LLMOps Space Courses

Building the Fine-Tuning Pipeline for Alignment of LLMs

Explore key aspects of aligning LLMs and set up infrastructure for a versatile alignment pipeline. Learn data collection, prompt tuning, and workflow management techniques.

• YouTube
• 45 minutes
• On-Demand
• Free Video

Traceability and Observability in Multi-Step LLM Systems - LLMOps

Explore advanced techniques for implementing traceability and observability in multi-step LLM systems, focusing on RAG systems and leveraging OpenTelemetry for deep insights.

• YouTube
• 49 minutes
• On-Demand
• Free Video

Vector and Keyword Search for Enhanced LLM Performance

Explore hybrid search techniques combining keyword and vector algorithms to enhance LLM performance, including metadata filtering, TF/IDF ranking, and advanced vector search methods.

• YouTube
• 53 minutes
• On-Demand
• Free Video

Private RAG with Open Source and Custom LLMs - BentoML and OpenLLM

Explore practical considerations for building private RAG applications using open source and custom LLMs. Learn about OpenLLM and optimize inference performance for RAG deployments.

• YouTube
• 51 minutes
• On-Demand
• Free Video

Building Multi-Modal Search and RAG with Vector Databases

Explore open-source multimodal embeddings for cross-modal search and MM-RAG. Learn techniques for integrating diverse data types, enhancing decision-making with real-time processing and LLMs.

• YouTube
• 52 minutes
• On-Demand
• Free Video

Config-Based Development for LLMs: Versioning, Routing, and Evaluating LLMs

Explore config-based development for LLMs, covering versioning, routing, and evaluation techniques to transition Generative AI apps from prototype to production efficiently.

• YouTube
• 47 minutes
• On-Demand
• Free Video

Fine-tuning LLMs with Hugging Face SFT and QLoRA - LLMOps Techniques

Explore advanced LLM fine-tuning techniques, from specialized tuning to instruction enhancement. Learn dataset preparation, model optimization, and leverage powerful libraries for efficient fine-tuning and deployment.

• YouTube
• 54 minutes
• On-Demand
• Free Video

The Science of LLM Benchmarks: Methods, Metrics, and Meanings

Explore LLM benchmarks, evaluation metrics, and critical assessment techniques to understand model strengths and limitations in this comprehensive talk on AI performance evaluation.

• YouTube
• 45 minutes
• On-Demand
• Free Video

Orchestrating RAG: Retrieval, Canopy, and Pinecone

Explore orchestrating RAG pipelines, optimizing retrieval strategies, and leveraging Canopy and Pinecone for scalable AI applications with billions of documents.

• YouTube
• 58 minutes
• On-Demand
• Free Video

Evaluating LLM-Based Apps - Deepchecks LLM Validation

Explore LLM hallucinations, evaluation methodologies, and golden sets. Witness a live demo of Deepchecks' new LLM evaluation module for robust performance benchmarking and quality assurance.

• YouTube
• 48 minutes
• On-Demand
• Free Video

Securing AI and LLM-based Applications: Best Practices

Explore security challenges in AI and LLM applications, learn attack scenarios, and discover best practices for mitigating risks and maintaining application integrity.

• YouTube
• 51 minutes
• On-Demand
• Free Video

Advanced RAG: Chunking, Embeddings, and Vector Databases

Explore advanced RAG concepts: chunking for efficient retrieval, embeddings for text representation, and vector databases for optimized storage and retrieval in LLM applications.

• YouTube
• 50 minutes
• On-Demand
• Free Video

Building LLM-Powered Apps: Best Practices for Vector Databases and LLMOps

Explore best practices for LLM-based app development, covering design considerations, technical aspects, and deployment strategies for optimal performance and scalability.

• YouTube
• 45 minutes
• On-Demand
• Free Video

Leveraging Open Source Large Language Models for Production

Explore open-source LLMs, compare with proprietary options, understand economic aspects, evaluate performance, and learn to operate and fine-tune models using dstack.

• YouTube
• 54 minutes
• On-Demand
• Free Video

Building an LLMOps Stack for Large Language Models

Explore LLMOps architecture: MLFlow for LLMs, Vector Databases, RAG strategies, and prompt evaluation. Gain insights into optimizing and deploying large language models effectively.

• YouTube
• 43 minutes
• On-Demand
• Free Video