LangChain v/s Llama-Index | Detailed Differences | Which one you should use?

[@ayushsonu531]

Big fan of your work sir continue this series dont leave in between

[@Trendz-w5d]

There's no link to download notes? Please help on this.

[@sunnysavita10]

github.com/sunnysavita10/Generative-AI-Indepth-Basic-to-Advance/tree/main/RAG%20Pipeline%20from%20Scratch

[@GHCVMADHUSS]

Sir please make a session on MLops 🙏

[@sunnysavita10]

Sure why not

[@satwindersingh1797]

Thanks for This Video - Confusion Removed

[@sobz4u214]

1 doubt .. When we use Liama index API or any LLM model apis for RAG application by connecting our own data , how much data security and privacy of our own data ? Even though , our own data is using for retrieval purposes, but in case of multiple queries which will be using by liama index, data privacy risk can be happen..rit?

[@sanchitkanojia5460]

Good news for you sir I am from FSDSM may 2023 batch student. Recently I got a internship offer from Synapse Health Tech which works in Health domain. Will you please make one video on KZbin related to No Code AI. Because first project which assigns to me is on No Code AI. I am not able to find any good resource. If possible please share any resource....

[@VivekShinde2795]

Hello sir can you please build a RAG chatbot with Mistral Instruct 7 b v0.2. Please build it with complete open source.

[@sunnysavita10]

Definitely.

[@preethiagarwal5355]

What is mistral instruct ? Who knows may b r n future rascal instruct may also come 😅😂

[@VivekShinde2795]

@@preethiagarwal5355 nice

[@Sundarampandey]

what will you start the langchain playlist???

[@sunnysavita10]

yes soon i will

[@solomonrajkumar5537]

Hi Sunny first of all thanks for make this Video... hats off to your effort... I don't have in depth back ground in AI... still in learning curve... I always have this question - basically if a LLM does not able to provide appropriate answers to some of the prompt that is what we are going via RAG - if so why we need to use LLM why can't we directly use RAG instead... basically my question is why via LLM?

[@sunnysavita10]

Please check with my rag from scratch implementation video

[@venkatn8262]

RAG will only fetch the raw content matching your query, but it can't format and present the exact information you require in natural way.

[@sathyavel8046]

we can create an index as part of vector dataase itself then y this llamaindex is required ?

[@uniwander]

Thanks so much for the content!

[@sunnysavita10]

My pleasure!

[@preethiagarwal5355]

Gr8 u hv demystified the jargons around LLM. Somehow , I feel that u r imitating Lil bit krish naik style 😅 try Lil diff way btw good job guy..keep up the momentum

[@sunnysavita10]

Sure 😊

[@umeyr7225]

Fantastic!!. Thank you

[@ARkhan-xw8ud]

Audio is very low

[@sathyavel8046]

well done