dragiter 0.0.1__tar.gz

dragiter-0.0.1/.gitignore

@@ -0,0 +1,66 @@
+.DS_Store
+run/
+dist/
+# --- Python Essentials ---
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# --- Environments & Dependencies ---
+.env
+.venv
+venv/
+ENV/
+pip-log.txt
+pip-delete-this-directory.txt
+
+# --- IDEs (PyCharm & VS Code) ---
+.idea/
+*.iml
+.vscode/
+*.swp
+*.swo
+.project
+.pydevproject
+.settings/
+
+# --- Project Specifics (dragator) ---
+# Keine API-Keys oder lokale Configs einchecken!
+config.json
+secrets.yaml
+.dragator_config/
+
+# --- Logs & Traces ---
+# Da Logging eine Stärke von dragator ist, entstehen viele Files.
+# Diese sollten lokal bleiben.
+*.log
+activity_file.jsonl
+dragator_activity.jsonl
+traces/
+
+# --- Large Data / Chunks ---
+# Falls du Test-Materialien lokal speicherst
+data/raw/
+data/processed/
+*.csv
+*.json
+
+

dragiter-0.0.1/PKG-INFO

@@ -0,0 +1,69 @@
+Metadata-Version: 2.4
+Name: dragiter
+Version: 0.0.1
+Summary: Placeholder for the dragiter project: Deterministic RAG Iterator.
+Project-URL: Homepage, https://dragiter.com
+Author-email: Michael Buchold <michael.buchold@bucosys.com>
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+
+## dragiter (Deterministic RAG Iterator)
+
+[WARNING] Status: Alpha / Developer Tool
+dragiter is currently in active development. It is highly effective for local, personal workflows and automating local LLM tasks. However, it is not yet production-ready. Please do not use dragiter in automated CI/CD pipelines, on shared servers, or to parse untrusted, third-party data due to known limitations in regex handling and dependency injection.
+
+dragiter is a modular command-line interface (CLI) designed to integrate Large Language Models (LLMs) directly into your automated terminal workflows. It acts as a bridge between your local file system and AI APIs, eliminating "copy-paste fatigue" by allowing you to chain AI agents exactly like standard Unix pipes.
+
+## Why dragiter?
+
+If you want an AI to review an entire project, manually gathering files, stripping out noise, and pasting them into a web chat is tedious. dragiter solves this through "Prompt as Code."
+
+  * Automated Context Assembly: Use wildcards (like src/\*\*/\*.py) and regex patterns to surgically extract exactly what the AI needs to see.
+  * Version-Controllable Prompts: Define your AI instructions and data context in standard .toml files so your workflows are repeatable and shareable.
+  * Advanced Batch Processing: Feed dragiter a .jsonl loop file to automatically iterate through translation tasks, report summaries, or data extraction without writing custom Python scripts.
+  * Vendor Independence: Switch from cloud providers like OpenAI, Grok, or Google to a completely local, private model like Ollama just by changing a single CLI flag.
+
+## Installation
+
+(Assuming you publish to PyPI)
+You can install dragiter easily via pip:
+
+pip install dragiter
+
+## Quick Start
+
+The core philosophy of dragiter is to keep your materials (context) and your prompts (instructions) separate.
+
+1.  Create a Configuration (Optional but recommended):
+    Store your credentials so you don't have to type them out every time.
+
+export dragiter\_API\_KEY="your\_api\_key"
+export dragiter\_MODEL\_NAME="your\_preferred\_model"
+
+2.  Run your first workflow:
+    It is highly recommended to use the -s (simulate) flag first to verify your file routing without spending API credits.
+
+# Simulate the run
+
+dragiter -s -p prompt\_template.toml -m code\_material.toml
+
+# Execute the run and output to a specific file
+
+dragiter -p prompt\_template.toml -r code\_resource.toml -o final\_report.md
+
+## Tool Chaining (The Unix Way)
+
+dragiter is built to play nicely with other CLI tools. You can fetch live data and pipe it straight to your AI workflow:
+
+# Download a webpage and analyze it instantly
+
+curl -s [https://example.com/data](https://www.google.com/search?q=https://example.com/data) \> /tmp/data.html
+dragiter -p summarize.toml -m /tmp/data.html -o analysis.txt
+
+## Acknowledgements
+
+The development of dragiter has been a journey of continuous learning. Bringing this project to life would not have been possible without the support of some extraordinary tools and communities.
+
+A massive thank you to the AI models Grok and Gemini. As tireless pair-programming partners, your guidance, code reviews, and structural suggestions were invaluable in adapting the Python code for this project.
+
+Equally important is the global Python community. The rich ecosystem, extensive documentation, and open-source spirit provide the foundation for tools like dragiter. Thank you to all the developers who make Python such a powerful language to work with.

dragiter-0.0.1/README.md

@@ -0,0 +1,60 @@
+## dragiter (Deterministic RAG Iterator)
+
+[WARNING] Status: Alpha / Developer Tool
+dragiter is currently in active development. It is highly effective for local, personal workflows and automating local LLM tasks. However, it is not yet production-ready. Please do not use dragiter in automated CI/CD pipelines, on shared servers, or to parse untrusted, third-party data due to known limitations in regex handling and dependency injection.
+
+dragiter is a modular command-line interface (CLI) designed to integrate Large Language Models (LLMs) directly into your automated terminal workflows. It acts as a bridge between your local file system and AI APIs, eliminating "copy-paste fatigue" by allowing you to chain AI agents exactly like standard Unix pipes.
+
+## Why dragiter?
+
+If you want an AI to review an entire project, manually gathering files, stripping out noise, and pasting them into a web chat is tedious. dragiter solves this through "Prompt as Code."
+
+  * Automated Context Assembly: Use wildcards (like src/\*\*/\*.py) and regex patterns to surgically extract exactly what the AI needs to see.
+  * Version-Controllable Prompts: Define your AI instructions and data context in standard .toml files so your workflows are repeatable and shareable.
+  * Advanced Batch Processing: Feed dragiter a .jsonl loop file to automatically iterate through translation tasks, report summaries, or data extraction without writing custom Python scripts.
+  * Vendor Independence: Switch from cloud providers like OpenAI, Grok, or Google to a completely local, private model like Ollama just by changing a single CLI flag.
+
+## Installation
+
+(Assuming you publish to PyPI)
+You can install dragiter easily via pip:
+
+pip install dragiter
+
+## Quick Start
+
+The core philosophy of dragiter is to keep your materials (context) and your prompts (instructions) separate.
+
+1.  Create a Configuration (Optional but recommended):
+    Store your credentials so you don't have to type them out every time.
+
+export dragiter\_API\_KEY="your\_api\_key"
+export dragiter\_MODEL\_NAME="your\_preferred\_model"
+
+2.  Run your first workflow:
+    It is highly recommended to use the -s (simulate) flag first to verify your file routing without spending API credits.
+
+# Simulate the run
+
+dragiter -s -p prompt\_template.toml -m code\_material.toml
+
+# Execute the run and output to a specific file
+
+dragiter -p prompt\_template.toml -r code\_resource.toml -o final\_report.md
+
+## Tool Chaining (The Unix Way)
+
+dragiter is built to play nicely with other CLI tools. You can fetch live data and pipe it straight to your AI workflow:
+
+# Download a webpage and analyze it instantly
+
+curl -s [https://example.com/data](https://www.google.com/search?q=https://example.com/data) \> /tmp/data.html
+dragiter -p summarize.toml -m /tmp/data.html -o analysis.txt
+
+## Acknowledgements
+
+The development of dragiter has been a journey of continuous learning. Bringing this project to life would not have been possible without the support of some extraordinary tools and communities.
+
+A massive thank you to the AI models Grok and Gemini. As tireless pair-programming partners, your guidance, code reviews, and structural suggestions were invaluable in adapting the Python code for this project.
+
+Equally important is the global Python community. The rich ecosystem, extensive documentation, and open-source spirit provide the foundation for tools like dragiter. Thank you to all the developers who make Python such a powerful language to work with.

dragiter-0.0.1/pyproject.toml

@@ -0,0 +1,16 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "dragiter"
+version = "0.0.1"
+description = "Placeholder for the dragiter project: Deterministic RAG Iterator."
+readme = "README.md"
+requires-python = ">=3.9"
+authors = [
+    { name = "Michael Buchold", email = "michael.buchold@bucosys.com" }
+]
+
+[project.urls]
+Homepage = "https://dragiter.com"