Skip to main content

Konvertiert Workshop-Fotos automatisch in PowerPoint-Präsentationen mithilfe von LLM Vision APIs

Project description

foto2pptx

Konvertiert Workshop-Fotos automatisch in PowerPoint-Praesentationen mithilfe von LLM Vision APIs.

Unterstuetzte Anbieter: Google Gemini · Anthropic Claude · OpenAI · Llama (lokal via Ollama)


Installation

# Basis-Installation
pip install -e .

# Mit einem spezifischen Provider
pip install -e ".[anthropic]"
pip install -e ".[gemini]"
pip install -e ".[openai]"
pip install -e ".[llama]"

# Alle Provider auf einmal
pip install -e ".[all]"

Verwendung

Als Python-Library (empfohlen)

from foto2pptx import foto_zu_powerpoint

# Einfachste Nutzung – ein Aufruf, fertig!
foto_zu_powerpoint(
    image_path  = "workshop.jpg",
    output_path = "ergebnis.pptx",
    provider    = "anthropic",
    api_key     = "sk-ant-...",
)

Fortgeschrittene / modulare Nutzung

from foto2pptx import analyse_bild, parse_llm_output, create_powerpoint

# Schritt 1: Bild analysieren
raw_text = analyse_bild(
    provider   = "openai",
    model_name = "gpt-4o",
    image_path = "bild.jpg",
    api_key    = "sk-...",
)

# Schritt 2: LLM-Ausgabe parsen
dataframes = parse_llm_output(raw_text)

# Schritt 3: PowerPoint erstellen
create_powerpoint(dataframes, "output.pptx")

Kommandozeile

Nach der Installation steht der foto2pptx Befehl global zur Verfuegung:

# Interaktiv (alle Parameter werden abgefragt)
foto2pptx

# Mit Argumenten
foto2pptx \
    --provider  anthropic \
    --api-key   sk-ant-... \
    --model     claude-opus-4-6 \
    --image     workshop.jpg \
    --output    ergebnis.pptx

# Mit Gemini
foto2pptx --provider gemini --api-key AIza... --image foto.png

# Mit lokalem Llama (kein API-Key noetig)
foto2pptx --provider llama --model llama3.2-vision --image foto.jpg

Provider & Modelle

Provider Empfohlenes Modell API-Key noetig
anthropic claude-opus-4-6 Ja
gemini gemini-2.5-flash Ja
openai gpt-4o Ja
llama llama3.2-vision Nein (lokal)

Projektstruktur

foto2pptx/
├── foto2pptx/
│   ├── __init__.py     ← Oeffentliche API
│   ├── constants.py    ← Farben, Prompts, Konfiguration
│   ├── utils.py        ← Datei-Hilfsfunktionen
│   ├── providers.py    ← LLM-Abstraktionsschicht
│   ├── parser.py       ← LLM-Output -> DataFrames
│   ├── converter.py    ← Pixel/EMU, Farben, Formen
│   ├── builder.py      ← PowerPoint-Erstellung
│   ├── pipeline.py     ← High-Level-Pipeline
│   └── cli.py          ← Kommandozeilen-Interface
├── tests/
│   └── test_converter.py
├── setup.py
├── pyproject.toml
└── README.md

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

foto2pptx-0.1.0.tar.gz (14.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

foto2pptx-0.1.0-py3-none-any.whl (15.2 kB view details)

Uploaded Python 3

File details

Details for the file foto2pptx-0.1.0.tar.gz.

File metadata

  • Download URL: foto2pptx-0.1.0.tar.gz
  • Upload date:
  • Size: 14.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.3

File hashes

Hashes for foto2pptx-0.1.0.tar.gz
Algorithm Hash digest
SHA256 cf1db84096d56536ce86fb9a5116d492d5c3cd901631bed2d7f1224224510865
MD5 27762a8f16cc163806091e1da6d09c83
BLAKE2b-256 0a422d76b3a950270ff3a7bd08d7ff9822f939903e8282110ce8351af0d7a6aa

See more details on using hashes here.

File details

Details for the file foto2pptx-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: foto2pptx-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 15.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.3

File hashes

Hashes for foto2pptx-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 b7a60c1ecba1ee887c6b197eb14abd4d0afca1d5ecd4eab4f884176b3bdcb0a6
MD5 1f3e40fec02202e1d01812a7455fd40c
BLAKE2b-256 0f7b72a5b4e626ab4b94a4a7f398109da494e4d4d71352a0d73e33b761e925e6

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page