pyproject.toml

[project]
name = "academic-research-rag"
version = "0.1.0"
description = "AI-powered agentic RAG system for Students & Researchers"
authors = [{ name = "Your Name" }]
requires-python = ">=3.11"

dependencies = [
    # ── Web framework ──────────────────────────────────────────────────────────
    "fastapi>=0.115.0",
    "uvicorn[standard]>=0.30.0",
    "starlette>=0.41.0",
    "python-multipart>=0.0.12",   # required by FastAPI for file/form uploads
    "sse-starlette>=2.1.0",       # Server-Sent Events for streaming chat

    # ── Validation & config ────────────────────────────────────────────────────
    "pydantic>=2.9.0",
    "pydantic-settings>=2.5.0",   # reads .env into Settings

    # ── Database ───────────────────────────────────────────────────────────────
    "motor>=3.6.0",               # async MongoDB driver
    "pymongo>=4.10.0",            # sync MongoDB driver (errors, types)
    "mongomock-motor>=0.0.21",    # in-memory Motor drop-in (HF Spaces / no MongoDB)

    # ── Vector store ───────────────────────────────────────────────────────────
    "chromadb>=0.5.0",            # local persistent ChromaDB

    # ── Embeddings ─────────────────────────────────────────────────────────────
    "sentence-transformers>=3.3.0",  # BAAI/bge-base-en-v1.5 embeddings

    # ── LLM / LangChain / LangGraph ───────────────────────────────────────────
    "langchain-core>=0.3.0",
    "langchain-groq>=0.2.0",      # Groq LLM via LangChain
    "langgraph>=0.2.0",           # StateGraph RAG pipeline

    # ── PDF parsing ────────────────────────────────────────────────────────────
    "pymupdf>=1.24.0",            # primary PDF parser (imports as `fitz`)
    "unstructured[pdf]>=0.15.0",  # fallback PDF parser

    # ── HTTP clients ───────────────────────────────────────────────────────────
    "httpx>=0.27.0",              # async HTTP — arXiv & Semantic Scholar APIs

    # ── Frontend ───────────────────────────────────────────────────────────────
    "streamlit>=1.40.0",
    "requests>=2.32.0",           # sync HTTP — Streamlit → backend calls
    "sseclient-py>=1.8.0",        # parse SSE stream in Streamlit
]

[project.optional-dependencies]
dev = [
    "pytest>=8.0.0",
    "pytest-asyncio>=0.24.0",
    "httpx>=0.27.0",              # AsyncClient for FastAPI test client
    "ruff>=0.6.0",
]

[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"

[tool.hatch.build.targets.wheel]
packages = ["backend", "frontend"]

# ── Ruff linter config ────────────────────────────────────────────────────────
[tool.ruff]
line-length = 100
target-version = "py311"

[tool.ruff.lint]
select = ["E", "F", "I"]   # pycodestyle errors, pyflakes, isort
ignore = ["E501"]           # line-length handled by formatter

# ── Pytest config ─────────────────────────────────────────────────────────────
[tool.pytest.ini_options]
asyncio_mode = "auto"
testpaths = ["tests"]