adnandi commited on
Commit
74005c4
Β·
1 Parent(s): a3073c2

update readme

Browse files
Files changed (3) hide show
  1. Dockerfile +0 -37
  2. README.md +0 -11
  3. plan.md +0 -36
Dockerfile DELETED
@@ -1,37 +0,0 @@
1
- FROM python:3.10-slim
2
-
3
- # System dependencies for newspaper3k (lxml parsing)
4
- RUN apt-get update && \
5
- apt-get install -y --no-install-recommends \
6
- build-essential \
7
- libxml2-dev \
8
- libxslt1-dev \
9
- libjpeg-dev \
10
- zlib1g-dev \
11
- && rm -rf /var/lib/apt/lists/*
12
-
13
- # Create non-root user (HF Spaces requirement)
14
- RUN useradd -m -u 1000 user
15
- USER user
16
- ENV HOME=/home/user \
17
- PATH=/home/user/.local/bin:$PATH
18
-
19
- WORKDIR $HOME/app
20
-
21
- # Install Python dependencies first (better Docker layer caching)
22
- COPY --chown=user requirements.txt .
23
- RUN pip install --no-cache-dir --user -r requirements.txt
24
-
25
- # Download NLTK data at build time (not runtime)
26
- RUN python -c "\
27
- import nltk; \
28
- nltk.download('punkt', quiet=True); \
29
- nltk.download('punkt_tab', quiet=True); \
30
- nltk.download('stopwords', quiet=True)"
31
-
32
- # Copy application code
33
- COPY --chown=user . .
34
-
35
- EXPOSE 7860
36
-
37
- CMD ["uvicorn", "dashboard_app.main:app", "--host", "0.0.0.0", "--port", "7860"]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
README.md CHANGED
@@ -1,15 +1,4 @@
1
- ---
2
- title: Trend Summarizer AI
3
- emoji: πŸ“ˆ
4
- colorFrom: blue
5
- colorTo: indigo
6
- sdk: docker
7
- pinned: false
8
- short_description: AI-powered industry trend analysis dashboard
9
- ---
10
-
11
  # Trend Summarizer AI
12
- A premium web dashboard prototype for automated industry trend scraping, clustering, and AI summarization.
13
 
14
  ## Local Development
15
  1. Install dependencies:
 
 
 
 
 
 
 
 
 
 
 
1
  # Trend Summarizer AI
 
2
 
3
  ## Local Development
4
  1. Install dependencies:
plan.md DELETED
@@ -1,36 +0,0 @@
1
- # Master Plan: Industry Trend Summarization AI
2
-
3
- ## 1. Deskripsi Proyek
4
- Proyek ini bertujuan untuk membangun solusi berbasis Artificial Intelligence (AI) yang berfungsi mengumpulkan, mengelompokkan, dan merangkum tren industri dari berbagai sumber publik (FMCG, Retail, Consumer Behavior) secara otomatis menjadi bentuk executive brief guna mendukung pengambilan keputusan strategis.
5
-
6
- ## 2. Referensi Arsitektur & Ketentuan
7
- * **Dokumen Acuan:** `image_9e7f9d.png` dan `image_9e7fa0.png`
8
- * **Bahasa Pemrograman Utama:** Python
9
- * **Daftar Tools & Library:**
10
- | Komponen | Teknologi |
11
- | :--- | :--- |
12
- | Scraper / Data Collection | Newspaper3k |
13
- | Topic Modeling & Clustering | Gensim, Scikit-learn |
14
- | NLP Preprocessing | NLTK / Spacy / Sastrawi |
15
- | Summarization (Extractive) | TextRank (Gensim / NetworkX) |
16
- | Summarization (Generative) | Hugging Face Transformers, OpenAI API (Opsional) |
17
- | Dashboard Visualization | Streamlit / Dash / FastAPI + React |
18
-
19
- ## 3. Garis Besar Struktur Folder Proyek
20
- β”œβ”€β”€ data/ # Penyimpanan raw data & clean data
21
- β”œβ”€β”€ src/
22
- β”‚ β”œβ”€β”€ scraper/ # Modul pengumpulan data (Newspaper3k)
23
- β”‚ β”œβ”€β”€ preprocessing/ # Modul pembersihan teks
24
- β”‚ β”œβ”€β”€ modeling/ # Modul Topic Modeling & Clustering
25
- β”‚ β”œβ”€β”€ summarizer/ # Modul AI Summarization (Extractive & Generative)
26
- β”‚ └── dashboard/ # Kode aplikasi dashboard visualisasi
27
- β”œβ”€β”€ evaluation/ # Script untuk pengujian ROUGE Score
28
- β”œβ”€β”€ plans/ # File detail tugas (Sub-plans)
29
- β”‚ β”œβ”€β”€ 01_data_pipeline.md
30
- β”‚ β”œβ”€β”€ 02_ai_modeling.md
31
- β”‚ └── 03_dashboard_eval.md
32
- β”œβ”€β”€ requirements.txt
33
- └── plan.md # File ini
34
-
35
- ## 4. Mekanisme Environment Project
36
- Gunakan WSL dan dan pakai Environment Conda bernama "inference-model".