- 24
- 184 681
Johannes Jolkkonen | Funktio AI
เข้าร่วมเมื่อ 9 ต.ค. 2013
Sharing my experiences building cutting-edge AI applications.
How to Automate Resume Screening in Workable
Want to build AI-applications and automations for your business? Get in touch!
cal.com/johannes-jolkkonen-xdjl0r/20min
Connect with me on LinkedIn:
www.linkedin.com/in/johannesjolkkonen/
cal.com/johannes-jolkkonen-xdjl0r/20min
Connect with me on LinkedIn:
www.linkedin.com/in/johannesjolkkonen/
มุมมอง: 80
วีดีโอ
How to Make LLMs More Reliable
มุมมอง 664หลายเดือนก่อน
Want to build AI-applications and automations for your business? Get in touch! cal.com/johannes-jolkkonen-xdjl0r/20min Connect with me on LinkedIn: www.linkedin.com/in/johannesjolkkonen/ Code: github.com/JohannesJolkkonen/llm-self-critique/tree/main ▬▬▬▬▬▬ T I M E S T A M P S ▬▬▬▬▬▬ 0:00 - Intro 1:15 - Key concepts 5:05 - LLM Self-Critique 8:34 - Tutorial 12:25 - Real world example
How to Use AI to Save Money In Construction
มุมมอง 259หลายเดือนก่อน
Want to build AI-applications and automations for your business? Get in touch! cal.com/johannes-jolkkonen-xdjl0r/20min Connect with me on LinkedIn: www.linkedin.com/in/johannesjolkkonen/ ▬▬▬▬▬▬ T I M E S T A M P S ▬▬▬▬▬▬ 0:00 - Intro 0:50 - Generating incident reports 3:21 - Exporting documents 3:59 - Sending reports to Teams and Sharepoint 5:14 - Scheduling automated reports
I Built an App To Generate Reports with LLMs
มุมมอง 6K3 หลายเดือนก่อน
Want to build AI-applications and automations for your business? Let's chat! cal.com/johannes-jolkkonen-xdjl0r/20min Connect with me on LinkedIn: www.linkedin.com/in/johannesjolkkonen/ Application repo: github.com/JohannesJolkkonen/llm-report-generation Jason Liu's article: jxnl.co/writing/2024/06/05/predictions-for-the-future-of-rag/ ▬▬▬▬▬▬ T I M E S T A M P S ▬▬▬▬▬▬ 0:00 - Intro 1:41 - Genera...
How to Create Powerpoint & Word Documents With AI
มุมมอง 5683 หลายเดือนก่อน
Want to build AI-applications and automations for your business? Get in touch! cal.com/johannes-jolkkonen-xdjl0r/20min Connect with me on LinkedIn: www.linkedin.com/in/johannesjolkkonen/ ▬▬▬▬▬▬ T I M E S T A M P S ▬▬▬▬▬▬ 0:00 - Intro 0:58 - Hubspot integration 4:05 - Docxtemplater 5:10 - Handling missing data 8:49 - Outro
The best way to publish your RAG application (Vercel + Modal)
มุมมอง 8655 หลายเดือนก่อน
In this video you'll learn to deploy a fullstack RAG application, built on React FastAPI. We will cover two straightforward options, Vercel and Modal. Aside from the deployment, we'll also make some improvements to the application we have previously built, namely using websockets to stream LLM responses in real-time, and also showing an alternative way to do RAG without LangChain. ▬▬▬▬▬▬ LINKS ...
How to build a dashboard-app with OpenAI's NEW GPT4o
มุมมอง 13K5 หลายเดือนก่อน
In this video we use Instructor and Timescale to create an interactive data visualization dashboard, where OpenAI's new GPT4o will figure out how to get data and how to properly visualize that data in order to answer user requests. ▬▬▬▬▬▬ LINKS ▬▬▬▬▬▬ Want to build AI-applications and automations for your business? Get in touch! funktio.ai Try TimeScale free for 90 days: tsdb.co/sign-up-johanne...
How to build AI-apps with React + FastAPI (full beginner tutorial)
มุมมอง 6K5 หลายเดือนก่อน
Python-frameworks like Streamlit and Gradio have become very popular in the AI-boom, as many people are excitedly building demos and prototypes to test the technology. While they are good for doing just that, they do lack the flexibility for building applications that are genuinely usable in the real world, at scale. In this video, I hope to demystify the leap to building more powerful, full-st...
I compared the best vision LLMs...
มุมมอง 8177 หลายเดือนก่อน
In this video we compare the most powerful options for visual language models. VLMs can not only reason over text but also images, enabling many interesting use-cases that were previously not possible. ▬▬▬▬▬▬ LINKS ▬▬▬▬▬▬ Connect with me on LinkedIn: www.linkedin.com/in/johannesjolkkonen/ Code: github.com/JohannesJolkkonen/funktio-ai-samples ▬▬▬▬▬▬ T I M E S T A M P S ▬▬▬▬▬▬ 0:00 - Intro to VLM...
How to Combine Vector Search and SQL for RAG
มุมมอง 3K7 หลายเดือนก่อน
By using a database like PostgreSQL or Timescale, we can build more complex and versatile RAG-systems that can retrieve not only text-documents, but also numerical data and time-series data. To manage these multiple query types, we will also implement a query planning step, where user questions are automatically translated into a sequence of database-queries. ▬▬▬▬▬▬ LINKS ▬▬▬▬▬▬ - Try Timescale...
Evaluate and Optimize RAG with TruLens (full tutorial)
มุมมอง 2.8K9 หลายเดือนก่อน
Evaluate and Optimize RAG with TruLens (full tutorial)
How to Chat With Knowledge Graphs (python tutorial)
มุมมอง 10K10 หลายเดือนก่อน
How to Chat With Knowledge Graphs (python tutorial)
How to Build Knowledge Graphs With LLMs (python tutorial)
มุมมอง 75K11 หลายเดือนก่อน
How to Build Knowledge Graphs With LLMs (python tutorial)
Advanced RAG with Knowledge Graphs (Neo4J demo)
มุมมอง 54Kปีที่แล้ว
Advanced RAG with Knowledge Graphs (Neo4J demo)
Automate web scraping with Python and AI (LangChain tutorial)
มุมมอง 2.9Kปีที่แล้ว
Automate web scraping with Python and AI (LangChain tutorial)
How to Auto-Format Your Notebooks on Databricks (new feature)
มุมมอง 634ปีที่แล้ว
How to Auto-Format Your Notebooks on Databricks (new feature)
Should You Start Using Microsoft Fabric Instead of Databricks?
มุมมอง 4.3Kปีที่แล้ว
Should You Start Using Microsoft Fabric Instead of Databricks?
How to Access On-Prem Files with Fabric Pipelines (Microsoft Fabric tutorial)
มุมมอง 971ปีที่แล้ว
How to Access On-Prem Files with Fabric Pipelines (Microsoft Fabric tutorial)
Get Started with Microsoft Fabric (hands-on demo)
มุมมอง 438ปีที่แล้ว
Get Started with Microsoft Fabric (hands-on demo)
Automating SQL-Table Creation With ChatGPT (with examples)
มุมมอง 399ปีที่แล้ว
Automating SQL-Table Creation With ChatGPT (with examples)
I am getting this error : Extracting entities and relationships for data/people_profiles\people-profiles1.md Error processing data/people_profiles\people-profiles1.md: Expecting value: line 1 column 1 (char 0) Extracting entities and relationships for data/people_profiles\people-profiles2.md Error processing data/people_profiles\people-profiles2.md: Expecting value: line 1 column 1 (char 0) Extracting entities and relationships for data/people_profiles\people-profiles3.md Error processing data/people_profiles\people-profiles3.md: Expecting value: line 1 column 1 (char 0) any help on resolving this please?? @johannes?
Hello! thanks for the valuable video! Q: Any way to copy all the files from a directory to a lakehouse with a pipeline? ( gateway is running on this machine)
Getting below error in vercel while deploying backend after creating requirements.txt - Error: A Serverless Function has exceeded the unzipped maximum size of 250 MB. Please help.
This is basically what I've wanted to do for years. (Originally GPT-2 & Neo4j) Haven't gotten far, but keep returning to it. So glad someone else had the same idea!
how to dockerize this and do this development into docker
Thanks so much! This was awesome! Not even AI could help me. This did it.
Thanks for this video, we have also similar tool for report generation. However I would like to know how can we generalize this for different types of report? We are using simple RAG to handle generalization you have any other suggestions?because every report can have different section and writing code for all makes it difficult?
Amazing content Johannes! Keep going bro
Johannes - thank you for the video! what r ur thoughts on building a KG-native CRM?
You look like Homelander. lol
Is it possible to access the file system path of on-premise files to be used in a Python notebook using Fabric?
This is gold! I just found your channel and been binge-watching all your videos - many thanks for your effort and time
Thank you, I'm glad to hear it!
Super high-quality video. Thank you so much!!
Wow, this is going to be interesting. Thanks for thinking of sharing your experience.
Thanks Ken, It's a bit of a different video from the technical how-to's, as I also want to show examples of connecting the technicals into real-world business scenarios. I'm glad you like it!
Wonderful tutorial. Thank you so much!!
Excellent!
Please a tutorial on full stack AI development
The walkthrough that you made on the GitHub repository was really great. Thanks for sharing your knowledge!
The video is great, thank you, but the background music made it difficult for me to focus :(
code repo please
i think you missed to add template files into git it was missing in git might be mentioned in gitignore
Templates are in /frontend/public/temp/
You can now find the full application code in the video description. (or here: github.com/JohannesJolkkonen/llm-report-generation/ ) Remember to read the README, to understand what API-credentials you need for running the application.
The quiality of the videos rhar you post are just impressive, perfect videos, im just wondering if theres a way to build this app but entirely local to run in an ipad is it possible to build it ? Im trying to build an HIPPA prove app for a local doctor who wants the ia take the conversation and generate a report
@@Hector-zr2lq Thank you. I'm not very familiar with iOS/mobile development, but I'm pretty sure it would be possible, including local llms running on ipads or such. But it's not at all necessary (or worth it, in my opinion) to go down that route. It's perfectly possible to build HIPAA apps on the cloud, using platforms such as Microsoft Azure, where you can also run OpenAI's models. That's probably where you want to look, and perhaps get in touch with their sales for more specific requirements.
Doing some research about NVIDIA NIM have you use it?
I landed on this video to find any solutions that could do this for videos. Would have loved to see something related to that as well.
Hi, Is it possible to use programmes like "Make" or "Zapier" to automate this kind of process ? Thank you .
Not really, no. While you can run custom code on those platforms, that custom code can't use any external libraries (such as DocxTemplater, which is crucial here for the actual document creation). Then there's also stuff around handling the data structures, doing parallel API calls and validating the LLM-outputs, just to name a few, that I think would be impossible to do in no/low-code
Sharing code is invaluable. ♥️
Thank you so much , excited to build AI applications and automations for our business.plz share repo link.
Thanks for showing a practical business use case. Very helpful.
Finally, a way to get my TPS reports done. 📠
It is very interesting ❤ Thanks so much If there is a possibility to explain the project in detail, it will be appreciated
Thanks everyone for the positive feedback! As many are asking, will share the code within the next 1-2 days, just want to structure it a bit better and write a short README first
Thank you very much Johannes for sharing! Looking forward!
Thanks Johannes!
Excellent work Johannes! Looking forward to play with the code when you are ready to share. Thanks !!
Amazing work🎉🎉
This is awesome Johannes - I think the approach you've taken (and crediting Jason Liu's work) is valid - the report itself has significant value. How can you 'protect' the data that is provided? The company information that is being queried in the LLM contains what might be sensitive company information - how do you know that it isn't being exposed for access by competitors or others?
Thank you! Regarding data protection, there's no particular risk of such exposure with LLMs. OpenAI and Anthropic both have it in their terms to not train models on API inputs or outputs, and also have robust security compliances (including SOC2 and HIPAA, which are 2 of the most common certifications that companies look for.) (links: trust.openai.com/, support.anthropic.com/en/collections/4078534-privacy-legal) There's also the option to use OpenAI's models via Azure, and Anthropic's via AWS. The guarantees are technically the same as above, but these major cloud platforms just have a longer track-record of trust and security behind them. So that's typically the go-to with more sensitive clients, like in my last 2 projects which were done for a bank and a major healthcare provider. But for most situations, using the APIs directly is perfectly fine. No more risky than any other SaaS, CRM or database the company is already using for their data. Might make a more detailed video about this at some point, as it is something that comes up quite often
@@johannesjolkkonenwill it be possible to run it with local stuff such as Ollama or LM studio ? OpenAI compatible API solution provided in the code?
@@artur50 Yup, all the LLMs used here (OpenAI, Anthropic, Groq for Llama3.1) follow the same OpenAI 'standard', so works with Ollama/LMstudio with very minimal adjustments
This video is very informative; I really appreciate it! Would it be possible to share the GitHub URL for this project? I'm not very proficient with coding, but I'd like to give it a try!
HI Johannes great work buddy, can you please share code snippits. so we can take some referebce from there
Can u share the GitHub link of the project?
Will you release the source? Would save me shit loads of timr
@@petersmith8153 Done, repo is now in the description and pinned comment (:
let's goooo
Excellent job 👏🏻
Thx for the video! Could you paste the link to the GitHub repo? Thx again!
please make a video how to deploy the same in AWS lambda / AWS ECS ?
Hi Johanes, thank you and congratulations for the video! On your prompts, when you instruct the LLM how to extract entities, you are kind of describing a model for the data, right? (Project, Technology, Client). On more traditional methodologies for generating knowledge graphs, this looks similar to the ontology. Do you think would be correct to think of it like this?
Very cool! 👍
Does anyone know if it's also possible to run black with command-line arguments like --line-length?
Great video!
I ama ctually still wondering... but missing version control is very very sad
At a Workspace settings you can configure Git integration with Azure DevOps which provides version control. Maybe the video is old before that feature!
@@casimircompaore2076 I think, it is still in preview, but thx a lot!
Awesome!! Thanks!! 👏👏👏
Can we do this with LlamaIndex?
Can I integrate the same solution with Memgraph?
Really helpful content but please dont add music while you are talking, especially overpowering music. Makes it very difficult to follow what you are speaking.
wow - it's been a while since I've seen someone so comfortable in their domain of expertise and who shares their skills and advice so willingly and effortlessly - bravo - we should talk! I've sent a connection request on LinkedIn. Thank you Johannes
Thank you Jonathan, much appreciated
Darn!! I have been working on something similar, slightly different approach