- 23
- 28 114
Tech at Worldline
เข้าร่วมเมื่อ 3 ส.ค. 2023
We are Worldline's tech team, sharing the latest insights, events and behind-the-scenes from our engineers around the world.
Running Local Models with LM Studio
Join Raphaël Semeteys, DevRel at Worldline, in the fourth episode of the tutorial series "GenAI's Lamp," focusing on Generative Artificial Intelligence. This episode is dedicated to the LM Studio tool.
🔍 What's Inside:
- Run local models like Llama 3 on your laptop even without a GPU
- Discover, download, and run local models from Hugging Faces
- Use the AI Chat feature to interact with the models
- Make API calls using Node.js within a Jupyter Notebook, and also interact with LM Studio using its TypeScript SDK
- Use the new LM Studio CLI
🔗 Associated content
github.com/worldline/GenAI-Lamp/blob/main/Notebooks/Nodebook%20LM%20Studio%20Llama%203.ipynb
📚 Resources of the video
jupyter.org
huggingface.co
lmstudio.ai
github.com/lmstudio-ai
🔗 Follow Raphaël
dev.to/raphiki/
github.com/worldline/GenAI-Lamp/
www.linkedin.com/in/raphaelsemeteys/
RaphaelSemeteys
raphiki.github.io
🔗 Follow us
blog.worldline.tech/
worldlinetech
🔍 What's Inside:
- Run local models like Llama 3 on your laptop even without a GPU
- Discover, download, and run local models from Hugging Faces
- Use the AI Chat feature to interact with the models
- Make API calls using Node.js within a Jupyter Notebook, and also interact with LM Studio using its TypeScript SDK
- Use the new LM Studio CLI
🔗 Associated content
github.com/worldline/GenAI-Lamp/blob/main/Notebooks/Nodebook%20LM%20Studio%20Llama%203.ipynb
📚 Resources of the video
jupyter.org
huggingface.co
lmstudio.ai
github.com/lmstudio-ai
🔗 Follow Raphaël
dev.to/raphiki/
github.com/worldline/GenAI-Lamp/
www.linkedin.com/in/raphaelsemeteys/
RaphaelSemeteys
raphiki.github.io
🔗 Follow us
blog.worldline.tech/
worldlinetech
มุมมอง: 66
วีดีโอ
Why should we say Internet3 rather than Web3? Let's demystify blockchains and decentralized apps! 🏗️
มุมมอง 30หลายเดือนก่อน
The speaker, Raphaël, begins by introducing the complexity of Web3 and aims to simplify it through an architectural lens. He draws on his background as an architect and an expert in open-source technology to navigate the topic. 💡 Raphaël provides an overview of Web3, describing it as a wide, complex, and evolving domain filled with buzzwords and complexities. 🔍 He aims to provide milestones and...
Uncovering the Potential of Hugging Face for AI Applications
มุมมอง 92หลายเดือนก่อน
Join Raphaël Semeteys, DevRel at Worldline, in the fourth episode of the tutorial series "GenAI's Lamp," focusing on Generative Artificial Intelligence. This episode is dedicated to Hugging Face. 🔍 What's Inside: - Overview of interacting with state-of-the-art models from Hugging Face - Demonstration of making API calls directly to a model by using Hugging Face libraries in Node.js - Exploratio...
No code LLM-based workflows with Flowise
มุมมอง 2632 หลายเดือนก่อน
Join Raphaël Semeteys, DevRel at Worldline, in the fifth episode of the tutorial series "GenAI's Lamp," focusing on Generative Artificial Intelligence. This episode is dedicated to Flowise, a no code solution to create your own LLM-based workflows and chatbots. 🔍 What's Inside: - Overview of Flowise as a no or low code solution for creating chatbots and AI assistants - Demonstration of using Fl...
Everything you always wanted to know about AI but were afraid to ask 😨 …
มุมมอง 842 หลายเดือนก่อน
🚀 With Urs Gubser, let's deep dive into an AI journey : 💡 Through AI History: Starting with Alan Turing's groundbreaking work in the 1950s, Urs traces the evolution of artificial intelligence through the decades. From early workshops to the AI winters of the '60s and '80s, to the resurgence in the '90s and the advent of machine learning, he provides a comprehensive overview of AI's journey. 🧠 U...
📶 Three levels of offline capabilities for your web apps
มุมมอง 1163 หลายเดือนก่อน
Join Sylvain Pollet-Villard as he dives into the realm of offline-capable web applications in this insightful video. 📱💻 Embark on a journey through the evolution of web technologies, from the early innovations to the recent advancements, and discover the potential of offline capabilities in enhancing the user experience. 🚀 In this comprehensive exploration, Sylvain presents a progressive roadma...
Go beyond Text with Google APIs
มุมมอง 443 หลายเดือนก่อน
Join Raphaël Semeteys, DevRel at Worldline, in the fourth episode of the tutorial series "GenAI's Lamp," focusing on Generative Artificial Intelligence. This episode is dedicated to Google APIs to manipulate text and image in a multimodal way. 🔍 What's Inside: - Demonstrations of imagen model's image generation and imagetext model's image captioning capabilities. - Use of visual question answer...
Why CLI is the new (green) UX ? 🌱💻
มุมมอง 2.8K4 หลายเดือนก่อน
Join Thomas Langlois and Philippe Duval as they explore the significance of Command Line Interface (CLI) in the modern tech landscape Both experts in cloud architecture and software automation, dive into three key areas throughout the session. With a blend of scientific research, environmental consciousness, and practical demonstrations, this video serves as a comprehensive guide for tech enthu...
Play with PaLM 2 APIs from Node.js
มุมมอง 884 หลายเดือนก่อน
Join Raphaël Semeteys, DevRel at Worldline, in the second episode of the tutorial series "GenAI's Lamp," focusing on Generative Artificial Intelligence. 🔍 What's Inside: - Introduction to Google PaLM 2 APIs and their use in Node.js - Installation of necessary Node.js modules including esm_hook, dotenv, Google Cloud AI platform module, and LangChain - Authentication and setup of Google Cloud Acc...
Discover OpenAI APIs with Node.js and Jupyter Notebook
มุมมอง 1504 หลายเดือนก่อน
Join Raphaël Semeteys, DevRel at Worldline, in the second episode of the tutorial series "GenAI's Lamp," focusing on Generative Artificial Intelligence. 🔍 What's Inside: - Introduction to OpenAI APIs: Understand the foundation of interacting with Large Language Models (LLMs) like GPT-4. - Setting up Your Environment: Learn how to install necessary NPM modules, manage environment variables, and ...
Run Node.js in Jupyter Notebook and play with GenAI APIs
มุมมอง 4725 หลายเดือนก่อน
Join Raphaël Semeteys, DevRel at Worldline, in the inaugural episode of the new tutorial series "GenAI's Lamp," focusing on Generative Artificial Intelligence. In this premiere, Raphaël delves into the setup and configuration of Jupyter Notebook for running Node.js scripts and executing API requests. This foundational episode paves the way for subsequent tutorials, where we'll further explore a...
Exploring specialized chatbots | Live demo
มุมมอง 2145 หลายเดือนก่อน
Join us for a captivating demonstration as we delve into the evolution from discriminative to generative AI in specialized chatbots using LangChain 🦜🔗. With Guillaume Coter , a data scientist and Marie Alice Blete, a software engineer uncover the challenges faced by general AI models when handling personalized and confidential information. During the demonstration, our experts showcase a demo w...
From discriminative to generative AI | Tech Interview
มุมมอง 2366 หลายเดือนก่อน
From discriminative to generative AI | Tech Interview
Boosting payment software development with ai assistance
มุมมอง 1927 หลายเดือนก่อน
Boosting payment software development with ai assistance
Build a Python Web App to chat with your datasets using GenAI
มุมมอง 22K7 หลายเดือนก่อน
Build a Python Web App to chat with your datasets using GenAI
AI vs Devs - Exploring the present and the future
มุมมอง 2168 หลายเดือนก่อน
AI vs Devs - Exploring the present and the future
Worldline UK Technical Conference 2023 - After Movie
มุมมอง 4510 หลายเดือนก่อน
Worldline UK Technical Conference 2023 - After Movie
Worldline TechForum Iberia 2023 - After Movie
มุมมอง 5110 หลายเดือนก่อน
Worldline TechForum Iberia 2023 - After Movie
Worldline TechForum 2023 - After Movie
มุมมอง 9310 หลายเดือนก่อน
Worldline TechForum 2023 - After Movie
I followed all steps but when adding Streamlitresponse is not working the responses anymore, can you help?
Can't believe you have only 525 subscribers! The content is really good.
Thank you. I have a personal channel with similar content if you want to check it out :)
Incredible video I can make it works in a few minutes ! Your explainations are super clear ! I just have a question about the deployment on github and streamlit. When I push this code in github it seems to have an error about cache or log... Did you try to deploy it ?
Images not loading in pickle format can you explain this video brief
Love the video ❤. Could you please do it using langchain once
ERROR: Could not find a version that satisfies the requirement pandasai==1.4.10 (from -r requirements.txt (line 2)) (from versions: none) ERROR: No matching distribution found for pandasai==1.4.10 (from -r requirements.txt (line 2)) hi i am facing this issue can you please resolve this issue for me ?
Very cool!! Any updates or new discoveries of chat with data methodologies??
It looks like I have to be a paid user for OpenAI, right? If so, any free alternatives that could be used with streamlit and pandas? Thank you in advance
we can make use of gemini from Google
Thanks for video. Tomorrow will try.
😀
I have questions, can it run follow up question ? Or it only work once and done ? Ex i want you show data 2023, follow up question show only Adams data ?
if i have my own csv data how do i convert to pkl
Hello! You can read your CSV into a Pandas file with pd.read_csv then convert to pickle with df.to_pickle Though these days I prefer recommending .to_parquet as a binary format
I really like this project will work on this coming weekend.
Awesome, good luck 🙂
Could u show, if the data is inside Postgres database ? Please
Hello! I can't write a link in comments, but if you browse through the PandasAI documentation, at the "SQL connectors" page you'll find an example using a Postgres connector
might be a dumb questions, but since i use my API key. will there be any costs in using this method?
No
Yes. But if your account is new, or you haven't used the API key before, you will spend your free credits first
ModuleNotFoundError: No module named 'pandasai.callbacks' How to resolve this issue
Hello, Apparently pandasai removed the pandasai.callbacks module in its more recent releases, so I have pinned pandasai to use version 1.4.10, can you try downgrading?
yes! with pip install pandasai==1.4.10 you'll fix the problem automatically
@@andfanilo Is there any workaround instead of downgrading the version?
I bought a book about developing apps with gpts with her name on the cover. Came to TH-cam to check it up, ended up clicking on this video, stayed for the whole thing. Seems to be so talented yet young. Amazing both in English and French.
Thank you for your valuable feedback! A youtube short has just been released, shedding light on Marie Alice and Olivier's AI book. Check it out!
Amazing, I'm a huge fan of your channel, and learned a lot thanks to you! However I got an issue, for some reason, the temp file of the graph is correctly generated (and stored in ./exports/charts/) however, it doesn't show up in Streamlit. Instead, it's displayed as a doc icon with a 0. Any idea what I might have done wrong?
Hey there! That's strange, I just cloned the project and I have the same problem. I ended up reloading the image with Pillow and passing this to st.image instead of passing the file path to st.image so: ``` from PIL import Image class StreamlitResponse(ResponseParser): def format_plot(self, result): img = Image.open(result["value"]) st.image(img) return ``` Pushing the changes to the repo :) (and also pinning pandasi as apparently callbacks have disappeared since the release of the video), thanks for sharing!
Awesome! 👍
Thanks for the feedback :)
thnk you, summary of what i needed.
Glad to hear it was useful 🙂