The Complete AI Fast Track Bootcamp - 2024

10h 59m 1s
English
Paid

The Complete AI Fast Track Bootcamp - 2024 is an intensive online course designed for the rapid acquisition of key skills in the field of artificial intelligence. It covers modern technologies, including large language models (LLM), generative AI, vector databases, LangChain, Hugging Face, Gemini Pro, and more.

Course Structure

Module 1: Large Language Models (LLMs)

Dive into the world of generative AI and next-generation language models to understand their impact and applications.

Module 2: Prompt Engineering

Acquire skills for creating effective prompts for models such as GPT-4 and Claude, empowering you to harness AI effectively.

Module 3: Ollama

Learn to work with open LLMs, customizing models to meet individual needs and enhance performance.

Module 4: Hugging Face

Explore the Hugging Face platform, which enables hosting and interacting with advanced NLP models.

Module 5: Vector Databases

Understand how text is represented as numerical vectors to optimize data storage and retrieval processes.

Module 6: Gemini Pro

Study the revolutionary Gemini technology and explore its applications in various AI projects.

Module 7: LangChain

Use the LangChain framework to enhance LLM capabilities by integrating external data sources and APIs.

Module 8: CrewAI

Organize interactions between AI agents to significantly boost productivity across tasks.

Module 9: Custom GPT Models

Gain an overview of the most interesting custom GPT models developed by pioneering developers and researchers.

Module 10: Function Calling and Assistants API

Learn the fundamentals of using the Function Calling and Assistants API from OpenAI to build responsive AI solutions.

Module 11: Speech and Vision

Apply AI to speech recognition and image processing tasks, enabling the creation of advanced applications and virtual assistants.

About the Author: Code4Startup (coderealprojects)

Code4Startup (coderealprojects) thumbnail
I designed and coded the Code4Startup platform with Ruby on Rails in 3 days only but it took me almost 2 and half months to create just 5 hours of video for my very first two educational courses ever, Zero and Ninja. WHY? Because I am not a native English speaker and I had to practice and repeat hundreds of times. But I kept trying and never gave up. I bootstrapped this startup with a dream of educating MILLIONS people from around the world. Code4Startup is not just about learning how to code, it's also about inspiring people to create something meaningful, something they are excited about.

Watch Online 114 lessons

This is a demo lesson (10:00 remaining)

You can watch up to 10 minutes for free. Subscribe to unlock all 114 lessons in this course and access 10,000+ hours of premium content across all courses.

View Pricing
0:00
/
#1: 2.1 Indirect prompt injection
All Course Lessons (114)
#Lesson TitleDurationAccess
1
2.1 Indirect prompt injection Demo
01:31
2
3.1 Quick intro
06:39
3
3.2 About local LLM
07:25
4
3.3 Installation
05:39
5
3.4 Run Llava
05:58
6
3.5 APIs with Postman
10:27
7
3.6 With OpenAI
04:57
8
3.7 With Ollama
02:38
9
3.8 With Langchain
02:00
10
3.9 Run Ollama with Chat UI
12:11
11
3.10 Ollama with custom models
09:28
12
4.1. What is Hugging Face.
01:52
13
4.2. Hugging Face ecosystem
04:37
14
4.3. Working with Transformers libirary
10:04
15
4.4. Generate text
09:54
16
4.5. Transcribing audio
02:59
17
4.6. Obje detection
10:51
18
4.7. What is Spaces.
03:46
19
4.8. Creating Gradio app
05:09
20
4.9. Creating Spaces
09:58
21
5.1. What is Gemini.
01:59
22
5.2. Getting API Key
02:05
23
5.3. Initialize Python project
01:20
24
5.4. Generate text
03:17
25
5.5. Interact with image
06:40
26
5.6. Chatbot
04:31
27
5.7. Text chatbot
07:35
28
5.8. Photo chatbot
12:18
29
5.9. Audio chatbot
05:00
30
6.1. Embeddings
03:44
31
6.2. Vector database
04:15
32
6.3. Token limit problem
08:02
33
6.4. What is RAG.
03:26
34
6.5. Chroma
02:27
35
6.6. Chroma embeddings
05:29
36
6.7. OpenAI embeddings
04:46
37
6.8. Hugging Face embeddings
02:47
38
6.9. Updating data
02:20
39
6.10. Removing data
01:43
40
6.11. Collection management
03:41
41
6.12. Prepare resumes
03:37
42
6.13. Code
10:36
43
7.1. Age
05:53
44
7.2. Chains
03:30
45
7.3. Chat with RAG
06:52
46
7.4. Generation
02:57
47
7.5. Go with Hugging Face and Groq
11:01
48
7.6. Go with OpenAI
07:10
49
7.7. Intro
04:00
50
7.8. Memory
05:03
51
7.9. RAG with PDF
12:42
52
7.10. Retrieval Augmented
11:25
53
7.11. Simple ChatUI with Ollama
05:40
54
7.12. Upload PDF
09:12
55
8.1. Intro
03:10
56
8.2. Workflow
06:01
57
8.3. Age
03:36
58
8.4. Tasks
04:55
59
8.5. Tools
03:43
60
8.6. Processes
01:55
61
8.7. Installation
03:32
62
8.8. Run Age
04:54
63
8.9. Run Tasks
03:22
64
8.10. Run Crew
06:19
65
8.11. Installation libraries
04:20
66
8.12. Set up compone
05:21
67
8.13. Crew
07:40
68
9.1. Intro
04:03
69
9.2. Create GPT
07:17
70
9.3. Add knowledge base
04:27
71
9.4. Nutrition API
03:02
72
9.5. Create your actions
06:24
73
9.6. Hacking instruction prompt
04:16
74
9.7. Hacking uploaded files
05:31
75
9.8. Advanced hacking prompt
07:00
76
9.9. Layer of protection
05:55
77
10.1. Problem #1
02:17
78
10.2. Problem #2
05:23
79
10.3. Solution
06:32
80
10.4. Multiple custom functions
05:40
81
10.5. Applications of function calling
05:14
82
10.6. Back to the problem
01:18
83
10.7. Function calling use cases
07:55
84
10.8. Overview
04:11
85
10.9. Create assistant in playground
04:48
86
10.10. Add knowledge base
04:06
87
10.11. Code intergreter
04:10
88
10.12. Knowledge base
06:42
89
10.13. Function calling
07:20
90
10.14. Basic Streamlit
08:30
91
10.15. Send email with Resend
07:16
92
10.16. Update utils - create assistant
09:02
93
10.17. Update utils - functions for assistant
05:16
94
10.18. Add logic
13:37
95
11.1. Speech reg vs Voice reg
01:27
96
11.2. OpenAI Whisper
06:12
97
11.3. Local Whisper
07:54
98
11.4. Transcribe Youtube
03:58
99
11.5. Deepgram STT
06:39
100
11.6. SpeechRecognition - Google
09:54
101
11.7. SpeechRecognition - Whisper
09:42
102
11.8. OpenAI
10:53
103
11.9. Deepgram
06:40
104
11.10. Structure
01:15
105
11.11. Add Speech-to-Text
04:01
106
11.12. Add Text-to-Speech
08:22
107
11.13. Add Groq
06:54
108
11.14. Working together
05:55
109
11.15. Work with remote image
06:02
110
11.16. Work with local image
10:19
111
11.17. Step 1 - Camera input
03:03
112
11.18. Step 2 - Input form
03:33
113
11.19. Step 3 - AI image function
06:01
114
11.20. Step 4 - Test on monile
09:11
Unlock unlimited learning

Get instant access to all 113 lessons in this course, plus thousands of other premium courses. One subscription, unlimited knowledge.

Learn more about subscription

Books

Read Book The Complete AI Fast Track Bootcamp - 2024

#Title
16.3 Token limit problem
27.12 Upload PDF
39.3 Add knowledge base
410.10 Add knowledge base