Rename to Pathology Evidence AI

hutaobo · hutaobo · commit 637479518164 · 2026-05-05T13:28:40.000+02:00
diff --git a/.env.example b/.env.example
@@ -4,12 +4,12 @@ APP_PORT=8000
 OPENAI_API_KEY=
 OPENAI_MODEL=gpt-5.4
 OPENAI_EMBEDDING_MODEL=text-embedding-3-large
-PATHOLOGY_PROJECT_NAME=Pathology RAG Workbench
-PATHOLOGY_PROJECT_SLUG=pathology-rag-workbench
-COMPOSE_PROJECT_NAME=pathology-rag-workbench
+PATHOLOGY_PROJECT_NAME=Pathology Evidence AI
+PATHOLOGY_PROJECT_SLUG=pathology-evidence-ai
+COMPOSE_PROJECT_NAME=pathology-evidence-ai
 PATHOLOGY_CLIENT_COMMAND=pathology-client
 PATHOLOGY_INGEST_COMMAND=pathology-ingest-local
-PATHOLOGY_OPENCLAW_SKILL_NAME=pathology-rag
+PATHOLOGY_OPENCLAW_SKILL_NAME=pathology-evidence-ai
 PATHOLOGY_INSTALL_GLOBAL_ALIAS=1
 PATHOLOGY_PDF_ROOT=pathologybook
 PATHOLOGY_DATA_DIR=data
@@ -24,4 +24,5 @@ POSTGRES_USER=pathology
 POSTGRES_PASSWORD=pathology
 POSTGRES_PORT=5432
 POSTGRES_URL=postgresql+psycopg://pathology:pathology@localhost:5432/pathology_ai
+POSTGRES_CONNECT_TIMEOUT=2
 OPENCLAW_PATHOLOGY_API=http://127.0.0.1:8000
diff --git a/.github/ISSUE_TEMPLATE/config.yml b/.github/ISSUE_TEMPLATE/config.yml
@@ -1,8 +1,8 @@
 blank_issues_enabled: false
 contact_links:
   - name: Security issue or unsafe data exposure
-    url: https://github.com/hutaobo/pathology-rag-workbench/blob/main/SECURITY.md
+    url: https://github.com/hutaobo/pathology-evidence-ai/blob/main/SECURITY.md
     about: Please report security and sensitive-data issues privately first.
   - name: Contribution guidelines
-    url: https://github.com/hutaobo/pathology-rag-workbench/blob/main/CONTRIBUTING.md
+    url: https://github.com/hutaobo/pathology-evidence-ai/blob/main/CONTRIBUTING.md
     about: Read this before opening a pull request.
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
@@ -1,6 +1,6 @@
 # Contributing
 
-Thanks for contributing to Pathology RAG Workbench.
+Thanks for contributing to Pathology Evidence AI.
 
 ## Before You Open a PR
 
diff --git a/README.md b/README.md
@@ -1,10 +1,10 @@
-# Pathology RAG Workbench
+# Pathology Evidence AI
 
-[![CI](https://github.com/hutaobo/pathology-rag-workbench/actions/workflows/ci.yml/badge.svg)](https://github.com/hutaobo/pathology-rag-workbench/actions/workflows/ci.yml)
+[![CI](https://github.com/hutaobo/pathology-evidence-ai/actions/workflows/ci.yml/badge.svg)](https://github.com/hutaobo/pathology-evidence-ai/actions/workflows/ci.yml)
 [![Python 3.11+](https://img.shields.io/badge/python-3.11%2B-3776AB.svg)](https://www.python.org/)
 [![License: PolyForm Noncommercial](https://img.shields.io/badge/license-PolyForm%20Noncommercial%201.0.0-5B4B8A.svg)](LICENSE)
 
-Pathology RAG Workbench is a local-first pathology PDF workspace. It helps you turn your own licensed pathology books or notes into a citation-backed retrieval system with a browser UI, a local API, and a CLI.
+Pathology Evidence AI is a local-first pathology evidence workspace. It helps you turn your own licensed pathology books or notes into AI-assisted answers with citation-backed evidence, a browser UI, a local API, and a CLI.
 
 This repository is public, but it is not open source in the OSI sense. It is released under the [PolyForm Noncommercial 1.0.0](LICENSE) license, so commercial use is not allowed.
 
@@ -15,8 +15,8 @@ If you only read one section, read this one.
 Clone the repo and run:
 
 ```bash
-git clone https://github.com/hutaobo/pathology-rag-workbench.git
-cd pathology-rag-workbench
+git clone https://github.com/hutaobo/pathology-evidence-ai.git
+cd pathology-evidence-ai
 bash scripts/deploy_portable.sh --allow-no-openai
 ```
 
@@ -136,17 +136,30 @@ Even without an OpenAI key, you can:
 - sync the local library
 - inspect library state
 - run retrieval previews instead of model-synthesized answers
+- create a synthetic demo library with fake educational PDFs
 
 Useful commands:
 
 ```bash
 pathology-client health
 pathology-client ui
+pathology-ingest create-demo-library
 pathology-client library
 pathology-client search --query "ductal carcinoma in situ"
 pathology-client sync-library
 ```
 
+## Try a Demo Library
+
+If you do not have pathology PDFs ready yet, generate a tiny synthetic demo corpus:
+
+```bash
+pathology-ingest create-demo-library
+pathology-client search --query "mucinous carcinoma of the prostate"
+```
+
+The demo PDFs are fake educational notes created by this project. They are only meant to prove that ingestion, search, citations, and page previews are working.
+
 ## Add Your Own PDFs
 
 No corpus is bundled with this repository.
diff --git a/apps/ingest_worker/cli.py b/apps/ingest_worker/cli.py
@@ -7,6 +7,7 @@
 from src.pathology_ai.embeddings import chunk_embedding_count, sync_chunk_embeddings
 from src.pathology_ai.analysis import analyze_pdf
 from src.pathology_ai.catalog import load_library_config
+from src.pathology_ai.demo_library import create_demo_library
 from src.pathology_ai.ingest import build_library_artifacts
 from src.pathology_ai.library_state import sync_local_library
 
@@ -53,6 +54,15 @@ def sync_library(
     typer.echo(json.dumps(result, indent=2, ensure_ascii=False))
 
 
+@app.command("create-demo-library")
+def create_demo_library_command(
+    force: bool = typer.Option(default=False, help="Replace existing demo PDFs before rebuilding the demo index."),
+    skip_index: bool = typer.Option(default=False, help="Create/register demo PDFs without rebuilding chunks."),
+) -> None:
+    result = create_demo_library(force=force, rebuild=not skip_index)
+    typer.echo(json.dumps(result, indent=2, ensure_ascii=False))
+
+
 def main() -> None:
     app()
 
diff --git a/apps/pathology_api/main.py b/apps/pathology_api/main.py
@@ -10,7 +10,7 @@
 from src.pathology_ai.settings import get_settings
 
 
-app = FastAPI(title="Pathology RAG Workbench API", version="0.1.0")
+app = FastAPI(title="Pathology Evidence AI API", version="0.1.0")
 static_dir = Path(__file__).resolve().parent / "static"
 app.mount("/assets", StaticFiles(directory=static_dir), name="assets")
 app.include_router(health.router)
diff --git a/apps/pathology_api/routers/rag.py b/apps/pathology_api/routers/rag.py
@@ -4,7 +4,7 @@
 from src.pathology_ai.retrieval import search_chunks
 from src.pathology_ai.schemas import AskRequest, AskResponse, SearchRequest, SearchHit
 
-router = APIRouter(tags=["rag"])
+router = APIRouter(tags=["evidence"])
 
 
 @router.post("/search", response_model=list[SearchHit])
diff --git a/apps/pathology_api/routers/ui.py b/apps/pathology_api/routers/ui.py
@@ -22,6 +22,25 @@ def _resolve_chunk_or_404(chunk_id: str):
     return chunk
 
 
+def _resolve_library_pdf_or_404(chunk_id: str) -> Path:
+    chunk = _resolve_chunk_or_404(chunk_id)
+    source_path = resolve_pdf_path(chunk.source_path)
+    settings = get_settings()
+    try:
+        resolved_source = source_path.resolve(strict=True)
+        resolved_root = settings.pathology_pdf_root.resolve(strict=True)
+    except FileNotFoundError as exc:
+        raise HTTPException(status_code=404, detail="Source PDF not found.") from exc
+
+    if resolved_source.suffix.lower() != ".pdf":
+        raise HTTPException(status_code=404, detail="Source PDF not found.")
+    try:
+        resolved_source.relative_to(resolved_root)
+    except ValueError as exc:
+        raise HTTPException(status_code=403, detail="Source PDF is outside the configured library root.") from exc
+    return resolved_source
+
+
 def _render_page_image(chunk_id: str, width: int = 1200) -> Path:
     chunk = _resolve_chunk_or_404(chunk_id)
     settings = get_settings()
@@ -31,9 +50,7 @@ def _render_page_image(chunk_id: str, width: int = 1200) -> Path:
     if image_path.exists():
         return image_path
 
-    source_path = resolve_pdf_path(chunk.source_path)
-    if not source_path.exists():
-        raise HTTPException(status_code=404, detail="Source PDF not found.")
+    source_path = _resolve_library_pdf_or_404(chunk_id)
 
     with fitz.open(source_path) as document:
         page_index = chunk.page_start - 1
@@ -64,8 +81,5 @@ def chunk_page_image(chunk_id: str, width: int = Query(default=1200, ge=600, le=
 
 @router.get("/chunks/{chunk_id}/pdf", include_in_schema=False)
 def chunk_pdf(chunk_id: str) -> FileResponse:
-    chunk = _resolve_chunk_or_404(chunk_id)
-    source_path = resolve_pdf_path(chunk.source_path)
-    if not source_path.exists():
-        raise HTTPException(status_code=404, detail="Source PDF not found.")
+    source_path = _resolve_library_pdf_or_404(chunk_id)
     return FileResponse(source_path, media_type="application/pdf", filename=source_path.name)
diff --git a/apps/pathology_api/static/pathology-ui.html b/apps/pathology_api/static/pathology-ui.html
@@ -3,7 +3,7 @@
   <head>
     <meta charset="utf-8" />
     <meta name="viewport" content="width=device-width, initial-scale=1" />
-    <title>Pathology AI Reader</title>
+    <title>Pathology Evidence AI</title>
     <link rel="stylesheet" href="/assets/pathology-ui.css" />
   </head>
   <body>
@@ -12,10 +12,10 @@
       <section class="hero">
         <div class="hero-bar">
           <div>
-            <p class="eyebrow" id="hero-eyebrow">Pathology RAG Workbench</p>
-            <h1 id="hero-title">Ask your local pathology library like a reference atlas.</h1>
+            <p class="eyebrow" id="hero-eyebrow">Pathology Evidence AI</p>
+            <h1 id="hero-title">Pathology Evidence AI</h1>
             <p class="lede" id="hero-lede">
-              Textbook-backed answers, page previews, and direct PDF evidence from your local collection.
+              Use local pathology PDFs for AI answers with citation-backed evidence.
             </p>
           </div>
           <div class="hero-controls">
diff --git a/apps/pathology_api/static/pathology-ui.js b/apps/pathology_api/static/pathology-ui.js
@@ -57,10 +57,10 @@ const state = {
 };
 const TRANSLATIONS = {
   en: {
-    pageTitle: "Pathology AI Reader",
-    heroEyebrow: "Pathology RAG Workbench",
-    heroTitle: "Ask your local pathology library like a reference atlas.",
-    heroLede: "Textbook-backed answers, page previews, and direct PDF evidence from your local collection.",
+    pageTitle: "Pathology Evidence AI",
+    heroEyebrow: "Pathology Evidence AI",
+    heroTitle: "Pathology Evidence AI",
+    heroLede: "Use local pathology PDFs for AI answers with citation-backed evidence.",
     languageLabel: "Interface & answer language",
     themeLabel: "Color mode",
     themeLight: "Light",
@@ -134,10 +134,10 @@ const TRANSLATIONS = {
     ],
   },
   sv: {
-    pageTitle: "Pathology AI Reader",
-    heroEyebrow: "Patologi RAG-arbetsyta",
-    heroTitle: "Fråga ditt lokala patologibibliotek som om det vore ett referensatlas.",
-    heroLede: "Läroboksbaserade svar, sidförhandsvisningar och direkt PDF-evidens från din lokala samling.",
+    pageTitle: "Pathology Evidence AI",
+    heroEyebrow: "Pathology Evidence AI",
+    heroTitle: "Pathology Evidence AI",
+    heroLede: "Use local pathology PDFs for AI answers with citation-backed evidence.",
     languageLabel: "Språk för gränssnitt och svar",
     themeLabel: "Färgläge",
     themeLight: "Ljust",
@@ -184,10 +184,10 @@ const TRANSLATIONS = {
     ],
   },
   "zh-CN": {
-    pageTitle: "Pathology AI Reader",
-    heroEyebrow: "病理 RAG 工作台",
-    heroTitle: "像查阅参考图谱一样提问你的本地病理资料库。",
-    heroLede: "基于教材证据的回答、页码预览，以及直接指向本地 PDF 的证据链。",
+    pageTitle: "Pathology Evidence AI",
+    heroEyebrow: "Pathology Evidence AI",
+    heroTitle: "Pathology Evidence AI",
+    heroLede: "Use local pathology PDFs for AI answers with citation-backed evidence.",
     languageLabel: "界面与回答语言",
     themeLabel: "配色模式",
     themeLight: "浅色",
@@ -260,10 +260,10 @@ const TRANSLATIONS = {
     ],
   },
   ja: {
-    pageTitle: "Pathology AI Reader",
-    heroEyebrow: "病理 RAG ワークベンチ",
-    heroTitle: "ローカル病理ライブラリを参照アトラスのように検索できます。",
-    heroLede: "教科書根拠の回答、ページプレビュー、ローカル PDF への直接リンクをまとめて確認できます。",
+    pageTitle: "Pathology Evidence AI",
+    heroEyebrow: "Pathology Evidence AI",
+    heroTitle: "Pathology Evidence AI",
+    heroLede: "Use local pathology PDFs for AI answers with citation-backed evidence.",
     languageLabel: "UI と回答言語",
     themeLabel: "カラーモード",
     themeLight: "ライト",
diff --git a/docs/ARCHITECTURE.md b/docs/ARCHITECTURE.md
@@ -1,6 +1,6 @@
 # Architecture
 
-Pathology RAG Workbench is organized around a small local pipeline:
+Pathology Evidence AI is organized around a small local pipeline:
 
 1. PDFs live under `pathologybook/` and are registered through `config/library.local.yaml` or the browser UI.
 2. `apps.ingest_worker` analyzes each PDF, extracts text, and writes normalized artifacts under `data/processed/`.
diff --git a/openclaw/workspace/skills/pathology-evidence-ai/SKILL.md b/openclaw/workspace/skills/pathology-evidence-ai/SKILL.md
@@ -1,9 +1,9 @@
 ---
-name: "pathology-rag"
+name: "pathology-evidence-ai"
 description: "Use the local pathology API and textbook index for pathology questions, source lookup, and citation-backed answers."
 ---
 
-# Pathology RAG Skill
+# Pathology Evidence AI Skill
 
 ## When to use
 
diff --git a/pyproject.toml b/pyproject.toml
@@ -3,9 +3,9 @@ requires = ["setuptools>=69", "wheel"]
 build-backend = "setuptools.build_meta"
 
 [project]
-name = "pathology-rag-workbench"
+name = "pathology-evidence-ai"
 version = "0.1.0"
-description = "Local pathology PDF ingestion, retrieval, and citation-backed RAG workbench."
+description = "Local pathology PDF ingestion, AI-assisted retrieval, and citation-backed evidence workspace."
 readme = "README.md"
 requires-python = ">=3.11"
 license = {file = "LICENSE"}
diff --git a/scripts/init_private_workspace.py b/scripts/init_private_workspace.py
@@ -8,7 +8,6 @@
 import shutil
 import socket
 import subprocess
-import sys
 from typing import Iterable
 
 import yaml
@@ -127,7 +126,7 @@ def write_private_env(target_root: Path, project_name: str, project_slug: str, a
     postgres_password = secrets.token_urlsafe(18)
     client_command = f"pathology-client-{project_slug}"
     ingest_command = f"pathology-ingest-{project_slug}"
-    skill_name = f"pathology-rag-{project_slug}"
+    skill_name = f"pathology-evidence-ai-{project_slug}"
     api_url = f"http://127.0.0.1:{app_port}"
 
     lines = [
@@ -160,6 +159,7 @@ def write_private_env(target_root: Path, project_name: str, project_slug: str, a
             "POSTGRES_URL",
             f"postgresql+psycopg://{postgres_user}:{postgres_password}@localhost:{postgres_port}/{postgres_db}",
         ),
+        env_line("POSTGRES_CONNECT_TIMEOUT", "2"),
         env_line("OPENCLAW_PATHOLOGY_API", api_url),
     ]
 
@@ -227,7 +227,7 @@ def init_git_repo(target_root: Path) -> str:
 
 def parse_args() -> argparse.Namespace:
     parser = argparse.ArgumentParser(
-        description="Create a private Pathology RAG workspace with isolated ports, database settings, and local config.",
+        description="Create a private Pathology Evidence AI workspace with isolated ports, database settings, and local config.",
     )
     parser.add_argument("target", help="Absolute or relative path for the new private workspace.")
     parser.add_argument("--name", help="Human-readable project name. Defaults to the target directory name.")
diff --git a/scripts/install_openclaw_integration.sh b/scripts/install_openclaw_integration.sh
@@ -24,7 +24,7 @@ PROJECT_NAME="${PATHOLOGY_PROJECT_NAME:-$(basename "${ROOT_DIR}")}"
 PROJECT_SLUG="${PATHOLOGY_PROJECT_SLUG:-$(slugify "${PROJECT_NAME}")}"
 CLIENT_COMMAND="${PATHOLOGY_CLIENT_COMMAND:-pathology-client}"
 INGEST_COMMAND="${PATHOLOGY_INGEST_COMMAND:-pathology-ingest-local}"
-SKILL_NAME="${PATHOLOGY_OPENCLAW_SKILL_NAME:-pathology-rag}"
+SKILL_NAME="${PATHOLOGY_OPENCLAW_SKILL_NAME:-pathology-evidence-ai}"
 INSTALL_GLOBAL_ALIAS="${PATHOLOGY_INSTALL_GLOBAL_ALIAS:-1}"
 API_URL="${OPENCLAW_PATHOLOGY_API:-http://127.0.0.1:${APP_PORT:-8000}}"
 
diff --git a/scripts/package_portable.sh b/scripts/package_portable.sh
@@ -37,7 +37,7 @@ cd "${ROOT_DIR}"
 mkdir -p "${OUTPUT_DIR}"
 
 STAMP="$(date +%Y%m%d-%H%M%S)"
-BUNDLE_NAME="pathology-rag-workbench-portable-${STAMP}.tar.gz"
+BUNDLE_NAME="pathology-evidence-ai-portable-${STAMP}.tar.gz"
 BUNDLE_PATH="${OUTPUT_DIR}/${BUNDLE_NAME}"
 TMP_BUNDLE="$(mktemp "/tmp/${BUNDLE_NAME}.XXXXXX")"
 OUTPUT_EXCLUDE=""
diff --git a/src/pathology_ai/__init__.py b/src/pathology_ai/__init__.py
@@ -1 +1 @@
-"""Shared library code for Pathology RAG Workbench."""
+"""Shared library code for Pathology Evidence AI."""
diff --git a/src/pathology_ai/db.py b/src/pathology_ai/db.py
@@ -11,7 +11,12 @@
 @lru_cache(maxsize=1)
 def get_engine():
     settings = get_settings()
-    return create_engine(settings.postgres_url, future=True, pool_pre_ping=True)
+    return create_engine(
+        settings.postgres_url,
+        future=True,
+        pool_pre_ping=True,
+        connect_args={"connect_timeout": settings.postgres_connect_timeout},
+    )
 
 
 @lru_cache(maxsize=1)
diff --git a/src/pathology_ai/demo_library.py b/src/pathology_ai/demo_library.py
diff --git a/src/pathology_ai/ingest.py b/src/pathology_ai/ingest.py
diff --git a/src/pathology_ai/settings.py b/src/pathology_ai/settings.py
diff --git a/tests/conftest.py b/tests/conftest.py
diff --git a/tests/test_demo_library.py b/tests/test_demo_library.py
diff --git a/tests/test_library_management.py b/tests/test_library_management.py
diff --git a/tests/test_private_workspace_generator.py b/tests/test_private_workspace_generator.py
diff --git a/tests/test_ui.py b/tests/test_ui.py
