RAG Explained
Вставка
- Опубліковано 6 тра 2024
- Get the interactive demo → ibm.biz/BdmPEb
Learn about the technology → ibm.biz/BdmPEp
Oftentimes, GAI and RAG discussions are interconnected. Learn more about about RAG is and how it works alongside your databases, LLMs and vector databases for better results with Luv Aggarwal and Shawn Brennan.
AI news moves fast. Sign up for a monthly newsletter for AI updates from IBM → ibm.biz/BdmP2c
Very simple and clear explanation.. cheers to IBM
Shawn & Luv!!!! Awesome job!!!!
Thanks for the straight forward description of RAG.
Thank you, great video. What would be also interesting to know is if you can limit the vector database based on the user. Also, how to go about testing the output with an automated and repeatable method, almost like a suite of tests that can be run when either the LLM or vector database is updated. Most especially the latter.
What I’ve seen most companies struggle with the most is still the step that came before GenAI arrived on the scene - data governance and integrity.
Neat and detail explanation.
Thanks guys, very clear!
Interesting , thanks both
Excellent video, love it
Thank for sharing !!
nice work.
Cool explanation
Informative
Love how this is presented. What tool or software are we using to draw this on air/glass/screen ?
marker
Awesome video
ok, gotcha 👌
There is good point of halucinations of AI and the video unfortunately does not address it. The data governance is not addressing this issue we still can have a scenario where input is valid but output generated by AI is a garbage.
What's the solution?
@@vintastic_you have to make sure the relevant data is going to the model. Good info into the data base is only half the battle. Semantic chunking. Size of chunks..types of search. Type of vector database used. For example PG Vector is a Postgres plugin and is not near as good at retrieval (usually) as something like pinecone
Then the prompt used can also tremendously affect the model. You have to put it in the right context and use industry specific terms when prompting. Even a genius needs context or a bit of time to think. No matter who good the model, you have to know a bit about the specific industry to obtain great results. It’s like explains a noise to you mechanic or telling them you have a miss-fire on cylinder 1.
Does not address how do you validate the Q1 results returned are accurate. You should have built in a process parallel to querying the LLM of actually querying the results and training the LLM to address any discrepancies, if that is possible or correct them.
Gotcha.
Nobody's ever been fired for buying RAGs from IBM.
👏👏
kabhi haans bhi liya karo..
(Smile a bit bros)
How in the world is this dude writing inverted for us too read straight lol
And then a wide spread global epidemic crisis is brought to light wherein our gold standard "books" (peer reviewed journals) are rife with bad and corrupt data due to mismatched incentivization and misalignment of directives; and we then realize...how much good data through science do we really have? Shame we polluted the books we are supposed to be able to trust now that we have this magnificent technology here. 😭
Dude, keep on topic. This isn’t the place for your grievances
Boring