Text Loom:📝🧵

💬 What?

Text Loom is a fun workspace for creating networks that manage queries and build on them.
All from the comfort of your terminal!

📃 How?

Text flows from one node to the next.
The Text Loom philosophy, it's backend, is all about text.
Specifically lists of text.

Nodes pass text to each other:

• One node creates text: (Text)
• Some nodes read and write text files: (FileIn, FileOut)
• Some nodes create lists: (Section, Split, MakeList)
• One node combines lists: (Merge)
• One node talks to an LLM: (Query)
• One node can contain other nodes and iterate over them in loops: (Looper)
• And one node does nothing at all except pass the text along: (Null)

🚀 Start (automagically)

curl -fsSL https://raw.githubusercontent.com/kleer001/Text_Loom/master/install.sh | bash ; cd Text_Loom

✨ Start (manual)

* Make sure you have **git** installed and **python3** (version 3.8 or higher) * **Clone** the repository git clone https://github.com/kleer001/Text_Loom ; cd Text_Loom * **Create** a local venv python3 -m venv .venv * **Activate** it and set PYTHONPATH source .venv/bin/activate ; export PYTHONPATH=\$PYTHONPATH:$(pwd)/src * **Install** in development mode pip install -e . * **Run** the program python3 src/TUI/tui_skeleton.py

Note for Windows users:
Replace source .venv/bin/activate with .venv\Scripts\activate
and export PYTHONPATH=$PYTHONPATH:$(pwd)/src with set PYTHONPATH=%PYTHONPATH%;%cd%\src

📦 Currently supported LLMS platforms

in src/core/settings.cfg

LLM Platform	URL	Endpoint
Ollama	localhost:11434	/api/generate
LM Studio	localhost:1234	/v1/chat/completions
GPT4All	localhost:4891	/v1/completions
LocalAI	localhost:8080	/v1/chat/completions
llama.cpp	localhost:8080	/completion
oobabooga	localhost:5000	/v1/chat/completions
ChatGPT	https://api.openai.com	/v1/chat/completions
Perplexity	https://api.perplexity.ai	/v1/chat/completions
Claude	https://api.anthropic.com	/v1/messages
Gemini	https://generativelanguage.googleapis.com	/v1/models/gemini-1.5-pro:generateContent

• Please suggest more free local LLMs if you like. And feel free to change your local settings.cfg to fit your own purposes. The structure should be self-evident from the examples in it.

🚶 GUI WALK THROUGH

👀 MAIN WINDOW

Primary Workspace

Each Primary window can be navigated to with the keycommand CTRL+(n/a/g)

• Node Network - Central workspace for creating and connecting nodes. Displays node states, connections, and hierarchies using visual indicators.
• Parameters - Center Top panel showing properties of selected nodes.
• Globals - Right Top panel. System-wide variables accessible across the network.

Execution and Output

• Output Display - Center bottom. Shows formatted results from node evaluations with clear item separation.
• Status Window - Right bottom. Real-time system message monitoring, capturing stdout and stderr streams.
• Help window - Bottom. Shows the key commands available for the active window.
• Mode Line - Gutter. Show the active window, current filename, last window switched to, and keypressed.

---

Please see the extensive wiki for more detailed information.