LLM-based search agent #ai #chatgpt #tech

Elvis Saravia · Intermediate ·🧠 Large Language Models ·1y ago

Key Takeaways

The video demonstrates building an LLM-based search agent using a web scraper and search API, with a focus on retrieving and processing information to answer user queries.

Full Transcript

the web scraper agent you can see the name here it's searching so it's using the search and if you click on search it has all the details on what it actually did so for instance it chose this to be the input just based on my own query and then the tool which is a search API return all of this information and hopefully within this information here the agent has all the sufficient information it needs to be able to answer my query properly so here it says day in B then it has a lot of information here then it says overall it looks like a day with considerable cloudiness and the possibility of rain throughout and it says today in believe so this is the final response in the end so definitely looks like it's correct so it's 28° C winds are light and varable coming from a Northwest and 5 to 10 mph the humidity is quite high at approximately 89% there is a significant chance of rain estimated at 50%

Original Description

Learn how to build with AI in my new courses here: https://dair-ai.thinkific.com/ Use code BLACKFRIDAY to get a 35% off. Offer expires 11/29 #ai #chatgpt #artificialintelligence
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Playlist

Uploads from Elvis Saravia · Elvis Saravia · 0 of 60

← Previous Next →
1 101 ways to solve search (by Pratik Bhavsar)
101 ways to solve search (by Pratik Bhavsar)
Elvis Saravia
 2 TLDR Generation of Scientific Documents | ML Interview #1 with Isabel Cachola
TLDR Generation of Scientific Documents | ML Interview #1 with Isabel Cachola
Elvis Saravia
 3 Sentiment Analysis: Key Milestones, Challenges and New Directions
Sentiment Analysis: Key Milestones, Challenges and New Directions
Elvis Saravia
 4 Discriminative Adversarial Search for Abstractive Summarization (by Thomas Scialom)
Discriminative Adversarial Search for Abstractive Summarization (by Thomas Scialom)
Elvis Saravia
 5 Question Understanding: COVID-Q: 1,600+ Questions about COVID-19
Question Understanding: COVID-Q: 1,600+ Questions about COVID-19
Elvis Saravia
 6 Getting Started with NLP
Getting Started with NLP
Elvis Saravia
 7 Building tools and frameworks for large-scale social media mining (by Dr. Juan M. Banda)
Building tools and frameworks for large-scale social media mining (by Dr. Juan M. Banda)
Elvis Saravia
 8 TextAttack: A Framework for Data Augmentation and Adversarial Training in NLP
TextAttack: A Framework for Data Augmentation and Adversarial Training in NLP
Elvis Saravia
 9 Dive into Deep Learning (Study Group): Introduction to Deep Learning | Session 1
Dive into Deep Learning (Study Group): Introduction to Deep Learning | Session 1
Elvis Saravia
 10 Dive into Deep Learning (Study Group): Multilayer Perceptrons | Session 4
Dive into Deep Learning (Study Group): Multilayer Perceptrons | Session 4
Elvis Saravia
 11 How I read and annotate ML papers
How I read and annotate ML papers
Elvis Saravia
 12 Keep Learning ML (Session 1) | DSV, CompLex, Modern tools for emotions
Keep Learning ML (Session 1) | DSV, CompLex, Modern tools for emotions
Elvis Saravia
 13 Dive into Deep Learning (Study Group): Preliminaries | Session 2
Dive into Deep Learning (Study Group): Preliminaries | Session 2
Elvis Saravia
 14 Keep Learning ML #2 | Language-conditioned policy learning, Effective ML Testing, EagerPy
Keep Learning ML #2 | Language-conditioned policy learning, Effective ML Testing, EagerPy
Elvis Saravia
 15 Dive into Deep Learning (Study Group): Linear Neural Networks | Session 3
Dive into Deep Learning (Study Group): Linear Neural Networks | Session 3
Elvis Saravia
 16 Dive into Deep Learning (Study Group): Multilayer Perceptrons | Session 4
Dive into Deep Learning (Study Group): Multilayer Perceptrons | Session 4
Elvis Saravia
 17 Keep Learning ML #3 | Contrastively Trained Structured World Models
Keep Learning ML #3 | Contrastively Trained Structured World Models
Elvis Saravia
 18 Dive into Deep Learning (Study Group): Deep Learning Computation with PyTorch | Session 5
Dive into Deep Learning (Study Group): Deep Learning Computation with PyTorch | Session 5
Elvis Saravia
 19 Dive into Deep Learning (Study Group): Convolutional Neural Networks | Session 6
Dive into Deep Learning (Study Group): Convolutional Neural Networks | Session 6
Elvis Saravia
 20 Dive into Deep Learning (Study Group): Modern CNNs | Session 7
Dive into Deep Learning (Study Group): Modern CNNs | Session 7
Elvis Saravia
 21 101 ways to solve neural search with Jina
101 ways to solve neural search with Jina
Elvis Saravia
 22 (Hopefully-Reusable) Life Lessons for PhD Students in NLP
(Hopefully-Reusable) Life Lessons for PhD Students in NLP
Elvis Saravia
 23 How to save the world and forward your career in 5 easy steps | Women in NLP Talks
How to save the world and forward your career in 5 easy steps | Women in NLP Talks
Elvis Saravia
 24 Prompt Engineering Overview
Prompt Engineering Overview
Elvis Saravia
 25 Getting Started with the OpenAI Playground
Getting Started with the OpenAI Playground
Elvis Saravia
 26 LM-Guided Chain of Thought
LM-Guided Chain of Thought
Elvis Saravia
 27 Elements of a Prompt
Elements of a Prompt
Elvis Saravia
 28 Reasoning with Intermediate Revision and Search with LLMs #chatgpt #ai #llms #science #programming
Reasoning with Intermediate Revision and Search with LLMs #chatgpt #ai #llms #science #programming
Elvis Saravia
 29 General Tips for Designing Prompts
General Tips for Designing Prompts
Elvis Saravia
 30 Efficient Infinite Context Transformers #ai #machinelearning #research #llms #science
Efficient Infinite Context Transformers #ai #machinelearning #research #llms #science
Elvis Saravia
 31 Best Practices and Lessons Learned on Synthetic Data for Language Models #ai #machinelearning #genai
Best Practices and Lessons Learned on Synthetic Data for Language Models #ai #machinelearning #genai
Elvis Saravia
 32 Reducing Hallucinations in Structured Outputs via RAG #chatgpt #ai #llms #programming
Reducing Hallucinations in Structured Outputs via RAG #chatgpt #ai #llms #programming
Elvis Saravia
 33 Basic Prompt Examples for LLMs
Basic Prompt Examples for LLMs
Elvis Saravia
 34 LLM In Context Recall is Prompt Dependent #llms #ai #chatgpt #machinelearning
LLM In Context Recall is Prompt Dependent #llms #ai #chatgpt #machinelearning
Elvis Saravia
 35 Zero-shot Prompting Explained
Zero-shot Prompting Explained
Elvis Saravia
 36 RAG Faithfulness #llms #ai #gpt4
RAG Faithfulness #llms #ai #gpt4
Elvis Saravia
 37 Understanding LLM Settings
Understanding LLM Settings
Elvis Saravia
 38 Llama 3 is here! | First impressions and thoughts
Llama 3 is here! | First impressions and thoughts
Elvis Saravia
 39 Llama 3 is Here! #ai #llms #llama3
Llama 3 is Here! #ai #llms #llama3
Elvis Saravia
 40 Microsoft introduces Phi-3 | The most capable small language model?
Microsoft introduces Phi-3 | The most capable small language model?
Elvis Saravia
 41 Microsoft introduces Phi-3! #ai #llms #microsoft
Microsoft introduces Phi-3! #ai #llms #microsoft
Elvis Saravia
 42 Make Your LLM Fully Utilize the Context #ai #llms #machinelearning
Make Your LLM Fully Utilize the Context #ai #llms #machinelearning
Elvis Saravia
 43 When to Retrieve? #ai #llms #machinelearning
When to Retrieve? #ai #llms #machinelearning
Elvis Saravia
 44 Training an LLM to effectively use information retrieval
Training an LLM to effectively use information retrieval
Elvis Saravia
 45 State-of-the-art open-source LLM judges #ai #machinelearning #gpt4
State-of-the-art open-source LLM judges #ai #machinelearning #gpt4
Elvis Saravia
 46 Better and Faster LLMs via Multi-token Prediction
Better and Faster LLMs via Multi-token Prediction
Elvis Saravia
 47 AlphaMath Almost Zero #ai #science #machinelearning
AlphaMath Almost Zero #ai #science #machinelearning
Elvis Saravia
 48 SWE-Agent | An LLM-based Software Engineering Agent
SWE-Agent | An LLM-based Software Engineering Agent
Elvis Saravia
 49 [LLM NEWS] AlphaFold 3, xLSTM, OpenAI's Model Spec, DeepSeek-V2, OpenDevin CodeAct 1.0
[LLM NEWS] AlphaFold 3, xLSTM, OpenAI's Model Spec, DeepSeek-V2, OpenDevin CodeAct 1.0
Elvis Saravia
 50 LLM-powered tool for web scraping #ai #chatgpt #engineering
LLM-powered tool for web scraping #ai #chatgpt #engineering
Elvis Saravia
 51 Learn about LLMs in this NEW course #ai #chatgpt #engineering
Learn about LLMs in this NEW course #ai #chatgpt #engineering
Elvis Saravia
 52 [LLM NEWS] KANs, Gemma 10M Context, OpenAI Updates?, Automatic Prompt Engineering, Tokenizer Arena
[LLM NEWS] KANs, Gemma 10M Context, OpenAI Updates?, Automatic Prompt Engineering, Tokenizer Arena
Elvis Saravia
 53 [LLM News] GPT4-o, Project Astra, Veo, Copilot+ PCs, Gemini 1.5 Flash, Chameleon
[LLM News] GPT4-o, Project Astra, Veo, Copilot+ PCs, Gemini 1.5 Flash, Chameleon
Elvis Saravia
 54 Enhancing Answer Selection in LLMs #ai #machinelearning #engineering
Enhancing Answer Selection in LLMs #ai #machinelearning #engineering
Elvis Saravia
 55 On exploring LLMs #ai #promptengineering #chatgpt
On exploring LLMs #ai #promptengineering #chatgpt
Elvis Saravia
 56 Transformers Can Do Arithmetic with the Right Embeddings #ai #machinelearning #engineering
Transformers Can Do Arithmetic with the Right Embeddings #ai #machinelearning #engineering
Elvis Saravia
 57 [LLM News] xAI Series B, Codestral, LLM Guide, AutoGen Course, Symbolic Chain-of-Thought
[LLM News] xAI Series B, Codestral, LLM Guide, AutoGen Course, Symbolic Chain-of-Thought
Elvis Saravia
 58 PR-Agent #ai #gpt4 #software
PR-Agent #ai #gpt4 #software
Elvis Saravia
 59 Extracting features from Claude 3 Sonnet
Extracting features from Claude 3 Sonnet
Elvis Saravia
 60 Has prompt engineering been solved?
Has prompt engineering been solved?
Elvis Saravia

This video teaches how to build an LLM-based search agent using a web scraper and search API, and demonstrates how to retrieve and process information to answer user queries. The agent is able to provide detailed and accurate responses to user queries. The video is relevant for those interested in building AI-powered search agents.

Key Takeaways
  1. Choose a web scraping tool to retrieve information from the web
  2. Select a search API to integrate with the LLM
  3. Design a prompt to input into the LLM
  4. Use the LLM to process the information and generate a response
  5. Test and refine the search agent to improve accuracy
💡 The key insight from this video is that LLMs can be used to build powerful search agents that can provide detailed and accurate responses to user queries, and that web scrapers and search APIs can be used to retrieve and process information to support this functionality.

Related Reads

📰
GPT-5.5 Complete Guide in 2026
Learn about GPT-5.5, its features, performance, and why it matters in 2026, and how to leverage it for improved AI-assisted tasks
Dev.to AI
 📰
AI Simplified — Why Structured Output Matters More Than a Fluent Answer
Learn why structured output is crucial for AI answers and how it can improve usability and automation
Dev.to AI
 📰
You Validated the Output. Who Validated the Process?
Validate AI processes, not just outputs, to ensure reliability and trustworthiness
Dev.to · Yura Solovey
 📰
I ran a 110B LLM on 16GB of RAM. Here's the equation that predicts any model's speed on your machine
Learn how to predict a large language model's speed on your machine using a simple equation, and discover how to run a 110B LLM on limited RAM
Dev.to · Federico Sciuca
Up next
5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems
Dave Ebbelaar (LLM Eng)
Watch →