End To End Advanced RAG App Using AWS Bedrock And Langchain
HTML-код
- Опубликовано: 19 июн 2024
- In this video we will be creating an end to end RAG App using AWS bedrock and Langchain using streamlit
github code: github.com/krishnaik06/AWS-Be...
-----------------------------------------------------------------------------------------------------------------
Support me by joining membership so that I can upload these kind of videos
/ @krishnaik06
-----------------------------------------------------------------------------------
►AWS Bedrock Playlist: • Generative AI In AWS-A...
►Llamindex Playlist: • Announcing LlamaIndex ...
►Google Gemini Playlist: • Google Is On Another L...
►Langchain Playlist: • Amazing Langchain Seri...
►Data Science Projects:
• Now you Can Crack Any ...
►Learn In One Tutorials
Statistics in 6 hours: • Complete Statistics Fo...
End To End RAG LLM APP Using LlamaIndex And OpenAI- Indexing And Querying Multiple Pdf's
Machine Learning In 6 Hours: • Complete Machine Learn...
Deep Learning 5 hours : • Deep Learning Indepth ...
►Learn In a Week Playlist
Statistics: • Live Day 1- Introducti...
Machine Learning : • Announcing 7 Days Live...
Deep Learning: • 5 Days Live Deep Learn...
NLP : • Announcing NLP Live co...
---------------------------------------------------------------------------------------------------
My Recording Gear
Laptop: amzn.to/4886inY
Office Desk : amzn.to/48nAWcO
Camera: amzn.to/3vcEIHS
Writing Pad:amzn.to/3OuXq41
Monitor: amzn.to/3vcEIHS
Audio Accessories: amzn.to/48nbgxD
Audio Mic: amzn.to/48nbgxD
great end to end project of RAG. This guy should be given Arjun Award !!!!
Hey Krish
This was a great tutorial and huge thanks for sharing knowledge. Bedrock provides the ability to create knowledge bases for your LLM which can be used in place of FAISS. The knowledge documents can be stored in S3 buckets and can be provided to llms.
Would like to see an end to end example where you make use of all bedrock features (e.g. knowledge bases, agents, etc.) to create a more advanced application where we invoke remote services via bedrock agents, query knowledge basis and the provide everything to llms to get the final response. Happy to collaborate on the same.
i'm actually looking forward to do this. do you have any resources for this to be done.
Hi, I have seen people talk about advanced fine tuning methods such as LORA and PEFT. If possible, please make a video implementing these techniques or atleast some insights on these topics. That would be greatly appreciated!!
Very good tutorial, clear and easy to follow, thank you :)
Suggestions for future videos:
Is there a way to use AWS Bedrock RAG feature programatically? So far I can only find examples of using it in the UI.
Im also interested in CrewAI if you want to do a video with integrating it with Bedrock.
Id also be interested in a video on how to use different models. Permissions, forming the dictionary in python etc.
Thanks so much.
Great video Krish sir...
Very useful video. Keep going.
Nice
Great video Sir..
Hi Krish,
Can u show the same example using llamaindex for indexing and rest part with langchain as u have showing in llamaindex vs Langchain video
👍🙏
First like🎉
Can you please upload videos on different prompting techniques
Hi krish, Im from UK and i cannot use Gemini AI is there any alternative way that i can use this and do projects ?
Hey, Amazing video! Just wanted to ask how can I connect my database and provide information stored in tables instead of PDF's.
Please let me know cause I/m badly stuck in this part :(
you have explained it for PDF files, what if I would like to have CSV files and will be having 100's of files and each file has mutiple columns and 100s of rows. Need to ask some NLP questions and generate some graphs or dependecy maps amongest files. shold that be possible in the similar way you have explained in this video? if not CSV files I might use JSON files too!
@Krish Sir, can I use offline aws bedrock if I have such use case to work with company data
Hello krish sir , I was working in genai t2I please upload some approach which will track me in right way for custom data,kindly requesting upload videos related LIM also .
Can we monitor this using the Langchain Interface? in Langsmith..
Does this also give relevant images from pdf in answer along with text?
I want to join your course I m in uk is it possible?
Hi, I do not have model access due to grant permission, I requested but how could get access from Amazon bedrock, is there any other way to have this?
Its a request to make a paid course where you can teach scalable LLM app.
Hey Krish , Could you please share pdf that you were referring in your code. I am getting ValueError: The de-serialization relies loading a pickle file. Pickle files can be modified to deliver a malicious payload that results in execution of arbitrary code on your machine.You will need to set `allow_dangerous_deserialization` to `True` to enable deserialization.
It worked with faiss_index = FAISS.load_local("faiss_index", bedrock_embeddings,allow_dangerous_deserialization=True)
You said Claude and used AI21 labs Jurassic model 😅
Hi, I'm getting error while running the code that is: """ValidationError: 1 validation error for LLMChain llm Can't instantiate abstract class BaseLanguageModel with abstract methods agenerate_prompt, apredict, apredict_messages, generate_prompt, predict, predict_messages (type=type_error)"""
Any solution for this?
I think the Langchain version issues
Its saying "no such file directory faiss_index"
Playlist on opensearch db
i hate aws is so outdated, everyone is using simple apikeys but they keep outdated, using aws cli, aws sdk, is not posible its useless i want to deploy it on heroku how i supposed to install aws sdk or aws cli if i am going to deploy on heroku this is so stupid, why they dont just give us Apike instead of using aws cli it doesnt make sense
chunk size 10000!?
Model id show in the video for claude is incorrect. The video shows an AI21 model. The model ID should be anthropic.claude-v2.
I want to join your course I m in uk is it possible?