Machine Unlearning in 2024
Learn AI
Practical Introduction to Natural Language Processing
Transform yourself from a Python Developer to a Junior NLP Data Scientist with practical projects.
How to Build High-Accuracy Serverless RAG Using Amazon Bedrock and Kendra on AWS
Serverless RAG on AWS — Amazon Bedrock, Amazon Kendra, AWS Lambda, Claude-2, LangChain, and Streamlit.
AmazonKendraRetriever
lyzr/lyzr/utils/chat_utils.py at a3325f58a086ef9610b9c08995c8bf86b777d408 · LyzrCore/lyzr
Lyzr SDKs help you to build all your favorite GenAI SaaS products as enterprise applications in minutes. - LyzrCore/lyzr
Building RAG at 5 different levels
The unreasonable effectiveness of embeddingsOr how I learned to stop worrying and love the hallucinations.This week I dived deep into vector databases. My go...
Musings on Building a Generative AI Product
When evaluating RAG, it's not just the final answer that is worth evaluating
Evaluating intermediate steps (like query rephrasing and retrieved documents) is also super important when trying to make sure RAG works
Goo tutorial by on how to do this!
— Harrison Chase (@hwchase17)
Building Agentic RAG with LlamaIndex - DeepLearning.AI
Learn how to build an agent that can reason over your documents and answer complex questions. Learn from the co-founder and CEO of LlamaIndex
Mervin Praison
Site Reliability Engineer
I'm writing a new vector search SQLite Extension
sqlite-vec is an new vector search SQLite extension, coming soon!
Blob<96>
adam-maj/tiny-gpu: A minimal GPU design in Verilog to learn how GPUs work from the ground up
A minimal GPU design in Verilog to learn how GPUs work from the ground up - adam-maj/tiny-gpu
microsoft/azurechat: 🤖 💼 Azure Chat Solution Accelerator powered by Azure Open AI Service
🤖 💼 Azure Chat Solution Accelerator powered by Azure Open AI Service - microsoft/azurechat
Generating 50k+ embeddings in 25 seconds using GTE 🧠 and MapReduce 💻
The official documentation for Sweep AI.
Llm.c – LLM training in simple, pure C/CUDA | Hacker News
Andrej's zero to hero course
sourcegraph/awesome-code-ai: A list of AI coding tools (assistants, completions, refactoring, etc.)
A list of AI coding tools (assistants, completions, refactoring, etc.) - sourcegraph/awesome-code-ai
Open Parse
Beyond text splitting - improved file parsing for LLM’s - Filimoa/open-parse
ScreenAI: A visual language model for UI and visually-situated language understanding
Automating Pull Request Reviews With CodiumAI PR-Agent
Motivation If you are a developer, you know how much time you spend on pull request reviews. We all try to write the best code we can. When we are done, we ask our team members to review our code. Sometimes, making a pull request is more complex than it sounds. Over time, teams learn that pull requests need to be standardized to speed things up and improve communication. That is why we have a pull request template, for example.
LocalSend
localsend/localsend: An open-source cross-platform alternative to AirDrop
An open-source cross-platform alternative to AirDrop - localsend/localsend
Spreadsheets are all you need.ai – A low-code way to learn AI
X
60 gen ai questions
Reverse engineering the recipe for excellent documentation
Stay updated with best practices for technical writers. Includes an API documentation course for technical writers and engineers learning how to document APIs. The course includes sections on what an API is, API reference documentation, OpenAPI specification and Swagger, docs-as-code publishing and workflows, conceptual topics, tutorials, API documentation jobs, and more.
Tiny Predictive Text - Adam Grant
Predictive Text Using only 13KB of JavaScript. No LLM. permy.gif Try it here | Code | Permy This is a simple POC of using Permy with a simple JSON dictionary for predictive text that is surprisingly …
Papers with Code - The latest in Machine Learning
Papers With Code highlights trending Machine Learning research and the code to implement it.
Happy New Year: GPT in 500 lines of SQL - EXPLAIN EXTENDED
A complete GPT2 implementation as a single SQL query in PostgreSQL.
BCG-X-Official/agentkit: Starter-kit to build constrained agents with Nextjs, FastAPI and Langchain
Starter-kit to build constrained agents with Nextjs, FastAPI and Langchain - BCG-X-Official/agentkit
Vector Embeddings 101: The New Building Blocks for Generative AI
Fundamental concepts to get you going and get the most from the latest craze in the generative AI community: vector databases.
Phi-2, the New Year Gift for Language Model Lovers
An introduction to Phi-2, a compact language model that is similar to Gemini Nano. The limits of LLM, and how to fix in engineering.