Description
Building a RAG application in Python is a Retrieval Augmentative Generation (RAG) course using Python and modern AI technologies published by Udemy Online Academy. This is a hands-on course that teaches developers how to build Retrieval Augmentative Generation (RAG) applications using Python and modern AI technologies. Students learn how to combine large language models (LLM) with external knowledge sources to produce more accurate, context-aware, and reliable answers. The course covers the entire RAG pipeline from data ingestion and document processing to vector embeddings, semantic search, retrieval mechanisms, and response generation.
Build a powerful Retrieval Augmentative Generation (RAG) application in Python – from an empty directory to a streaming web chat with multi-threaded memory, hybrid retrieval, image retrieval, and two interchangeable backends for vector storage. No LangChain, no LlamaIndex, no magic. You write each line yourself and at the end you know exactly what each one does. You will build the pipeline from scratch – chunking, embeddings, auto-digestion, semantic-to-lexical hybrid retrieval with Reciprocal Rank Fusion, a query rewrite for subsequent queries, a token stream sent from the server, a visual model branch for images – on plain Postgres (with pgvector) and a local Ollama server.
What you will learn in Building a RAG application in Python:
- Building a complete generation-boosted retrieval pipeline in Python, from document retrieval to chat output playback
- Running Postgres with the pgvector plugin via Docker Compose, including HNSW indexing for fast approximate-nearest-neighbor vector lookups
- Running fragmented documents with paragraph-aware segmentation and overlap, and explaining why each fragmenting choice affects retrieval quality
- Implementing self-sufficient and atomic document retrieval using SHA-256 content hashes and transactional upserts
- Using the OpenAI SDK to call local Ollama models and the OpenAI hosted API via the same code path
- Implementing hybrid retrieval that combines dense vector search with Postgres full-text BM25, along with Reciprocal Rank Fusion
- Building a query rewrite that translates into follow-up questions like “What does it eat?” to independent search queries that actually retrieve useful pieces
- Build a directory watcher with watchdog, including per-path debouncing, so the editor never reads half-written files
- And …
Course specifications
Publisher: Udemy
Instructors: Trevor Sawler
Language: English
Level: Introductory
Number of Lessons: 75
Duration: 9 hours and 50 minutes
Course topics
Building a RAG application in Python Prerequisites
Basic Python skills, basic SQL, comfort with the command line and Docker. No prior LLM or vector-database experience needed.
Pictures
Building a RAG application in Python introduction video
Installation guide
After Extract, watch with your favorite Player.
Subtitle: None
Quality: 1080p
Downloadly link
Rapidgator link
File password (s): www.downloadly.ir
Size
6.6 GB
