00:04 Building a cold email generator using Lama 3.1 02:38 Automated email generation based on job post skills 08:19 Using Llama3.1 for fast response 10:55 Creating and manipulating collections in ChromaDB using Python 16:27 Web B loader for web scraping and data extraction 19:09 Utilizing prompt extract for data extraction and email generation 24:08 Creation and retrieval of data using Python code 26:28 Creating prompt templates for email generation using Gen AI Project 31:02 Streamlit framework for quick UI prototyping 33:42 Best practice for storing API key separately from code 38:34 Automating job application process with Gen AI Project using Llama3.1 40:46 Using Llama3.1 for Gen AI Project
Can Help??? collection.add( documents=[ "This document is about New York", "This document is about Delhi" ], ids=["id1", "id2"] ) Whenever i am running the above code block i am getting the error mentioned below, i can the run the above cell and below cell just not this one, same issue is coming in the same cell even i have open a new notebook and copied the code there
"""The kernel for Jupyter/Cold Email Generator/tutorial_chromadb.ipynb appears to have died. It will restart automatically."""
Can Help??? collection.add( documents=[ "This document is about New York", "This document is about Delhi" ], ids=["id1", "id2"] ) Whenever i am running the above code block i am getting the error mentioned below, i can the run the above cell and below cell just not this one, same issue is coming in the same cell even i have open a new notebook and copied the code there
"""The kernel for Jupyter/Cold Email Generator/tutorial_chromadb.ipynb appears to have died. It will restart automatically."""
Can Help??? collection.add( documents=[ "This document is about New York", "This document is about Delhi" ], ids=["id1", "id2"] ) Whenever i am running the above code block i am getting the error mentioned below, i can the run the above cell and below cell just not this one, same issue is coming in the same cell even i have open a new notebook and copied the code there
"""The kernel for Jupyter/Cold Email Generator/tutorial_chromadb.ipynb appears to have died. It will restart automatically."""
Outstanding exploration of Gen AI with Llama3.1! AI agents such as SmythOS provide infinite integration opportunities and pre-built templates for individuals that want to investigate additional solutions. #GenAI #AIInnovation
Thank you very much for this crip and clear content on the LLM with llama. I would rewrite your video of Restuarant suggestion application (which was using OpenAI) with llama. Once again thank you for this video. Appreciate your efforts.
Can Help??? collection.add( documents=[ "This document is about New York", "This document is about Delhi" ], ids=["id1", "id2"] ) Whenever i am running the above code block i am getting the error mentioned below, i can the run the above cell and below cell just not this one, same issue is coming in the same cell even i have open a new notebook and copied the code there
"""The kernel for Jupyter/Cold Email Generator/tutorial_chromadb.ipynb appears to have died. It will restart automatically."""
Sir Thank you for the useful videos , Have a question Does chromadb has preloaded embeddings? because at 13:06 when you asked about chole bhature, I was wondering how the result came correctly ? We have not provided wiki sources for Delhi /Newyork , how did it do semantic search , does your local chromadb has already some preloaded embeddings? Little confused , Thank you
Hello, in the JsonOutputParser section, the type of json_res is coming as list and not a dictionary. Update: setting json_res[0] instead of json_res solves the issue.
Hi In the second example, we uploaded couple of docs and fired a query. It gave relevance numbers. But, we did not link an llm to the chromabd at that point. So how does embedding/vectorization work while loading a document when we do not link any llm to chromadb?
hi, Its simple, 1. Open file explorer and then 2. click on "This PC" and there open C drive . Now when u are in C drive , create a new folder and name it is as "Code", and u are done 😁😁. To open the jupyter notebook , open that "Code" folder that u just created and right click and find an option called as "Git bash here", then a terminal window opens and there u can write the code as given in video "python -m notebook".
Thanks again for the detailed tutorial, I have two questions 1. What is the cost of running such models in production. 2. While scraping the links, any rate limiting issues you have faced ?
Hello Sir while using chroma db it is not running and a dialogue box appears and shows the kernel for chromadb.ipynb appears to have died. It will restart automatically. I am using it in Jupyter notebook please help
How is it determining whether Delhi is closer to Chole Battura than New York? Who has fed those semantic information into the system? Is it possible to configure those semantic data ?
Sir, when query like you did in the tutorial i got an empty response. Why would it happen? Does it require an internet connection to work properly? It works on juoyter notebook but not in vscode why?
can someone throw light on how we decided to get the job requirements in JSON format from the webbased loader? i would like to know the thought process behind the decision please
The 'job' variable is not described well in the video and even the code has an error. It is used before being defined. It could be improved for clarity of the novice.
@@codebasics that's good to hear. But I believe it would be only for personal use. If I want to scale it up and use for production purposes at my work, will this work? If not, is there any other way out?
Thank you for the video. When you send a prompt containing more text than the LLM can process as input, what happens to the extra text? How do you manage this?
I'm exploring options for integrating large AI models like LLaMA into my app. Besides Grok, what are some user-friendly alternatives you recommend for beginners? Thanks!
I have a doubt . Chromadb is a vector database , which stores vectors , I want to know where and which Embedding technique you used for storing the portfolios into chromadb. Could any one clarify this??
Hello Dhaval sir, first of all thankyou for the the quality content..😁 I had a little doubt. I think this code is good enough for a college project, but for solving the same problem on an industrial level, do we need some extra tools or services. And how can I learn to code like industry standards. Thank You😇
This is pretty much an industry standard. Additional enhancements you can make is to deploy streamlit app on a community cloud or in your company's internal cloud.
@@manavgora Can Help??? collection.add( documents=[ "This document is about New York", "This document is about Delhi" ], ids=["id1", "id2"] ) Whenever i am running the above code block i am getting the error mentioned below, i can the run the above cell and below cell just not this one, same issue is coming in the same cell even i have open a new notebook and copied the code there
"""The kernel for Jupyter/Cold Email Generator/tutorial_chromadb.ipynb appears to have died. It will restart automatically."""
@@codebasics Can Help??? collection.add( documents=[ "This document is about New York", "This document is about Delhi" ], ids=["id1", "id2"] ) Whenever i am running the above code block i am getting the error mentioned below, i can the run the above cell and below cell just not this one, same issue is coming in the same cell even i have open a new notebook and copied the code there
"""The kernel for Jupyter/Cold Email Generator/tutorial_chromadb.ipynb appears to have died. It will restart automatically."""
"I'm getting a Kernel dead error when running chromadb. Any suggestions on how to fix this?""I'm getting a Kernel dead error when running chromadb. Any suggestions on how to fix this?"
hey there my code is completely working in jupyter notebook but in next step when we built classes and functions in vs code after all that it's giving error that chromadb module not found even though I have it installed in my folder , i tried installing it again but still its not working
Hi Sir, Thank you the clear Cut Explanation and knowledge. I learn and follow ur projects max. I have one doubt, how to use gemini AI in-stand of groq cloud. Please help me. Thank you so much🎉.
Can i add this project in resume Sir? can you please tell me which project should i add to get job in data science or data analytivs to impress manager by this projects??
i have one question that did you deployed this on instance or doing locally. whenever need just run code and get the cold email like that. if lets suppose i am in TCS and i have to create such application then can you tell us as deployment wise how we will do.
This is running locally but using streamlit public cloud you can deploy it to cloud very easily. On youtube, you will find videos on this (trust me it is very easy and straight forward)
Facing a lot of issues with Python 3.12 and latest chromaDB. Also numpy version conflicts arising. @codebasics please mention the python version you are using.
Planning to fine tune GPT 2 small LLM model (145 million parameters.) locally in a machine Will a laptop consisting of i5 13th Gen and Nvidia RTX 3050 6GB Graphics card, able to do all this task
Can Help??? collection.add( documents=[ "This document is about New York", "This document is about Delhi" ], ids=["id1", "id2"] ) Whenever i am running the above code block i am getting the error mentioned below, i can the run the above cell and below cell just not this one, same issue is coming in the same cell even i have open a new notebook and copied the code there
"""The kernel for Jupyter/Cold Email Generator/tutorial_chromadb.ipynb appears to have died. It will restart automatically."""
Sir I made a Law Based LLM app which can answer questions based on Indian Context and no rag / fine tuning was required with lamma 3.1 So does lamma 3.1 have that much data about india, isn't a threat then?
Can Help??? collection.add( documents=[ "This document is about New York", "This document is about Delhi" ], ids=["id1", "id2"] ) Whenever i am running the above code block i am getting the error mentioned below, i can the run the above cell and below cell just not this one, same issue is coming in the same cell even i have open a new notebook and copied the code there
"""The kernel for Jupyter/Cold Email Generator/tutorial_chromadb.ipynb appears to have died. It will restart automatically."""
streamlit : The term 'streamlit' is not recognized as the name of a cmdlet, function, script file, or operable program. Check the spelling of the name, or if a path was included, verify that the path is correct and try again. It is showing error.....please any help who completed this project
@@codebasics I have put all effort required to make this project.....but at last its not working......showing the above error.....Please help to fix it.
Check codebasics.io/ for practical AI courses where I teach AI concepts in an intuitive, industry relevant way.
Excellent video just a suggestion sir please explain more lines as this is new it is tough to understand
00:04 Building a cold email generator using Lama 3.1
02:38 Automated email generation based on job post skills
08:19 Using Llama3.1 for fast response
10:55 Creating and manipulating collections in ChromaDB using Python
16:27 Web B loader for web scraping and data extraction
19:09 Utilizing prompt extract for data extraction and email generation
24:08 Creation and retrieval of data using Python code
26:28 Creating prompt templates for email generation using Gen AI Project
31:02 Streamlit framework for quick UI prototyping
33:42 Best practice for storing API key separately from code
38:34 Automating job application process with Gen AI Project using Llama3.1
40:46 Using Llama3.1 for Gen AI Project
Sir i got my job in London as remote ML engineer. Your video helps me to crack the interview
Can Help???
collection.add(
documents=[
"This document is about New York",
"This document is about Delhi"
],
ids=["id1", "id2"]
)
Whenever i am running the above code block i am getting the error mentioned below, i can the run the above cell and below cell just not this one, same issue is coming in the same cell even i have open a new notebook and copied the code there
"""The kernel for Jupyter/Cold Email Generator/tutorial_chromadb.ipynb appears to have died. It will restart automatically."""
Hey I am also ML engineer doing Deep learning specialization from coursera by Andrew ng is it worth it to do and please tell me how you got this job??
@@eternalsgaming2467 use google colab, it solved the issue for me
Sir I thank you from bottom of my heart for this amazing tutorials . Really getting to learn a lot!!!!
bro how did you get the csv file?
Can Help???
collection.add(
documents=[
"This document is about New York",
"This document is about Delhi"
],
ids=["id1", "id2"]
)
Whenever i am running the above code block i am getting the error mentioned below, i can the run the above cell and below cell just not this one, same issue is coming in the same cell even i have open a new notebook and copied the code there
"""The kernel for Jupyter/Cold Email Generator/tutorial_chromadb.ipynb appears to have died. It will restart automatically."""
Your guidance has been greatly beneficial to me as a data science student.
Dont know about peter pandey but you definitely are Spider man of Teaching. Rise and Shine
Outstanding exploration of Gen AI with Llama3.1! AI .. Thank you sir
Glad you liked it!
@@codebasics Hi bro, Your videos are excellent, may I translate them to uzbek lang, for may channel?
Can Help???
collection.add(
documents=[
"This document is about New York",
"This document is about Delhi"
],
ids=["id1", "id2"]
)
Whenever i am running the above code block i am getting the error mentioned below, i can the run the above cell and below cell just not this one, same issue is coming in the same cell even i have open a new notebook and copied the code there
"""The kernel for Jupyter/Cold Email Generator/tutorial_chromadb.ipynb appears to have died. It will restart automatically."""
@@eternalsgaming2467 could you please explain what is that c folder mean and what did he done at 7:03 of the video
@@mohamedaashik8063 he is just creating a folder so that he can have all the files related to the project at one place
Thank you from the bottom of my heart. You explain everything very well, and each line of code is working perfectly. You have saved my career.
I am learning SO Much from you. This was such a useful video. Incredibly grateful . Thank you !!
This is Amazing ! The best part you described the very basic things going to the website document which builds the confidence in us.
u have an amazing talent of sharing whatever knowledge u have . u are a very good teacher .
Peter Pandey. Amazing Videos. The way you explain step by step in Jupyter and then IDE is amazing. Great to understand what is happening.
Outstanding exploration of Gen AI with Llama3.1! AI agents such as SmythOS provide infinite integration opportunities and pre-built templates for individuals that want to investigate additional solutions. #GenAI #AIInnovation
What a great lesson!! I always learn so much from you. Thank You
Wishing you a happy teachers' day, Dhaval sir 🤍 Thank you for uploading yet another amazing tutorial!
Very helpful project which can be expanded and leveraged to many other use cases. Thank you sir for your excellent teaching and detailed explanations!
love you ho gya g level daa hiraaa bandaa hai g wawa sariya muhabtaaaa bhai dy naaal sady aloo
Thank you very much for this crip and clear content on the LLM with llama. I would rewrite your video of Restuarant suggestion application (which was using OpenAI) with llama. Once again thank you for this video. Appreciate your efforts.
Go for it. Wish you all the best 👍
Can Help???
collection.add(
documents=[
"This document is about New York",
"This document is about Delhi"
],
ids=["id1", "id2"]
)
Whenever i am running the above code block i am getting the error mentioned below, i can the run the above cell and below cell just not this one, same issue is coming in the same cell even i have open a new notebook and copied the code there
"""The kernel for Jupyter/Cold Email Generator/tutorial_chromadb.ipynb appears to have died. It will restart automatically."""
Thanks for the sales nuggets-key input for contextual cold emails!
phenomenal work dhaval bhai
great work done with clear work and no time waste
What a coincidence! I created a POC in my company with almost the exact same tech stack and almost similar application 😊
Hi
which company?
I dont think this language work efficiently, unable to extract data from ocr text
poc means?
@@rashedin6356 proof of concept
Kudos to you for explaining in detail 😀
Amazing, thank you for your easy to follow and understand video 👌👌🙏🙏
Thankyou very much sir you are a pure blessing
This is awesome and informative, thank you!
Thanks for sharing new stuff with us.
this video is very helpfull for me, thank you so much sir for creating this amazing video🥰🥰
hey folk, did u put this project in ur CV ?
Looks like, you are busy in your company work now a days. ! video after long time. As usual its great !!!
What a session!!!
Awesome. Please make more videos like that.
This is great , thank you
Awesome work. Love your videos
Really amazing sir
Sir Thank you for the useful videos , Have a question
Does chromadb has preloaded embeddings?
because at 13:06 when you asked about chole bhature, I was wondering how the result came correctly ? We have not provided wiki sources for Delhi /Newyork , how did it do semantic search , does your local chromadb has already some preloaded embeddings? Little confused , Thank you
I got it clarified, Thank you
I Just finished my End to End NLP project, now I'll start this one 👻👻
what project did u make bro?
From where did u make
All I can say is - WOW !
Great work, Thank you. Pls keep on adding more videos like this.
Wonderful project. Keep it up
you are great sir🎉❤
Hello, in the JsonOutputParser section, the type of json_res is coming as list and not a dictionary.
Update: setting json_res[0] instead of json_res solves the issue.
Great job, thank you !
Hi
In the second example, we uploaded couple of docs and fired a query. It gave relevance numbers. But, we did not link an llm to the chromabd at that point. So how does embedding/vectorization work while loading a document when we do not link any llm to chromadb?
7:03 can anyone of you explain please what is that c code folder and how to create and run that api in that?
hi, Its simple, 1. Open file explorer and then 2. click on "This PC" and there open C drive . Now when u are in C drive , create a new folder and name it is as "Code", and u are done 😁😁. To open the jupyter notebook , open that "Code" folder that u just created and right click and find an option called as "Git bash here", then a terminal window opens and there u can write the code as given in video "python -m notebook".
It's amazing project.
Thank you Dhaval for sharing.
I have question how to evaluate this model
thanks a lot man, love you
Thanks again for the detailed tutorial, I have two questions
1. What is the cost of running such models in production.
2. While scraping the links, any rate limiting issues you have faced ?
Thank you very much sir
LOved it!
Hello Sir while using chroma db it is not running and a dialogue box appears and shows the kernel for chromadb.ipynb appears to have died. It will restart automatically.
I am using it in Jupyter notebook please help
@ codebasics Dhaval sir we are ideally waiting for Microsoft Azure tutorial
Also, please talk about AI/ML security in some videos. If possible, give code examples in the cybersecurity domain.
How is it determining whether Delhi is closer to Chole Battura than New York? Who has fed those semantic information into the system? Is it possible to configure those semantic data ?
Sir, when query like you did in the tutorial i got an empty response. Why would it happen? Does it require an internet connection to work properly?
It works on juoyter notebook but not in vscode why?
Sir I am a fresher. At 7:10 u opened a terminal.Which terminal was it? please add those steps in video
same my doubt too
It was git bash, come with git(optionally), not exactly based on linux, but provide some linux type command line interface
at 12:31 while runing my kernel dies and it says it will restart, how to overcome
Same
@plasmak3297 hi bro I uploaded the ipynb file in vs code and it worked. Try that,it says it's running out of memory in jupiter notebook.
@@Saisujal_11 alright thanks friend
@@Saisujal_11 bro showing the same error? how did you do that
@pranjitdas2198 I uploaded the ipynb to vs code and it worked, try to do this ir use some other online kernel..
I am getting portfolio.csv not found error please help
can someone throw light on how we decided to get the job requirements in JSON format from the webbased loader? i would like to know the thought process behind the decision please
The 'job' variable is not described well in the video and even the code has an error. It is used before being defined. It could be improved for clarity of the novice.
Great video!! I have a question
What about the cost? Will it also incur cost based on the tokens or is there any way to run it locally?
It is free
@@codebasics that's good to hear. But I believe it would be only for personal use.
If I want to scale it up and use for production purposes at my work, will this work? If not, is there any other way out?
Thank you for the video. When you send a prompt containing more text than the LLM can process as input, what happens to the extra text? How do you manage this?
I'm exploring options for integrating large AI models like LLaMA into my app. Besides Grok, what are some user-friendly alternatives you recommend for beginners? Thanks!
Sir when can we expect the launch of full and proper data science course like your data analytics bootcamp 3.0 ?
Is creating chromaDb and storing portfolio work links a RAG in this use case?
1:47 LMAO I DIDNT EXPECT YOU MENTIONED INDONESIA (fr I want to go to overseas company because even in Indonesia it's too low 💀)
I have a doubt . Chromadb is a vector database , which stores vectors , I want to know where and which Embedding technique you used for storing the portfolios into chromadb. Could any one clarify this??
Thank you
for some websites, no proper text-extraction is done which shows: "Just a moment...Enable JavaScript and cookies to continue". How to handle this ?
Great! Now create a cold email reader/analyzer and action taker, make them middlemen, managers useless!
Hello Dhaval sir, first of all thankyou for the the quality content..😁
I had a little doubt.
I think this code is good enough for a college project, but for solving the same problem on an industrial level, do we need some extra tools or services.
And how can I learn to code like industry standards.
Thank You😇
This is pretty much an industry standard. Additional enhancements you can make is to deploy streamlit app on a community cloud or in your company's internal cloud.
@@codebasics ok sir, thankyou for your response
@@manavgora Can Help???
collection.add(
documents=[
"This document is about New York",
"This document is about Delhi"
],
ids=["id1", "id2"]
)
Whenever i am running the above code block i am getting the error mentioned below, i can the run the above cell and below cell just not this one, same issue is coming in the same cell even i have open a new notebook and copied the code there
"""The kernel for Jupyter/Cold Email Generator/tutorial_chromadb.ipynb appears to have died. It will restart automatically."""
@@codebasics Can Help???
collection.add(
documents=[
"This document is about New York",
"This document is about Delhi"
],
ids=["id1", "id2"]
)
Whenever i am running the above code block i am getting the error mentioned below, i can the run the above cell and below cell just not this one, same issue is coming in the same cell even i have open a new notebook and copied the code there
"""The kernel for Jupyter/Cold Email Generator/tutorial_chromadb.ipynb appears to have died. It will restart automatically."""
@@eternalsgaming2467 start using google colab
langchain_community module not found error keeps on popping up when i try to deploy it using streamlit. any solutions
Thanks 🙏
"I'm getting a Kernel dead error when running chromadb. Any suggestions on how to fix this?""I'm getting a Kernel dead error when running chromadb. Any suggestions on how to fix this?"
hey there my code is completely working in jupyter notebook but in next step when we built classes and functions in vs code after all that it's giving error that chromadb module not found even though I have it installed in my folder , i tried installing it again but still its not working
When i hit the submit button it is creating multiple results continuously without stopping. How to fix this..
Hi Sir,
Thank you the clear Cut Explanation and knowledge. I learn and follow ur projects max. I have one doubt, how to use gemini AI in-stand of groq cloud.
Please help me.
Thank you so much🎉.
How can i generate code, that is fine tune also ? Which ai model should i use that is for free ?
I want to learn machine learning and make a project on it, so is the graphics card from Intel Iris enough or will a dedicated one be required
When you’re going to launch generative ai course ?
Is there any way i can add documents through UI into chroma db. Like milvus have attu as UI
AttributeError: 'Collection' object has no attribute 'model_fields' i got this error in 3 line of tutorila_chromadb while making collection
Can you give some ideas on a End to End GenAI projects in Finance domain. I not able to any idea what can be made in Finance domain.
@codebasics
Please make some videos on langchain memory and langgraph.
Can i add this project in resume Sir? can you please tell me which project should i add to get job in data science or data analytivs to impress manager by this projects??
i have one question that did you deployed this on instance or doing locally. whenever need just run code and get the cold email like that. if lets suppose i am in TCS and i have to create such application then can you tell us as deployment wise how we will do.
This is running locally but using streamlit public cloud you can deploy it to cloud very easily. On youtube, you will find videos on this (trust me it is very easy and straight forward)
is that csv file of portfolio necessary ? if so can you provide it it would be of great help,Thanks!
How to deploy please make a video because llm file is not inserted in chatgpt
please upload more end to end Gen Ai projects
Yes one more project is coming up
In tutorial_chromadb , there is error came in 3 line while making the collection, if someone knows kindly helppp
Facing a lot of issues with Python 3.12 and latest chromaDB. Also numpy version conflicts arising. @codebasics please mention the python version you are using.
Try using conda instead of pip install. You may also need to downgrade your python version to 3.10
tks sir
Not able to get he api key of lamma3.1 in console.groq is not able to verify you are human. Please help me in that.
Planning to fine tune GPT 2 small LLM model (145 million parameters.) locally in a machine
Will a laptop consisting of i5 13th Gen and Nvidia RTX 3050 6GB Graphics card, able to do all this task
Thank you. This is so wonderful.
Can I use FAISS db instead of chromadb
yes
Can Help???
collection.add(
documents=[
"This document is about New York",
"This document is about Delhi"
],
ids=["id1", "id2"]
)
Whenever i am running the above code block i am getting the error mentioned below, i can the run the above cell and below cell just not this one, same issue is coming in the same cell even i have open a new notebook and copied the code there
"""The kernel for Jupyter/Cold Email Generator/tutorial_chromadb.ipynb appears to have died. It will restart automatically."""
Sir I made a Law Based LLM app which can answer questions based on Indian Context and no rag / fine tuning was required with lamma 3.1
So does lamma 3.1 have that much data about india, isn't a threat then?
Can Help???
collection.add(
documents=[
"This document is about New York",
"This document is about Delhi"
],
ids=["id1", "id2"]
)
Whenever i am running the above code block i am getting the error mentioned below, i can the run the above cell and below cell just not this one, same issue is coming in the same cell even i have open a new notebook and copied the code there
"""The kernel for Jupyter/Cold Email Generator/tutorial_chromadb.ipynb appears to have died. It will restart automatically."""
I am not able to retrieve the data using web scraping
streamlit : The term 'streamlit' is not recognized as the name of a cmdlet, function, script file, or operable program. Check the
spelling of the name, or if a path was included, verify that the path is correct and try again. It is showing error.....please any help who completed this project
pip install streamlit
@@codebasics I did this on my PowerShell terminal.....but still not working
@@codebasics I have put all effort required to make this project.....but at last its not working......showing the above error.....Please help to fix it.
Hi sir make communication master class
For data analyst modules
sir can u make a end to end project related to vapi Ai assistant plzzzzzzzz
Once you get this please help me in that also. I am also working on this
attributeerror: 'collection' object has no attribute 'model_fields' facing this issue on mac os
AttributeError: type object 'ListOutputParser' has no attribute 'model_rebuild'