LLAMA-Ai

 

 AI Model  : Using local model OLLAMA

DISCLAIMER

• The information provided on this website is intended to provide a basic understanding of certain technologies and is not intended to be a comprehensive guide. 
• Therefore, it should not be relied upon as the sole source of information and should not be used as a substitute for professional advice or expert analysis.
• Please exercise caution when visiting or downloading from websites mentioned on this website and verify the safety of the website and software. 
• Some websites and software may be flagged as malware by antivirus programs.
• The reader assumes all responsibility for their use of the information contained on this website and any consequences that may arise.
• The author disclaims any liability for any damages or losses that may result from the use of this website or the information contained herein.
• The author reserves the right to update or change the information contained on this website at any time without prior notice.
• Any attempts to perform penetration testing or ethical hacking on systems or networks should be done with the explicit permission of the system/network owner. 
• Unauthorized access is illegal and can result in serious legal consequences.
• It is important to fully understand the scope of the testing and to only test within that scope. Testing outside the agreed upon scope is considered unauthorized and may result in legal action.
• Any findings or vulnerabilities discovered during testing should be reported to the system/network owner immediately and kept confidential until a fix can be implemented.
• It is recommended to use a separate, dedicated testing environment rather than testing on a live production system to minimize the risk of accidentally causing damage or downtime.
• It is important to take steps to protect your own identity and prevent accidental data leaks or exposure of sensitive information during testing.
• It is also recommended to follow a standard code of ethics for ethical hacking and penetration testing.

Contents: 

• YouTube: Extracting YouTube Transcript  using Fabric framework.

• Summarizing : Generating summary, extracting insights from the transcripts, using fabric framework

• Fabric : fabric is an open-source framework for augmenting humans using AI.

• Downloading Installing Fabric Framework

• Installing missing files: from warning output. 

• Installing OLLAMA AI model:

• Creating Short cuts for copy and paste: 

• Running AI query to Extract YouTube transcript 

• Saving YouTube transcript  to File and generating AI queries 

References:

• danielmiessler: https://github.com/danielmiessler/fabric
• Network Chuck: https://www.youtube.com/watch?v=UbDyjIIGaxQ&t=657s

************************************************************************************

Fabric Framework:

August 20, 2024 — We have migrated to Go, and the transition has been pretty smooth! The biggest thing to know is that the previous installation instructions in the various Fabric videos out there will no longer work because they were for the legacy (Python) version.

 https://github.com/danielmiessler/fabric

Downloading

Downloading go: https://go.dev/doc/install

•  sudo tar -C /usr/local -xzf go1.23.0.linux-amd64.tar.gz

• export PATH=$PATH:/usr/local/go/bin

Installing Fabric Framework:

• go install github.com/danielmiessler/fabric@latest
• 
  

Refreshing env path: 

• sudo  nano ~/.bashrc

# Golang environment variables

• export GOROOT=/usr/local/go

• export GOPATH=$HOME/go

• export PATH=$GOPATH/bin:$GOROOT/bin:$HOME/.local/bin:$PATH:

Refreshing Window: 

• source ~/.bashrc

pipx install .

Fabric set up:  adding API keys 

• fabric --setup

setup

default model

• fabric --list

• fabric --listmodels

Installing missing files: from warning output. 

 

• sudo apt install ffmpeg

• source ~/.bashrc

Installing OLLAMA AI model:

• sudo apt install curl -y

• curl -fsSL https://ollama.com/install.sh | sh

Installing OLLAMA AI model:

Starting the OLLAMA AI model:

• ollama run llama3

Starting the OLLAMA AI model:

Starting OLLAMA in Windows: WSL

ollama serve

ollama run llama3

Creating Short cuts for copy and paste: 

• sudo  nano ~/.bashrc

• alias pbcopy='xsel --input --clipboard'

• alias pbpaste='xsel --output --clipboard'

• source ~/.bashrc

Testing the command:

• eco "testing" | pbcopy

• pbpaste

Short cuts for copy and paste: 

Windows: WSL : Creating Short cuts for copy and paste: 

• sudo  nano ~/.bashrc

• alias clip='powershell.exe -c clip.exe'

• alias past='powershell.exe -c Get-Clipboard'

• source ~/.bashrc

• echo "test" | clip

• past

Changing default model to LLAMA3

• fabric  --changeDefaultModel llama3:latest

• source ~/.bashrc

• fabric --listmodels

Running AI query to Extract YouTube transcript 

Installing yt - transcript:

• go install github.com/danielmiessler/yt@latest

Getting transcripts from you tube: 

• yt --transcript https://www.youtube.com/watch?v=4TyfNtFGAC4&t=21s | fabric  -sp summarize

Extract YouTube transcript 

• yt --transcript https://www.youtube.com/watch?v=4TyfNtFGAC4&t=21s | fabric  -sp extract_insights

Copying YouTube transcript to clipboard and generating AI queries 

• yt https://www.youtube.com/watch?v=mmU7XZOVAdI | pbcopy 

• pbpast | fabric  -sp summarize

Copying YouTube transcript to clipboard 

Saving Output to a file:

yt https://www.youtube.com/watch?v=mmU7XZOVAdI | fabric -o isowebirnar.txt

Saving YouTube transcript  to File and generating AI queries 

cat imple271.txt | fabric -sp extract_recommendations

cat imple271.txt | fabric -sp summarize

Saving YouTube transcript  to File 

cat iso-transcript.txt | fabric -sp clean_text

yt --transcript https://www.youtube.com/watch?v=mmU7XZOVAdI | fabric -sp raw_query

**************************

fabric -sp clean_text:

Clean_text option Provides much more better transcript extract using fabric command.

 yt --transcript https://www.youtube.com/watch?v=4B6_xQ7lxik | fabric -sp clean_text

fabric -sp clean_text

**************************

TGPT

https://github.com/aandrew-me/tgpt

• tgpt is a cross-platform command-line interface (CLI) tool that allows you to use AI chatbot in your Terminal without requiring API keys.