Overview

Google, IBM & Meta Certificates – 40% Off

One Coursera Plus subscription covers most Professional Certificates on Coursera.

Building an LLM application requires more than a single prompt: it means calling model APIs, controlling output, connecting tools, and grounding answers in your own data. This course shows you how to build LLM applications in Python that use tool calling and retrieval-augmented generation (RAG). Through follow-along demos, you will call multiple LLM providers from one codebase, compose chains in LangChain, index documents with LlamaIndex, and store embeddings in ChromaDB, Pinecone, and Weaviate. By the end of this course, you will be able to: • Integrate LLM provider APIs and estimate token cost and latency. • Control output with generation parameters, streaming, and JSON schemas. • Implement tool calling to connect Python functions to a model. • Build chains, memory, and agents with LangChain and LlamaIndex. • Store and search embeddings using vector databases and ANN indexes. • Develop a RAG pipeline with chunking, retrievers, and cited answers. This course is designed for software developers, backend engineers, Python programmers, and AI engineers who want to turn LLM prototypes into working applications. You should be comfortable with Python and basic prompt engineering before you begin. Enroll now to build tool-using, retrieval-backed LLM applications.

Syllabus

Calling LLM APIs Across Providers
- Examine the LLM API landscape by comparing providers, endpoints, rate limits, and pricing. Develop foundational skills by configuring a Python project with API keys and calling multiple providers from a single codebase. Build practical capabilities by estimating token cost and latency for LLM-powered features.
Generation Controls, Structured Outputs, and Tool Calling
- Analyze how generation parameters and sampling techniques shape model output. Develop foundational skills by tuning temperature, top-p, max tokens, and stop sequences, and by streaming responses while tracking token usage. Build practical capabilities by producing schema-valid JSON with structured outputs and exposing Python functions through tool calling.
Orchestration with LangChain and LlamaIndex
- Differentiate LangChain and LlamaIndex by examining chains, agents, tools, memory, and document indexing. Develop foundational skills by composing LCEL chains, integrating tools, managing conversation memory, and indexing documents with LlamaIndex. Build practical capabilities by combining both frameworks and justifying framework choices for application architectures.
Embeddings, Vector Databases, and Similarity Search
- Analyze how embeddings represent meaning and how vector databases enable similarity search. Develop foundational skills by generating embeddings, measuring semantic similarity, and managing data in ChromaDB, Pinecone, and Weaviate. Build practical capabilities by tuning nearest-neighbour indexes and selecting embedding models and vector databases for specific use cases.
Building a Retrieval-Augmented Pipeline
- Analyze RAG architectures by examining document loaders, chunking strategies, and retrieval chains. Develop foundational skills by building retrievers and retrieval chains with effective chunking. Build practical capabilities by designing grounded prompts with citations and safe no-answer responses, and by diagnosing retrieval failures.
Building a Tool-Using, Retrieval-Backed LLM Application
- Evaluate the end-to-end LLM application lifecycle by examining how API integration, orchestration, and retrieval combine in a working system. Develop foundational skills by integrating provider APIs, tuning generation parameters, and building multi-step chains. Build practical capabilities by designing and scoping a tool-using, retrieval-backed LLM application.

Taught by

Edureka

Reviews

Start your review of Building LLM Applications with Tools and Retrieval

Taught by

Never Stop Learning.