HuiMi24 · HuiMi24 · Mar 14, 2026 · Mar 14, 2026 · Mar 14, 2026 · Mar 14, 2026
diff --git a/.gitignore b/.gitignore
@@ -1,139 +1,9 @@
-# Byte-compiled / optimized / DLL files
 __pycache__/
-*.py[cod]
-*$py.class
-
-# C extensions
-*.so
-
-# Distribution / packaging
-.Python
-build/
-develop-eggs/
-dist/
-downloads/
-eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-pip-wheel-metadata/
-share/python-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-MANIFEST
-
-# PyInstaller
-#  Usually these files are written by a python script from a template
-#  before PyInstaller builds the exe, so as to inject date/other infos into it.
-*.manifest
-*.spec
-
-# Installer logs
-pip-log.txt
-pip-delete-this-directory.txt
-
-# Unit test / coverage reports
-htmlcov/
-.tox/
-.nox/
-.coverage
-.coverage.*
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-*.py,cover
-.hypothesis/
-.pytest_cache/
-
-# Translations
-*.mo
-*.pot
-
-# Django stuff:
-*.log
-local_settings.py
-db.sqlite3
-db.sqlite3-journal
-
-# Flask stuff:
-instance/
-.webassets-cache
-
-# Scrapy stuff:
-.scrapy
-
-# Sphinx documentation
-docs/_build/
-
-# PyBuilder
-target/
-
-# Jupyter Notebook
-.ipynb_checkpoints
-
-# IPython
-profile_default/
-ipython_config.py
-
-# pyenv
-.python-version
-
-# pipenv
-#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
-#   However, in case of collaboration, if having platform-specific dependencies or dependencies
-#   having no cross-platform support, pipenv may install dependencies that don't work, or not
-#   install all needed dependencies.
-#Pipfile.lock
-
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow
-__pypackages__/
-
-# Celery stuff
-celerybeat-schedule
-celerybeat.pid
-
-# SageMath parsed files
-*.sage.py
-
-# Environments
-.env
-.venv
-env/
-venv/
-ENV/
-env.bak/
-venv.bak/
-
-# Spyder project settings
-.spyderproject
-.spyproject
-
-# Rope project settings
-.ropeproject
-
-# mkdocs documentation
-/site
-
-# mypy
-.mypy_cache/
-.dmypy.json
-dmypy.json
-
-# Pyre type checker
-.pyre/
-
-# the generate content
+*.pyc
+*.pyo
 *.pptx
-
-# Pipe files
-Pipfile
-Pipfile.lock
-
-# VSCode
-.vscode/
+.env
+.venv/
+backend/.venv/
+frontend/node_modules/
+frontend/dist/
diff --git a/.pylintrc b/.pylintrc
@@ -0,0 +1,29 @@
+[MASTER]
+ignore-patterns=^frontend/.*,^backend/generated/.*
+
+[MESSAGES CONTROL]
+disable=
+    missing-module-docstring,
+    missing-class-docstring,
+    missing-function-docstring,
+    too-few-public-methods,
+    broad-exception-caught,
+    broad-exception-raised,
+    import-outside-toplevel,
+    line-too-long,
+    raise-missing-from,
+    wrong-import-order,
+    invalid-name,
+    possibly-used-before-assignment,
+    inconsistent-return-statements,
+    unreachable,
+    no-else-return,
+    consider-using-sys-exit,
+    consider-using-with,
+    consider-using-in
+
+[TYPECHECK]
+ignored-modules=openai,pptx,pptx.dml.color,pptx.enum.shapes,pptx.util,fastapi,fastapi.middleware.cors,fastapi.staticfiles,pydantic,streamlit,ollama
+
+[FORMAT]
+max-line-length=120
diff --git a/README.md b/README.md
@@ -1,84 +1,138 @@
-# ChatPPT
+# ChatPPT Studio (React + FastAPI)
 
-ChatPPT is a tool powered by chatgpt/ollama that helps you generate PPT/slide. It supports output in English and Chinese.
+ChatPPT Studio generates new PowerPoint decks, supports live text editing, and applies chat-driven revisions.
 
-## Table of Contents
+- Backend: FastAPI + `python-pptx`
+- Frontend: React (Vite)
+- Dependency manager (backend): `uv`
+- LLM usage is optional. If `OPENAI_API_KEY` is missing, deterministic fallback generation is used.
 
-- [What's New](#whats-new)
-- [What is ChatPPT](#what-is-chatppt)
-- [Requirements](#requirements)
-- [Installation](#installation)
-- [Usage](#usage)
-- [Contributing](#contributing)
-- [License](#license)
+## Features
 
-## What's New
+1. Generate a new PPT from topic input
+- `POST /api/generate`
+- Supports `preset`, `audience`, `tone`, `slide_count`, and `language`
+- Returns output path, outline, and theme metadata
 
-ChatPPT now supports Ollama and includes a sample UI.
+2. Parse and edit PPT text content
+- `GET /api/ppt`
+- `POST /api/ppt/update`
 
-![UI demo 1](ui_demo_1.png)
-![UI demo 2](ui_demo_2.png)
+3. Chat-based edits (existing compatibility retained)
+- `POST /api/chat`
 
-## What is ChatPPT
+4. Apply inferred theme to an existing PPT (existing compatibility retained)
+- `POST /api/theme/apply`
 
-ChatPPT is powered by chatgpt/ollama. It can help you generate PPT/slide in English and Chinese.
+## Project Layout
 
-![What is GPT | 600](demo1.png)
-![什么是AWS | 400](demo2.png)
+```text
+chatppt/
+├── backend/
+│   ├── app/
+│   │   ├── main.py
+│   │   ├── models.py
+│   │   ├── ppt_service.py
+│   │   ├── chat_service.py
+│   │   └── generator_service.py
+│   ├── tests/test_services.py
+│   └── requirements.txt
+├── frontend/
+│   ├── src/App.jsx
+│   ├── src/App.test.jsx
+│   └── src/styles.css
+└── README.md
+```
 
-## Requirements
+## Environment Variables
 
-Python 3.8.10 or higher
+Backend (optional):
 
-## Installation
-
-### Ollama
-
-Follow the [guide](https://ollama.com/) to install ollama
-
-### OpenAI
+```bash
+export OPENAI_API_KEY=your_key
+export OPENAI_MODEL=gpt-3.5-turbo
+# Optional for online demo testing without real LLM calls:
+export FAKE_LLM_RESPONSES=1
+```
 
-Generate your OpenAI API key at <https://platform.openai.com/account/api-keys>
+Frontend (optional):
 
-## Usage
+```bash
+export VITE_API_BASE=http://127.0.0.1:8000
+```
 
-1. Install requirements
+## Run Locally
 
-    ```
-    pip install -r requirements.txt
-    ```
+### 1) Start backend
 
-2. Start Streamlit
+```bash
+cd backend
+uv venv
+source .venv/bin/activate
+uv pip install -r requirements.txt
+uv run uvicorn app.main:app --reload --host 0.0.0.0 --port 8000
+```
 
-    ```
-    streamlit run chatppt_ui.py
-    ```
+### 2) Start frontend
 
-3. Open the Streamlit URL in your browser (<http://localhost:8501>)
+```bash
+cd frontend
+npm install
+npm run dev
+```
+
+Open `http://127.0.0.1:5173`.
+
+## API Example
+
+### `POST /api/generate`
+
+Request:
+
+```json
+{
+  "topic": "AI customer support product roadmap",
+  "preset": "Tech",
+  "audience": "Executive team",
+  "tone": "Concise",
+  "slide_count": 6,
+  "language": "en-US",
+  "output_path": "generated/ai-roadmap.pptx"
+}
+```
+
+Response:
+
+```json
+{
+  "output_path": "generated/ai-roadmap.pptx",
+  "outline": [{ "title": "...", "bullets": ["..."] }],
+  "theme": {
+    "name": "preset-tech",
+    "font_name": "Segoe UI",
+    "title_size_pt": 38,
+    "body_size_pt": 19
+  }
+}
+```
+
+Notes:
+- `preset` is optional (`Business`, `Tech`, `Education`, `Marketing`).
+- Explicit `audience`, `tone`, `language`, and `slide_count` still work as before and take precedence over preset defaults.
+
+## Quality Checks
+
+Backend tests:
 
-![UI](ui.png)
+```bash
+cd backend
+PYTHONPATH=. uv run python -m unittest tests/test_services.py
+```
 
-> You can also use ChatPPT in the command line:
+Frontend tests and build:
 
 ```bash
-> python chatppt.py -h
-usage: chatppt.py [-h] [-m {openai,ollama}] -t TOPIC [-k API_KEY] [-u OLLAMA_URL] [-o OLLAMA_MODEL] [-p PAGES] [-l {cn,en}]
-
-I am your PPT assistant, I can help to you generate PPT.
-
-options:
-  -h, --help            show this help message and exit
-  -m {openai,ollama}, --ai_model {openai,ollama}
-                        Select the AI model
-  -t TOPIC, --topic TOPIC
-                        Your topic name
-  -k API_KEY, --api_key API_KEY
-                        Your api key file path
-  -u OLLAMA_URL, --ollama_url OLLAMA_URL
-                        Your ollama url
-  -o OLLAMA_MODEL, --ollama_model OLLAMA_MODEL
-                        Specify the Ollama model to use
-  -p PAGES, --pages PAGES
-                        How many slides to generate
-  -l {cn,en}, --language {cn,en}
-                        Output language
+cd frontend
+npm test
+npm run build
+```
diff --git a/backend/app/__init__.py b/backend/app/__init__.py
@@ -0,0 +1 @@
+# package