46 lines
1.1 KiB
Plaintext
46 lines
1.1 KiB
Plaintext
fastapi==0.104.1
|
|
uvicorn[standard]==0.24.0
|
|
httpx==0.25.2
|
|
pydantic==2.5.0
|
|
pyyaml==6.0.1
|
|
python-multipart==0.0.6
|
|
|
|
# HuggingFace dependencies for OCR models
|
|
torch>=2.0.0
|
|
torchvision>=0.15.0
|
|
transformers>=4.35.0
|
|
accelerate>=0.25.0
|
|
pillow>=10.0.0
|
|
tiktoken>=0.5.0
|
|
sentencepiece>=0.1.99
|
|
einops>=0.7.0
|
|
verovio>=4.3.1
|
|
|
|
# STT (Speech-to-Text) dependencies
|
|
faster-whisper>=1.0.0
|
|
openai-whisper>=20231117
|
|
|
|
# Image Generation (Diffusion models)
|
|
diffusers @ git+https://github.com/huggingface/diffusers.git
|
|
safetensors>=0.4.0
|
|
|
|
# Web Scraping & Search
|
|
trafilatura>=1.6.0
|
|
ddgs>=6.0.0
|
|
lxml_html_clean>=0.1.0
|
|
googlesearch-python>=1.2.0
|
|
|
|
# TTS (Text-to-Speech) - OPTIONAL, install separately if needed
|
|
# TTS has pandas<2.0 requirement, conflicts with docling
|
|
# pip install TTS # Run manually if TTS needed
|
|
|
|
# Document Processing - OPTIONAL, install separately if needed
|
|
# docling has pandas>=2.1.4 requirement, conflicts with TTS
|
|
# pip install docling # Run manually if document processing needed
|
|
|
|
# Lightweight alternative: pdfplumber for PDF text extraction
|
|
pdfplumber>=0.10.0
|
|
python-docx>=1.1.0
|
|
openpyxl>=3.1.2
|
|
chardet>=5.2.0
|