AI Products @tenstorrent 📕 Author of books on GPT-3 & Neural Search in Prod ✍️ Tweets about LLMs & Prompt Engineering 📩 DMs open for collab
6 subscribed
May 12 • 13 tweets • 4 min read
Build a Web Scrapping AI Agent with RAG in just 30 lines of Python Code (step-by-step instructions):
We'll use ScrapeGraphAI, a Python library that uses LLMs to create smart scraping pipelines.
It involves four main steps: 1. Fetch: Retrieve the data 2. Parse: Analyze and structure the data 3. RAG: Processes the parsed data to find relevant information 4. Generate Answer
May 9 • 6 tweets • 2 min read
Document OCR in 90+ languages using python (100% free and without internet):
For document OCR, we'll use opensource toolkit Surya.
Python toolkit that does:
• OCR in 90+ languages
• Line-level text detection in any language
• Layout analysis (table, image detection)
• Reading order detection
• Outperforms Tesseract, on par with Google Cloud vision
May 4 • 11 tweets • 4 min read
Build a LLM app with RAG to chat with any AI newsletter on Substack in just 30 lines of Python Code (step-by-step instructions):
1. Import necessary libraries
• Streamlit for building the web app
• Embedchain for the RAG functionality
• tempfile for creating temporary files and directories
May 2 • 13 tweets • 4 min read
Build a RAG app with Llama-3 running locally on your computer
(100% free and without internet):
1. Install the necessary Python Libraries
Run the following command from your terminal.
May 1 • 16 tweets • 6 min read
Build a LLM app with RAG to chat with your Gmail Inbox in just 30 lines of Python Code (step-by-step instructions):
1. Install the necessary Python Libraries
Run the following command from your terminal.
Apr 29 • 10 tweets • 3 min read
Build a LLM app with RAG to chat with YouTube videos in just 30 lines of Python Code (step-by-step instructions):
1. Import necessary libraries
• Streamlit for building the web app
• Embedchain for the RAG functionality
• tempfile for creating temporary files and directories
Apr 28 • 10 tweets • 3 min read
Build a LLM app with RAG to chat with PDF in just 30 lines of Python Code
(step-by-step instructions):
1. Import necessary libraries
• Streamlit for building the web app
• Embedchain for the RAG functionality
• tempfile for creating temporary files and directories
Apr 26 • 6 tweets • 2 min read
Build LLM app with RAG in a few lines of Python Code (step-by-step instructions):
1. Install Embedchain
Embedchain is an opensource AI framework for creating LLM apps with RAG. It effectively segments data into manageable chunks, generates relevant embeddings, and stores them in a vector database for optimized retrieval.
Apr 20 • 6 tweets • 2 min read
3 ways to run Llama-3 locally (100% free and without internet):
1. GPT4All
An open-source project that provides tools and software to run powerful LLMs on your computer, without needing access to expensive GPU hardware or cloud services.
Apr 1 • 23 tweets • 4 min read
30-day study plan to learn AI and Machine Learning
Bookmark for reference 📌
Day 1: Introduction to AI and ML
• Objective: Understand AI, ML, and Deep Learning (DL)
• Task: Read the introductory chapter of “Artificial Intelligence: A Guide for Thinking Humans” by Melanie Mitchell.
• Exercise: Summarize the differences between AI, ML, and DL.
Mar 31 • 6 tweets • 3 min read
Stop LLM hallucination with this Python library
Outlines is a Python library that makes text generated by large language models (LLMs) more consistent and predictable.
It lets you control how LLMs generate text, making sure they follow a specific, expected format.
In this post, you'll read about:
1. Make LLMs answer MCQs without Hallucination 2. Make LLMs generate efficient JSON 3. Prompt Management with Templates
Before you move forward, subscribe to Unwind AI for more such AI updates: unwindai.substack.com
Mar 2 • 10 tweets • 2 min read
Support Vector Machines (SVM) Clearly Explained with Python Code:
What is SVM?
SVM is a supervised ML algorithm primarily used for classification tasks.
Imagine you're at a party, and you want to separate the pizza lovers from the burger lovers. SVM is the friend who draws the perfect line to divide them neatly.
Jan 20 • 5 tweets • 2 min read
Drag & Drop to build AI agents 🤯
Meet n8n, a visual UI for building AI agents with LangChain without writing a single line of Python code.
Want to build automation around LLM apps with Nocode, get started now:
How does it work?
1. Connect & Set Up: Choose your n8n experience and set triggers to fetch data across apps.
2. Integrate Using App Nodes: Utilize 400+ app nodes to manage your data.
3. Automate: Let your workflow handle tasks, from monthly sync to massive data executions.
Oct 29, 2023 • 5 tweets • 2 min read
ChatGPT just went FULLY multimodal 🤯
With one update, OpenAI killed 1000s of AI startups. ChatGPT’s strategy: Consolidate, Innovate, & Dominate.
ChatGPT becomes the ultimate AI super-app combining Midjourney, PDF Chat, Perplexity AI, and advanced Data analysis all in one app.
Here’s is what you can do with multimodal ChatGPT (Example by @ldjconfirmed)
Generate Image, Edit images with text, chat with images, documents and so much more 🤯
Oct 10, 2023 • 6 tweets • 3 min read
Drag & Drop to build AI agents 🤯
Introducing n8n, a visual UI for building AI agents with LangChain without writing a single line of Python code.
Now build automation around LLM apps with NoCode and give superpowers to ChatGPT.
How does it work?
1. Connect & Set Up: Choose your n8n experience and set triggers to fetch data across apps.
2. Integrate Using App Nodes: Utilize 400+ app nodes to manage your data.
3. Automate: Let your workflow handle tasks, from monthly sync to massive data executions.
Jul 24, 2023 • 7 tweets • 2 min read
LLMOps is the holy grail for deploying LLMs in Production.
Here is the roadmap to go from playground to production:
Platforms for LLMs
Think of LLM platforms as your personal Formula 1 pit crew - managing the heavy-lifting of infrastructure, fine-tuning, versioning, and deployment. They come in two flavors:
It has already taken the internet by storm and blowing everyone's mind!
Here are 15 amazing things that it can do: https://t.co/9toL4OWCxstwitter.com/i/web/status/1…
Bookmark this thread to come to back to when you experiment with Code Interpreter.
In this thread, you will see how Code Interpreter can:
- Be a data scientist
- Extract text from images (OCR)
- Generate animations and Videos
- Generate QR codes
- & so much more!
Jun 17, 2023 • 9 tweets • 5 min read
Are you ready to take your machine learning and data science skills to the next level?
I've got an incredible resource to share with you!
(A thread) 👇🧵
I came across @brilliantorg courses that teach you from first principles, making complex concepts intuitive and engaging.
Turn problems into simple exercises!
Jun 17, 2023 • 12 tweets • 6 min read
Top 10 ChatGPT Alternatives!
No signup required.
Bookmark this 📌
1. Perplexity AI
Perplexity AI unlocks the power of knowledge with information discovery and sharing. It can access the latest information using the web browsing feature.