Building News AI Agents Using CrewAI And Google Gemini Pro LLM Models

CrewAI tools empower agents with capabilities ranging from web searching and data analysis to collaboration and delegating tasks among coworkers. This documentation outlines how to create, integrate, and leverage these tools within the CrewAI framework, including a new focus on collaboration tools.
In this video we will create a News AI Agents using CrewAI ith Google Gemini LLM Models
Code Github: github.com/kri...
---------------------------------------------------------------------------------------------------
Support me by joining membership so that I can upload these kind of videos
/ @krishnaik06
-----------------------------------------------------------------------------------
►GenAI on AWS Cloud 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

[@aloybanerjee9460]

Thank you so much for the clear explanation and for your incredibly helpful videos! I just needed to make one small modification as per the Crew AI documentation, which involves defining the LLM explicitly. Everything else worked perfectly. 😊 Modified Code: from crewai import LLM gemini_llm = LLM( model="gemini/gemini-1.5-pro-latest", verbose=True, temperature=0.3, google_api_key = google_api_key )

[@dhruvtiwari661]

Thanks very much for this course, you're teaching better than Andre Ng and keeping us at the forefront of AI

[@maheshSingh-yb2vn]

Sir ... please complete Advance NPL series . After the lecture 11 .... Your content is helping alot to understand the concept .... You teaches in simplest way i ever learned ... Please sir continue the series as you promised also ....

[@riswanbashas6256]

The development of LLM models and chatbot is totally impressive. But, Could you please walk us through about how to validate our built LLM model (Testing and Validation) in the real world usecase.

[@dipali5562]

thanks for putting so much effort to explain us so well

[@yashsonune4391]

Could you please make a video on, specifically what specific things and learnings to focus on rather than learning every framework and other tech. The Generative AI and Data Science field is dynamically changing.

[@KumR]

Thanks Krish. Can you please add yesterdays video also to same playlist ? Also Can u make videos on real industry projects?

[@SahilSanganis]

Can you make a community where we can ask doubts?

[@omchaithanya56]

Here I don't see the agents communicating with each other. They are doing individual and independent tasks.

[@jayrock5638]

Can u please make how can we use agents to automate any task like sending emails creating LinkedIn post and automatically post it. Basically how can we use agents to automate tasks.

[@krishnaik06]

Yes will make that soon

[@ayushmishra5861]

​@@krishnaik06Please bring it on the Hindi channel as well.

[@yazanrisheh5127]

@@krishnaik06 Could you deploy on streamlit and allow user to give human input?

[@anubhavshroti5284]

Can you please make a video. Read the pdf having text image table and flowchart .and able to answering the questions like RAG

[@AryanKumarBaghel-cp1jv]

how agents are communicating? if yes, then whats the need to define tools for 2nd agents? the first agent should directly send data to the second agent

[@rkjyoti4167]

Superb Boss!

[@Aman-yu4re]

Thank you so much ! You are excellent

[@athakur33]

Krish naik sir when will you back teaching in ineuron platform?

[@tonystark9315]

Hi Krish, Can you tell me If we can use multiple LLm's in one project. Like one agent uses chatgpt and other uses some other like gemini

[@MahvishSadaf]

yes

[@BS-up7wf]

Hi Krish , I have three years of experience and am currently employed as a software engineer. Is it therefore appropriate for the weekend AI MTech course, which lasts for two years?

[@SaurabhSingh-qx1fd]

@Krish Naik, Sir want to have one question with you. Can we build text to sql application with relational database, so that, it can be able to give response from different relational table database. I have built one but the issue is it cannot be able to handle that much data. I have tested it with 2000 data points from 4 different table. Each table contains 500 data points. Application was giving 90% accuracy. when that data reaches to 40000, 10000 from each table, model response got disturbed and accuracy dropped to below 50%. Can you please suggest something.

[@MihirPrakash-wq1oc]

I am trying to generate the Gemini API key, but it's asking for an administrator account

[@nkvs1248]

Might be using college or company gmail id

[@shreyaschhetri9434]

Hi Sir can you please make a video about Guardrails especially NeMo and Guardrails AI using Ollama LLM models like open ai or mistral or llama it'll be very helpful

[@MahvishSadaf]

i second that

[@AryanKumarBaghel-cp1jv]

does serp api provides scrapped data from all websites, or it just gives the link of websites?

[@vinithkumar4975]

Does this work with current or today's news articles????

[@dibzp5017]

What is the need of multiple agents here, can't we directly ask llm to do the task?

[@Legend-sd7gr]

Hello Sir, The code for "Live 15 hour Session In Implementing End To End Data Science Projects- Community Event" is not available anymore.Could you please avail it. It could be of massive help. Regards.

[@dhananjaychandel1770]

Can we do this with Gemini basic without pro???

[@MahvishSadaf]

yes

[@aiforeveryone]

Amazing

[@sergeistadnik8305]

I encountered {'message': 'Unauthorized.', 'statusCode': 403} error while running python crew.py. Seems that is a crewai related problem.

[@lionsinescanor405]

Did u clear the error?

[@sergeistadnik8305]

@@lionsinescanor405 no

[@aishnagupta6793]

getting same error, any solution?

[@kalyangoud-pk7cy]

Hi Sir, are there any models for trading also

[@shivajimutnale3979]

Sir I request to make one video on Natural Language to sql [ PL/SQL] also .

[@harishankar-cz9tx]

I am trying to run this on my Linux Ubuntu desktop. and even after I copied the file contents form the github, I am facing the error "AttributeError: 'int' object has no attribute 'name'" can someone confirm if this works on Linux system?

[@SohamSathe-p5i]

hello sir, I am getting an import error cannot import tool from tools and cannot import research_task from task. can you please help me with solving the error.

[@rakeshkumarsharma195]

Hi, I am getting below error in agents section, ERROR:root:Failed to get supported params: argument of type 'NoneType' is not iterable please reply if anyone resolved above error, Thanks

[@ridhoaditya9280]

change your llm initialization method from langchain to LLM method from crewai

[@manohars2939]

@@ridhoaditya9280 can you explain, did'nt understood!!!

[@ramankhanna9526]

plz show the documentation as well side by side

[@nagendrababumannem8206]

Hi , could anyone please help me how to create virtual environment.i am encountering issues

[@dwarakanadhareddybayana4948]

create conda -p venv python==3.10 -y

[@dwarakanadhareddybayana4948]

Second command,conda activate venv/

[@nagendrababumannem8206]

I followed the instructions but encountering issues, any references that would be appreciate

[@jaredpeck9880]

@@nagendrababumannem8206 conda create -n myenv python=3.10 conda activate myenv

[@lionsinescanor405]

Run create conda command in anaconda prompt to create venv and select new venv as interpreter in vs code

[@FreakProYT]

CanSomeone please help me with short term load forecasting code in Python

[@RishiRajxtrim]

👍👍

[@Adi-vi1ro]

thank you

[@afnankhan1278]

any one else getting dumb issue like, topic is not changing, it only writing article on a single topic ai trend in 2023 even though i have changes it to somthing else, also tired memory to False still same issue

[@afnankhan1278]

@krishnaik if you could help