requirements.txt

# ── Environment ────────────────────────────────────────────────────────────────
python-dotenv                 # load .env for local dev

# ── Document Fetching ──────────────────────────────────────────────────────────
requests==2.32.4              # HTTP calls to SEC EDGAR

# ── Document Parsing ──────────────────────────────────────────────────────────
docling                       # PDF/HTML parser with table understanding
tf-keras                      # fixes Keras 3 conflict with transformers

# ── Chunking ──────────────────────────────────────────────────────────────────
langchain-experimental        # SemanticChunker (gradient method)
langchain-text-splitters      # RecursiveCharacterTextSplitter (fallback)

# ── Embeddings ────────────────────────────────────────────────────────────────
langchain-huggingface         # HuggingFaceEmbeddings wrapper
sentence-transformers         # all-MiniLM-L6-v2 + ms-marco reranker + NLI verifier

# ── Vector Store ──────────────────────────────────────────────────────────────
chromadb                      # local vector DB (dev / notebook use)
qdrant-client                 # Qdrant Cloud vector DB (production / deployment)

# ── LLM + RAG Chain ───────────────────────────────────────────────────────────
langchain                     # RAG chain orchestration
langchain-community           # Ollama LLM wrapper (local fallback)
langchain-core                # base abstractions
langchain-google-genai        # Google Gemini API (primary LLM for deployment)
google-generativeai           # Gemini SDK

# ── Verification + Grounding ──────────────────────────────────────────────────
nltk                          # sentence tokenizer for claim splitting
# NLI model auto-downloaded on first use:
# cross-encoder/nli-deberta-v3-small (~180 MB)

# ── Data Handling ─────────────────────────────────────────────────────────────
pandas                        # dataframe operations
numpy<2.0                     # pinned — docling + pyarrow need <2.0

# ── Web Application ───────────────────────────────────────────────────────────
streamlit>=1.39.0             # chat UI for Hugging Face Spaces deployment