Remember my Obsidian project?
I am working on an obsidian-deck inspired by the Dystopian Hackers using Cyberdecks which gives them in the Shadowrun RPG, the grand-father of Dystopian interactive worlds, the name Deggers.
This up there is first of all a big knot with many connections. It shows impressively that my interactions with DeepSeek are connected. The dots in my case don't show the source file names, but tags created by an AI NLP model running over them. The three core main tags are: #knowledge_management #Obsidian and #notes-taking by having most connections.
That is a surprise considering how much Cyberpunk Stories about Shadow Runners inspired by the Shadowrun RPG Source Books I have created. These terms just don't have as many connections as the three main contenders. It is also a main reflection of my last job, in a Secret Service covered op Enterprise I couldn't possibly catch, and shows my deeply routed Jedi faith to train body and mind.
The Obsidian-deck is a terminal environment in a python 13 environment on a Linux Mint Computer.
(cyberdeck-env) J4v@M920:~/Scripts$ python3 obsidian-deck.py --vault /home/J4v/Vault/
⚠️ Ensure Ollama is installed and models are downloaded:
ollama pull mixtral:8x7b
ollama pull llama3
⏳ Indexing vault...
🔗 Processed 346 notes with 0 errors
✅ Vault indexed: 346 notes
🧠Available NLP models: mixtral:8x7b, llama3:latest
ℹ️ Type 'help' for available commands
ℹ️ Type 'list_tags' to see all available tags/concepts
🧠AI-Powered Obsidian Knowledge Explorer
Type 'help' for commands. 'exit' to quit.
obsidian>
This is the manual to it:
Ollama with models: ollama pull mixtral:8x7b and ollama pull llama3
COMMANDS:
CLUSTER [type] [name]
Define a note cluster by metadata type
all: Search across all metadata fields
tag: Search only tags
concept: Search only concepts
meta_tag: Search only meta tags
meta_keyword: Search only keywords
Example: cluster all raspberry
Display current cluster with perfect formatting
Automatically adjusts to note name length
Shows word count and first 7 tags
Multi-line formatting for long names/tags
LIST_TAGS
Show structured metadata index:
Section I: By category (Tags, Concepts, etc.)
Section II: Alphabetical index with counts
Shows total unique metadata items
SUMMARIZE [type]
Generate AI summary of current cluster
summary: Use note summaries only (faster)
deep: Use first 500 words of content (more detailed)
Example: summarize deep
MODEL [name]
Switch between NLP models
mixtral:8x7b: Higher quality (slower)
llama3:latest: Faster (good for most tasks)
Example: model mixtral:8x7b
BFS_CLUSTER [depth]
Expand cluster via graph relationships
Default depth: 2
Finds notes linked to current cluster
Example: bfs_cluster 3
VISUALIZE
Open current cluster in Obsidian
Highlights notes in graph view
Uses Obsidian's search URI scheme
HELP
Show available commands
help [command]: Show detailed help for specific command
EXIT
Quit the explorer
accent (1), adhesive (1), administration (1), aerodynamics (2)
aeronautics (1), aircraft (2), algorithm (1), analysis (3), analytics (4)
android (1), arbitrage (1), armor (1), augmented (1), authentication (1)
automating (1),
aaa (1), aarch64 (2), academia (1), academic (1), accent (1)
access_control (2), accessibility (1), accuracy (2), acer_aspire_i7 (1)
action-adventure (1), action_camera (2), adaptability (2), adaptation (2)
adaptivetradingbot (2), adb (2), adhesive (1), adhesives (1)
admin_privileges (2),
obsidian>
🧩 Cluster defined: 223 notes with all 'obsidian'
obsidian>
Walmart-Historical-Trade-Analogy | 1178 | #history, #decentralization, #obsidian,
| | #knowledge_management, #cosmopolitanism
- | | -
Walrus-Operator-Python-Compatibility-Fix | 40751 | #obsidian, #syntax_error, #python_3,
| | #knowledge-management, #walrus_operator,
| | #beautifulsoup, #elementtree
- | | -
Zte-Blade-A35e-Vr-On-Beowulf-Cluster | 12207 | #raspberrypi, #cloudflare-warp, #apt-
| | error, #distributed-computing, #proxy-
| | setup, #raspberrypi-proxy, #binance-
| | latency
- | | -
------------------------------------------------------------------------------------------------
Total notes: 223 | Total words: 1978858
obsidian>