structured-data-extractor / requirements.txt
aditya0103's picture
Initial commit: schemas, extraction engine, dataset prep, 54 passing tests
44c2f50
Raw
History Blame Contribute Delete
1.09 kB
# === Core LLM ===
openai>=1.40.0
pydantic>=2.7.0
tenacity>=8.2.3 # retry logic for API calls
# === Document processing ===
pdfplumber>=0.11.0 # text-based PDFs
pymupdf>=1.24.0 # fast PDF rendering + fallback text
Pillow>=10.3.0 # image handling for GPT-4o vision
pdf2image>=1.17.0 # convert PDF pages to images for vision
# === Backend ===
fastapi>=0.111.0
uvicorn[standard]>=0.30.0
python-multipart>=0.0.9 # file uploads
slowapi>=0.1.9 # rate limiting
# === Frontend ===
streamlit>=1.35.0
requests>=2.32.0
# === Data + eval ===
pandas>=2.2.0
numpy>=1.26.0
rapidfuzz>=3.9.0 # fuzzy matching for eval
scikit-learn>=1.5.0 # precision/recall/f1
datasets>=2.19.0 # HuggingFace datasets (SROIE/CORD)
# === SEC filings (v2) ===
sec-edgar-downloader>=5.0.0
beautifulsoup4>=4.12.0
lxml>=5.2.0
# === Observability ===
python-dotenv>=1.0.1
loguru>=0.7.2
# === Dev / test ===
pytest>=8.2.0
pytest-cov>=5.0.0
pytest-asyncio>=0.23.0
httpx>=0.27.0 # async test client for FastAPI
ruff>=0.4.0
black>=24.4.0