3-Langchain Series-Production Grade Deployment LLM As API With Langchain And FastAPI
github: github.com/krishnaik06/Update...
LangServe helps developers deploy LangChain runnables and chains as a REST API.This library is integrated with FastAPI and uses pydantic for data validation.In addition, it provides a client that can be used to call into runnables deployed on a server. A JavaScript client is available in LangChain.js.
#krishnaik
---------------------------------------------------------------------------------------------
Support me by joining membership so that I can upload these kind of videos
/ @krishnaik06
-----------------------------------------------------------------------------------
►LLM Fine Tuning Playlist: • Steps By Step Tutorial...
►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
Пікірлер: 55
Support me by joining membership so that I can upload these kind of videos kzread.info/dron/NU_lfiiWBdtULKOw6X0Dig.htmljoin
I have done your nlp deep learning one shot and I will say you have done really great work that you increased my interested in this field. Thanks for this video too. - Somesh Panchal, Pune.
Thank you so excited for the continuation of this great series!!
Such a great start to this series, thx!
I'm loving the courses! Thank you so much I'm learning a lot.
Thanks for a great tutorial and a great series!
excellent video sir .keep it up
Great work!
Amazing video !
Nice work!!!
Thank you for making amazing tutorial... 👍
langchain and Krish sir makes it super easy!
Thank you so much sir..
Excellent video on KZread! No other videos can match such great things on planet as far as AI learning is concerned! I need to know minimum hardware configuration to run all these program! 1. Can I run the program without NVIDIA graphics processor! If at all I have to purchase, what should be the configuration as there is no such requirements.txt for Hardware ! Kindly let us know, if possible make one video simpley stating LLM vs Hardware Configuration and Price as well as renting remote VPS for deployment!
Great video. Clear and crisp explaination of the concept and code. Can we use this use case for the comparing different LLM model response? or somthing else.
waiting for next video
❤❤
Please provide a video with deepseek Krish Thanks for your hardwork really helping me.
Thank you Krish, when you will start RAG system using Langchain
Sir can you make a playlist of gen ai and llm course and project videos
Hi Krish, when you starting the 1% data scientist programme? I am eagerly waiting for that.
Hi Krish, I wanted to share some feedback. I'm a regular viewer of your videos, and I often find it challenging to locate a specific video when I don't remember its title. Implementing a consistent naming convention or series titles could significantly improve the searchability of your content. I truly value the insights your videos provide.
Sir, Thank you for the insightful video; regarding hosting, could we utilize Hugging Face for hosting? Thank you very much again.
Thanks ! But the first add_routes() was not needed. Not sure why that was added.
Hi Krish, First of all want to great work on videos really learning a lot from your videos. I have question, can you please share how can we deploy langgraph using langserve? Thanks
Can you make a video on how to adapt an LLM model to its specific use case? Is fine-tuning the right approach, or should one tie the model to a database (RAG) that provides the necessary information? In my case, I'm currently trying to integrate a 'learning coach' chatbot within a Moodle course. Naturally, it should know the contents of the Moodle course to be able to provide targeted help...
Hello Krish, I'm currently working on a PostgreSQL query using LangChain. I'm interested in obtaining the output in Excel format. Could you please advise on how to achieve this?
Hi sir can we use langchain in real production environment in large scale
Hi Kris. plz explain the reason in details for every line of code. Explaining on a high level keeps confusing. Like the add_routes section - you should explain it in more detail.
@krish please try to explain some little things like why u used chatpromptemplate.from_template why other project u have used .from_messge otherwise it's type of confusion not for all but those who we are poor students
what about multiple users using at a time.does that increase latency sir
Hey Krish! Great video. But im encountering an error after creating the routes where it is asking me to add a runnable sequence. How do i solve it?
How I can create API key for back end llm,s
Krish, can you make a video on how to get an internship in Generative AI field, I have worked a lot on genai, and currently also learning, now wanted some real world experience in the field.
Hi Kris. You are just writing codes by watching your left side screen, please explain the concepts in more detail.
@studology67
23 күн бұрын
yes this is what i want, why are we creating api in the first place?
Hi sir, I'm not able to use 'gemma' instead of 'llama2', don't know why?, I'm able to run llama2 successfully, Is there any changes to be done to use gemma. I'm able to run from cmd line using ollama! Please help.
Can you please show how to stream the response using fastapi to streamlit?
I am getting some error on the prompt1 line of code .
There is conflict coming in langserve, langsmith, langchain_core version. I am getting errors due to this library. Please share the version of this library to install. Thanks
Hi Krish - a small bug in your code because of which it is not generating a poem - instead of prompt|llm it should be prompt|model for the poem routes add_routes( app, prompt2|llm, path="/poem"
🙂🙏
How can high school developers get placed❤ plz reply
Hi guys , how to solve this error: json.decoder.jsondecodeerror: expecting value: line 1 column 1 (char 0)
Hey krish , there is an error , whenever I try to run the app.py file, I go to the url, then do /docs, then there appears that the API load has failed, please make one non-openai version of this video as well, since those not having tokens in openai are unable to execute what is provided in this video, I think that is the reason , since I did not add os.environ, to my code since I did not have tokens in my openai account.
how we will add memory in apis
@keshavchhabra6419
3 ай бұрын
by using a vector database
@mahmadmusffir8459
3 ай бұрын
@@keshavchhabra6419 i mean chat history
why are we creating API, whats the benefit
Sir ML vs ds vs dl vs Generative Ai kiya sikhu mai. Smaj nahi aa rha 🙏🙏🙏🙏😢😢🙏🙏🙏🙏🙏🙏🙏🙏
@SantK1208
3 ай бұрын
Sab seekh le
@ridj41
3 ай бұрын
maine sab sikha hua hai, sabse important data analytics aur ml hai jobs perspective se, par sabse kam competition generative ai mein hai kyuki baaki sab cheeze seekhne k baad genai seekhte hai directly nhi. GenAI ki prereq NLP hai, aur NLP ki prereq- ML/DL/etc.
from the api it clearly seems llama needs to get updated, its very inaccurate in producing results as compared to others