docsmind 0.2.0__tar.gz → 0.3.0__tar.gz

{docsmind-0.2.0 → docsmind-0.3.0}/CHANGELOG.md

@@ -2,6 +2,34 @@
 
 All notable changes to this project will be documented in this file.
 
+## [0.3.0] - 2026-10-03
+
+### Added
+
+- Bundled frontend UI in the Python package: release UI assets are copied into
+  `src/docsmind/server/ui` and served by `docsmind serve` at `/`.
+- `scripts/bundle_frontend.py` helper to copy `../frontend/dist` into the package
+  before publishing.
+- `docsmind delete <version-id> [-y]` command to remove one ingested version and
+  its derived sections/chunks/images/tables.
+- HTTP `DELETE /api/documents/{version_id}` endpoint.
+
+### Changed
+
+- `docsmind serve` now serves the bundled SPA (when present), in addition to
+  `/api/*` and `/blobs/*`.
+- Ingestion now checks `content_hash` before parsing and raises a friendly
+  "already ingested" error instead of surfacing a raw Postgres unique-constraint
+  failure.
+
+### Fixed
+
+- Image extraction de-duplicates repeated embedded images (e.g. page logo reused
+  across many pages) using perceptual hash, preventing inflated image counts.
+- API duplicate-ingest responses now return HTTP 409 with structured details.
+
+
+
 ## [0.2.0] - 2026-09-27
 
 First functional release: documents can now be ingested from PDF into
@@ -70,9 +98,7 @@ implemented" below).
 - Embeddings and hybrid vector/keyword search. Chunks are stored without
   embeddings, and `hybrid_search` raises `NotImplementedError`.
 - Image captioning with a vision model.
-- The chat agent behind `docsmind chat` and the change-analysis subagent
-  behind `docsmind diff`. Both commands exist but have no implementation
-  behind them yet.
+- The chat agent behind `docsmind chat`.
 - DOCX and plain-text parsers, S3/Supabase blob storage, and the server/UI.
 - Multi-column reading order: PDFs with genuine multi-column layouts may have
   their text interleaved in the saved full text.

{docsmind-0.2.0 → docsmind-0.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: docsmind
-Version: 0.2.0
+Version: 0.3.0
 Summary: Chat with your documents. Version-aware retrieval, change analysis, and an editable table workspace, backed by Postgres/pgvector.
 Project-URL: Homepage, https://github.com/yauheniya-ai/docsmind
 Project-URL: Repository, https://github.com/yauheniya-ai/docsmind
@@ -29,11 +29,13 @@ Requires-Dist: pydantic>=2.6
 Requires-Dist: pymupdf>=1.24
 Requires-Dist: rich>=13.7
 Requires-Dist: sqlalchemy[asyncio]>=2.0
+Requires-Dist: tiktoken>=0.7
 Requires-Dist: typer>=0.12
 Provides-Extra: all
 Requires-Dist: anthropic>=0.34; extra == 'all'
 Requires-Dist: fastapi>=0.111; extra == 'all'
 Requires-Dist: openai>=1.30; extra == 'all'
+Requires-Dist: python-multipart>=0.0.9; extra == 'all'
 Requires-Dist: uvicorn[standard]>=0.30; extra == 'all'
 Provides-Extra: anthropic
 Requires-Dist: anthropic>=0.34; extra == 'anthropic'
@@ -49,6 +51,7 @@ Provides-Extra: openai
 Requires-Dist: openai>=1.30; extra == 'openai'
 Provides-Extra: server
 Requires-Dist: fastapi>=0.111; extra == 'server'
+Requires-Dist: python-multipart>=0.0.9; extra == 'server'
 Requires-Dist: uvicorn[standard]>=0.30; extra == 'server'
 Description-Content-Type: text/markdown
 
@@ -58,8 +61,6 @@ Description-Content-Type: text/markdown
 [![Python versions](https://img.shields.io/pypi/pyversions/docsmind.svg)](https://pypi.org/project/docsmind/)
 [![Downloads](https://static.pepy.tech/badge/docsmind)](https://pepy.tech/project/docsmind)
 [![Downloads / month](https://static.pepy.tech/badge/docsmind/month)](https://pepy.tech/project/docsmind)
-[![Tests](https://github.com/yauheniya-ai/docsmind/actions/workflows/test.yml/badge.svg)](https://github.com/yauheniya-ai/docsmind/actions/workflows/test.yml)
-[![Coverage](https://img.shields.io/endpoint?url=https://gist.githubusercontent.com/yauheniya-ai/<GIST_ID>/raw/docsmind-coverage.json)](https://github.com/yauheniya-ai/docsmind/actions/workflows/test.yml)
 [![License: MIT](https://img.shields.io/pypi/l/docsmind.svg)](https://github.com/yauheniya-ai/docsmind/blob/main/LICENSE)
 [![Code style: ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
 [![Status: alpha](https://img.shields.io/badge/status-alpha-orange.svg)](#status)
@@ -82,11 +83,13 @@ its compliance implications, with citations back to exact pages.
 | ✅ Postgres + pgvector storage | Local Docker, or any Postgres with pgvector (Neon, Supabase) |
 | ✅ Inspection CLI | `versions`, `fulltext`, `outline`, `chunks` read back exactly what was saved |
 | ✅ `docsmind doctor` | Checks database, blob storage and API keys, and tells you what to fix |
-| 🚧 Embeddings + hybrid search | Chunks are stored without embeddings for now |
-| 🚧 Image captioning | Images are extracted and stored; vision captioning is next |
+| ✅ Table extraction | Extract and store tables skipping repeating ones (e.g. headers or footers) |
+| ✅ server + UI | FastAPI backend (`docsmind serve`) + React UI (`frontend/`): add documents, browse indexed content, image and table galleries |
 | 🚧 Chat agent (the Mind) | `docsmind chat` exists as a command, without an agent behind it yet |
+| 🚧 Image captioning | Images are extracted and stored; vision captioning is next |
+| 🚧 Embeddings + hybrid search | Chunks are stored without embeddings for now |
 | 🚧 Change analysis (diffra) | `docsmind diff` exists as a command, without an implementation yet |
-| 🚧 DOCX/text parsers, S3/Supabase blob storage, server + UI | Planned |
+| 🚧 DOCX/text parsers, S3/Supabase blob storage | Planned |
 
 ## Install
 
@@ -96,7 +99,7 @@ pip install docsmind
 pip install "docsmind[all]"
 ```
 
-Extras: `docsmind[openai]`, `docsmind[anthropic]`, `docsmind[server]` (FastAPI, planned UI),
+Extras: `docsmind[openai]`, `docsmind[anthropic]`, `docsmind[server]` (FastAPI, serves the bundled UI),
 `docsmind[mlflow]` (tracing/eval export). Requires Python 3.10+.
 
 ## Quickstart
@@ -158,7 +161,33 @@ docsmind chunks <version-id> --page 12  # the chunk(s) saved for one page
 
 You can also inspect the tables directly with `docsmind db psql`.
 
-### 4. Coming next
+### 4. Browse it in the UI
+
+```bash
+pip install "docsmind[server]"
+docsmind serve              # FastAPI backend on http://127.0.0.1:8000
+```
+
+Open `http://127.0.0.1:8000`.
+
+The React UI is bundled into the Python package and served directly by `docsmind serve`
+from `docsmind/src/docsmind/server/ui`.
+
+Clicking **+ Add Document** in the UI runs the same `docsmind ingest` pipeline on the
+uploaded PDF. Selecting a document shows its saved full text/outline (**Content**), and
+galleries of everything extracted from it (**Images**, **Tables**).
+
+For contributors refreshing bundled UI assets before a release:
+
+```bash
+cd ../frontend
+npm install
+npm run build
+cd ../docsmind
+python scripts/bundle_frontend.py
+```
+
+### 5. Coming next
 
 ```python
 print(dm.chat("What are our data retention obligations?"))   # planned
@@ -180,6 +209,9 @@ heuristics that work on one PDF break on the next.
   reconstruct structure.
 - **Images** are extracted with their page and position, skipping tiny icons, and saved
   under a readable path: `images/<collection>/<title>/<version>-<id>/`.
+  Visually repeated images (e.g. logo on every page) are de-duplicated by perceptual hash.
+- **Tables** are detected with PyMuPDF and rendered as PNG snippets, saved under
+  `tables/<collection>/<title>/<version>-<id>/`.
 
 ## CLI reference
 
@@ -190,8 +222,10 @@ heuristics that work on one PDF break on the next.
 | `docsmind fulltext <id> [--full]` | Print the saved full text |
 | `docsmind outline <id>` | Print the saved outline |
 | `docsmind chunks <id> [--page N] [--full]` | Print saved chunks |
+| `docsmind delete <id> [-y]` | Delete one version and its derived chunks/images/tables |
 | `docsmind db up` / `upgrade` / `psql` | Start local Postgres, apply migrations, open psql |
 | `docsmind doctor` | Check your setup |
+| `docsmind serve [--host] [--port] [--reload]` | Run the FastAPI backend for the `frontend/` UI |
 | `docsmind chat`, `docsmind diff` | Planned |
 
 ## Architecture
@@ -223,11 +257,22 @@ src/docsmind/
 ├── cli/                   # Typer app: ingest, versions, fulltext, outline, chunks, db, doctor
 ├── retrieval/             # hybrid vector + keyword search (planned)
 ├── agent/                 # the Mind + diffra subagent (planned)
-└── server/                # FastAPI + UI (planned)
+└── server/                # FastAPI app + routes backing frontend/ (documents: ingest, read back content/images/tables)
 
-alembic/   tests/   examples/   docs/   ui/
+alembic/   tests/   examples/   docs/
 ```
 
+The UI source lives one level up as a sibling project: `frontend/` (React + TypeScript +
+TailwindCSS, see the repo-root `CLAUDE.md`). Release builds are bundled into
+`src/docsmind/server/ui` and served by `server/app.py` at `/`. The UI talks to `server/`
+over `/api/*`, and loads extracted images/tables straight from disk via `/blobs/*`.
+
+## Artwork attribution
+
+- Workspace 3D graph artwork inspiration: Angela Galliat,
+  "Neural nervous system of a brain" (CodePen):
+  https://codepen.io/agalliat/pen/vYGXJxQ
+
 ### Design notes
 
 - **Ports and adapters, once.** `domain/ports.py` defines every external dependency as a
@@ -242,7 +287,9 @@ alembic/   tests/   examples/   docs/   ui/
   Outline paths (e.g. `03.13.11`) give version comparison something stable to align on
   where a document has a table of contents.
 - **Tables are shared state, not a UI feature.** `AgentTable` is a domain object that
-  both the agent and the user write to (append-only revisions).
+  both the agent and the user write to (append-only revisions). This is distinct from
+  the `tables` storage table (extracted PDF table *regions*, rendered as images
+  alongside `images` — browsable read-only in the UI's **Tables** gallery).
 
 ## Development
 

{docsmind-0.2.0 → docsmind-0.3.0}/README.md

@@ -4,8 +4,6 @@
 [![Python versions](https://img.shields.io/pypi/pyversions/docsmind.svg)](https://pypi.org/project/docsmind/)
 [![Downloads](https://static.pepy.tech/badge/docsmind)](https://pepy.tech/project/docsmind)
 [![Downloads / month](https://static.pepy.tech/badge/docsmind/month)](https://pepy.tech/project/docsmind)
-[![Tests](https://github.com/yauheniya-ai/docsmind/actions/workflows/test.yml/badge.svg)](https://github.com/yauheniya-ai/docsmind/actions/workflows/test.yml)
-[![Coverage](https://img.shields.io/endpoint?url=https://gist.githubusercontent.com/yauheniya-ai/<GIST_ID>/raw/docsmind-coverage.json)](https://github.com/yauheniya-ai/docsmind/actions/workflows/test.yml)
 [![License: MIT](https://img.shields.io/pypi/l/docsmind.svg)](https://github.com/yauheniya-ai/docsmind/blob/main/LICENSE)
 [![Code style: ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
 [![Status: alpha](https://img.shields.io/badge/status-alpha-orange.svg)](#status)
@@ -28,11 +26,13 @@ its compliance implications, with citations back to exact pages.
 | ✅ Postgres + pgvector storage | Local Docker, or any Postgres with pgvector (Neon, Supabase) |
 | ✅ Inspection CLI | `versions`, `fulltext`, `outline`, `chunks` read back exactly what was saved |
 | ✅ `docsmind doctor` | Checks database, blob storage and API keys, and tells you what to fix |
-| 🚧 Embeddings + hybrid search | Chunks are stored without embeddings for now |
-| 🚧 Image captioning | Images are extracted and stored; vision captioning is next |
+| ✅ Table extraction | Extract and store tables skipping repeating ones (e.g. headers or footers) |
+| ✅ server + UI | FastAPI backend (`docsmind serve`) + React UI (`frontend/`): add documents, browse indexed content, image and table galleries |
 | 🚧 Chat agent (the Mind) | `docsmind chat` exists as a command, without an agent behind it yet |
+| 🚧 Image captioning | Images are extracted and stored; vision captioning is next |
+| 🚧 Embeddings + hybrid search | Chunks are stored without embeddings for now |
 | 🚧 Change analysis (diffra) | `docsmind diff` exists as a command, without an implementation yet |
-| 🚧 DOCX/text parsers, S3/Supabase blob storage, server + UI | Planned |
+| 🚧 DOCX/text parsers, S3/Supabase blob storage | Planned |
 
 ## Install
 
@@ -42,7 +42,7 @@ pip install docsmind
 pip install "docsmind[all]"
 ```
 
-Extras: `docsmind[openai]`, `docsmind[anthropic]`, `docsmind[server]` (FastAPI, planned UI),
+Extras: `docsmind[openai]`, `docsmind[anthropic]`, `docsmind[server]` (FastAPI, serves the bundled UI),
 `docsmind[mlflow]` (tracing/eval export). Requires Python 3.10+.
 
 ## Quickstart
@@ -104,7 +104,33 @@ docsmind chunks <version-id> --page 12  # the chunk(s) saved for one page
 
 You can also inspect the tables directly with `docsmind db psql`.
 
-### 4. Coming next
+### 4. Browse it in the UI
+
+```bash
+pip install "docsmind[server]"
+docsmind serve              # FastAPI backend on http://127.0.0.1:8000
+```
+
+Open `http://127.0.0.1:8000`.
+
+The React UI is bundled into the Python package and served directly by `docsmind serve`
+from `docsmind/src/docsmind/server/ui`.
+
+Clicking **+ Add Document** in the UI runs the same `docsmind ingest` pipeline on the
+uploaded PDF. Selecting a document shows its saved full text/outline (**Content**), and
+galleries of everything extracted from it (**Images**, **Tables**).
+
+For contributors refreshing bundled UI assets before a release:
+
+```bash
+cd ../frontend
+npm install
+npm run build
+cd ../docsmind
+python scripts/bundle_frontend.py
+```
+
+### 5. Coming next
 
 ```python
 print(dm.chat("What are our data retention obligations?"))   # planned
@@ -126,6 +152,9 @@ heuristics that work on one PDF break on the next.
   reconstruct structure.
 - **Images** are extracted with their page and position, skipping tiny icons, and saved
   under a readable path: `images/<collection>/<title>/<version>-<id>/`.
+  Visually repeated images (e.g. logo on every page) are de-duplicated by perceptual hash.
+- **Tables** are detected with PyMuPDF and rendered as PNG snippets, saved under
+  `tables/<collection>/<title>/<version>-<id>/`.
 
 ## CLI reference
 
@@ -136,8 +165,10 @@ heuristics that work on one PDF break on the next.
 | `docsmind fulltext <id> [--full]` | Print the saved full text |
 | `docsmind outline <id>` | Print the saved outline |
 | `docsmind chunks <id> [--page N] [--full]` | Print saved chunks |
+| `docsmind delete <id> [-y]` | Delete one version and its derived chunks/images/tables |
 | `docsmind db up` / `upgrade` / `psql` | Start local Postgres, apply migrations, open psql |
 | `docsmind doctor` | Check your setup |
+| `docsmind serve [--host] [--port] [--reload]` | Run the FastAPI backend for the `frontend/` UI |
 | `docsmind chat`, `docsmind diff` | Planned |
 
 ## Architecture
@@ -169,11 +200,22 @@ src/docsmind/
 ├── cli/                   # Typer app: ingest, versions, fulltext, outline, chunks, db, doctor
 ├── retrieval/             # hybrid vector + keyword search (planned)
 ├── agent/                 # the Mind + diffra subagent (planned)
-└── server/                # FastAPI + UI (planned)
+└── server/                # FastAPI app + routes backing frontend/ (documents: ingest, read back content/images/tables)
 
-alembic/   tests/   examples/   docs/   ui/
+alembic/   tests/   examples/   docs/
 ```
 
+The UI source lives one level up as a sibling project: `frontend/` (React + TypeScript +
+TailwindCSS, see the repo-root `CLAUDE.md`). Release builds are bundled into
+`src/docsmind/server/ui` and served by `server/app.py` at `/`. The UI talks to `server/`
+over `/api/*`, and loads extracted images/tables straight from disk via `/blobs/*`.
+
+## Artwork attribution
+
+- Workspace 3D graph artwork inspiration: Angela Galliat,
+  "Neural nervous system of a brain" (CodePen):
+  https://codepen.io/agalliat/pen/vYGXJxQ
+
 ### Design notes
 
 - **Ports and adapters, once.** `domain/ports.py` defines every external dependency as a
@@ -188,7 +230,9 @@ alembic/   tests/   examples/   docs/   ui/
   Outline paths (e.g. `03.13.11`) give version comparison something stable to align on
   where a document has a table of contents.
 - **Tables are shared state, not a UI feature.** `AgentTable` is a domain object that
-  both the agent and the user write to (append-only revisions).
+  both the agent and the user write to (append-only revisions). This is distinct from
+  the `tables` storage table (extracted PDF table *regions*, rendered as images
+  alongside `images` — browsable read-only in the UI's **Tables** gallery).
 
 ## Development
 

{docsmind-0.2.0 → docsmind-0.3.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "docsmind"
-version = "0.2.0"
+version = "0.3.0"
 description = "Chat with your documents. Version-aware retrieval, change analysis, and an editable table workspace, backed by Postgres/pgvector."
 readme = "README.md"
 requires-python = ">=3.10"
@@ -38,12 +38,13 @@ dependencies = [
     "pillow>=10.0",
     "imagehash>=4.3",
     "rich>=13.7",
+    "tiktoken>=0.7",
 ]
 
 [project.optional-dependencies]
 openai = ["openai>=1.30"]
 anthropic = ["anthropic>=0.34"]
-server = ["fastapi>=0.111", "uvicorn[standard]>=0.30"]
+server = ["fastapi>=0.111", "uvicorn[standard]>=0.30", "python-multipart>=0.0.9"]
 mlflow = ["mlflow>=2.14"]
 dev = ["pytest>=8.0", "pytest-asyncio>=0.23", "testcontainers[postgres]>=4.4", "ruff>=0.5", "mypy>=1.10"]
 all = ["docsmind[openai,anthropic,server]"]
@@ -61,6 +62,15 @@ Issues = "https://github.com/yauheniya-ai/docsmind/issues"
 
 [tool.hatch.build.targets.wheel]
 packages = ["src/docsmind"]
+include = ["src/docsmind/server/ui/**"]
+
+[tool.hatch.build.targets.sdist]
+include = [
+  "src/docsmind/**",
+  "README.md",
+  "CHANGELOG.md",
+  "scripts/bundle_frontend.py",
+]
 
 [tool.pytest.ini_options]
 asyncio_mode = "auto"
@@ -79,4 +89,4 @@ target-version = "py310"
 # image is corrupt" — and a single malformed image in an otherwise-fine PDF
 # shouldn't abort the whole ingest, so we deliberately catch broadly here and
 # skip the one image rather than propagate.
-"src/docsmind/ingestion/parsers/pdf.py" = ["BLE001"]
+"src/docsmind/ingestion/parsers/pdf.py" = ["BLE001"]

{docsmind-0.2.0 → docsmind-0.3.0}/src/docsmind/adapters/storage/postgres/repository.py

@@ -14,7 +14,7 @@ from __future__ import annotations
 
 from uuid import UUID
 
-from sqlalchemy import insert, select
+from sqlalchemy import delete, insert, select
 
 from docsmind.adapters.storage.postgres.engine import get_sessionmaker
 from docsmind.adapters.storage.postgres.tables import (
@@ -32,6 +32,9 @@ from docsmind.adapters.storage.postgres.tables import (
 from docsmind.adapters.storage.postgres.tables import (
     sections as sections_table,
 )
+from docsmind.adapters.storage.postgres.tables import (
+    tables as tables_table,
+)
 from docsmind.config import DocsmindConfig
 from docsmind.domain.documents import (
     Chunk,
@@ -137,6 +140,27 @@ class PostgresRepository:
                     insert(chunks_table),
                     [self._chunk_row(c) for c in parsed.chunks],
                 )
+            if parsed.tables:
+                await session.execute(
+                    insert(tables_table),
+                    [
+                        {
+                            "id": t.id,
+                            "version_id": t.version_id,
+                            "page_number": t.page_number,
+                            "bbox_x0": t.bbox[0],
+                            "bbox_y0": t.bbox[1],
+                            "bbox_x1": t.bbox[2],
+                            "bbox_y1": t.bbox[3],
+                            "uri": t.uri,
+                            "width": t.width,
+                            "height": t.height,
+                            "format": t.format,
+                            "phash": t.phash,
+                        }
+                        for t in parsed.tables
+                    ],
+                )
             await session.commit()
 
     @staticmethod
@@ -205,6 +229,7 @@ class PostgresRepository:
         async with self._sessionmaker() as session:
             stmt = (
                 select(
+                    documents_table.c.id.label("document_id"),
                     documents_table.c.title,
                     documents_table.c.collection,
                     document_versions_table.c.id,
@@ -223,6 +248,80 @@ class PostgresRepository:
             result = await session.execute(stmt)
             return [dict(row) for row in result.mappings().all()]
 
+    async def get_version(self, version_id: UUID) -> dict | None:
+        """Metadata for one version, joined back to its parent `Document` —
+        everything the detail view needs besides full text/outline/chunks."""
+        async with self._sessionmaker() as session:
+            stmt = (
+                select(
+                    documents_table.c.id.label("document_id"),
+                    documents_table.c.title,
+                    documents_table.c.collection,
+                    document_versions_table.c.id,
+                    document_versions_table.c.label,
+                    document_versions_table.c.created_at,
+                    document_versions_table.c.char_count,
+                    document_versions_table.c.word_count,
+                    document_versions_table.c.token_count_estimate,
+                    document_versions_table.c.blob_uri,
+                )
+                .select_from(
+                    document_versions_table.join(
+                        documents_table, documents_table.c.id == document_versions_table.c.document_id
+                    )
+                )
+                .where(document_versions_table.c.id == version_id)
+            )
+            result = await session.execute(stmt)
+            row = result.mappings().first()
+            return dict(row) if row else None
+
+    async def get_version_by_content_hash(self, content_hash: str) -> dict | None:
+        """Look up an already-ingested version by its file content hash —
+        used *before* parsing to detect "this exact file is already here"
+        without wastefully re-extracting images/tables first. Returns the
+        same shape as `get_version` (joined back to the parent `Document`)."""
+        async with self._sessionmaker() as session:
+            stmt = (
+                select(
+                    documents_table.c.id.label("document_id"),
+                    documents_table.c.title,
+                    documents_table.c.collection,
+                    document_versions_table.c.id,
+                    document_versions_table.c.label,
+                    document_versions_table.c.created_at,
+                )
+                .select_from(
+                    document_versions_table.join(
+                        documents_table, documents_table.c.id == document_versions_table.c.document_id
+                    )
+                )
+                .where(document_versions_table.c.content_hash == content_hash)
+            )
+            result = await session.execute(stmt)
+            row = result.mappings().first()
+            return dict(row) if row else None
+
+    async def delete_version(self, version_id: UUID) -> bool:
+        """Delete one `DocumentVersion` and everything that hangs off it
+        (sections/images/tables/chunks all have `ON DELETE CASCADE` back to
+        `document_versions` — see migrations 0001-0003). Useful for clearing
+        out a version that was ingested before a pipeline fix (e.g. the
+        image-dedup / table-persistence fixes) so it can be cleanly
+        re-ingested. Does *not* delete the parent `Document` row, even if
+        this was its only version — `documents` rows are cheap and harmless
+        to leave orphaned, and deleting them too would cascade-delete any
+        sibling versions.
+
+        Returns True if a row was deleted, False if `version_id` didn't exist.
+        """
+        async with self._sessionmaker() as session:
+            result = await session.execute(
+                delete(document_versions_table).where(document_versions_table.c.id == version_id)
+            )
+            await session.commit()
+            return result.rowcount > 0
+
     async def get_full_text(self, version_id: UUID) -> str | None:
         async with self._sessionmaker() as session:
             result = await session.execute(
@@ -266,4 +365,29 @@ class PostgresRepository:
             if page is not None:
                 stmt = stmt.where(chunks_table.c.page_start == page)
             result = await session.execute(stmt)
+            return [dict(row) for row in result.mappings().all()]
+
+    async def get_images(self, version_id: UUID) -> list[dict]:
+        """Saved images for one version, in page order — `uri` is a
+        `file://...` (or other `BlobStore`-specific) URI; the server layer
+        resolves these into servable URLs, not this repository."""
+        async with self._sessionmaker() as session:
+            stmt = (
+                select(images_table)
+                .where(images_table.c.version_id == version_id)
+                .order_by(images_table.c.page_number)
+            )
+            result = await session.execute(stmt)
+            return [dict(row) for row in result.mappings().all()]
+
+    async def get_tables(self, version_id: UUID) -> list[dict]:
+        """Saved extracted tables (rendered as images) for one version, in
+        page order."""
+        async with self._sessionmaker() as session:
+            stmt = (
+                select(tables_table)
+                .where(tables_table.c.version_id == version_id)
+                .order_by(tables_table.c.page_number)
+            )
+            result = await session.execute(stmt)
             return [dict(row) for row in result.mappings().all()]

{docsmind-0.2.0 → docsmind-0.3.0}/src/docsmind/adapters/storage/postgres/tables.py

@@ -96,6 +96,23 @@ images = Table(
     Column("captioned_at", DateTime(timezone=True), nullable=True),
 )
 
+tables = Table(
+    "tables",
+    metadata,
+    Column("id", UUID(as_uuid=True), primary_key=True),
+    Column("version_id", UUID(as_uuid=True), ForeignKey("document_versions.id", ondelete="CASCADE"), nullable=False),
+    Column("page_number", Integer, nullable=False),
+    Column("bbox_x0", Float, nullable=False),
+    Column("bbox_y0", Float, nullable=False),
+    Column("bbox_x1", Float, nullable=False),
+    Column("bbox_y1", Float, nullable=False),
+    Column("uri", Text, nullable=False),
+    Column("width", Integer, nullable=False),
+    Column("height", Integer, nullable=False),
+    Column("format", Text, nullable=False),
+    Column("phash", Text, nullable=True),
+)
+
 _chunks_columns = [
     Column("id", UUID(as_uuid=True), primary_key=True),
     Column("version_id", UUID(as_uuid=True), ForeignKey("document_versions.id", ondelete="CASCADE"), nullable=False),

{docsmind-0.2.0 → docsmind-0.3.0}/src/docsmind/cli/app.py

@@ -23,6 +23,7 @@ app.command("doctor")(doctor.doctor)
 from docsmind.cli import chat as _chat
 from docsmind.cli import diff as _diff
 from docsmind.cli import inspect as _inspect
+from docsmind.cli import serve as _serve
 
 app.command("chat")(_chat.chat)
 app.command("diff")(_diff.diff)
@@ -30,6 +31,8 @@ app.command("versions")(_inspect.versions)
 app.command("fulltext")(_inspect.fulltext)
 app.command("outline")(_inspect.outline)
 app.command("chunks")(_inspect.chunks)
+app.command("delete")(_inspect.delete)
+app.command("serve")(_serve.serve)
 
 
 def main() -> None:

{docsmind-0.2.0 → docsmind-0.3.0}/src/docsmind/cli/ingest.py

@@ -16,7 +16,12 @@ def ingest(
     ),
 ) -> None:
     from docsmind import Docsmind
+    from docsmind.domain.errors import DocumentAlreadyExistsError
 
     dm = Docsmind()
-    result = dm.ingest(path, collection=collection, version=version)
+    try:
+        result = dm.ingest(path, collection=collection, version=version)
+    except DocumentAlreadyExistsError as exc:
+        console.print(f"[yellow]Already ingested.[/yellow] {exc}")
+        raise typer.Exit(code=1) from None
     console.print(f"[green]Ingested[/green] {path.name} -> version {result.id} ({result.label})")

{docsmind-0.2.0 → docsmind-0.3.0}/src/docsmind/cli/inspect.py

@@ -169,4 +169,41 @@ def chunks(
                 suffix = "..." if len(content) > 200 else ""
                 console.print(f"[{label}] TEXT ({word_count} words): {preview}{suffix}")
 
+    asyncio.run(_run())
+
+
+def delete(
+    version_id: UUID = typer.Argument(..., help="A version id from `docsmind versions`."),
+    yes: bool = typer.Option(False, "--yes", "-y", help="Skip the confirmation prompt."),
+) -> None:
+    """Delete one ingested version (sections/images/tables/chunks cascade with it).
+
+    Useful for clearing out a version that was ingested before a pipeline
+    fix landed (e.g. the image-dedup or table-persistence fixes) so you can
+    re-ingest the same file cleanly afterwards — re-ingesting identical bytes
+    is otherwise a no-op (see `DocumentAlreadyExistsError`).
+    """
+
+    async def _run() -> None:
+        from docsmind.adapters.storage.postgres.repository import PostgresRepository
+        from docsmind.config import DocsmindConfig
+
+        repo = PostgresRepository(DocsmindConfig())
+        existing = await repo.get_version(version_id)
+        if existing is None:
+            console.print(f"[yellow]No version found with id {version_id}.[/yellow]")
+            return
+
+        if not yes:
+            confirm = typer.confirm(
+                f"Delete '{existing['title']}' ({existing['collection']} / {existing['label']}, "
+                f"version {version_id})? This also deletes its chunks, images and tables."
+            )
+            if not confirm:
+                console.print("Aborted.")
+                return
+
+        await repo.delete_version(version_id)
+        console.print(f"[green]Deleted[/green] version {version_id}.")
+
     asyncio.run(_run())

docsmind-0.3.0/src/docsmind/cli/serve.py

@@ -0,0 +1,29 @@
+"""`docsmind serve` — runs the FastAPI app (`server/app.py`) behind uvicorn,
+for the `frontend/` UI to talk to. Requires the `server` extra:
+`pip install "docsmind[server]"`.
+"""
+
+from __future__ import annotations
+
+import typer
+from rich.console import Console
+
+console = Console()
+
+
+def serve(
+    host: str = typer.Option("127.0.0.1", "--host", help="Bind address."),
+    port: int = typer.Option(8000, "--port", "-p", help="Bind port."),
+    reload: bool = typer.Option(False, "--reload", help="Auto-reload on code changes (dev only)."),
+) -> None:
+    """Start the docsmind API server used by the frontend UI."""
+    try:
+        import uvicorn
+    except ImportError as exc:  # pragma: no cover - import guard
+        console.print(
+            "[red]uvicorn isn't installed.[/red] Run `pip install \"docsmind[server]\"` first."
+        )
+        raise typer.Exit(1) from exc
+
+    console.print(f"[green]Starting docsmind server[/green] on http://{host}:{port}")
+    uvicorn.run("docsmind.server.app:app", host=host, port=port, reload=reload)