docs: capture pdf domain language and deferred ingestion backlog

Co-authored-by: Cursor <cursoragent@cursor.com>

.env.example

@@ -26,3 +26,6 @@ SEMANTIC_MIN_CHUNK_SIZE=3
 
 # SQLite database path
 DATABASE_URL=sqlite:///./data/chunking_benchmark.db
+# Text PDF gate (reject scanned/image PDFs)
+PDF_MIN_TOTAL_CHARS=100
+PDF_MIN_MEDIAN_CHARS_PER_PAGE=40

CONTEXT.md

@@ -19,9 +19,33 @@ The ability to visualize what a specific strategy produces for a given document
 _Avoid_: Chunk inspection, chunk view
 
 **Tab**:
-A persistent top-level navigation section of the Dashboard (Home, Documents, Query, Benchmarks, Admin). Tabs stay mounted when switching — state survives.
+A persistent top-level navigation section of the Dashboard (Home, Documents, Query, Benchmarks, Admin, PDF). Tabs stay mounted when switching — state survives.
 _Avoid_: Page, route, view
 
+**PDF Workspace**:
+The PDF Tab’s end-to-end surface for Text PDF work: upload, process Strategies, Chunk Preview, query, run Experiments, and open reports — scoped to PDF documents only. Documents / Query / Benchmarks Tabs list Word documents only (`.doc`/`.docx`). Inside the Tab, features are collapsible accordion sections (Upload & Process open by default); Admin-only ops (health, Qdrant CRUD) stay on Admin. Built from shared Dashboard section components with a format filter — not a forked UI.
+_Avoid_: PDF page, PDF mode, PDF dashboard
+
+**Text PDF**:
+A PDF with a real, selectable text layer that can be extracted without OCR. In scope for PDF ingestion v1.
+_Avoid_: Digital PDF, native PDF, searchable PDF (ambiguous in ops talk)
+
+**Scanned PDF**:
+A PDF whose pages are images (or have a useless/empty text layer) and need OCR before chunking. Out of scope for PDF ingestion v1.
+_Avoid_: Image PDF, photo PDF, OCR PDF
+
+**Heading Reconstruction**:
+Inferring section/article boundaries from PDF signals in priority order — outline bookmarks, then font size/weight, then Farsi/English text heuristics — and emitting markdown `#` / `##` for Strategies. Later signals fill gaps; they do not override outline titles when an outline is present.
+_Avoid_: Heading detection, structure recovery, outline parsing (too narrow)
+
+**Text-layer Gate**:
+Upload-time check that a PDF has enough extractable text to count as a Text PDF; failure rejects the upload. Scanned PDFs never enter the benchmark corpus.
+_Avoid_: OCR check, PDF validation, empty-page filter
+
+**Table Flattening**:
+Turning table cells into sequential plain-text blocks in reading order (same contract for DOCX and Text PDF). Strategies never receive grid/markdown-table structure in v1.
+_Avoid_: Table extraction, table parsing, structured tables
+
 ## Architecture Decisions
 
 | # | Decision | Status |
@@ -40,3 +64,5 @@ _Avoid_: Page, route, view
  ADR-0012 | Chunk Preview: table with expandable rows. Select document + strategy, click Load. Rows show index + 80-char text preview + token/char counts. Click to expand full text. Parent column hidden by default. | Approved |
  ADR-0013 | Questions Management: file list table + upload button + expandable row detail (id, question, category, difficulty, expected answer) + delete + "Use This File" shortcut to set Benchmarks tab path and switch tabs. Auto-refresh after mutations. | Approved |
  ADR-0014 | Cost Estimator: two number inputs (questions, strategies), Estimate button, result card with total cost in amber, token estimate, 3 breakdown cards (embedding/queries/evaluation). Simple numbers, no tables. | Approved |
+ ADR-0016 | Text PDF extraction via PyMuPDF + Heading Reconstruction; Scanned PDFs hard-rejected (Text-layer Gate). See docs/adr/0016-*.md | Approved |
+ ADR-0017 | PDF Workspace via shared Dashboard sections + format filter (not a forked UI). See docs/adr/0017-*.md | Approved |

backlog/README.md

@@ -0,0 +1,12 @@
+# Backlog — PDF & ingestion follow-ups
+
+Items deferred from PDF ingestion v1 (Text PDF + PyMuPDF + Heading Reconstruction).
+
+| Item | When to pick up |
+|------|-----------------|
+| [Scanned PDF OCR](./scanned-pdf-ocr.md) | After Text PDF Experiments are stable; chatbot needs image PDFs |
+| [Persian / cloud OCR](./persian-cloud-ocr.md) | Local OCR quality on Farsi sample set is too low |
+| [pdfplumber tables](./pdfplumber-tables.md) | PyMuPDF table flattening hurts Experiment scores |
+| [LibreOffice PDF→DOCX fallback](./libreoffice-pdf-to-docx-fallback.md) | Heading Reconstruction false-positives dominate; want second opinion path |
+| [Multi-column layout](./multi-column-layout.md) | Reading order is wrong on multi-column policies |
+| [Page metadata in chunks](./page-metadata-in-chunks.md) | Users need “page N” citations in answers / Chunk Preview |

backlog/libreoffice-pdf-to-docx-fallback.md

@@ -0,0 +1,20 @@
+# LibreOffice PDF→DOCX fallback
+
+## Why deferred
+
+We already convert `.doc` → `.docx` via LibreOffice. PDF→DOCX is tempting for “reuse the DOCX parser,” but styles/fonts often come out wrong — fighting the reason we chose PyMuPDF.
+
+## Trigger
+
+Heading Reconstruction on PyMuPDF has an unacceptable false-positive/false-negative rate on a representative sample, and bookmarks/fonts are absent.
+
+## Approach to try
+
+1. Optional fallback: `soffice --headless --convert-to docx` then existing `parse_docx`
+2. Compare markdown side-by-side (PyMuPDF vs converted DOCX) in Chunk Preview before making it default
+3. Keep as opt-in or auto-fallback only when PDF outline + font variance is below a threshold
+
+## Success criteria
+
+- Converted DOCX headings beat PyMuPDF heuristics on the failing sample set
+- Conversion time acceptable for upload UX (or async later — currently sync REST)

backlog/multi-column-layout.md

@@ -0,0 +1,20 @@
+# Multi-column layout reading order
+
+## Why deferred
+
+Many Text PDFs are single-column policies. Multi-column (or sidebar) layouts can make naive top-to-bottom extraction interleave columns.
+
+## Trigger
+
+Chunk Preview shows sentences from column A mixed with column B; Experiment Faithfulness drops on those docs only.
+
+## Approach to try
+
+1. Use PyMuPDF block/bbox clustering to detect columns
+2. Read column-by-column (right-to-left for Farsi multi-column if applicable)
+3. Add a fixture PDF with known two-column layout to regression tests
+
+## Success criteria
+
+- Reading order matches human reading on the fixture
+- No regression on single-column Farsi docs

backlog/page-metadata-in-chunks.md

@@ -0,0 +1,20 @@
+# Page metadata in chunks
+
+## Why deferred
+
+v1 Strategies and Qdrant payloads don’t need page numbers. Page-as-section markdown was rejected (arbitrary cuts). Page info is citation UX, not chunking semantics.
+
+## Trigger
+
+Users (or the chatbot) need “see page N” citations, or Chunk Preview should show page ranges per chunk.
+
+## Approach to try
+
+1. During PDF parse, map character/block offsets → page numbers
+2. Attach optional `page_start` / `page_end` on Chunk / ChunkMetadata (nullable for DOCX)
+3. Do **not** inject `## Page N` into markdown unless a Strategy specifically needs it
+
+## Success criteria
+
+- DOCX path unchanged (null pages)
+- Query/answer path can cite pages without changing Strategy ranking logic

backlog/pdfplumber-tables.md

@@ -0,0 +1,20 @@
+# pdfplumber for tables
+
+## Why deferred
+
+v1 uses PyMuPDF only. Dual extractors add complexity before we know tables are the failure mode.
+
+## Trigger
+
+Chunk Preview / Experiments show table cells concatenated in wrong order, or key cells missing, on table-heavy insurance PDFs — after Heading Reconstruction is otherwise fine.
+
+## Approach to try
+
+1. Keep PyMuPDF for body text + Heading Reconstruction
+2. Detect table regions (PyMuPDF or pdfplumber) and extract those via pdfplumber
+3. Flatten tables the same way DOCX does (sequential text blocks), not HTML tables in markdown (unless Strategies learn to use them)
+
+## Success criteria
+
+- Questions that answer from table cells improve without regressing prose headings
+- No second full-document parse path unless necessary

backlog/persian-cloud-ocr.md

@@ -0,0 +1,22 @@
+# Persian / cloud OCR
+
+## Why deferred
+
+Local OCR (e.g. Tesseract + `fas`/`fa`) may be good enough — or may destroy RTL, digits, and legal phrasing. Don’t commit to a vendor until measured.
+
+## Trigger
+
+Local OCR on a Farsi Scanned PDF sample set produces systematically bad characters, broken line order, or unusable tables.
+
+## Options to A/B
+
+| Option | Pros | Cons |
+|--------|------|------|
+| Tesseract + Persian models | Free, offline, no data leaving the box | Quality varies; tuning burden |
+| Cloud OCR (Google / Azure / etc.) | Often better on Persian print | Cost, latency, compliance |
+| Commercial Persian-focused OCR | Domain fit | Vendor lock-in |
+
+## Success criteria
+
+- Character error rate low enough that answer Faithfulness in Experiments doesn’t collapse vs Text PDF baseline
+- RTL paragraphs stay coherent in Chunk Preview

backlog/scanned-pdf-ocr.md

@@ -0,0 +1,25 @@
+# Scanned PDF OCR (v1.1+)
+
+## Why deferred
+
+v1 only accepts Text PDFs and applies a Text-layer Gate: Scanned PDFs are hard-rejected at upload (not stored, not processed). OCR is a second product surface: noisy text poisons every Strategy equally and makes Experiment comparisons misleading.
+
+## Trigger
+
+Pick this up when:
+
+1. Text PDF path is trusted on real docs
+2. You have ~10–20 labeled Scanned PDFs + question JSONs matching chatbot traffic
+3. Production coverage of those docs matters more than clean benchmarks alone
+
+## Approach to try
+
+1. Detect empty / near-empty text layer at upload (same gate as v1 rejection)
+2. Run OCR as an **explicit pre-step** that still emits `ParseResult` (markdown + DocumentTree)
+3. Tag source as `ocr` so Experiments can filter Text PDF vs Scanned PDF runs
+4. Reuse Heading Reconstruction heuristics on OCR text (expect more false positives)
+
+## Success criteria
+
+- OCR’d markdown is readable enough that recursive Strategy headings aren’t nonsense
+- Side-by-side Experiment: Text PDF original vs OCR of a scan of the same doc — score delta understood, not mysterious

docs/adr/0016-pymupdf-for-text-pdf-extraction.md

@@ -0,0 +1,16 @@
+# PyMuPDF for Text PDF extraction
+
+Text PDF ingestion uses PyMuPDF (`fitz`) so Heading Reconstruction can read font size/weight, text blocks, and outline bookmarks — the same structural signals `python-docx` gives us for DOCX. We rejected flat string extractors (`pypdf`), table-first libraries as the primary path (`pdfplumber`), and LibreOffice PDF→DOCX conversion (lossy styles, slow, fights ADR 0006’s “prefer native structure”).
+
+## Considered Options
+
+- **PyMuPDF** — chosen; best fit for Heading Reconstruction; AGPL acceptable while this stays an internal benchmarker
+- **pdfplumber** — strong tables, weaker hierarchy; deferred to backlog if tables are a measured failure
+- **pypdf** — too little layout/font signal
+- **LibreOffice PDF→DOCX → existing parser** — reuses DOCX path but conversion quality is unreliable
+
+## Consequences
+
+- Add `pymupdf` dependency; keep a single PDF code path in the documents parser seam
+- If we later ship the parser as a distributed service, revisit AGPL vs a permissive alternative
+- Table-heavy and Scanned PDF work stays out of this ADR (see `backlog/`)

docs/adr/0017-shared-dashboard-sections-format-filter.md

@@ -0,0 +1,11 @@
+# Shared Dashboard sections with format filter
+
+The PDF Workspace is not a second UI. Documents, Query, Benchmarks, and Chunk Preview are composed from shared section components in `index.html`, parameterized by a format filter (`word` | `pdf`). That keeps Word Tabs and the PDF Tab behaviorally identical while listing different documents, and avoids cloning the single-file Dashboard (ADR-0004).
+
+Rejected: copy-paste PDF Tab (diverges immediately) and “filter props only with zero extraction” when it would still duplicate large JSX blocks.
+
+## Consequences
+
+- Refactor existing Tab bodies to call shared panels before adding the PDF Tab
+- Filtering is client-side by filename suffix; APIs stay format-agnostic
+- Report generator stays shared; PDF Experiments only get a source-format badge

pyproject.toml

@@ -13,6 +13,7 @@ dependencies = [
     "pydantic>=2.5.0",
     "pydantic-settings>=2.1.0",
     "python-docx>=1.0.0",
+    "pymupdf>=1.24.0",
     "openai>=1.6.0",
     "qdrant-client>=1.7.0",
     "tiktoken>=0.5.0",

src/benchmarking/report.py

@@ -7,6 +7,7 @@ Design: Dark mode, amber/teal accents, Inter + JetBrains Mono.
 
 from __future__ import annotations
 
+import html
 import json
 from typing import Any
 
@@ -34,8 +35,104 @@ FONT_DISPLAY = "'Inter', -apple-system, sans-serif"
 FONT_DATA = "'JetBrains Mono', 'Fira Code', monospace"
 
 
+# ── Compare Answers Modal (JS) ────────────────────────────────────
+
+_MODAL_JS = """
+        // ── Compare Answers Modal ─────────────────────────────────
+        function escapeHtml(str) {
+            if (str == null) return '';
+            return String(str)
+                .replace(/&/g, '&')
+                .replace(/</g, '&lt;')
+                .replace(/>/g, '&gt;')
+                .replace(/"/g, '&quot;')
+                .replace(/'/g, '&#39;');
+        }
+
+        function scoreChip(label, val) {
+            val = Number(val) || 0;
+            const cls = val >= 8 ? 'high' : (val >= 6 ? 'mid' : 'low');
+            return '<span class="score-chip ' + cls + '">' + label + ' ' + val.toFixed(1) + '</span>';
+        }
+
+        function showCompare(idx) {
+            const q = perQuestion[idx];
+            if (!q) return;
+
+            document.getElementById('modalQId').textContent = 'Question ' + (q.question_id || (idx + 1));
+            document.getElementById('modalQuestion').textContent = q.question || '';
+
+            const expected = q.expected_answer || '';
+            document.getElementById('modalExpected').innerHTML = expected
+                ? '<div class="expected-block"><strong>Expected Answer (Ground Truth)</strong><p>' + escapeHtml(expected) + '</p></div>'
+                : '';
+
+            const grid = document.getElementById('modalAnswers');
+            grid.innerHTML = strategies.map(s => {
+                const strat = (q.strategies || {})[s] || {};
+                const scores = strat.scores || {};
+                const hasError = !!strat.error;
+                const hasAnswer = !!(strat.answer && String(strat.answer).trim());
+                const answer = hasAnswer
+                    ? strat.answer
+                    : (hasError ? ('Error: ' + strat.error) : 'No answer recorded.');
+
+                const chips = [];
+                if (scores.context_relevance != null) chips.push(scoreChip('Context', scores.context_relevance));
+                if (scores.answer_similarity != null) chips.push(scoreChip('Sim', scores.answer_similarity));
+                if (scores.faithfulness != null) chips.push(scoreChip('Faith', scores.faithfulness));
+                if (scores.hallucination != null) {
+                    chips.push(scores.hallucination
+                        ? '<span class="score-chip low">Hallucinated</span>'
+                        : '<span class="score-chip high">No Hallucination</span>');
+                }
+                if (strat.latency && strat.latency.query_seconds != null) {
+                    chips.push('<span class="score-chip">' + Number(strat.latency.query_seconds).toFixed(2) + 's</span>');
+                }
+                const usage = strat.token_usage || {};
+                if (usage.total_tokens != null) {
+                    chips.push('<span class="score-chip">' + Number(usage.total_tokens).toLocaleString() + ' tokens</span>');
+                }
+
+                return '<div class="answer-card">'
+                    + '<div class="strategy-name">' + escapeHtml(s)
+                    + '<span class="badge pill ' + (hasError ? 'low' : 'mid') + '">' + (hasError ? 'FAILED' : 'ANSWER') + '</span></div>'
+                    + '<div class="score-row">' + chips.join('') + '</div>'
+                    + '<div class="answer-text' + (hasAnswer ? '' : ' empty') + '">' + escapeHtml(answer) + '</div>'
+                    + '</div>';
+            }).join('');
+
+            document.getElementById('compareModal').classList.add('open');
+            document.body.style.overflow = 'hidden';
+        }
+
+        function closeCompare() {
+            document.getElementById('compareModal').classList.remove('open');
+            document.body.style.overflow = '';
+        }
+
+        document.getElementById('compareModal').addEventListener('click', function (e) {
+            if (e.target === this) closeCompare();
+        });
+
+        document.addEventListener('keydown', function (e) {
+            if (e.key === 'Escape') closeCompare();
+        });
+"""
+
+
 # ── Main Entry Points ─────────────────────────────────────────────
 
+def _source_format_label(experiment: dict) -> str:
+    """Human-readable source format badge from document filename."""
+    filename = (experiment.get("document_filename") or "").lower()
+    if filename.endswith(".pdf"):
+        return "Text PDF"
+    if filename.endswith(".docx") or filename.endswith(".doc"):
+        return "DOCX"
+    return ""
+
+
 def generate_report(experiment: dict, view: str = "managerial") -> str:
     """Generate report for specified view.
 
@@ -67,6 +164,8 @@ def generate_managerial_report(experiment: dict) -> str:
             total_completion_tokens += usage.get("completion_tokens", 0)
 
     estimated_cost = (total_prompt_tokens * 0.15 + total_completion_tokens * 0.60) / 1_000_000
+    source_label = _source_format_label(experiment)
+    source_meta = f" &middot; Source: {source_label}" if source_label else ""
 
     html = _base_html(experiment, "Managerial View", f"""
         <!-- Header -->
@@ -76,7 +175,7 @@ def generate_managerial_report(experiment: dict) -> str:
             <div class="meta">
                 {config.get('num_questions', 0)} questions &middot;
                 {len(strategies)} strategies &middot;
-                ${estimated_cost:.4f} cost
+                ${estimated_cost:.4f} cost{source_meta}
             </div>
         </header>
 
@@ -196,6 +295,8 @@ def generate_technical_report(experiment: dict) -> str:
 
     # Estimate latency (rough: ~0.5s per query + ~1s per evaluation)
     estimated_latency = total_queries * 1.5
+    source_label = _source_format_label(experiment)
+    source_meta = f" &middot; Source: {source_label}" if source_label else ""
 
     html = _base_html(experiment, "Technical View", f"""
         <!-- Header -->
@@ -205,7 +306,7 @@ def generate_technical_report(experiment: dict) -> str:
             <div class="meta">
                 Experiment: {experiment.get('id', 'N/A')[:16]}... &middot;
                 {total_questions} questions &middot;
-                {len(strategies)} strategies
+                {len(strategies)} strategies{source_meta}
             </div>
         </header>
 
@@ -279,6 +380,7 @@ def generate_technical_report(experiment: dict) -> str:
             <h2>Per-Question Results</h2>
             <div class="line"></div>
         </div>
+        <div class="hint">&#128269; Click any question to compare full answers from all strategies side by side.</div>
         <div class="table-wrapper">
             <table>
                 <thead>
@@ -489,6 +591,34 @@ def _base_html(experiment: dict, title: str, content: str) -> str:
         .link-text {{ flex: 1; font-weight: 500; }}
         .link-arrow {{ color: var(--accent); font-size: 18px; }}
 
+        .question-link {{ color: var(--accent); cursor: pointer; text-decoration: none; border-bottom: 1px dashed var(--accent); }}
+        .question-link:hover {{ color: var(--accent-dim); border-bottom-style: solid; }}
+
+        .hint {{ font-size: 12px; color: var(--text-muted); font-family: {FONT_DATA}; margin-bottom: 16px; }}
+
+        .modal-overlay {{ position: fixed; inset: 0; background: rgba(4, 8, 12, 0.72); display: none; align-items: center; justify-content: center; z-index: 1000; padding: 24px; backdrop-filter: blur(4px); }}
+        .modal-overlay.open {{ display: flex; }}
+        .modal {{ background: var(--surface); border: 1px solid var(--border); border-radius: 16px; max-width: 1100px; width: 100%; max-height: 85vh; display: flex; flex-direction: column; box-shadow: 0 24px 48px rgba(0, 0, 0, 0.5); }}
+        .modal-header {{ padding: 24px 28px; border-bottom: 1px solid var(--border); display: flex; align-items: flex-start; gap: 16px; }}
+        .modal-header .eyebrow {{ margin-bottom: 8px; }}
+        .modal-header h3 {{ font-size: 18px; font-weight: 600; line-height: 1.4; }}
+        .modal-close {{ margin-left: auto; background: var(--surface-hover); border: 1px solid var(--border); color: var(--text-muted); width: 36px; height: 36px; border-radius: 8px; font-size: 20px; line-height: 1; cursor: pointer; flex-shrink: 0; transition: all 0.2s ease; }}
+        .modal-close:hover {{ color: var(--text); border-color: var(--accent); }}
+        .modal-body {{ padding: 24px 28px; overflow-y: auto; }}
+        .expected-block {{ background: rgba(139, 92, 246, 0.08); border-left: 3px solid var(--violet); border-radius: 8px; padding: 16px 20px; margin-bottom: 20px; }}
+        .expected-block strong {{ font-size: 12px; color: var(--violet); text-transform: uppercase; letter-spacing: 1px; display: block; margin-bottom: 6px; }}
+        .expected-block p {{ font-size: 13px; color: var(--text); margin: 0; }}
+        .answer-grid {{ display: grid; grid-template-columns: repeat(auto-fit, minmax(320px, 1fr)); gap: 16px; }}
+        .answer-card {{ background: var(--surface-hover); border: 1px solid var(--border); border-radius: 12px; padding: 20px; display: flex; flex-direction: column; gap: 12px; }}
+        .answer-card .strategy-name {{ font-size: 13px; font-weight: 600; color: var(--accent); display: flex; align-items: center; justify-content: space-between; gap: 8px; }}
+        .answer-card .answer-text {{ font-size: 13px; line-height: 1.7; color: var(--text); white-space: pre-wrap; word-break: break-word; background: var(--surface); border: 1px solid var(--border); border-radius: 8px; padding: 14px 16px; max-height: 320px; overflow-y: auto; }}
+        .answer-card .answer-text.empty {{ color: var(--text-muted); font-style: italic; }}
+        .score-row {{ display: flex; flex-wrap: wrap; gap: 8px; }}
+        .score-chip {{ font-family: {FONT_DATA}; font-size: 11px; padding: 3px 8px; border-radius: 6px; background: var(--surface); border: 1px solid var(--border); }}
+        .score-chip.high {{ color: var(--emerald); border-color: rgba(16, 185, 129, 0.4); }}
+        .score-chip.mid {{ color: var(--accent); border-color: rgba(245, 158, 11, 0.4); }}
+        .score-chip.low {{ color: var(--rose); border-color: rgba(244, 63, 94, 0.4); }}
+
         .footer {{ padding-top: 32px; border-top: 1px solid var(--border); font-size: 12px; color: var(--text-muted); text-align: center; }}
 
         @media (max-width: 768px) {{
@@ -508,6 +638,27 @@ def _base_html(experiment: dict, title: str, content: str) -> str:
     <div class="page">
         {content}
 
+        <!-- Compare Answers Modal -->
+        <div class="modal-overlay" id="compareModal">
+            <div class="modal">
+                <div class="modal-header">
+                    <div>
+                        <div class="eyebrow" id="modalQId">Question</div>
+                        <h3 id="modalQuestion"></h3>
+                    </div>
+                    <button class="modal-close" onclick="closeCompare()" aria-label="Close">&times;</button>
+                </div>
+                <div class="modal-body">
+                    <div id="modalExpected"></div>
+                    <div class="section-header">
+                        <h2>Answers by Strategy</h2>
+                        <div class="line"></div>
+                    </div>
+                    <div class="answer-grid" id="modalAnswers"></div>
+                </div>
+            </div>
+        </div>
+
         <footer class="footer">
             Generated by RAG Chunking Benchmarker &middot; {experiment.get('created_at', 'N/A')}
         </footer>
@@ -517,64 +668,73 @@ def _base_html(experiment: dict, title: str, content: str) -> str:
         const colors = {json.dumps(CHART_COLORS)};
         const strategies = {json.dumps(strategies)};
         const aggregate = {json.dumps(aggregate)};
+        const perQuestion = {json.dumps(experiment.get("per_question", []), ensure_ascii=False).replace("</", "<\\/")};
+
+        {_MODAL_JS}
 
         // Radar
-        new Chart(document.getElementById('radarChart'), {{
+        const radarEl = document.getElementById('radarChart');
-            type: 'radar',
+        if (radarEl) {{
-            data: {{
+            new Chart(radarEl, {{
-                labels: ['Context', 'Similarity', 'Faithfulness', 'Consistency'],
+                type: 'radar',
-                datasets: strategies.map((s, i) => ({{
+                data: {{
-                    label: s,
+                    labels: ['Context', 'Similarity', 'Faithfulness', 'Consistency'],
-                    data: [
+                    datasets: strategies.map((s, i) => ({{
-                        aggregate[s]?.avg_context_relevance || 0,
+                        label: s,
-                        aggregate[s]?.avg_answer_similarity || 0,
+                        data: [
-                        aggregate[s]?.avg_faithfulness || 0,
+                            aggregate[s]?.avg_context_relevance || 0,
-                        (1 - (aggregate[s]?.hallucination_rate || 0)) * 10
+                            aggregate[s]?.avg_answer_similarity || 0,
-                    ],
+                            aggregate[s]?.avg_faithfulness || 0,
-                    borderColor: colors[i % colors.length],
+                            (1 - (aggregate[s]?.hallucination_rate || 0)) * 10
-                    backgroundColor: colors[i % colors.length] + '20',
+                        ],
-                    pointBackgroundColor: colors[i % colors.length],
+                        borderColor: colors[i % colors.length],
-                    borderWidth: 2
+                        backgroundColor: colors[i % colors.length] + '20',
-                }}))
+                        pointBackgroundColor: colors[i % colors.length],
-            }},
+                        borderWidth: 2
-            options: {{
+                    }}))
-                responsive: true,
+                }},
-                maintainAspectRatio: false,
+                options: {{
-                plugins: {{ legend: {{ display: false }} }},
+                    responsive: true,
-                scales: {{
+                    maintainAspectRatio: false,
-                    r: {{
+                    plugins: {{ legend: {{ display: false }} }},
-                        beginAtZero: true,
+                    scales: {{
-                        max: 10,
+                        r: {{
-                        grid: {{ color: '{COLORS["border"]}' }},
+                            beginAtZero: true,
-                        angleLines: {{ color: '{COLORS["border"]}' }},
+                            max: 10,
-                        pointLabels: {{ color: '{COLORS["text-muted"]}', font: {{ family: "'JetBrains Mono'", size: 11 }} }},
+                            grid: {{ color: '{COLORS["border"]}' }},
-                        ticks: {{ display: false }}
+                            angleLines: {{ color: '{COLORS["border"]}' }},
+                            pointLabels: {{ color: '{COLORS["text-muted"]}', font: {{ family: "'JetBrains Mono'", size: 11 }} }},
+                            ticks: {{ display: false }}
+                        }}
                     }}
                 }}
-            }}
+            }});
-        }});
+        }}
 
         // Bar
-        new Chart(document.getElementById('barChart'), {{
+        const barEl = document.getElementById('barChart');
-            type: 'bar',
+        if (barEl) {{
-            data: {{
+            new Chart(barEl, {{
-                labels: strategies.map(s => s.length > 12 ? s.substring(0, 12) + '...' : s),
+                type: 'bar',
-                datasets: [
+                data: {{
-                    {{ label: 'Context', data: strategies.map(s => aggregate[s]?.avg_context_relevance || 0), backgroundColor: colors[0] }},
+                    labels: strategies.map(s => s.length > 12 ? s.substring(0, 12) + '...' : s),
-                    {{ label: 'Similarity', data: strategies.map(s => aggregate[s]?.avg_answer_similarity || 0), backgroundColor: colors[1] }},
+                    datasets: [
-                    {{ label: 'Faithfulness', data: strategies.map(s => aggregate[s]?.avg_faithfulness || 0), backgroundColor: colors[2] }}
+                        {{ label: 'Context', data: strategies.map(s => aggregate[s]?.avg_context_relevance || 0), backgroundColor: colors[0] }},
-                ]
+                        {{ label: 'Similarity', data: strategies.map(s => aggregate[s]?.avg_answer_similarity || 0), backgroundColor: colors[1] }},
-            }},
+                        {{ label: 'Faithfulness', data: strategies.map(s => aggregate[s]?.avg_faithfulness || 0), backgroundColor: colors[2] }}
-            options: {{
+                    ]
-                responsive: true,
+                }},
-                maintainAspectRatio: false,
+                options: {{
-                plugins: {{ legend: {{ position: 'bottom', labels: {{ color: '{COLORS["text-muted"]}', font: {{ family: "'Inter'" }} }} }} }},
+                    responsive: true,
-                scales: {{
+                    maintainAspectRatio: false,
-                    x: {{ grid: {{ display: false }}, ticks: {{ color: '{COLORS["text-muted"]}' }} }},
+                    plugins: {{ legend: {{ position: 'bottom', labels: {{ color: '{COLORS["text-muted"]}', font: {{ family: "'Inter'" }} }} }} }},
-                    y: {{ beginAtZero: true, max: 10, grid: {{ color: '{COLORS["border"]}' }}, ticks: {{ color: '{COLORS["text-muted"]}' }} }}
+                    scales: {{
+                        x: {{ grid: {{ display: false }}, ticks: {{ color: '{COLORS["text-muted"]}' }} }},
+                        y: {{ beginAtZero: true, max: 10, grid: {{ color: '{COLORS["border"]}' }}, ticks: {{ color: '{COLORS["text-muted"]}' }} }}
+                    }}
                 }}
-            }}
+            }});
-        }});
+        }}
     </script>
 </body>
 </html>"""
@@ -739,13 +899,16 @@ def _build_strategy_headers(strategies: list) -> str:
 
 
 def _build_per_question_rows(per_question: list, strategies: list) -> str:
-    """Build per-question rows."""
+    """Build per-question rows with clickable questions opening the compare modal."""
     rows = ""
-    for qr in per_question:
+    for idx, qr in enumerate(per_question):
-        q_id = qr.get("question_id", "")
+        q_id = html.escape(str(qr.get("question_id", "")))
-        q_text = qr.get("question", "")[:40]
+        full_q = str(qr.get("question", "") or "")
-        category = qr.get("category", "")
+        q_preview = full_q[:60] + ("..." if len(full_q) > 60 else "")
-        difficulty = qr.get("difficulty", "")
+        q_text = html.escape(q_preview)
+        category = html.escape(str(qr.get("category", "") or ""))
+        difficulty = str(qr.get("difficulty", "") or "")
+        difficulty_safe = html.escape(difficulty)
 
         cells = ""
         for strategy in strategies:
@@ -755,11 +918,11 @@ def _build_per_question_rows(per_question: list, strategies: list) -> str:
             cells += f"<td>{_pill(sim)}</td>"
 
         rows += f"""
-        <tr>
+        <tr style="cursor: pointer;" onclick="showCompare({idx})" title="Click to compare all strategy answers">
             <td style="font-family: {FONT_DATA}; color: var(--text-muted);">{q_id}</td>
-            <td>{q_text}...</td>
+            <td><span class="question-link">{q_text}</span></td>
             <td style="color: var(--text-muted);">{category}</td>
-            <td><span class="pill {'high' if difficulty == 'easy' else 'mid' if difficulty == 'medium' else 'low'}">{difficulty}</span></td>
+            <td><span class="pill {'high' if difficulty == 'easy' else 'mid' if difficulty == 'medium' else 'low'}">{difficulty_safe}</span></td>
             {cells}
         </tr>"""
 
@@ -770,21 +933,24 @@ def _build_detailed_rows(per_question: list, strategies: list) -> str:
     """Build detailed score rows."""
     rows = ""
     for qr in per_question:
-        q_id = qr.get("question_id", "")
+        q_id = html.escape(str(qr.get("question_id", "")))
         for strategy in strategies:
             strat = qr.get("strategies", {}).get(strategy, {})
             scores = strat.get("scores", {})
-            answer = strat.get("answer", "")[:60]
+            full_answer = str(strat.get("answer", "") or "")
+            answer_preview = full_answer[:60] + ("..." if len(full_answer) > 60 else "")
+            answer = html.escape(answer_preview)
+            strategy_safe = html.escape(str(strategy))
 
             rows += f"""
             <tr>
                 <td style="font-family: {FONT_DATA}; font-size: 12px;">{q_id}</td>
-                <td>{strategy}</td>
+                <td>{strategy_safe}</td>
                 <td>{_pill(scores.get('context_relevance', 0))}</td>
                 <td>{_pill(scores.get('answer_similarity', 0))}</td>
                 <td>{_pill(scores.get('faithfulness', 0))}</td>
                 <td>{'&#10003;' if not scores.get('hallucination', False) else '&#10007;'}</td>
-                <td style="font-size: 13px; color: var(--text-muted);">{answer}...</td>
+                <td style="font-size: 13px; color: var(--text-muted);">{answer}</td>
             </tr>"""
 
     return rows

src/core/config.py

@@ -35,5 +35,9 @@ class Settings(BaseSettings):
     # Database
     database_url: str = "sqlite:///./data/chunking_benchmark.db"
 
+    # Text PDF gate (reject Scanned PDFs with near-empty text layer)
+    pdf_min_total_chars: int = 100
+    pdf_min_median_chars_per_page: int = 40
+
 
 settings = Settings()

src/documents/heading_heuristics.py

@@ -0,0 +1,79 @@
+"""Shared heading detection heuristics for DOCX and Text PDF parsers.
+
+Used when native styles/fonts/outlines are missing or incomplete
+(common in table-heavy Farsi documents).
+"""
+
+from __future__ import annotations
+
+import re
+from typing import Protocol
+
+
+class StyledBlock(Protocol):
+    """Minimal block interface: mutable style_name + text."""
+
+    style_name: str
+    text: str
+
+
+_HEADING_PATTERNS: list[tuple[re.Pattern[str], int]] = [
+    (re.compile(r"^بخش\s+"), 1),
+    (re.compile(r"^\d+[\-\.]\d+"), 2),
+    (re.compile(r"^\*\s*بخش\s+"), 1),
+    (re.compile(r"^\*\s*\S"), 2),
+]
+
+
+def heading_level_from_style(style_name: str) -> int | None:
+    """Return heading level from a style name like 'Heading 1' or 'Heading1'."""
+    m = re.match(r"^heading\s*(\d+)$", style_name.strip(), re.IGNORECASE)
+    if m:
+        return int(m.group(1))
+    return None
+
+
+def is_likely_heading(text: str) -> int | None:
+    """Detect heading-like patterns in body text.
+
+    Returns heading level (1 or 2) if detected, else None.
+    """
+    text = text.strip()
+    if len(text) > 150:
+        return None
+    for pattern, level in _HEADING_PATTERNS:
+        if pattern.match(text):
+            return level
+    return None
+
+
+def apply_heading_heuristics(
+    blocks: list[StyledBlock],
+    *,
+    only_when_no_headings: bool = True,
+) -> bool:
+    """Upgrade Normal blocks to HeadingN via text patterns.
+
+    Args:
+        blocks: Mutable text blocks with style_name / text.
+        only_when_no_headings: If True (DOCX default), skip when any
+            Heading styles already exist. If False, only upgrade remaining
+            Normal blocks (PDF gap-fill after outline/font).
+
+    Returns:
+        True if any blocks were upgraded.
+    """
+    if only_when_no_headings:
+        if any(heading_level_from_style(b.style_name) is not None for b in blocks):
+            return False
+
+    upgraded = False
+    for block in blocks:
+        if block.style_name != "Normal":
+            continue
+        level = is_likely_heading(block.text)
+        if level is not None:
+            block.style_name = f"Heading{level}"
+            upgraded = True
+
+    return upgraded

src/documents/parser.py

@@ -1,18 +1,13 @@
-"""DOCX parser: extracts document tree + flat markdown.
+"""Document parser: DOCX/DOC + dispatcher for all supported formats.
 
-Uses python-docx to read paragraph styles and build a hierarchical
+Produces a hierarchical DocumentTree (Document > Section > Article > Paragraph)
-DocumentTree (Document > Section > Article > Paragraph).  Also produces
+and markdown consumed by chunking strategies.
-a markdown representation consumed by chunking strategies.
 
-Supports both .docx and .doc formats.  .doc files are converted to
+Supports .docx, .doc (via LibreOffice), and .pdf (via pdf_parser).
-.docx via LibreOffice headless mode before parsing.
-
-Handles documents where content is in tables (not just paragraphs).
 """
 
 from __future__ import annotations
 
-import re
 import subprocess
 import tempfile
 from pathlib import Path
@@ -27,6 +22,10 @@ from src.core.models import (
     NodeType,
 )
 from src.core.exceptions import DocumentProcessingError
+from src.documents.heading_heuristics import (
+    apply_heading_heuristics,
+    heading_level_from_style,
+)
 
 
 # ── Heading level → node type mapping ──────────────────────────────
@@ -34,89 +33,41 @@ from src.core.exceptions import DocumentProcessingError
 _HEADING_MAP: dict[int, NodeType] = {
     1: NodeType.SECTION,
     2: NodeType.ARTICLE,
-    # 3+ also ARTICLE (nesting depth determines hierarchy)
 }
 
 
-def _heading_level(style_name: str) -> int | None:
-    """Return the heading level from a style name, or None if not a heading.
-
-    Handles both "Heading 1" (display name) and "Heading1" (style ID from XML).
-    """
-    m = re.match(r"^heading\s*(\d+)$", style_name.strip(), re.IGNORECASE)
-    if m:
-        return int(m.group(1))
-    return None
-
-
 def _node_type_for_level(level: int) -> NodeType:
     return _HEADING_MAP.get(level, NodeType.ARTICLE)
 
 
-# ── Heuristic heading detection for table-heavy documents ──────────
+# ── Text block ─────────────────────────────────────────────────────
 
-# Patterns that look like section/article headings in Farsi/English docs
+class TextBlock:
-_HEADING_PATTERNS: list[tuple[str, int]] = [
+    """A unit of text extracted from a document, preserving reading order."""
-    # Farsi section markers: "بخش اول", "بخش دوم", etc.
-    (re.compile(r"^بخش\s+"), 1),
-    # Numbered sections: "1-1", "2-1", "10-1", "1-1-8"
-    (re.compile(r"^\d+[\-\.]\d+"), 2),
-    # Starred sections: "*بخش اول", "*تعریف"
-    (re.compile(r"^\*\s*بخش\s+"), 1),
-    (re.compile(r"^\*\s*\S"), 2),
-]
 
+    __slots__ = ("style_name", "text", "font_size", "bold", "page", "locked")
 
-def _is_likely_heading(text: str) -> int | None:
+    def __init__(
-    """Detect heading-like patterns in table-extracted text.
+        self,
-
+        style_name: str,
-    Returns the heading level (1 or 2) if detected, else None.
+        text: str,
-    Used when the document has no real heading styles (table-only content).
+        *,
-    """
+        font_size: float = 0.0,
-    text = text.strip()
+        bold: bool = False,
-    if len(text) > 150:  # headings are short
+        page: int = 0,
-        return None
+        locked: bool = False,
-    for pattern, level in _HEADING_PATTERNS:
+    ) -> None:
-        if pattern.match(text):
+        self.style_name = style_name
-            return level
+        self.text = text
-    return None
+        self.font_size = font_size
-
+        self.bold = bold
-
+        self.page = page
-def _detect_heading_blocks(blocks: list[_TextBlock]) -> bool:
+        self.locked = locked
-    """Upgrade paragraph blocks to heading blocks based on content patterns.
-
-    Returns True if any blocks were upgraded.
-    Only activates when no real headings exist in the document.
-    """
-    # Check if there are already real headings
-    has_headings = any(_heading_level(b.style_name) is not None for b in blocks)
-    if has_headings:
-        return False
-
-    upgraded = False
-    for block in blocks:
-        if block.style_name != "Normal":
-            continue
-        level = _is_likely_heading(block.text)
-        if level is not None:
-            block.style_name = f"Heading{level}"
-            upgraded = True
-
-    return upgraded
 
 
 # ── Text block extraction (paragraphs + tables) ───────────────────
 
-class _TextBlock:
+def _extract_text_blocks(doc: DocxDocumentType) -> list[TextBlock]:
-    """A unit of text extracted from the document, preserving reading order."""
-    __slots__ = ("style_name", "text")
-
-    def __init__(self, style_name: str, text: str) -> None:
-        self.style_name = style_name
-        self.text = text
-
-
-def _extract_text_blocks(doc: DocxDocumentType) -> list[_TextBlock]:
     """Walk the document body in reading order, extracting paragraphs and tables.
 
     This handles documents where content lives inside table cells
@@ -124,20 +75,17 @@ def _extract_text_blocks(doc: DocxDocumentType) -> list[_TextBlock]:
     """
     from docx.oxml.ns import qn
 
-    blocks: list[_TextBlock] = []
+    blocks: list[TextBlock] = []
 
     for element in doc.element.body:
         tag = element.tag.split("}")[-1] if "}" in element.tag else element.tag
 
         if tag == "p":
-            # Paragraph — extract text and style
             text = element.text or ""
-            # Also check for runs (text split across formatting)
             if not text.strip():
                 runs = element.findall(qn("w:r"))
                 text = "".join(r.text or "" for r in runs)
 
-            # Get style name
             ppr = element.find(qn("w:pPr"))
             style_name = "Normal"
             if ppr is not None:
@@ -146,19 +94,15 @@ def _extract_text_blocks(doc: DocxDocumentType) -> list[_TextBlock]:
                     style_name = pstyle.get(qn("w:val"), "Normal")
 
             if text.strip():
-                blocks.append(_TextBlock(style_name, text.strip()))
+                blocks.append(TextBlock(style_name, text.strip()))
 
         elif tag == "tbl":
-            # Table — extract all cell text as paragraph blocks
             for row in element.findall(qn("w:tr")):
                 for cell in row.findall(qn("w:tc")):
                     for para in cell.findall(qn("w:p")):
-                        # Get paragraph text
-                        text = ""
                         runs = para.findall(qn("w:r"))
                         text = "".join(r.text or "" for r in runs)
 
-                        # Get style
                         ppr = para.find(qn("w:pPr"))
                         style_name = "Normal"
                         if ppr is not None:
@@ -167,39 +111,36 @@ def _extract_text_blocks(doc: DocxDocumentType) -> list[_TextBlock]:
                                 style_name = pstyle.get(qn("w:val"), "Normal")
 
                         if text.strip():
-                            blocks.append(_TextBlock(style_name, text.strip()))
+                            blocks.append(TextBlock(style_name, text.strip()))
 
     return blocks
 
 
 # ── Tree builder ───────────────────────────────────────────────────
 
-def build_document_tree(paragraphs: list[Paragraph] | list[_TextBlock]) -> DocumentTreeNode:
+def build_document_tree(paragraphs: list[Paragraph] | list[TextBlock]) -> DocumentTreeNode:
     """Build a DocumentTreeNode tree from a list of text blocks.
 
-    Accepts either python-docx Paragraph objects or _TextBlock objects.
+    Accepts either python-docx Paragraph objects or TextBlock objects.
     """
     root = DocumentTreeNode(node_type=NodeType.DOCUMENT, text="", heading=None, heading_level=None)
 
-    # Stack of (level, node) for current nesting.  level 0 = root.
     stack: list[tuple[int, DocumentTreeNode]] = [(0, root)]
 
     for block in paragraphs:
-        # Get style name and text from either type
+        if isinstance(block, TextBlock):
-        if isinstance(block, _TextBlock):
             style_name = block.style_name
             text = block.text
         else:
             style_name = block.style.name
             text = block.text.strip()
 
-        level = _heading_level(style_name)
+        level = heading_level_from_style(style_name)
 
         if not text:
-            continue  # skip blank paragraphs
+            continue
 
         if level is not None:
-            # Pop back to parent level
             while len(stack) > 1 and stack[-1][0] >= level:
                 stack.pop()
 
@@ -212,7 +153,6 @@ def build_document_tree(paragraphs: list[Paragraph] | list[_TextBlock]) -> Docum
             stack[-1][1].children.append(node)
             stack.append((level, node))
         else:
-            # Body text — add as paragraph child of current heading
             node = DocumentTreeNode(
                 node_type=NodeType.PARAGRAPH,
                 text=text,
@@ -244,7 +184,7 @@ def tree_to_markdown(node: DocumentTreeNode, depth: int = 0) -> str:
 # ── Public API ─────────────────────────────────────────────────────
 
 class ParseResult:
-    """Output of parse_docx(): tree + markdown + raw text."""
+    """Output of parse_document() / parse_docx() / parse_pdf()."""
 
     __slots__ = ("tree", "markdown", "plain_text", "paragraph_count")
 
@@ -261,6 +201,31 @@ class ParseResult:
         self.paragraph_count = paragraph_count
 
 
+SUPPORTED_SUFFIXES = (".docx", ".doc", ".pdf")
+
+
+def parse_document(file_path: str | Path) -> ParseResult:
+    """Parse a supported document into DocumentTree + markdown.
+
+    Dispatches by suffix: .pdf → pdf_parser; .docx/.doc → parse_docx.
+    """
+    path = Path(file_path)
+    if not path.exists():
+        raise DocumentProcessingError(f"File not found: {path}")
+
+    suffix = path.suffix.lower()
+    if suffix == ".pdf":
+        from src.documents.pdf_parser import parse_pdf
+
+        return parse_pdf(path)
+    if suffix in (".docx", ".doc"):
+        return parse_docx(path)
+
+    raise DocumentProcessingError(
+        f"Not a supported file format: {suffix} (expected {', '.join(SUPPORTED_SUFFIXES)})"
+    )
+
+
 # ── .doc → .docx conversion ───────────────────────────────────────
 
 def _convert_doc_to_docx(doc_path: Path) -> Path:
@@ -268,9 +233,6 @@ def _convert_doc_to_docx(doc_path: Path) -> Path:
 
     Returns the path to the converted .docx file (in a temp directory).
     The caller is responsible for cleanup.
-
-    Raises:
-        DocumentProcessingError: If conversion fails.
     """
     out_dir = Path(tempfile.mkdtemp(prefix="docconv_"))
     try:
@@ -291,7 +253,6 @@ def _convert_doc_to_docx(doc_path: Path) -> Path:
                 f"LibreOffice conversion failed: {result.stderr}"
             )
 
-        # Find the converted file
         converted = out_dir / doc_path.with_suffix(".docx").name
         if not converted.exists():
             raise DocumentProcessingError(
@@ -312,15 +273,6 @@ def parse_docx(file_path: str | Path) -> ParseResult:
     """Parse a .docx or .doc file into a DocumentTree + markdown.
 
     .doc files are automatically converted to .docx via LibreOffice.
-
-    Args:
-        file_path: Path to the .docx or .doc file.
-
-    Returns:
-        ParseResult with tree, markdown, plain_text, and paragraph_count.
-
-    Raises:
-        DocumentProcessingError: If the file cannot be parsed.
     """
     path = Path(file_path)
     if not path.exists():
@@ -328,9 +280,10 @@ def parse_docx(file_path: str | Path) -> ParseResult:
 
     suffix = path.suffix.lower()
     if suffix not in (".docx", ".doc"):
-        raise DocumentProcessingError(f"Not a supported file format: {suffix} (expected .docx or .doc)")
+        raise DocumentProcessingError(
+            f"Not a supported file format: {suffix} (expected .docx or .doc)"
+        )
 
-    # Convert .doc to .docx if needed
     if suffix == ".doc":
         path = _convert_doc_to_docx(path)
 
@@ -339,14 +292,12 @@ def parse_docx(file_path: str | Path) -> ParseResult:
     except Exception as exc:
         raise DocumentProcessingError(f"Failed to open DOCX: {exc}") from exc
 
-    # Extract text blocks from paragraphs + tables (preserves reading order)
     blocks = _extract_text_blocks(doc)
 
     if not blocks:
         raise DocumentProcessingError("Document contains no text content")
 
-    # Detect heading patterns in table-only documents
+    apply_heading_heuristics(blocks, only_when_no_headings=True)
-    _detect_heading_blocks(blocks)
 
     root = build_document_tree(blocks)
     tree = DocumentTree(root=root)

src/documents/pdf_parser.py

@@ -0,0 +1,228 @@
+"""Text PDF parser via PyMuPDF with Heading Reconstruction.
+
+Pipeline:
+  1. Text-layer Gate — reject Scanned PDFs (near-empty text)
+  2. Extract reading-order blocks (Table Flattening via block order)
+  3. Heading Reconstruction: outline → font size → shared heuristics
+  4. Build DocumentTree + markdown (same contract as DOCX)
+"""
+
+from __future__ import annotations
+
+import statistics
+from pathlib import Path
+
+import fitz  # PyMuPDF
+
+from src.core.config import settings
+from src.core.exceptions import DocumentProcessingError
+from src.core.models import DocumentTree
+from src.documents.heading_heuristics import apply_heading_heuristics
+from src.documents.parser import (
+    ParseResult,
+    TextBlock,
+    build_document_tree,
+    tree_to_markdown,
+)
+
+
+def _median_chars_per_page(page_char_counts: list[int]) -> float:
+    if not page_char_counts:
+        return 0.0
+    return float(statistics.median(page_char_counts))
+
+
+def _enforce_text_layer_gate(doc: fitz.Document) -> None:
+    """Hard-reject PDFs without enough extractable text (Scanned PDFs)."""
+    page_counts: list[int] = []
+    for page in doc:
+        page_counts.append(len(page.get_text("text").strip()))
+
+    total = sum(page_counts)
+    median = _median_chars_per_page(page_counts)
+
+    if total < settings.pdf_min_total_chars or median < settings.pdf_min_median_chars_per_page:
+        raise DocumentProcessingError(
+            "PDF has no usable text layer (likely a scanned/image PDF). "
+            "OCR is not enabled for this benchmarker — only Text PDFs are supported. "
+            f"(total_chars={total}, median_chars_per_page={median:.0f}; "
+            f"need total>={settings.pdf_min_total_chars} and "
+            f"median>={settings.pdf_min_median_chars_per_page})"
+        )
+
+
+def _line_font_meta(line: dict) -> tuple[str, float, bool]:
+    """Return (text, max_font_size, any_bold) for a dict-line."""
+    spans = line.get("spans") or []
+    parts: list[str] = []
+    max_size = 0.0
+    any_bold = False
+    for span in spans:
+        text = (span.get("text") or "").strip()
+        if text:
+            parts.append(span.get("text") or "")
+        size = float(span.get("size") or 0)
+        if size > max_size:
+            max_size = size
+        # flags bit 4 (16) = bold in PyMuPDF
+        if int(span.get("flags") or 0) & 2**4:
+            any_bold = True
+    return ("".join(parts).strip(), max_size, any_bold)
+
+
+def _extract_blocks(doc: fitz.Document) -> list[TextBlock]:
+    """Extract reading-order text blocks with font metadata (tables flattened)."""
+    blocks: list[TextBlock] = []
+    for page_index, page in enumerate(doc):
+        page_dict = page.get_text("dict", flags=fitz.TEXT_PRESERVE_WHITESPACE)
+        for block in page_dict.get("blocks") or []:
+            if block.get("type") != 0:  # 0 = text
+                continue
+            for line in block.get("lines") or []:
+                text, font_size, bold = _line_font_meta(line)
+                if not text:
+                    continue
+                blocks.append(
+                    TextBlock(
+                        style_name="Normal",
+                        text=text,
+                        font_size=font_size,
+                        bold=bold,
+                        page=page_index + 1,
+                        locked=False,
+                    )
+                )
+    return blocks
+
+
+def _normalize(s: str) -> str:
+    return " ".join(s.split()).casefold()
+
+
+def _apply_outline_headings(doc: fitz.Document, blocks: list[TextBlock]) -> int:
+    """Mark blocks that match PDF outline/bookmark titles. Returns match count."""
+    toc = doc.get_toc(simple=True)
+    if not toc:
+        return 0
+
+    matched = 0
+    used: set[int] = set()
+
+    for level, title, page in toc:
+        title_norm = _normalize(title)
+        if not title_norm:
+            continue
+        level = max(1, min(int(level), 6))
+
+        # Prefer same page; fall back to any unused block with matching title
+        candidates = [
+            (i, b)
+            for i, b in enumerate(blocks)
+            if i not in used and not b.locked
+        ]
+        same_page = [(i, b) for i, b in candidates if b.page == page]
+        search_order = same_page + [(i, b) for i, b in candidates if b.page != page]
+
+        for i, block in search_order:
+            block_norm = _normalize(block.text)
+            if block_norm == title_norm or title_norm in block_norm or block_norm in title_norm:
+                block.style_name = f"Heading{level}"
+                block.locked = True
+                used.add(i)
+                matched += 1
+                break
+
+    return matched
+
+
+def _apply_font_headings(blocks: list[TextBlock]) -> int:
+    """Mark unlocked blocks as headings from font size clusters vs body size."""
+    sizes = [b.font_size for b in blocks if b.font_size > 0]
+    if len(sizes) < 3:
+        return 0
+
+    body_size = statistics.median(sizes)
+    if body_size <= 0:
+        return 0
+
+    # Distinct sizes clearly above body text
+    heading_sizes = sorted(
+        {round(s, 1) for s in sizes if s >= body_size * 1.2},
+        reverse=True,
+    )
+    if not heading_sizes:
+        # Bold + short lines at/near body size as weak H2
+        upgraded = 0
+        for block in blocks:
+            if block.locked or block.style_name != "Normal":
+                continue
+            if block.bold and len(block.text) <= 150:
+                block.style_name = "Heading2"
+                upgraded += 1
+        return upgraded
+
+    size_to_level: dict[float, int] = {}
+    for idx, size in enumerate(heading_sizes):
+        size_to_level[size] = 1 if idx == 0 else 2
+
+    upgraded = 0
+    for block in blocks:
+        if block.locked or block.style_name != "Normal":
+            continue
+        if len(block.text) > 150:
+            continue
+        rounded = round(block.font_size, 1)
+        level = size_to_level.get(rounded)
+        if level is None:
+            continue
+        block.style_name = f"Heading{level}"
+        upgraded += 1
+
+    return upgraded
+
+
+def parse_pdf(file_path: str | Path) -> ParseResult:
+    """Parse a Text PDF into DocumentTree + markdown.
+
+    Raises DocumentProcessingError for missing files, Scanned PDFs, or empty text.
+    """
+    path = Path(file_path)
+    if not path.exists():
+        raise DocumentProcessingError(f"File not found: {path}")
+    if path.suffix.lower() != ".pdf":
+        raise DocumentProcessingError(f"Not a PDF: {path.suffix}")
+
+    try:
+        doc = fitz.open(path)
+    except Exception as exc:
+        raise DocumentProcessingError(f"Failed to open PDF: {exc}") from exc
+
+    try:
+        if doc.page_count < 1:
+            raise DocumentProcessingError("PDF has no pages")
+
+        _enforce_text_layer_gate(doc)
+        blocks = _extract_blocks(doc)
+        if not blocks:
+            raise DocumentProcessingError("PDF contains no extractable text blocks")
+
+        _apply_outline_headings(doc, blocks)
+        _apply_font_headings(blocks)
+
+        # Gap-fill remaining Normal blocks (outline titles stay locked).
+        # When outline/font found nothing, this is a full heuristic pass.
+        apply_heading_heuristics(blocks, only_when_no_headings=False)
+
+        root = build_document_tree(blocks)
+        tree = DocumentTree(root=root)
+        markdown = tree_to_markdown(root)
+        plain_text = "\n".join(b.text for b in blocks if b.text)
+
+        return ParseResult(
+            tree=tree,
+            markdown=markdown,
+            plain_text=plain_text,
+            paragraph_count=len(blocks),
+        )
+    finally:
+        doc.close()

src/documents/routes.py

@@ -1,8 +1,8 @@
 """Document and strategy API routes.
 
 Endpoints:
-  POST   /documents              Upload a .docx file
+  POST   /documents              Upload a .docx / .doc / .pdf file
-  POST   /documents/{id}/process  Run chunking strategies (stub until Phase 2)
+  POST   /documents/{id}/process  Run chunking strategies
   DELETE /documents/{id}          Remove document + vectors
   GET    /strategies              List available chunking strategies
 """
@@ -10,7 +10,6 @@ Endpoints:
 from fastapi import APIRouter, File, UploadFile
 
 from src.core.exceptions import DocumentProcessingError
-from src.core.models import PaginatedResponse, StrategyName
 from src.documents.models import (
     DeleteResponse,
     DocumentResponse,
@@ -20,6 +19,7 @@ from src.documents.models import (
     StrategiesResponse,
     StrategyInfo,
 )
+from src.documents.parser import SUPPORTED_SUFFIXES
 from src.documents import service
 
 router = APIRouter()
@@ -39,11 +39,15 @@ async def list_documents(offset: int = 0, limit: int = 50):
 
 @router.post("/documents", response_model=DocumentResponse, status_code=201)
 async def upload_document(file: UploadFile = File(...)):
-    """Upload a .docx file. Parses it, stores the document tree in SQLite."""
+    """Upload a document. Parses it, stores the document tree in SQLite."""
     if not file.filename:
         raise DocumentProcessingError("No filename provided")
-    if not file.filename.lower().endswith((".docx", ".doc")):
+
-        raise DocumentProcessingError("Only .docx and .doc files are supported")
+    lower = file.filename.lower()
+    if not any(lower.endswith(s) for s in SUPPORTED_SUFFIXES):
+        raise DocumentProcessingError(
+            f"Only {', '.join(SUPPORTED_SUFFIXES)} files are supported"
+        )
 
     content = await file.read()
     if not content:
@@ -61,10 +65,7 @@ async def upload_document(file: UploadFile = File(...)):
 
 @router.post("/documents/{doc_id}/process", response_model=ProcessResponse)
 async def process_document(doc_id: str, request: ProcessRequest):
-    """Run selected chunking strategies on an uploaded document.
+    """Run selected chunking strategies on an uploaded document."""
-
-    Currently returns stub results until Phase 2 implements the strategies.
-    """
     return service.process_document(doc_id, request)
 
 

src/documents/service.py

@@ -16,7 +16,7 @@ from src.documents.models import (
     ProcessResponse,
     StrategyResult,
 )
-from src.documents.parser import parse_docx
+from src.documents.parser import parse_document, SUPPORTED_SUFFIXES
 from src.storage import sqlite as db
 from src.storage import qdrant as qdr
 
@@ -49,17 +49,22 @@ STRATEGY_DESCRIPTIONS: dict[StrategyName, str] = {
 # ── Upload ─────────────────────────────────────────────────────────
 
 def upload_document(filename: str, file_bytes: bytes) -> dict[str, Any]:
-    """Parse a .docx upload, store in SQLite, return document record."""
+    """Parse an uploaded document, store in SQLite, return document record."""
     import tempfile
     from pathlib import Path
 
-    suffix = Path(filename).suffix or ".docx"
+    suffix = Path(filename).suffix.lower()
+    if suffix not in SUPPORTED_SUFFIXES:
+        raise DocumentProcessingError(
+            f"Only {', '.join(SUPPORTED_SUFFIXES)} files are supported"
+        )
+
     with tempfile.NamedTemporaryFile(suffix=suffix, delete=False) as tmp:
         tmp.write(file_bytes)
         tmp_path = tmp.name
 
     try:
-        result = parse_docx(tmp_path)
+        result = parse_document(tmp_path)
     finally:
         Path(tmp_path).unlink(missing_ok=True)
 

src/static/index.html

@@ -276,6 +276,35 @@ async function api(path, opts = {}) {
   return res.json();
 }
 
+// -- Format filter helpers (ADR-0017) -----------------------
+function isPdfFilename(name) {
+  return (name || '').toLowerCase().endsWith('.pdf');
+}
+function isWordFilename(name) {
+  const n = (name || '').toLowerCase();
+  return n.endsWith('.doc') || n.endsWith('.docx');
+}
+function filterDocuments(docs, format) {
+  if (format === 'pdf') return (docs || []).filter(d => isPdfFilename(d.filename));
+  if (format === 'word') return (docs || []).filter(d => isWordFilename(d.filename));
+  return docs || [];
+}
+function filterExperiments(exps, format) {
+  if (format === 'pdf') return (exps || []).filter(e => isPdfFilename(e.document_filename || ''));
+  if (format === 'word') return (exps || []).filter(e => isWordFilename(e.document_filename || ''));
+  return exps || [];
+}
+function formatAccept(format) {
+  if (format === 'pdf') return '.pdf';
+  if (format === 'word') return '.doc,.docx';
+  return '.doc,.docx,.pdf';
+}
+function formatDropLabel(format) {
+  if (format === 'pdf') return '.pdf';
+  if (format === 'word') return '.doc or .docx';
+  return '.doc, .docx, or .pdf';
+}
+
 // -- Toast system -------------------------------------------
 let _toastId = 0;
 function ToastContainer({ toasts, removeToast }) {
@@ -329,10 +358,10 @@ function HomeTab() {
     React.createElement('div', { className: 'card mt-4' },
       React.createElement('div', { className: 'card-title' }, '⚡ Quick Start'),
       React.createElement('ol', { style: { paddingLeft: '20px', lineHeight: '2' } },
-        React.createElement('li', null, 'Upload a document in the ', React.createElement('b', null, 'Documents'), ' tab'),
+        React.createElement('li', null, 'Upload a Word document in ', React.createElement('b', null, 'Documents'), ' or a Text PDF in ', React.createElement('b', null, 'PDF')),
         React.createElement('li', null, 'Process it with chunking strategies'),
-        React.createElement('li', null, 'Ask a question in the ', React.createElement('b', null, 'Query'), ' tab'),
+        React.createElement('li', null, 'Ask a question in ', React.createElement('b', null, 'Query'), ' (or inside PDF Workspace)'),
-        React.createElement('li', null, 'Run a full benchmark in the ', React.createElement('b', null, 'Benchmarks'), ' tab'),
+        React.createElement('li', null, 'Run a full benchmark in ', React.createElement('b', null, 'Benchmarks'), ' / PDF Workspace'),
         React.createElement('li', null, 'Check system health in the ', React.createElement('b', null, 'Admin'), ' tab')
       )
     )
@@ -340,12 +369,13 @@ function HomeTab() {
 }
 
 // -- Tab: Documents -----------------------------------------
-function DocumentsTab({ documents, setDocuments, strategies, addToast }) {
+function DocumentsTab({ documents, setDocuments, strategies, addToast, formatFilter = 'word', hideTitle = false }) {
   const [uploading, setUploading] = useState(false);
   const [processing, setProcessing] = useState({});
   const [selectedStrategies, setSelectedStrategies] = useState({});
   const [dragOver, setDragOver] = useState(false);
   const fileRef = useRef(null);
+  const visibleDocs = filterDocuments(documents, formatFilter);
 
   const fetchDocs = useCallback(() => {
     api('/documents').then(d => setDocuments(d.items || [])).catch(() => {});
@@ -355,6 +385,15 @@ function DocumentsTab({ documents, setDocuments, strategies, addToast }) {
 
   const handleUpload = async (file) => {
     if (!file) return;
+    const name = file.name || '';
+    if (formatFilter === 'pdf' && !isPdfFilename(name)) {
+      addToast('Only .pdf files are allowed here', 'error');
+      return;
+    }
+    if (formatFilter === 'word' && !isWordFilename(name)) {
+      addToast('Only .doc / .docx files are allowed here', 'error');
+      return;
+    }
     setUploading(true);
     try {
       const form = new FormData();
@@ -425,7 +464,7 @@ function DocumentsTab({ documents, setDocuments, strategies, addToast }) {
   };
 
   return React.createElement('div', null,
-    React.createElement('h1', { style: { color: 'var(--text-heading)', marginBottom: '16px', fontSize: '22px' } }, 'Documents'),
+    !hideTitle && React.createElement('h1', { style: { color: 'var(--text-heading)', marginBottom: '16px', fontSize: '22px' } }, 'Documents'),
 
     // Upload zone
     React.createElement('div', {
@@ -439,9 +478,9 @@ function DocumentsTab({ documents, setDocuments, strategies, addToast }) {
       React.createElement('div', { className: 'text' },
         uploading
           ? 'Uploading...'
-          : React.createElement('span', null, 'Drag & drop a ', React.createElement('strong', null, '.doc or .docx'), ' file, or click to browse')),
+          : React.createElement('span', null, 'Drag & drop a ', React.createElement('strong', null, formatDropLabel(formatFilter)), ' file, or click to browse')),
       React.createElement('input', {
-        ref: fileRef, type: 'file', accept: '.doc,.docx', style: { display: 'none' },
+        ref: fileRef, type: 'file', accept: formatAccept(formatFilter), style: { display: 'none' },
         onChange: (e) => handleUpload(e.target.files[0])
       })
     ),
@@ -449,13 +488,13 @@ function DocumentsTab({ documents, setDocuments, strategies, addToast }) {
     // Documents table
     React.createElement('div', { className: 'card mt-4' },
       React.createElement('div', { className: 'flex-between mb-2' },
-        React.createElement('div', { className: 'card-title mb-0' }, `Uploaded Documents (${documents.length})`),
+        React.createElement('div', { className: 'card-title mb-0' }, `Uploaded Documents (${visibleDocs.length})`),
         React.createElement('button', { className: 'btn btn-secondary btn-sm', onClick: fetchDocs }, '↻ Refresh')
       ),
-      documents.length === 0
+      visibleDocs.length === 0
         ? React.createElement('div', { className: 'empty-state' },
             React.createElement('div', { className: 'icon' }, '📭'),
-            React.createElement('div', null, 'No documents uploaded yet'))
+            React.createElement('div', null, formatFilter === 'pdf' ? 'No PDF documents uploaded yet' : 'No documents uploaded yet'))
         : React.createElement('table', null,
             React.createElement('thead', null,
               React.createElement('tr', null,
@@ -468,7 +507,7 @@ function DocumentsTab({ documents, setDocuments, strategies, addToast }) {
               )
             ),
             React.createElement('tbody', null,
-              documents.map(doc =>
+              visibleDocs.map(doc =>
                 React.createElement('tr', { key: doc.id },
                   React.createElement('td', null,
                     React.createElement('span', { className: 'truncate', style: { display: 'inline-block' } }, doc.filename)),
@@ -534,10 +573,11 @@ function DocumentsTab({ documents, setDocuments, strategies, addToast }) {
 }
 
 // -- Tab: Query ---------------------------------------------
-function QueryTab({ documents, strategies, addToast }) {
+function QueryTab({ documents, strategies, addToast, formatFilter = 'word', hideTitle = false }) {
   const [form, setForm] = useState({ document_id: '', strategy: '', question: '', top_k: 5 });
   const [result, setResult] = useState(null);
   const [loading, setLoading] = useState(false);
+  const visibleDocs = filterDocuments(documents, formatFilter);
 
   const handleQuery = async () => {
     if (!form.document_id || !form.strategy || !form.question.trim()) {
@@ -557,7 +597,7 @@ function QueryTab({ documents, strategies, addToast }) {
   };
 
   return React.createElement('div', null,
-    React.createElement('h1', { style: { color: 'var(--text-heading)', marginBottom: '16px', fontSize: '22px' } }, 'Query'),
+    !hideTitle && React.createElement('h1', { style: { color: 'var(--text-heading)', marginBottom: '16px', fontSize: '22px' } }, 'Query'),
 
     React.createElement('div', { className: 'card' },
       React.createElement('div', { className: 'row' },
@@ -568,7 +608,7 @@ function QueryTab({ documents, strategies, addToast }) {
             onChange: e => setForm({ ...form, document_id: e.target.value })
           },
             React.createElement('option', { value: '' }, 'Select document...'),
-            documents.map(d => React.createElement('option', { key: d.id, value: d.id }, d.filename))
+            visibleDocs.map(d => React.createElement('option', { key: d.id, value: d.id }, d.filename))
           )
         ),
         React.createElement('div', { className: 'col' },
@@ -868,13 +908,15 @@ function ComparisonView({ experiments, addToast, onBack }) {
 }
 
 // -- Tab: Benchmarks ----------------------------------------
-function BenchmarksTab({ documents, strategies, addToast, questionsFile }) {
+function BenchmarksTab({ documents, strategies, addToast, questionsFile, formatFilter = 'word', hideTitle = false }) {
   const [experiments, setExperiments] = useState([]);
   const [form, setForm] = useState({
     document_id: '', strategies: strategies.map(s => s.name),
     questions_file: questionsFile, top_k: 5, dry_run: false
   });
   const [running, setRunning] = useState(false);
+  const visibleDocs = filterDocuments(documents, formatFilter);
+  const visibleExps = filterExperiments(experiments, formatFilter);
 
   // Comparison state
   const [selectedExps, setSelectedExps] = useState(new Set());
@@ -914,10 +956,10 @@ function BenchmarksTab({ documents, strategies, addToast, questionsFile }) {
   };
 
   const selectAllExps = () => {
-    if (selectedExps.size === experiments.length) {
+    if (selectedExps.size === visibleExps.length) {
       setSelectedExps(new Set());
     } else {
-      setSelectedExps(new Set(experiments.map(e => e.id)));
+      setSelectedExps(new Set(visibleExps.map(e => e.id)));
     }
   };
 
@@ -975,7 +1017,7 @@ function BenchmarksTab({ documents, strategies, addToast, questionsFile }) {
     }
     setRunning(true);
     try {
-      const result = await api('/benchmarks', { method: 'POST', body: form });
+      await api('/benchmarks', { method: 'POST', body: form });
       addToast(`Benchmark ${form.dry_run ? 'estimate' : 'complete'}`, 'success');
       if (!form.dry_run) fetchExperiments();
     } catch (e) {
@@ -995,7 +1037,7 @@ function BenchmarksTab({ documents, strategies, addToast, questionsFile }) {
   }
 
   return React.createElement('div', null,
-    React.createElement('h1', { style: { color: 'var(--text-heading)', marginBottom: '16px', fontSize: '22px' } }, 'Benchmarks'),
+    !hideTitle && React.createElement('h1', { style: { color: 'var(--text-heading)', marginBottom: '16px', fontSize: '22px' } }, 'Benchmarks'),
 
     // Run benchmark form
     React.createElement('div', { className: 'card' },
@@ -1008,7 +1050,7 @@ function BenchmarksTab({ documents, strategies, addToast, questionsFile }) {
             onChange: e => setForm({ ...form, document_id: e.target.value })
           },
             React.createElement('option', { value: '' }, 'Select document...'),
-            documents.map(d => React.createElement('option', { key: d.id, value: d.id }, d.filename))
+            visibleDocs.map(d => React.createElement('option', { key: d.id, value: d.id }, d.filename))
           )
         ),
         React.createElement('div', { className: 'col', style: { maxWidth: '120px' } },
@@ -1070,7 +1112,7 @@ function BenchmarksTab({ documents, strategies, addToast, questionsFile }) {
     // Experiments list
     React.createElement('div', { className: 'card mt-4' },
       React.createElement('div', { className: 'flex-between mb-2' },
-        React.createElement('div', { className: 'card-title mb-0' }, `Experiments (${experiments.length})`),
+        React.createElement('div', { className: 'card-title mb-0' }, `Experiments (${visibleExps.length})`),
         React.createElement('div', { style: { display: 'flex', gap: '6px', alignItems: 'center' } },
           selectedExps.size >= 2 ? React.createElement('button', {
             className: 'btn btn-primary btn-sm',
@@ -1080,17 +1122,17 @@ function BenchmarksTab({ documents, strategies, addToast, questionsFile }) {
           React.createElement('button', { className: 'btn btn-secondary btn-sm', onClick: fetchExperiments }, '↻ Refresh')
         )
       ),
-      experiments.length === 0
+      visibleExps.length === 0
         ? React.createElement('div', { className: 'empty-state' },
             React.createElement('div', { className: 'icon' }, '📊'),
-            React.createElement('div', null, 'No experiments yet'))
+            React.createElement('div', null, formatFilter === 'pdf' ? 'No PDF experiments yet' : 'No experiments yet'))
         : React.createElement('table', null,
             React.createElement('thead', null,
               React.createElement('tr', null,
                 React.createElement('th', { style: { width: '36px' } },
                   React.createElement('input', {
                     type: 'checkbox',
-                    checked: experiments.length > 0 && selectedExps.size === experiments.length,
+                    checked: visibleExps.length > 0 && selectedExps.size === visibleExps.length,
                     onChange: selectAllExps,
                     style: { cursor: 'pointer' }
                   })
@@ -1104,7 +1146,7 @@ function BenchmarksTab({ documents, strategies, addToast, questionsFile }) {
               )
             ),
             React.createElement('tbody', null,
-              experiments.map(exp => React.createElement(React.Fragment, { key: exp.id },
+              visibleExps.map(exp => React.createElement(React.Fragment, { key: exp.id },
                 React.createElement('tr', {
                   className: selectedExps.has(exp.id) ? 'cmp-highlight' : '',
                   style: { cursor: 'pointer' },
@@ -1228,6 +1270,165 @@ function CollapseSection({ title, icon, open, onToggle, badge, children }) {
   );
 }
 
+// -- Shared: Chunk Preview Panel ----------------------------
+function ChunkPreviewPanel({ documents, strategies, addToast, formatFilter = 'all' }) {
+  const visibleDocs = filterDocuments(documents, formatFilter);
+  const [chunkDocId, setChunkDocId] = useState('');
+  const [chunkStrategy, setChunkStrategy] = useState('');
+  const [chunkData, setChunkData] = useState(null);
+  const [chunkLoading, setChunkLoading] = useState(false);
+  const [expandedChunks, setExpandedChunks] = useState({});
+
+  const loadChunks = async () => {
+    if (!chunkDocId) { addToast('Select a document', 'error'); return; }
+    setChunkLoading(true);
+    setChunkData(null);
+    setExpandedChunks({});
+    try {
+      let url = `/admin/chunks/${chunkDocId}`;
+      if (chunkStrategy) url += `?strategy=${chunkStrategy}`;
+      const data = await api(url);
+      setChunkData(data);
+    } catch (e) { addToast(`Chunk load failed: ${e.message}`, 'error'); }
+    finally { setChunkLoading(false); }
+  };
+
+  return React.createElement(React.Fragment, null,
+    React.createElement('div', { className: 'row mb-4' },
+      React.createElement('div', { className: 'col' },
+        React.createElement('label', null, 'Document'),
+        React.createElement('select', {
+          value: chunkDocId,
+          onChange: e => { setChunkDocId(e.target.value); setChunkData(null); }
+        },
+          React.createElement('option', { value: '' }, 'Select document...'),
+          visibleDocs.map(d => React.createElement('option', { key: d.id, value: d.id }, d.filename))
+        )
+      ),
+      React.createElement('div', { className: 'col' },
+        React.createElement('label', null, 'Strategy (optional)'),
+        React.createElement('select', {
+          value: chunkStrategy,
+          onChange: e => { setChunkStrategy(e.target.value); setChunkData(null); }
+        },
+          React.createElement('option', { value: '' }, 'All strategies'),
+          strategies.map(s => React.createElement('option', { key: s.name, value: s.name }, s.name))
+        )
+      ),
+      React.createElement('div', { style: { flex: 'none' } },
+        React.createElement('button', {
+          className: 'btn btn-primary', onClick: loadChunks, disabled: chunkLoading || !chunkDocId,
+        }, chunkLoading ? React.createElement('span', { className: 'spinner' }) : 'Load Chunks')
+      )
+    ),
+    chunkData && Object.entries(chunkData.strategies || {}).map(([stratName, stratData]) =>
+      React.createElement('div', { key: stratName, style: { marginBottom: '16px' } },
+        React.createElement('div', { className: 'flex-between mb-2' },
+          React.createElement('h3', { style: { fontSize: '14px', fontWeight: 600, color: 'var(--text-heading)' } },
+            `${stratName} `,
+            React.createElement('span', { className: 'badge badge-accent' }, `${stratData.count} chunks`)),
+          stratData.error ? React.createElement('span', { className: 'badge badge-danger' }, stratData.error) : null
+        ),
+        stratData.count === 0
+          ? React.createElement('div', { className: 'text-sm text-muted', style: { padding: '8px 0' } }, 'No chunks for this strategy')
+          : React.createElement('table', null,
+              React.createElement('thead', null,
+                React.createElement('tr', null,
+                  React.createElement('th', { style: { width: '40px' } }, '#'),
+                  React.createElement('th', null, 'Text'),
+                  React.createElement('th', { style: { width: '60px' } }, 'Tokens'),
+                  React.createElement('th', { style: { width: '60px' } }, 'Chars'),
+                )
+              ),
+              React.createElement('tbody', null,
+                (stratData.chunks || []).map((chunk, i) => {
+                  const key = `${stratName}-${chunk.chunk_index ?? i}`;
+                  const isExpanded = expandedChunks[key];
+                  return React.createElement(React.Fragment, { key },
+                    React.createElement('tr', {
+                      className: 'chunk-row',
+                      onClick: () => setExpandedChunks(prev => ({ ...prev, [key]: !prev[key] })),
+                    },
+                      React.createElement('td', { className: 'text-muted text-sm' }, chunk.chunk_index ?? i + 1),
+                      React.createElement('td', { className: 'text-sm' },
+                        React.createElement('span', { style: { display: '-webkit-box', WebkitLineClamp: isExpanded ? 'unset' : 1, WebkitBoxOrient: 'vertical', overflow: isExpanded ? 'visible' : 'hidden' } },
+                          chunk.text || '')),
+                      React.createElement('td', { className: 'text-sm text-muted' }, chunk.token_count),
+                      React.createElement('td', { className: 'text-sm text-muted' }, chunk.character_count),
+                    ),
+                    isExpanded ? React.createElement('tr', null,
+                      React.createElement('td', { colSpan: 4 },
+                        React.createElement('div', { className: 'chunk-detail' },
+                          React.createElement('div', null, chunk.text || '(empty)'),
+                          React.createElement('div', { className: 'meta' },
+                            `chunk_id: ${chunk.chunk_id} | parent: ${chunk.parent_id || 'none'}`)
+                        )
+                      )
+                    ) : null
+                  );
+                })
+              )
+            )
+      )
+    )
+  );
+}
+
+// -- Tab: PDF Workspace -------------------------------------
+function PdfWorkspaceTab({ documents, setDocuments, strategies, addToast, questionsFile }) {
+  const [openSections, setOpenSections] = useState({
+    upload: true, chunks: false, query: false, benchmarks: false,
+  });
+  const toggle = (key) => setOpenSections(prev => ({ ...prev, [key]: !prev[key] }));
+  const pdfCount = filterDocuments(documents, 'pdf').length;
+
+  return React.createElement('div', null,
+    React.createElement('h1', { style: { color: 'var(--text-heading)', marginBottom: '8px', fontSize: '22px' } }, 'PDF Workspace'),
+    React.createElement('p', { className: 'text-muted mb-4', style: { maxWidth: '640px' } },
+      'Text PDF only — upload, process, preview chunks, query, and benchmark. Scanned/image PDFs are rejected at upload.'),
+
+    React.createElement(CollapseSection, {
+      title: 'Upload & Process', icon: '📄', open: openSections.upload,
+      onToggle: () => toggle('upload'),
+      badge: pdfCount ? `${pdfCount} PDFs` : '0',
+    },
+      React.createElement(DocumentsTab, {
+        documents, setDocuments, strategies, addToast,
+        formatFilter: 'pdf', hideTitle: true,
+      })
+    ),
+
+    React.createElement(CollapseSection, {
+      title: 'Chunk Preview', icon: '📦', open: openSections.chunks,
+      onToggle: () => toggle('chunks'),
+    },
+      React.createElement(ChunkPreviewPanel, {
+        documents, strategies, addToast, formatFilter: 'pdf',
+      })
+    ),
+
+    React.createElement(CollapseSection, {
+      title: 'Query', icon: '⚡', open: openSections.query,
+      onToggle: () => toggle('query'),
+    },
+      React.createElement(QueryTab, {
+        documents, strategies, addToast,
+        formatFilter: 'pdf', hideTitle: true,
+      })
+    ),
+
+    React.createElement(CollapseSection, {
+      title: 'Benchmarks', icon: '📊', open: openSections.benchmarks,
+      onToggle: () => toggle('benchmarks'),
+    },
+      React.createElement(BenchmarksTab, {
+        documents, strategies, addToast, questionsFile,
+        formatFilter: 'pdf', hideTitle: true,
+      })
+    )
+  );
+}
+
 // -- Tab: Admin ---------------------------------------------
 function AdminTab({ addToast, documents, strategies, setActiveTab, setQuestionsFile }) {
   // Collapse state for each section
@@ -1253,27 +1454,6 @@ function AdminTab({ addToast, documents, strategies, setActiveTab, setQuestionsF
   // -- Qdrant state --
   const [collectionsData, setCollectionsData] = useState([]);
 
-  // -- Chunk Preview state --
-  const [chunkDocId, setChunkDocId] = useState('');
-  const [chunkStrategy, setChunkStrategy] = useState('');
-  const [chunkData, setChunkData] = useState(null);
-  const [chunkLoading, setChunkLoading] = useState(false);
-  const [expandedChunks, setExpandedChunks] = useState({});
-
-  const loadChunks = async () => {
-    if (!chunkDocId) { addToast('Select a document', 'error'); return; }
-    setChunkLoading(true);
-    setChunkData(null);
-    setExpandedChunks({});
-    try {
-      let url = `/admin/chunks/${chunkDocId}`;
-      if (chunkStrategy) url += `?strategy=${chunkStrategy}`;
-      const data = await api(url);
-      setChunkData(data);
-    } catch (e) { addToast(`Chunk load failed: ${e.message}`, 'error'); }
-    finally { setChunkLoading(false); }
-  };
-
   // -- Questions state --
   const [qFiles, setQFiles] = useState([]);
   const [qLoading, setQLoading] = useState(false);
@@ -1425,85 +1605,10 @@ function AdminTab({ addToast, documents, strategies, setActiveTab, setQuestionsF
     React.createElement(CollapseSection, {
       title: '📦 Chunk Preview', icon: '', open: openSections.chunks,
       onToggle: () => toggle('chunks'),
-      badge: chunkData ? `${chunkData.strategies ? Object.values(chunkData.strategies).reduce((a, s) => a + (s.count || 0), 0) : 0} chunks` : null,
     },
-      React.createElement('div', { className: 'row mb-4' },
+      React.createElement(ChunkPreviewPanel, {
-        React.createElement('div', { className: 'col' },
+        documents, strategies, addToast, formatFilter: 'all',
-          React.createElement('label', null, 'Document'),
+      })
-          React.createElement('select', {
-            value: chunkDocId,
-            onChange: e => { setChunkDocId(e.target.value); setChunkData(null); }
-          },
-            React.createElement('option', { value: '' }, 'Select document...'),
-            documents.map(d => React.createElement('option', { key: d.id, value: d.id }, d.filename))
-          )
-        ),
-        React.createElement('div', { className: 'col' },
-          React.createElement('label', null, 'Strategy (optional)'),
-          React.createElement('select', {
-            value: chunkStrategy,
-            onChange: e => { setChunkStrategy(e.target.value); setChunkData(null); }
-          },
-            React.createElement('option', { value: '' }, 'All strategies'),
-            strategies.map(s => React.createElement('option', { key: s.name, value: s.name }, s.name))
-          )
-        ),
-        React.createElement('div', { style: { flex: 'none' } },
-          React.createElement('button', {
-            className: 'btn btn-primary', onClick: loadChunks, disabled: chunkLoading || !chunkDocId,
-          }, chunkLoading ? React.createElement('span', { className: 'spinner' }) : 'Load Chunks')
-        )
-      ),
-      chunkData && Object.entries(chunkData.strategies || {}).map(([stratName, stratData]) =>
-        React.createElement('div', { key: stratName, style: { marginBottom: '16px' } },
-          React.createElement('div', { className: 'flex-between mb-2' },
-            React.createElement('h3', { style: { fontSize: '14px', fontWeight: 600, color: 'var(--text-heading)' } },
-              `${stratName} `,
-              React.createElement('span', { className: 'badge badge-accent' }, `${stratData.count} chunks`)),
-            stratData.error ? React.createElement('span', { className: 'badge badge-danger' }, stratData.error) : null
-          ),
-          stratData.count === 0
-            ? React.createElement('div', { className: 'text-sm text-muted', style: { padding: '8px 0' } }, 'No chunks for this strategy')
-            : React.createElement('table', null,
-                React.createElement('thead', null,
-                  React.createElement('tr', null,
-                    React.createElement('th', { style: { width: '40px' } }, '#'),
-                    React.createElement('th', null, 'Text'),
-                    React.createElement('th', { style: { width: '60px' } }, 'Tokens'),
-                    React.createElement('th', { style: { width: '60px' } }, 'Chars'),
-                  )
-                ),
-                React.createElement('tbody', null,
-                  (stratData.chunks || []).map((chunk, i) => {
-                    const key = `${stratName}-${chunk.chunk_index ?? i}`;
-                    const isExpanded = expandedChunks[key];
-                    return React.createElement(React.Fragment, { key },
-                      React.createElement('tr', {
-                        className: 'chunk-row',
-                        onClick: () => setExpandedChunks(prev => ({ ...prev, [key]: !prev[key] })),
-                      },
-                        React.createElement('td', { className: 'text-muted text-sm' }, chunk.chunk_index ?? i + 1),
-                        React.createElement('td', { className: 'text-sm' },
-                          React.createElement('span', { style: { display: '-webkit-box', WebkitLineClamp: isExpanded ? 'unset' : 1, WebkitBoxOrient: 'vertical', overflow: isExpanded ? 'visible' : 'hidden' } },
-                            chunk.text || '')),
-                        React.createElement('td', { className: 'text-sm text-muted' }, chunk.token_count),
-                        React.createElement('td', { className: 'text-sm text-muted' }, chunk.character_count),
-                      ),
-                      isExpanded ? React.createElement('tr', null,
-                        React.createElement('td', { colSpan: 4 },
-                          React.createElement('div', { className: 'chunk-detail' },
-                            React.createElement('div', null, chunk.text || '(empty)'),
-                            React.createElement('div', { className: 'meta' },
-                              `chunk_id: ${chunk.chunk_id} | parent: ${chunk.parent_id || 'none'}`)
-                          )
-                        )
-                      ) : null
-                    );
-                  })
-                )
-              )
-        )
-      )
     ),
 
     // -- 4. Questions Management --
@@ -1651,6 +1756,7 @@ function App() {
 
   useEffect(() => {
     api('/strategies').then(d => setStrategies(d.strategies || [])).catch(() => {});
+    api('/documents').then(d => setDocuments(d.items || [])).catch(() => {});
   }, []);
 
   const addToast = useCallback((message, type = 'success') => {
@@ -1666,6 +1772,7 @@ function App() {
   const tabs = [
     { id: 'home', label: 'Home' },
     { id: 'documents', label: 'Documents' },
+    { id: 'pdf', label: 'PDF' },
     { id: 'query', label: 'Query' },
     { id: 'benchmarks', label: 'Benchmarks' },
     { id: 'admin', label: 'Admin' },
@@ -1675,11 +1782,13 @@ function App() {
     switch (activeTab) {
       case 'home': return React.createElement(HomeTab);
       case 'documents': return React.createElement(DocumentsTab, {
-        documents, setDocuments, strategies, addToast });
+        documents, setDocuments, strategies, addToast, formatFilter: 'word' });
+      case 'pdf': return React.createElement(PdfWorkspaceTab, {
+        documents, setDocuments, strategies, addToast, questionsFile });
       case 'query': return React.createElement(QueryTab, {
-        documents, strategies, addToast });
+        documents, strategies, addToast, formatFilter: 'word' });
       case 'benchmarks': return React.createElement(BenchmarksTab, {
-        documents, strategies, addToast, questionsFile });
+        documents, strategies, addToast, questionsFile, formatFilter: 'word' });
       case 'admin': return React.createElement(AdminTab, {
         addToast, documents, strategies, setActiveTab, setQuestionsFile });
       default: return null;