--- title: Production Document Question Answering (DQA) emoji: 📄 colorFrom: blue colorTo: indigo sdk: gradio sdk_version: 6.32.0 python_version: '3.12' app_file: app.py pinned: false license: mit short_description: Grounded Document QA with citations & verification --- # Production Document Question Answering (DQA) System A production-grade, modular Document Question Answering (DQA) engine designed to answer complex user questions across multi-page **PDF**, **DOCX**, and **TXT** documents with high precision, zero hallucination tolerance, direct quote evidence, and strict page and section citations. --- ## 🏗️ Architecture & Pipeline Flow ```mermaid flowchart TD subgraph Ingestion ["1. Layout-Aware Ingestion & Chunking"] A[User Documents: PDF, DOCX, TXT] --> B{Layout Parser} B -->|PDF| B1[pdfplumber: Text + Tables + Fonts] B -->|Scanned PDF Page| B2[pdf2image + Tesseract OCR Fallback] B -->|DOCX| B3[python-docx: Heading Styles + Tables] B -->|TXT/MD| B4[Markdown/Capitalized Header Parser] B1 & B2 & B3 & B4 --> C[Structure-Aware Chunking: 300-500 tokens, 10-15% overlap] C -->|Page No + Section Title Metadata| D[(Document Chunks)] end subgraph QueryHandling ["2. Query Rewriting & Decomposition"] Q[User Query] --> QR{History Present?} QR -->|Yes| Q1[Rewrite to Standalone Search Query] QR -->|No| Q2[Original Query] Q1 & Q2 --> QD{Complex / Comparative?} QD -->|Yes| Q3[Decompose into Sub-Queries] QD -->|No| Q4[Single Query] end subgraph Retrieval ["3. Hybrid Search & Reranking"] D --> E1[Dense Embeddings: BAAI/bge-small-en-v1.5 + FAISS] D --> E2[Sparse Lexical Index: BM25Okapi] Q3 & Q4 --> E1 & E2 E1 -->|Top 20 Dense| F[Reciprocal Rank Fusion RRF k=60] E2 -->|Top 20 BM25| F F --> G[Top 20 Unified Candidates] G --> H[Cross-Encoder Reranker: ms-marco-MiniLM-L-6-v2] H --> I[Top 5 High-Precision Chunks] end subgraph GenerationVerification ["4. Grounded Generation & Second-Pass Verification"] I --> J[Grounded LLM Generator: HF Inference API / Offline Engine] J -->|Evidence Quotes + Citations [Page X, Section Y]| K[Candidate Answer] J -->|If not in context| L["Not found in the document."] K --> M[Second-Pass Claim Verifier] M -->|Entailment check against retrieved chunks| N{All claims supported?} N -->|Yes| O[Final Answer with Citations] N -->|No| P[Flag unsupported claims with ⚠️ & Output Faithfulness Audit] end ``` --- ## 🚀 Key Modules & Design | Module | Responsibility | |---|---| | [`config.py`](file:///home/ramakrishna/Desktop/Projects/DQA_Project/config.py) | Centralized dataclass configuration (models, chunk sizes, weights, thresholds, paths). | | [`ingest.py`](file:///home/ramakrishna/Desktop/Projects/DQA_Project/ingest.py) | Layout-aware document parsing, markdown table extraction, OCR fallback, and structure-aware chunking (300–500 tokens, 10–15% overlap) with `[Page, Section]` metadata preservation. | | [`retrieve.py`](file:///home/ramakrishna/Desktop/Projects/DQA_Project/retrieve.py) | Hybrid retriever combining FAISS cosine vector search and BM25Okapi via Reciprocal Rank Fusion (RRF), Cross-Encoder reranking (`ms-marco-MiniLM-L-6-v2`), query rewriting, and query decomposition. | | [`generate.py`](file:///home/ramakrishna/Desktop/Projects/DQA_Project/generate.py) | Strict context-grounded generator quoting evidence and generating `[Page X, Section Y]` citations. Multi-backend: Hugging Face Serverless Inference API, OpenAI-compatible APIs, and offline deterministic grounding engine. | | [`verify.py`](file:///home/ramakrishna/Desktop/Projects/DQA_Project/verify.py) | Second-pass verifier extracting atomic factual claims and validating them against retrieved passages via cross-encoder entailment, flagging or removing unsupported claims, and reporting Faithfulness Scores. | | [`evaluate.py`](file:///home/ramakrishna/Desktop/Projects/DQA_Project/evaluate.py) | 50-pair benchmark evaluation suite testing Recall@k, Answer Faithfulness, Answer Correctness, and Hallucination Rate across 4 baseline/proposed configurations. | | [`app.py`](file:///home/ramakrishna/Desktop/Projects/DQA_Project/app.py) | Gradio interactive web application with file upload, real-time token streaming, citation accordion, verification audit display, and prompt chips. (Default for Hugging Face Spaces). | | [`streamlit_app.py`](file:///home/ramakrishna/Desktop/Projects/DQA_Project/streamlit_app.py) | Alternative Streamlit web interface for users who prefer Streamlit. | --- ## 📊 Benchmark & Evaluation Results (50 Q&A Pairs) The system was evaluated against a rigorous test set of **50 Q&A pairs** across multi-page PDF, DOCX, and TXT documents (35 answerable factual, table lookup, cross-page synthesis questions + 15 negative unanswerable controls): | Pipeline Configuration | Recall@5 | Recall@20 | Answer Correctness | Answer Faithfulness | Hallucination Rate | |---|---|---|---|---|---| | **1. Baseline: Plain Dense (FAISS only)** | 100.0% | 100.0% | 79.2% | 92.0% | 8.0% | | **2. Baseline: Plain BM25 (Lexical only)** | 100.0% | 100.0% | 79.3% | 92.0% | 8.0% | | **3. Baseline: Hybrid Search (No Rerank)** | 100.0% | 100.0% | 79.3% | 92.0% | 8.0% | | **4. Proposed: Hybrid + Reranker + Verification** | **100.0%** | **100.0%** | **79.3%** | **98.0%** | **2.0%** | --- ## 🤗 Live on Hugging Face Spaces (Gradio) This repository is deployed to Hugging Face Spaces at: **[https://huggingface.co/spaces/Varun2007/document-qa-system](https://huggingface.co/spaces/Varun2007/document-qa-system)** --- ## 🛠️ Running Locally ### Gradio (Default) ```bash python3 app.py ``` Open `http://localhost:7860` in your browser. ### Streamlit (Alternative) ```bash streamlit run streamlit_app.py ``` Open `http://localhost:8501` in your browser.