- 11
- 9 670
W.W. AI Adventures
United Kingdom
เข้าร่วมเมื่อ 16 ส.ค. 2024
Data Scientist, AI Engineer and Educator.
Fascinated with building AI Agents in python & teaching others about the latest and greatest advances.
Get in touch if theres anything you'd like to see covered in this channel. Im here to serve!
Fascinated with building AI Agents in python & teaching others about the latest and greatest advances.
Get in touch if theres anything you'd like to see covered in this channel. Im here to serve!
Agentic Framework LangGraph explained in 8 minutes | Beginners Guide
Get started with LangGraph quickly & Learn Why its becoming one of the most popular agentic frameworks.
🎥 Channel: @ww_dot
GitHub repo:
👉 github.com/whitew1994WW/LangGraphForBeginners
# ============================
Chapters
0:00 🕒 Intro
00:41 Value Proposition of LangGraph
02:49 Building Blocks
03:58 Practical Example
04:47 Code Walkthrough
# ===========================
Stay Connected with Me!
📧 Email: will@axies.ai (Consultancy coming soon!)
💬 Discord: discord.gg/wF3yU4r4
🔗 LinkedIn: www.linkedin.com/in/william-white-data-scientist
👨💻 GitHub: github.com/whitew1994WW
# ===========================
About
In this video, I’ll give you an introduction to what langgraph is, why you should use it and also a practical example in python & jupyter notebooks with langchain and langgraph using GPT-4o from openai.
I also touch on agentic design patterns and how the main benefit of langgraph is it's flexibility.
📌 Tags:
#AI #LangGraph #AgenticAI #OpenAI #GPT4 #Python #APIs #AIResearch #langchain
🎥 Channel: @ww_dot
GitHub repo:
👉 github.com/whitew1994WW/LangGraphForBeginners
# ============================
Chapters
0:00 🕒 Intro
00:41 Value Proposition of LangGraph
02:49 Building Blocks
03:58 Practical Example
04:47 Code Walkthrough
# ===========================
Stay Connected with Me!
📧 Email: will@axies.ai (Consultancy coming soon!)
💬 Discord: discord.gg/wF3yU4r4
🔗 LinkedIn: www.linkedin.com/in/william-white-data-scientist
👨💻 GitHub: github.com/whitew1994WW
# ===========================
About
In this video, I’ll give you an introduction to what langgraph is, why you should use it and also a practical example in python & jupyter notebooks with langchain and langgraph using GPT-4o from openai.
I also touch on agentic design patterns and how the main benefit of langgraph is it's flexibility.
📌 Tags:
#AI #LangGraph #AgenticAI #OpenAI #GPT4 #Python #APIs #AIResearch #langchain
มุมมอง: 2 099
วีดีโอ
Build Your Own AI Research Assistant in Python That Works While You Sleep!
มุมมอง 43119 ชั่วโมงที่ผ่านมา
If you're looking for daily research summaries ✉️ and want to explore LangGraph, then this project is for you! Interested in GraphRAG? Watch my other video here 👉th-cam.com/video/NA9tJU3kL-c/w-d-xo.html 🎥 Channel: @ww_dot 📂 Set up your email assistant with step-by-step instructions from my GitHub repo: 👉 github.com/whitew1994WW/email_research_assistant Chapters 0:00 🕒 Don't waste time doing you...
GraphRag vs Normal RAG - Summarise a Whole Book in python!
มุมมอง 1.3Kหลายเดือนก่อน
Microsofts GraphRAG is a powerful algorithm. It isnt perfect, but it can add value if you need your RAG queries to have visibility of your entire text datatbase. If you're looking to learn about GraphRAG✉️ and want to see how it can be used for massive text summarisation, then youre in the right place! 👉 github.com/whitew1994WW/GraphRAG 🎥 Channel: @ww_dot Chapters 00:00 - Intro 00:37 - What is ...
Retrieval Augmented Generation (RAG) & Vector Databases | Beginners Intro in 6 minutes
มุมมอง 4853 หลายเดือนก่อน
RAG & Vector Databases can be challenging concepts, understand them through diagrams in this video. 🎥 Channel: @ww_dot Chapters 00:00 - Intro 00:35 - Why use RAG 01:20 - RAG Pipeline 02:15 - Ingesting Data 03:34 - Vector Database 04:35 - Querying Data 06:18 - Wrap up Stay Connected with Me! 📧 Email: will@axies.ai (Consultancy coming soon!) 💬 Discord: discord.gg/wF3yU4r4 🔗 LinkedIn: www.linkedin...
LangGraph Customer Support Agent Ep 4: Customer Management Tools
มุมมอง 4473 หลายเดือนก่อน
Python AI Customer Support Agent Ep 4: Customer Management Tools In this episode we will create a fake customers database and give our LangGraph chatbot the ability to manage it with two new agent tools: - Retrieving customer details with a DPA check - Creating a new customer 00:00 - What we will build 02:27 - Creating customers database 03:20 - Creating tools 03:54 - Data protection check tool...
LangGraph Customer Support Agent Ep 5: Order Management Tools
มุมมอง 2533 หลายเดือนก่อน
LangGraph Customer Support Agent Ep 5: In this episode we will create a fake orders database and connect our LangGraph agent chatbot to it by creating two more tools: - Retrieving an existing order (to check the status) - Placing a new order 00:00 - What we will build 01:26 - Create Fake Orders Database 01:45 - Create retrieve existing customer tool 04:04 - Place orders tool 11:10 - Update Lang...
LangGraph Customer Support Agent Ep 3: Agent Setup with LangGraph
มุมมอง 5283 หลายเดือนก่อน
LangGraph Customer Support Agent Ep 3: Agent Setup with LangGraph In this episode we will setup LangGraph to act as an an Agentic Chatbot. We will connect our Agent with the RAG database we setup in the last episode with two tools that the Agent can use to retrieve information on demand. We will use few shot prompting in our tool definition to teach our language model how to use them effectivel...
LangGraph Customer Support Agent Ep 2: Create a local RAG database
มุมมอง 4793 หลายเดือนก่อน
LangGraph Customer Support Agent Ep 2: Create a local RAG database In this episode we will setup a local RAG database with ChromaDB, HuggingFace and LlamaIndex in order to be able to retrieve relevant products and FAQ questions. We will also connect it to the frontend we built in the previous episode to test it interactively. 00:00 - What we will build 01:11 - Setting up FAQs & Product reccomme...
LangGraph Customer Support Agent Ep 1: Streamlit + Setup
มุมมอง 5263 หลายเดือนก่อน
LangGraph Customer Support Agent Ep 1: Streamlit Setup: In this episode we will setup the python project, and create a streamlit front end to get ready for debugging our chatbot and RAG pipeline. 00:00 - What we will build 00:22 - Project setup 01:12 - Streamlit setup 12:28 - Wrap Up Series Info: A tutorial series on building a customer support agent/chatbot in python using: - Streamlit (fronte...
LangGraph Customer Support Agent Ep 0: Project Overview
มุมมอง 3133 หลายเดือนก่อน
A tutorial series on building a customer support agent/chatbot in python for an online flower shop using: - Streamlit (frontend) - LangGraph (agent logic) - Chromadb (local vector database) - HuggingFace (RAG embedding model) - LlamaIndex (local hosting) The core of the chatbot is LangGraph, a python library for builging AI Agentic applications. You will build features into the chatbot such as:...
Building an AI Receptionist with LangGraph
มุมมอง 3.4K4 หลายเดือนก่อน
I found LangGraph challenging to wrap your head around, so let me share my learnings with you. Code: github.com/whitew1994WW/LangGraphReceptionistTutorial Take a look at Lang Graphs tutorials - they are really good and there are loads more example use cases here: github.com/langchain-ai/langgraph/tree/main/examples @LangChain 🎥 Channel: @ww_dot Chapters Intro - 00:00 Demo of what we will build ...
Love this style and the colours you use, so unique. Subscribed. Keep it up!!!!
Thank you! Will do 😃
create a series of video on langgraph and agentic frameworks
Thanks. I've been thinking about something like this - different agentic architectures in langGraph - or did you have something else in mind?
@@WW_AI_Adventuresyes please cover it . Some basic to advance service. How to customise it how to create node & diff workflow
Go Yorkshire ❤🎉 Bradford lad in Australia here. I know this would double the work, but it would be good to have one playlist for Python (call it namby pamby playlist) and one for JS (called Cool Kids, obviously). Great work, keep it up.
Go Yorkshire ❤🎉
Amazing, keep this educational approach, stating the structure and role and logic before delving into the code. Very informative thank you
Thanks for the feedback! Id like to do one of these types of videos every other one
Are you wearing Indonesian Batik? Great short lesson, thank you for sharing!
@@treflatface Thanks! I don't think so but I just looked this up and I love the colours of Batik.
Great demo
@@Maskra_ thanks 🙏🙏 what did you like about it?
I liked how you explained everything end-to-end. I hope more projects like this will come. Have you scraped any code documentation before? Do you know if there are any ways to automate scraping for code and documentation?
@@erentorlak7522 Scraping fish the API I used would work fine for this - but you would need to parse the HTML coming out. You could use an LLM (a smaller one) to convert the HTML into yaml/json for your use. If you want to do it all yourself then yourself you could use selenium for doing the scraping which uses a local firefox/chrome driver to render locally, then you could use an LLM to extract the information that you need. Good luck - let me know how it goes!
@@WW_AI_Adventures Thanks !
"Interested in GraphRAG? Watch my other video here 👉" - no, graphrag is too expensive, there's a better solution already
Dear Sir, I hope you are well. I have visited your TH-cam channel. Your videos are very nice, and I’m enjoying them. However, your channel is not growing fast, so your videos are not reaching your targeted audience. Your TH-cam channel needs to be updated and your videos need SEO. If you want to promote your videos to your targeted audience and grow your channel fast, you need to update your channel with all video SEO. Then, your TH-cam channel will reach more people, get regular subscribers, and increase views. I am a professional digital marketer and TH-cam expert. I can help you update your channel if you like, and I provide channel monetization services. I have completed many orders successfully so far. If you are interested, please ask me for more details. If you want to learn more about me or my work, let's arrange a Zoom meeting in your free time. I'm looking forward to hearing back from you. Kind Regards Barkat
Wow this is such a goldmine of information! I instantly subscribed, looking forward to your next videos!!!
@@franknillard Thanks so much bro!
Very useful and well presented! Pydantic AI?
Yeah I use pydantic for the structured output - I love it.
Great video brother. Easy to understand
So glad you liked it! What kinda stuff are you interested in?
@ww_dot Please make a video on customer support bot. Like Agent will collect information from conversation
@@pycoder8233 ah gotcha - collecting information about the customer? What type of info do you mean?
@@WW_AI_Adventures For example: Amazon shopping bot. Bot should collect Fulle name, Loaction, Issue person facing with the product etc.
ERROR: Cannot install llama-index-embeddings-huggingface==0.1.3, llama-index-embeddings-huggingface==0.1.4 and llama-index-embeddings-huggingface==0.1.5 because these package versions have conflicting dependencies. The conflict is caused by: llama-index-embeddings-huggingface 0.1.5 depends on torch<3.0.0 and >=2.1.2 llama-index-embeddings-huggingface 0.1.4 depends on torch<3.0.0 and >=2.1.2 llama-index-embeddings-huggingface 0.1.3 depends on torch<3.0.0 and >=2.1.2 To fix this you could try to: 1. loosen the range of package versions you've specified 2. remove package versions to allow pip to attempt to solve the dependency conflict ERROR: ResolutionImpossible: for help visit pip.pypa.io/en/latest/topics/dependency-resolution/#dealing-with-dependency-conflicts Can you help me resolve this? I am getting this while I execute pip install llama-index-embeddings-huggingface
this one is really good
The best series for langgraph… need one series with cool project like this in multi agent system
Thank you for sharing such rich content. It's quite easy to connect with. . The entire world needs to come see what is being offered here about Gen AI
Will, Please add your LinkedIn profile link to the channel. Can you create us another video series about ChatGPT powered personal assistant
Frontend was showing error>> HumanMessage has no Attribute last_message.tool_calls: I had to remove >>> output_parser = StrOutputParser from the lECL chain llm_with_prompt = chat_template | gemmaChatModel.bind_tools(tools) #| output_parser
@@paulntalo1425 thanks for sharing!
Good stuff, Thank you SUbscribed
I asked >>> what is the best day for delieveries? @11:44 my chatbot output does not show the user question in the AI message. It's including * 'embeddings': None, 'documents': * Why is my output format different >>> from Will's chatbot output format @11:44 mins? Could it be that the model doesn't respond well to quuestions that it has been hypothetically exposed to in the knowledge base for FAQ? {'ids': [['8', '2b60de29-0560-4dab-932f-b36616a4e88e', '77ab7fdf-da73-4d3d-913d-aed593276f27', '16', 'd3923f72-0b49-4c1c-927c-d91d946583ec']], 'embeddings': None, 'documents': [['What payment methods do you accept?', 'What payment methods do you accept?', 'What payment methods do you accept?', 'What if the flowers I want are out of season?', 'What if the flowers I want are out of season?']], 'uris': None, 'data': None, 'metadatas': [[{'answer': 'We accept all major credit cards, PayPal, and Apple Pay for online orders. For large corporate orders, we also offer invoicing options.', 'question': 'What payment methods do you accept?'}, {'answer': 'We accept all major credit cards, PayPal, and Apple Pay for online orders. For large corporate orders, we also offer invoicing options.', 'question': 'What payment methods do you accept?'}, {'answer': 'We accept all major credit cards, PayPal, and Apple Pay for online orders. For large corporate orders, we also offer invoicing options.', 'question': 'What payment methods do you accept?'}, {'answer': 'If certain flowers are out of season, we offer similar alternatives or can create custom arrangements using in-season blooms that match your desired style and color scheme.', 'question': 'What if the flowers I want are out of season?'}, {'answer': 'If certain flowers are out of season, we offer similar alternatives or can create custom arrangements using in-season blooms that match your desired style and color scheme.', 'question': 'What if the flowers I want are out of season?'}]], 'distances': [[0.16856716573238373, 0.16856716573238373, 0.16856716573238373, 0.1977671980857849, 0.1977671980857849]], 'included': [<IncludeEnum.distances: 'distances'>, <IncludeEnum.documents: 'documents'>, <IncludeEnum.metadatas: 'metadatas'>]}
Sorry for the delay in replying - Yes if the question isn't in the knowledge base then it won't be able to answer it. I also haven't spent much time trying to optimise the knowledge base here, so it might be that it just isn't retrieving the right Q&A from the knowledge base
This is world class teaching materials and agent building approaches. Am learning a lot. Thank you so much.
Thank you for these amazing video series. The best of the kind online. Besides that, after adding the vector store script to the chatbot. The start and response time has increased to morethan a minute before it starts running. What could be causing this?
@@paulntalo1425 I use a local embedding model here, so perhaps the PC you are using is slow? I'm not sure though!
@ww_dot am using NVIDIA RTX 3050 GPU. Perhaps it could be due to some lines of code that I didn't put right. Thank you for the reply. We waiting for more content 🙏👍
Thank you for sharing and creating such a real world end-to-end project. The best of the kind on the internet so far.
Cool..!
Thanks, I appreciated your initiative. this is an example of the "human in the loop" graph, very useful. I would suggest you to insert the memory in the graph as well. [.compile(checkpointer=memory)]
Just finished the series and wanna say thank you. Hope you will soon make another serie about Multi AI System using LangGraph. 🇭🇹 🇭🇹 🇭🇹
This is by far the best tutorial I have ever seen on TH-cam. You should keep doing more tutorials like this. I'm a developer living in Haiti and rigth now my goal is to become an AI engineer and I would be glad if you can help me acheive my goal. Thanks a lot
Great tutorial series, I really enjoyed. Would be great if you could make more videos series like this about AI Agent with complete fullstack development. From Haiti
Thanks for the feedback - will consider it!
Thanks for putting this series together. Best wishes for your channel
@@SoloJetMan Thanks! Glad they helped 😃
Clear as crystal. Thanks 👍
I love it! The video is full of value, as well as your other content. Subscribed, definitely want to see more of this :)
@@franknillard Thanks a bunch!
Hey, can you recommend a book for learning Python? I'm new to it
@@dusktildawn-ue8jq I'm not a big fan of books, but sentdex on TH-cam and his site realpython.com/ are really good and I have used them before. He has good tutorials in most domains as well
@@WW_AI_Adventures thanks
Really high quality content man!
@@peterroshdy1269 thanks a bunch!
What kind of stuff are you interested in seeing in this space?
Just more content like that with demos to cool ai applications and use cases
@@peterroshdy1269 happy to oblige!
Well done mate.
Thanks Dong 🙏
Yo you are a saviour needed this for my bachelor's thesis project
@@mathew5880 xD haha so glad I could help. What's your thesis on?
@@WW_AI_Adventures actually my prof actually asked me to make like a search engine where you would make graphs of research papers from pubmed and using a graph convolutional neural network ,when the user types a keyword it would get the most similar paper to it from the graph So really generating results based on that is what my project is on ,still figuring out the details but yeah this helps If you know something else that could help out do suggest
Working on something similar for my thesis as well.
Ah graph rag sounds perfect for this. Graph Convolutional networks sound like they might be overkill though, but I'm no expert, I'd probably try with just graph-rag first (with a cheaper LLM than openAI though at first)
@@WW_AI_Adventures yeah I guess your probably right but will try out both and see how it goes
such a dope project
hey man great video
@@AyushRaj-sf5wk Thanks! Did you like anything in particular? Or any other topics you're interested in?
@@WW_AI_Adventures well I was trying to study about RAG and the visual representation helped good work
Can you please improve audio?
Thanks for the feedback - Do you mean the microphone quality or the editing?
@@WW_AI_Adventures it was quite low, probaby mic issue
@@stanTrX thanks!
it's really great explanation and example
@@ganesh301b thanks 🙏
Hello. tested agentzero, autogen etc imo biggest problem with these are reliability. Hope to get better results using langgraph
@@stanTrX LangGraph can still be unreliable, but I think you have more controls to make it better, and more flexibility with the graph structure
you have written laba_index instead of llama_index
@@SayeedAhmedKhan-d1x ah good spot!
Very cool bro <3
Great tutorial, was looking for a way to join my agents/ tools and langgraph is a sure choice. Btw, with function calling now possible with most queries, you can actually write a prompt that will produce a json result witg tool name & parameter. This way you have full control over your agents and you dont have to depend of langchain @tool.
@@wesleymogaka ah good idea! So far I haven't had an issue with langchains abstraction, but will certainly keep this in mind
Hi Will thank for the videos they are very useful and well done, I just want to tell you that in the third git hub repo there are only the readme file.
Ah thanks you - I will update it later today
thanks for a clear concise run thru!
@@ahmedkhan25 thanks - do you prefer shorter content in general over longer more in depth content?
@@WW_AI_Adventures anything - actually anything exploring langgraph and agentic functionality is great
thanks, it's a great video to start with LangGraph.
Very nice video! I would love to see a tutorial on a customer support ticket agent. For example the agent is able to answer questions from a knowledge base and use tools to check order status, etc.
Thanks for the feedback - Nice idea
You create an agent that uses RAG as a tool alongside other tools like ticketing
@@wesleymogaka And use functions to connect externals api.
Hi. Loved your explanation. Looking forward to more agentic ai based videos. Also, is there a way to have a 1:1 session with you?
@@ajkdrag Thanks, glad it helped! Anything in particular you'd like to see - Incorporating RAG, writing code, copywriting etc. Send me an email - whitew1994@gmail.com and we might be able to sort something out!