DiscoverLangTalks
Claim Ownership
27 Episodes
Reverse
how to solve latency issues with minimal compromise on quality and cost
The 12 most common challenges around building an effective RAG pipeline and the best practices for solutions
exploring the reranker component in the 2 stage retrieval system
how to define effective requirements for llm apps, and first steps after going to production
What are transformers, why it is so expensive to train a Transformer-based model and what is the architecture of the future LLMs
LCEL, LangGraph, LangSmith
Indexing knowledgebases with KG for RAG applications
ragas framework for evaluating unstructured retrievals and generations
Retrieval Augmented Generation process, Llama index vs LangChain, indexing
OpenAI DevDay announcements recap
Evaluating LLMs and AI pipeline in dev and production environments. How to work with datasets
multimodality is a type of model that can analyze multiple data types like language, images, voice, etc.
Find the most suitable project for volunteer support "Iron swords" war efforts
Advanced prompt engineering techniques: skeleton of thoughts, directional stimulus prompting, graph of thoughts, augmentations
Full stack LLM app development, Typescript vs Python
Finetuning techniques (SFT, RLHF...), pros & cons, tools (technical episode)
why should you care about open source models, when and how to finetune, inference best practices, deployment & serving tools, models overview
Drill down on a summarization task use case
Save time building applications with LLMs by utilizing tools like LangChain, Llama index, Guidance, GPTCache and many more
Why you might need a VectorDB, which features to consider when choosing a provider, and use cases examples