Best explanation
"you actually optimize your rag"
Building Production-Ready RAG Applications: Jerry Liu
Public index moment — strongest composite transcript signals for this topic (heuristic).
Topic research hub
retrieval evaluation
retrieval evaluation: model once you've defined your evalve benchmark now you want to think about how do you actually optimize your rag…
High-signal research hub
Best transcript moments
Canonical moments ranked from the public index — preferring multi-word, semantic excerpts where available.
you actually optimize your rag
Building Production-Ready RAG Applications: Jerry Liu
8:17
you actually optimize your rag systems so I sent a teaser on this slide
Building Production-Ready RAG Applications: Jerry Liu
8:19
you actually retrieve from a vector database and how do you synthesize that with an
Building Production-Ready RAG Applications: Jerry Liu
2:19
I use a runable Lambda you can see the retrieve docs stage and the invoke llm
Online Evaluation (RAG) | LangSmith Evaluations - Part 20
2:48
you synthesize that with an L1 so that's basically the key stack
Building Production-Ready RAG Applications: Jerry Liu
2:21
these challenges with naive rag
Building Production-Ready RAG Applications: Jerry Liu
2:56
this what this is is this is automatically uh just a dict that
Online Evaluation (RAG) | LangSmith Evaluations - Part 20
4:43
you use llms for for
Building Production-Ready RAG Applications: Jerry Liu
14:35
you incorporate agents towards
Building Production-Ready RAG Applications: Jerry Liu
9:38
with this sentence Transformers embedding model
Evaluating Retrieval Augmented Generation for a PubMed QA App
1:44
you actually get language models to
Building Production-Ready RAG Applications: Jerry Liu
0:49
similar elements from your vector database
Building Production-Ready RAG Applications: Jerry Liu
4:39
Videos discussing this topic
Related topics
Related searches
you actually optimize your ragyou actually optimize your rag systems so I sent a teaser on this slideyou actually retrieve from a vector database and how do you synthesize that with anI use a runable Lambda you can see the retrieve docs stage and the invoke llmyou synthesize that with an L1 so that's basically the key stackthese challenges with naive ragthis what this is is this is automatically uh just a dict thatyou use llms for foryou incorporate agents towardswith this sentence Transformers embedding model
Creators discussing this topic
No mapped creator profiles for these moments yet.
Continue researching
Jump into search, other hubs, and the public moment index to go deeper in-session.
Research lens
Best answer across indexed moments
Grouped by transcript heuristics only — not generative summaries and not fact-checking. Empty slots mean we did not find a confident match for that role in this hub.
Beginner explanation
"this what this is is this is automatically uh just a dict that"
Online Evaluation (RAG) | LangSmith Evaluations - Part 20
Public index moment — beginner / definitional wording in the excerpt.
Technical explanation
"with this sentence Transformers embedding model"
Evaluating Retrieval Augmented Generation for a PubMed QA App
Public index moment — technical vocabulary or systems detail in the excerpt.
Compare explanations
Different experts and framings on the same topic — compare before you decide.
"you actually optimize your rag"
Building Production-Ready RAG Applications: Jerry Liu
Technical / systems framing
"I use a runable Lambda you can see the retrieve docs stage and the invoke llm"
Online Evaluation (RAG) | LangSmith Evaluations - Part 20
Beginner-oriented framing
"with this sentence Transformers embedding model"
Evaluating Retrieval Augmented Generation for a PubMed QA App
Technical / systems framing
Referenced by multiple experts — 3 distinct channels in this comparison.
Help grow the technical explanation index
Get notified as we index more engineering talks and tutorials for in-video transcript search.