Loading video player...
Master IT skills with Dargslan - No Filler, Just Knowledge. š Get our 300+ Tech & IT eBooks: https://dargslan.com In this video, we dive deep into professional IT workflows to help you learn faster and code smarter. Whether you're a DevOps engineer, a SysAdmin, or a curious developer, our "No Filler" approach ensures you get the facts without the fluff. In Part 11 you understood embeddings, and a Python list worked fine ā for 10 documents. Reality bites at 1 million: searching a list takes 5 seconds per query, and your user has already clicked away. This part is the **storage layer** of the RAG pipeline. Two concrete solutions in Docker: **Chroma** (Python-native, automatic Ollama embedding plugin, up to ~1M vectors) and **Qdrant** (Rust-based, REST + dashboard, 10M+ vectors). Both stood up with one Docker command, both used from Python, both compared on real features. The middle stone of Phase 3 ā in Part 13 (RAG Basics) the LLMs join in, and **your own AI starts answering from your own documents**. š IN THIS PART YOU'LL LEARN ā Why a Python list doesn't scale ā 4 concrete problems ā What a vector DB actually does ā store + index + filter ā The 5 self-hostable options: Chroma, Qdrant, Weaviate, Milvus, pgvector ā Chroma in Docker ā one `docker run` command ā Chroma Python: HttpClient + OllamaEmbeddingFunction + collection ā The structure `query()` returns: ids, documents, distances, metadatas ā Metadata + filters: `where={"source":"faq", "year":2025}` ā Qdrant in Docker + the built-in dashboard ā Qdrant Python: explicit dimension, payload, PointStruct ā Chroma vs Qdrant side-by-side comparison ā 5 most common vector DB traps (volume mount, dimension mismatch, ā¦) ā 4 things to build tonight ā±ļø TIMESTAMPS 00:00 Intro ā the storage layer 00:30 Why a list doesn't scale 01:00 What a vector DB does 01:30 The landscape: 5 options 02:00 Chroma in Docker 03:00 Chroma Python ā add + query 03:30 What query() returns 04:00 Metadata + filters 05:00 Qdrant in Docker 06:00 Qdrant Python 06:30 Chroma vs Qdrant ā pick one 07:00 5 vector DB traps 07:30 4 things to build tonight 08:00 Recap + cheat sheet ā” IF THIS WAS HELPFUL š Like ā strongest signal to YouTube š Subscribe + bell ā new part every week š¬ Comment ā questions, requests, feedback š¤ Share ā with anyone learning AI #localai #ollama #vectordb #chroma #qdrant #docker #rag #embeddings #llm #ai #linux #aitutorial #2026ai #dargslan #aifor beginners š Subscribe for weekly IT insights: https://m.youtube.com/channel/UCv2QLrkCMSBljYG5XKd8IEA About Dargslan: We are dedicated to sharing high-quality, practical IT knowledge. Our mission is to provide the most efficient learning resources for the modern tech industry. #DevOps #ITMastery #Dargslan #Linux #CloudEngineering #NoFillerTech