelines for latency, throughput, and token/cost efficiency. • Design prompt and chain strategies (dynamic templates, caching, auto-tuning) to improve reliability and speed. • Implement memory, tools, and agents to enable contextual, goal-oriented behavior. • Integrate real-world data via secure APIs and hybrid retrieval across structured, unstructured, and multimodal sources. • Orchestrate data and evaluation workflows using LlamaIndex and LangGraph for scalable reasoning. • Build, secure, containerize, and deploy a FastAPI service with JWT/OAuth, monitoring, and CI/CD automation. This course is ideal for AI developers, data scientists, and software engineers ready to move beyond prompt experimentation and deliver production-ready LLM applications. A working knowledge of Python and APIs is recommended; all steps are guided to help you master the deployment stack. Join us to learn the engineering patterns that power modern, scalable generative AI—from optimization and orchestration to secure cloud deployment.