Deepnote’s Post

Better and faster Deepnote AI is here!

🚀 Just published a new blog post on revolutionizing stock trading with AI and ML! Explore how these technologies are reshaping the trading landscape, offering new insights and automating trading systems. Learn about the opportunities and challenges, and dive into a hands-on Python demo for forecasting stock values. Check it out here: https://lnkd.in/dvs_yMqm

🚀 Alert ! AI Enthusiasts! 🚀 I'm thrilled to share the below third part of our groundbreaking video series on creating an AI Sales Agent that can autonomously handle calls! This tutorial takes you through the final steps of integrating Twilio with Python, OpenAI, and Elevenlabs to get your AI ready for real-world use. ✨ Watch here: https://lnkd.in/es4krrgm

We’re excited to announce the Code Step AI Helper, now available in your AirOps workspace. If your AI workflows need a Code Step for advanced operations, you can now use AI to generate the Javascript and Python using our AI helper in a flash. To get started, add a Code step to your workflow, click on Generate With AI, describe the code you want generated, and go! The helper has context of your entire workflow and available variables. It can also modify and explain existing code. To learn more about how to use the AI Helper to write your code, watch this short video from our team member Ana with more details.

🚀 Just wrapped up an exciting exercise using machine learning pipelines on the Titanic dataset! 🚀 I created a robust pipeline featuring five transformers: 1. Handling missing values 2. One-Hot Encoding (OHE) 3. Scaling 4. Feature selection 5. Decision Tree classifier Each step was carefully crafted to ensure data integrity and enhance model performance. After building the pipeline, I exported it as a pickle file for easy deployment and reusability. 🎉 Here's a brief overview of the process: 1. Constructed the pipeline with transformers as shown in the image. 2. Saved the complete pipeline using the pickle module. 3. Imported the pipeline from the pickle file. 4. Successfully made predictions with the imported pipeline! This approach not only streamlined the workflow but also ensured consistency and scalability. A big step forward in my data science journey! #MachineLearning #DataScience #Python #Pipelines #TitanicDataset #AI #DataScienceJourney

Experimenting with automation! Started with a Word template that was basically empty except for a couple of fields. With some Python help from GPT-4, I turned it into "mail merge on steroids." Now it gathers user input and generates a personalized document fully generated by AI. Just a small demo of how automation can spice things up. Can't wait to see where this goes! Please forgive the formatting on the Word document. I'm viewing on my phone.

Unveiling My Latest Article on Sentiment Analysis in the World of AI and Medications! 💊 I'm thrilled to share that my latest article, titled "AI and Meds: How I Figured Out What People Feel about Drugs," has just been published. In this comprehensive guide, I went into sentiment analysis, breaking down complex concepts into beginner-friendly insights. From understanding the basics of sentiment analysis to hands-on implementation using Python, TensorFlow, and Pandas, this article is a perfect resource for anyone interested in exploring the intersection of AI and healthcare. 🔗 [Read the Full Article Here] https://lnkd.in/eMAGNY9J

📍Day 3 of my #TensorFlow journey! 🚀 After exploring constant and Variable, today we’re diving into tensor operations. We’ll cover slicing, indexing, and performing arithmetic operations on tensors, which are essential skills for manipulating data in TensorFlow. Understanding these operations will pave the way for more complex tasks as we build towards creating sophisticated models. Attached is the Google Colab notebook 📚 for Day 3, where we dive into tensor operations, slicing, and indexing in TensorFlow. This hands-on guide will help you explore these essential operations, which are key to effective data manipulation in TensorFlow. Download the file to explore the code, and don’t forget to check out all the related files and updates on my GitHub repository 🔖 : [TensorFlow Masters on GitHub](https://lnkd.in/dhf9JCUU). #DeepLearning #AI #MachineLearning #Python #DataScience

🧩 distilabel supports dedicated and serverless inference via the Inference API. Thanks to Philipp Schmid (https://buff.ly/3vQaIBX), distilabel supports dedicated Inference Endpoints and serverless Inference Endpoints from version 0.4, via the Inference API. Our InferenceEndpointsLLM class can now search for endpoints or server-less deployments of model in the Hugging Face Hub, and use them for inference. Why not give it a try? This feature was introduced thanks to the community. Do you wanna contribute to the project? Have a look at the issues open https://buff.ly/3U8yfbj or join the conversation in our Slack community https://buff.ly/42e935l. We'll be there to help you all the way. Argilla's GitHub: https://buff.ly/3U8yfYR  Join our online community meetup: https://buff.ly/47Q39IK  distilabel, our new open-source AI feedback framework: https://buff.ly/3SGg3EZ  #nlproc #llms #python #opensource 

🚀 We're excited to announce that huggingface_hub's InferenceClient now supports OpenAI's Python client syntax! For developers integrating AI into their codebases, this means you can switch to open-source models with just three lines of code. Here's a quick example of how easy it is. Why use the InferenceClient? 🔄 Seamless transition: keep your existing code structure while leveraging LLMs hosted on the Hugging Face Hub. 🤗 Direct integration: easily launch a model to run inference using our Inference Endpoint service. 🚀 Stay Updated: always be in sync with the latest Text-Generation-Inference (TGI) updates. More details in https://lnkd.in/ebqUuyWb