🧩 #Chrome's Hidden Gems: Best Extensions of 2024

https://undercodenews.com/chromes-hidden-gems-best-extensions-of-2024/

@Undercode_News

Creating Festive Magic with Pixel: A Holiday Card Journey

https://undercodenews.com/creating-festive-magic-with-pixel-a-holiday-card-journey/

@Undercode_News

🦑 top cybersecurity job sites:

https://www.cyberseek.org

https://www.hays.com

https://www.comptia.org

🦑Advanced Steganography Tool made with Python:

Installation

1. Clone the repository:

   kali@kali:~$ git clone https://github.com/Sanjipan/Steganography
   

2. Install required Python libraries:

   kali@kali:~$ pip install argparse
   kali@kali:~$ pip install Wave
   kali@kali:~$ sudo pip install opencv-python
   kali@kali:~$ pip install numpy
   kali@kali:~$ pip install Pillow
   kali@kali:~$ pip install pytest-shutil
   kali@kali:~$ pip install subprocess.run
   kali@kali:~$ sudo pip install stegano
   

How to Use

1. Navigate to the project directory:

   kali@kali:~$ cd Steganography
   

2. Encoding/Decoding Files:

- For Audio Files:
- Encoding:

       sudo python3 ./Steganography.py -a -e <location of file>
       

- Decoding:

       sudo python3 ./Steganography.py -a -d <location of file>
       

- For Video Files:
- Encoding:

       sudo python3 ./Steganography.py -v -e <location of file>
       

- Decoding:

       sudo python3 ./Steganography.py -v -d <location of file>
       

- For Image Files:
- Encoding:

       sudo python3 ./Steganography.py -i -e <location of file>
       

- Decoding:

       sudo python3 ./Steganography.py -i -d <location of file>
       

- For Text Files:
- Encoding:

       sudo python3 ./Steganography.py -t -e <location of file>
       

- Decoding:

       sudo python3 ./Steganography.py -t -d <location of file>
       

3. For Help:

   sudo python3 ./Steganography.py -h
   sudo python3 ./Steganography.py --help
   

For more detailed usage and code, visit the repository [here](https://github.com/Sanjipan/Steganography).

🔍 LeMaterial: Accelerating Materials Discovery with Open-Source Innovation

https://undercodenews.com/lematerial-accelerating-materials-discovery-with-open-source-innovation/

@Undercode_News

🧨 Hide Data/Malwares in Images:

https://youtu.be/4TsEqrs09SM

One UI 70 Beta Arrives in India on December 12th

https://undercodenews.com/one-ui-70-beta-arrives-in-india-on-december-12th/

@Undercode_News

🎮 Black Girl Gamers: Creating Safe Spaces in the #Gaming World

https://undercodenews.com/black-girl-gamers-creating-safe-spaces-in-the-gaming-world/

@Undercode_News

▁ ▂ ▄ U𝕟𝔻Ⓔ𝐫Ć𝔬𝓓ⓔ ▄ ▂ ▁

🦑Wild! Google announced that their quantum chip Willow was able to do a computation in 5 minutes that would take current top-tier computers 10,000,000,000,000,000,000,000,000 years to figure out 😳

The 105-qubit chip brings insane error correction, focusing on stability rather than just stacking more qubits. The result? A leap toward practical quantum computing that could revolutionize medicine, AI, and energy in the near future.

But here comes the crazy part.

As part of the Willow announcement, Google basically confirmed we're living in a multiverse:

"It lends credence to the notion that quantum computation occurs in many parallel universes, in line with the idea that we live in a multiverse, a prediction first made by David Deutsch."

▁ ▂ ▄ U𝕟𝔻Ⓔ𝐫Ć𝔬𝓓ⓔ ▄ ▂ ▁

#Microsoft's Strategic #AI Play: A Global Chess Match

https://undercodenews.com/microsofts-strategic-ai-play-a-global-chess-match/

@Undercode_News

Moxie's Demise: A Heartbreaking End for a Child's #AI Companion

https://undercodenews.com/moxies-demise-a-heartbreaking-end-for-a-childs-ai-companion/

@Undercode_News

🎮 #AI-Powered Solutions Streamline Government Contracting and Business Operations

https://undercodenews.com/ai-powered-solutions-streamline-government-contracting-and-business-operations/

@Undercode_News

Venture Capital Firm Dimension Raises 00 Million for Second Fund

https://undercodenews.com/venture-capital-firm-dimension-raises-00-million-for-second-fund/

@Undercode_News

⚡️ A New Wave of #AI: WaveForms Aims to Revolutionize Voice Interaction

https://undercodenews.com/a-new-wave-of-ai-waveforms-aims-to-revolutionize-voice-interaction/

@Undercode_News

⚡️ Anthropic's New Claude: A Step Towards Autonomous #AI

https://undercodenews.com/anthropics-new-claude-a-step-towards-autonomous-ai/

@Undercode_News

#AI's Voice: #OpenAI's Advanced Voice Mode and the Future of #AI Interaction

https://undercodenews.com/ais-voice-openais-advanced-voice-mode-and-the-future-of-ai-interaction/

@Undercode_News

🛡️ #OpenAI Bolsters Security with Former NSA Chief

https://undercodenews.com/openai-bolsters-security-with-former-nsa-chief/

@Undercode_News

▁ ▂ ▄ U𝕟𝔻Ⓔ𝐫Ć𝔬𝓓ⓔ ▄ ▂ ▁

🦑 Hack GraphRAG implementation:

Nano-GraphRAG is a lightweight, efficient, and portable implementation of GraphRAG. It's designed to be more user-friendly and hackable than the official version while retaining the core features.

Key Features
- Small yet powerful: ~1100 lines of core code (excluding tests/prompts).
- Highly portable: Supports integrations with Faiss, Neo4j, Ollama, etc.
- Asynchronous and fully typed: Suitable for modern Python workflows.
- Flexible backends:
- LLM: OpenAI, Amazon Bedrock, Ollama, others.
- Vector DB: Built-in nano-vectordb, HNSWlib, Milvus-lite, Faiss.
- Graph Storage: NetworkX (default), Neo4j (optional).
- Incremental and batch data handling: Easy to scale as data grows.



Installation
From Source (Recommended)

 Clone the repository
git clone https://github.com/gusye1234/nano-graphrag.git
cd nano-graphrag
pip install -e .

From PyPI

pip install nano-graphrag

Quick Start
1. Set up API Keys:
- OpenAI API:

     export OPENAI_API_KEY="sk-..."
     

- For Azure OpenAI or Amazon Bedrock, refer to .env.example.

2. Download a sample text:

   curl https://raw.githubusercontent.com/gusye1234/nano-graphrag/main/tests/mock_data.txt > ./book.txt
   

3. Basic Usage:

   from nano_graphrag import GraphRAG, QueryParam

    Initialize GraphRAG
   graph_func = GraphRAG(working_dir="./dickens")

    Insert text data
   with open("./book.txt") as f:
       graph_func.insert(f.read())

    Perform a global search
   print(graph_func.query("What are the top themes in this story?"))

    Perform a local search for scalability
   print(graph_func.query("What are the top themes in this story?", param=QueryParam(mode="local")))
   

4. Reuse Stored Contexts:
- Reinitialize with the same working_dir to reload previous contexts.



Advanced Features
- Batch Insert:

  graph_func.insert(["TEXT1", "TEXT2", ...])
  

- Incremental Insert:

  graph_func.insert("New text to add")
  

- Async Support:

  await graph_func.ainsert("Async text")
  await graph_func.aquery("What is this text about?")
  

- Customizable Parameters:
- Use help(GraphRAG) and help(QueryParam) to explore.



Components and Extensibility
Built-in Components:
- LLM: OpenAI, Amazon Bedrock.
- Vector DB: Nano-vectordb, HNSWlib.
- Graph Storage: NetworkX, Neo4j.

Example Extensions:
- Embedding: Sentence-transformers, custom embeddings.
- Visualization: GraphML-based visualizations.
- Chunking: Token-based or custom splitters.



Benchmarking and Contributions
- Benchmarks for performance comparisons are available under examples/benchmarks.
- Contributions for new components and features are welcomed!

Nano-GraphRAG is ideal for developers seeking a nimble and efficient RAG solution, especially for those who want the flexibility to experiment or build on top of it.

▁ ▂ ▄ U𝕟𝔻Ⓔ𝐫Ć𝔬𝓓ⓔ ▄ ▂ ▁

🚨 A Critical Vulnerability in #Windows Common Log File System Driver

https://undercodenews.com/a-critical-vulnerability-in-windows-common-log-file-system-driver/

@Undercode_News

⚡️ #Windows 11 Build 261002605: A Closer Look at the Latest Patch Tuesday #Update

https://undercodenews.com/windows-11-build-261002605-a-closer-look-at-the-latest-patch-tuesday-update/

@Undercode_News

⚡️ #Windows 11's Final 2024 Security #Update: A Closer Look

https://undercodenews.com/windows-11s-final-2024-security-update-a-closer-look/

@Undercode_News