James Briggs Courses

Metadata Filtering for Vector Search - Latest Filter Tech

Explore pre-, post-, and single-stage metadata filtering for vector similarity search, with Pinecone code examples showing how filtering affects accuracy and speed.

• YouTube
• 34 minutes
• Self-Paced
• Free Video

Locality Sensitive Hashing for Search with Shingling + MinHashing - Python

Learn the traditional LSH pipeline for approximate similarity search, from text shingling and MinHash signatures to banded hashing and candidate-pair tuning.

• YouTube
• 27 minutes
• Self-Paced
• Free Video

Training and Testing an Italian BERT - Transformers From Scratch

Train an Italian RoBERTa masked-language model from scratch, troubleshoot CUDA and indexing errors, then test its fill-mask predictions.

• YouTube
• 31 minutes
• Self-Paced
• Free Video

Fixing LLM Hallucinations with Retrieval Augmentation in LangChain

Build a LangChain retrieval pipeline that gives LLMs access to current external knowledge and adds citations to generated answers.

• YouTube
• 31 minutes
• Self-Paced
• Free Video

Chatbot with LangChain Agents + GPT 3.5

Build a conversational Lex Fridman podcast chatbot with LangChain agents, vector search retrieval, conversational memory, and GPT-3.5 Turbo.

• YouTube
• 33 minutes
• Self-Paced
• Free Video

Using MPT-7B in Hugging Face and LangChain

Configure MPT-7B models in Hugging Face and LangChain to generate text and connect the model to LangChain tools.

• YouTube
• 19 minutes
• Self-Paced
• Free Video

Hugging Face Agents — First Look

A first look at building conversational agents with Hugging Face, including how to query them and connect community tools.

• YouTube
• 19 minutes
• Self-Paced
• Free Video

Build Conversational Agents with Vector DBs - LangChain

Combine agent-driven retrieval with vector search so a chatbot consults external knowledge only when a query needs it.

• YouTube
• 19 minutes
• Self-Paced
• Free Video

Chatbots with RAG - LangChain Full Walkthrough

Build a chatbot that retrieves relevant knowledge to ground its answers and reduce hallucinations.

• YouTube
• 36 minutes
• Self-Paced
• Free Video

Hugging Face LLMs with SageMaker - RAG with Pinecone

Build a retrieval-augmented generation pipeline that grounds open-source Hugging Face LLM responses in a searchable FAQ dataset.

• YouTube
• 33 minutes
• Self-Paced
• Free Video

Chatbot with LangChain

Build a single-GPU chatbot using the chat-tuned MPT-30B open-source language model.

• YouTube
• 21 minutes
• Self-Paced
• Free Video

Nvidia's NeMo Guardrails - Full Walkthrough for Chatbots - AI

Build a Python chatbot with NVIDIA NeMo Guardrails, using deterministic dialogue flows to guide topics, control behavior, and trigger actions such as human handoff.

• YouTube
• 21 minutes
• Self-Paced
• Free Video

Create Custom Tools for Chatbots in LangChain

Build custom LangChain tools for LLM agents, from a calculator with multiple parameters to prompts and image understanding.

• YouTube
• 25 minutes
• Self-Paced
• Free Video

Cohere vs. OpenAI Embeddings - Multilingual Search

Build multilingual semantic search with Cohere embeddings, compare them with OpenAI, and index cross-language queries in Pinecone.

• YouTube
• 24 minutes
• Self-Paced
• Free Video

Supercharge eCommerce Search - OpenAI's CLIP, BM25, and Python

Build a multimodal e-commerce search engine that combines CLIP image-text embeddings with BM25 sparse retrieval and Pinecone hybrid queries.

• YouTube
• 35 minutes
• Self-Paced
• Free Video