From 9e75730e0f238194c88721c9634feb9e3fea46f8 Mon Sep 17 00:00:00 2001
From: yichuan520030910320 <yichuan_wang@berkeley.edu>
Date: Sat, 27 Jun 2026 00:52:55 -0700
Subject: [PATCH 1/3] fix(index): render markdown properly and resolve relative
 image paths

Follow-up to #101. The original implementation wrapped all text file
content in <pre> tags with html.escape(), so markdown syntax showed as
raw text. This changes .md files to use the markdown library (with
tables + fenced_code extensions) for proper rendering, while keeping
<pre> for .txt files. Also rewrites relative src/href paths to absolute
file:// URIs so local images load correctly during CDP rendering, and
switches to TemporaryDirectory for automatic cleanup.
---
 index/src/pixelrag_index/pipelines.py | 79 ++++++++++++++++++---------
 pyproject.toml                        |  2 +-
 uv.lock                               | 30 +++++-----
 3 files changed, 69 insertions(+), 42 deletions(-)

diff --git a/index/src/pixelrag_index/pipelines.py b/index/src/pixelrag_index/pipelines.py
index 6d6f6180..5fc7d611 100644
--- a/index/src/pixelrag_index/pipelines.py
+++ b/index/src/pixelrag_index/pipelines.py
@@ -95,41 +95,68 @@ def build(config: dict, limit: int | None = None, force: bool = False) -> Path:
     # Render text files (.md, .txt) — convert to styled HTML, then render via CDP
     if text_docs:
         import html as html_mod
+        import re
         import tempfile
 
+        import markdown as md_lib
+
         _HTML_TEMPLATE = (
             '<html><head><meta charset="utf-8"><style>'
-            "body { font-family: -apple-system, system-ui, sans-serif; "
-            "max-width: 860px; margin: 40px auto; padding: 20px; line-height: 1.7; "
-            "color: #1a1a1a; } "
-            "pre, code { background: #f4f4f5; padding: 2px 6px; border-radius: 4px; "
-            "font-size: 14px; } "
-            "pre { padding: 16px; overflow-x: auto; white-space: pre-wrap; } "
-            "h1,h2,h3 { color: #111; } "
-            "table { border-collapse: collapse; width: 100%; } "
-            "th, td { border: 1px solid #ddd; padding: 8px; text-align: left; }"
+            "body { font-family: -apple-system, system-ui, 'Segoe UI', Helvetica, Arial, sans-serif; "
+            "max-width: 860px; margin: 40px auto; padding: 20px; line-height: 1.6; "
+            "color: #1f2328; font-size: 16px; } "
+            "h1, h2, h3 { border-bottom: 1px solid #d1d9e0; padding-bottom: 0.3em; } "
+            "h1 { font-size: 2em; } h2 { font-size: 1.5em; } h3 { font-size: 1.25em; } "
+            "code { background: #eff1f3; padding: 0.2em 0.4em; border-radius: 6px; font-size: 85%%; "
+            "font-family: ui-monospace, 'SFMono-Regular', Menlo, Consolas, monospace; } "
+            "pre { background: #f6f8fa; padding: 16px; border-radius: 6px; overflow-x: auto; } "
+            "pre code { background: none; padding: 0; } "
+            "table { border-collapse: collapse; width: 100%%; margin: 16px 0; } "
+            "th, td { border: 1px solid #d1d9e0; padding: 6px 13px; } "
+            "th { background: #f6f8fa; font-weight: 600; } "
+            "a { color: #0969da; text-decoration: none; } "
+            "blockquote { border-left: 4px solid #d1d9e0; margin: 0; padding: 0 16px; color: #59636e; } "
+            "img { max-width: 100%%; } "
+            "hr { border: none; border-top: 1px solid #d1d9e0; margin: 24px 0; } "
             "</style></head><body>"
         )
-        tmp_dir = tempfile.mkdtemp(prefix="pixelrag_text_")
+
+        def _resolve_relative_paths(html_str: str, base_dir: str) -> str:
+            """Rewrite relative src/href paths to file:// so the browser can load them."""
+            def _repl(m: re.Match) -> str:
+                attr, quote, url = m.group(1), m.group(2), m.group(3)
+                if url.startswith(("http://", "https://", "file://", "data:", "#")):
+                    return m.group(0)
+                resolved = (Path(base_dir) / url).resolve()
+                return f'{attr}={quote}{resolved.as_uri()}{quote}'
+            return re.sub(r'(src|href)=(["\'])([^"\']+)\2', _repl, html_str)
+
         text_urls = []
         text_stems = []
 
-        for idx, doc in text_docs:
-            if (tiles_dir / f"{idx}.png.tiles" / "tiles.json").exists():
-                continue
-            content = Path(doc.path).read_text(errors="replace")
-            escaped = html_mod.escape(content)
-            html_content = f"{_HTML_TEMPLATE}<pre>{escaped}</pre></body></html>"
-            html_path = Path(tmp_dir) / f"{idx}.html"
-            html_path.write_text(html_content)
-            text_urls.append(f"file://{html_path.resolve()}")
-            text_stems.append(str(idx))
-
-        if text_urls:
-            text_ingest = {k: v for k, v in ingest_cfg.items() if k != "backend"}
-            render_urls(
-                text_urls, str(tiles_dir), backend="cdp", stems=text_stems, **text_ingest
-            )
+        with tempfile.TemporaryDirectory(prefix="pixelrag_text_") as tmp_dir:
+            for idx, doc in text_docs:
+                if (tiles_dir / f"{idx}.png.tiles" / "tiles.json").exists():
+                    continue
+                src_path = Path(doc.path)
+                content = src_path.read_text(errors="replace")
+                ext = (doc.metadata or {}).get("extension", src_path.suffix.lower())
+                if ext == ".md":
+                    body = md_lib.markdown(content, extensions=["tables", "fenced_code"])
+                else:
+                    body = f"<pre>{html_mod.escape(content)}</pre>"
+                body = _resolve_relative_paths(body, str(src_path.parent))
+                html_content = f"{_HTML_TEMPLATE}{body}</body></html>"
+                html_path = Path(tmp_dir) / f"{idx}.html"
+                html_path.write_text(html_content)
+                text_urls.append(f"file://{html_path.resolve()}")
+                text_stems.append(str(idx))
+
+            if text_urls:
+                text_ingest = {k: v for k, v in ingest_cfg.items() if k != "backend"}
+                render_urls(
+                    text_urls, str(tiles_dir), backend="cdp", stems=text_stems, **text_ingest
+                )
         logger.info("  Rendered %d text files (.md/.txt)", len(text_docs))
 
     # Render PDFs
diff --git a/pyproject.toml b/pyproject.toml
index 3346f8e7..afc6f006 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -42,7 +42,7 @@ serve = [
     "qwen-vl-utils",
     "pydantic>=2.0.0",
 ]
-index = ["pixelrag[embed]", "pyyaml>=6.0"]
+index = ["pixelrag[embed]", "pyyaml>=6.0", "markdown>=3.4"]
 all = ["pixelrag[embed,serve,index]"]
 gpu = ["faiss-gpu-cu12>=1.13.2; sys_platform == 'linux'"]
 playwright = ["playwright>=1.40.0"]
diff --git a/uv.lock b/uv.lock
index 8e97dc3a..a40f0618 100644
--- a/uv.lock
+++ b/uv.lock
@@ -1,5 +1,5 @@
 version = 1
-revision = 3
+revision = 2
 requires-python = ">=3.12"
 resolution-markers = [
     "python_full_version >= '3.14' and platform_machine != 'aarch64' and sys_platform == 'linux'",
@@ -909,6 +909,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/d9/76/7ffc1d3005cf7749123bc47cb3ea343cd97b0ac2211bab40f57283577d0e/lxml_html_clean-0.4.4-py3-none-any.whl", hash = "sha256:ce2ef506614ecb85ee1c5fe0a2aa45b06a19514ec7949e9c8f34f06925cfabcb", size = 14565, upload-time = "2026-02-27T09:35:51.86Z" },
 ]
 
+[[package]]
+name = "markdown"
+version = "3.10.2"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/2b/f4/69fa6ed85ae003c2378ffa8f6d2e3234662abd02c10d216c0ba96081a238/markdown-3.10.2.tar.gz", hash = "sha256:994d51325d25ad8aa7ce4ebaec003febcce822c3f8c911e3b17c52f7f589f950", size = 368805, upload-time = "2026-02-09T14:57:26.942Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/de/1f/77fa3081e4f66ca3576c896ae5d31c3002ac6607f9747d2e3aa49227e464/markdown-3.10.2-py3-none-any.whl", hash = "sha256:e91464b71ae3ee7afd3017d9f358ef0baf158fd9a298db92f1d4761133824c36", size = 108180, upload-time = "2026-02-09T14:57:25.787Z" },
+]
+
 [[package]]
 name = "markupsafe"
 version = "3.0.3"
@@ -1367,9 +1376,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/43/e3/fdc657359e919462369869f1c9f0e973f353f9a9ee295a39b1fea8ee1a77/pillow-12.2.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:62f5409336adb0663b7caa0da5c7d9e7bdbaae9ce761d34669420c2a801b2780", size = 7087215, upload-time = "2026-04-01T14:43:26.758Z" },
     { url = "https://files.pythonhosted.org/packages/8b/f8/2f6825e441d5b1959d2ca5adec984210f1ec086435b0ed5f52c19b3b8a6e/pillow-12.2.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:01afa7cf67f74f09523699b4e88c73fb55c13346d212a59a2db1f86b0a63e8c5", size = 6509783, upload-time = "2026-04-01T14:43:29.56Z" },
     { url = "https://files.pythonhosted.org/packages/67/f9/029a27095ad20f854f9dba026b3ea6428548316e057e6fc3545409e86651/pillow-12.2.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:fc3d34d4a8fbec3e88a79b92e5465e0f9b842b628675850d860b8bd300b159f5", size = 7212112, upload-time = "2026-04-01T14:43:32.091Z" },
-    { url = "https://files.pythonhosted.org/packages/4a/01/53d10cf0dbad820a8db274d259a37ba50b88b24768ddccec07355382d5ad/pillow-12.2.0-cp313-cp313-ios_13_0_arm64_iphoneos.whl", hash = "sha256:8297651f5b5679c19968abefd6bb84d95fe30ef712eb1b2d9b2d31ca61267f4c", size = 4100837, upload-time = "2026-04-01T14:43:41.506Z" },
-    { url = "https://files.pythonhosted.org/packages/0f/98/f3a6657ecb698c937f6c76ee564882945f29b79bad496abcba0e84659ec5/pillow-12.2.0-cp313-cp313-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:50d8520da2a6ce0af445fa6d648c4273c3eeefbc32d7ce049f22e8b5c3daecc2", size = 4176528, upload-time = "2026-04-01T14:43:43.773Z" },
-    { url = "https://files.pythonhosted.org/packages/69/bc/8986948f05e3ea490b8442ea1c1d4d990b24a7e43d8a51b2c7d8b1dced36/pillow-12.2.0-cp313-cp313-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:766cef22385fa1091258ad7e6216792b156dc16d8d3fa607e7545b2b72061f1c", size = 3640401, upload-time = "2026-04-01T14:43:45.87Z" },
     { url = "https://files.pythonhosted.org/packages/34/46/6c717baadcd62bc8ed51d238d521ab651eaa74838291bda1f86fe1f864c9/pillow-12.2.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:5d2fd0fa6b5d9d1de415060363433f28da8b1526c1c129020435e186794b3795", size = 5308094, upload-time = "2026-04-01T14:43:48.438Z" },
     { url = "https://files.pythonhosted.org/packages/71/43/905a14a8b17fdb1ccb58d282454490662d2cb89a6bfec26af6d3520da5ec/pillow-12.2.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:56b25336f502b6ed02e889f4ece894a72612fe885889a6e8c4c80239ff6e5f5f", size = 4695402, upload-time = "2026-04-01T14:43:51.292Z" },
     { url = "https://files.pythonhosted.org/packages/73/dd/42107efcb777b16fa0393317eac58f5b5cf30e8392e266e76e51cff28c3d/pillow-12.2.0-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:f1c943e96e85df3d3478f7b691f229887e143f81fedab9b20205349ab04d73ed", size = 6280005, upload-time = "2026-04-01T14:43:54.242Z" },
@@ -1386,9 +1392,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/36/a3/f9a77144231fb8d40ee27107b4463e205fa4677e2ca2548e14da5cf18dce/pillow-12.2.0-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:efd8c21c98c5cc60653bcb311bef2ce0401642b7ce9d09e03a7da87c878289d4", size = 7115667, upload-time = "2026-04-01T14:44:32.773Z" },
     { url = "https://files.pythonhosted.org/packages/c1/fc/ac4ee3041e7d5a565e1c4fd72a113f03b6394cc72ab7089d27608f8aaccb/pillow-12.2.0-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:9f08483a632889536b8139663db60f6724bfcb443c96f1b18855860d7d5c0fd4", size = 6538966, upload-time = "2026-04-01T14:44:35.252Z" },
     { url = "https://files.pythonhosted.org/packages/c0/a8/27fb307055087f3668f6d0a8ccb636e7431d56ed0750e07a60547b1e083e/pillow-12.2.0-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:dac8d77255a37e81a2efcbd1fc05f1c15ee82200e6c240d7e127e25e365c39ea", size = 7238241, upload-time = "2026-04-01T14:44:37.875Z" },
-    { url = "https://files.pythonhosted.org/packages/bf/98/4595daa2365416a86cb0d495248a393dfc84e96d62ad080c8546256cb9c0/pillow-12.2.0-cp314-cp314-ios_13_0_arm64_iphoneos.whl", hash = "sha256:3adc9215e8be0448ed6e814966ecf3d9952f0ea40eb14e89a102b87f450660d8", size = 4100848, upload-time = "2026-04-01T14:44:48.48Z" },
-    { url = "https://files.pythonhosted.org/packages/0b/79/40184d464cf89f6663e18dfcf7ca21aae2491fff1a16127681bf1fa9b8cf/pillow-12.2.0-cp314-cp314-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:6a9adfc6d24b10f89588096364cc726174118c62130c817c2837c60cf08a392b", size = 4176515, upload-time = "2026-04-01T14:44:51.353Z" },
-    { url = "https://files.pythonhosted.org/packages/b0/63/703f86fd4c422a9cf722833670f4f71418fb116b2853ff7da722ea43f184/pillow-12.2.0-cp314-cp314-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:6a6e67ea2e6feda684ed370f9a1c52e7a243631c025ba42149a2cc5934dec295", size = 3640159, upload-time = "2026-04-01T14:44:53.588Z" },
     { url = "https://files.pythonhosted.org/packages/71/e0/fb22f797187d0be2270f83500aab851536101b254bfa1eae10795709d283/pillow-12.2.0-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:2bb4a8d594eacdfc59d9e5ad972aa8afdd48d584ffd5f13a937a664c3e7db0ed", size = 5312185, upload-time = "2026-04-01T14:44:56.039Z" },
     { url = "https://files.pythonhosted.org/packages/ba/8c/1a9e46228571de18f8e28f16fabdfc20212a5d019f3e3303452b3f0a580d/pillow-12.2.0-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:80b2da48193b2f33ed0c32c38140f9d3186583ce7d516526d462645fd98660ae", size = 4695386, upload-time = "2026-04-01T14:44:58.663Z" },
     { url = "https://files.pythonhosted.org/packages/70/62/98f6b7f0c88b9addd0e87c217ded307b36be024d4ff8869a812b241d1345/pillow-12.2.0-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:22db17c68434de69d8ecfc2fe821569195c0c373b25cccb9cbdacf2c6e53c601", size = 6280384, upload-time = "2026-04-01T14:45:01.5Z" },
@@ -1424,6 +1427,7 @@ dependencies = [
 all = [
     { name = "faiss-cpu", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "fastapi", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "markdown", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "numpy", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "pydantic", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "pyyaml", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
@@ -1469,6 +1473,7 @@ gpu = [
 ]
 index = [
     { name = "faiss-cpu", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "markdown", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "numpy", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "pyyaml", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "torch", version = "2.9.1+cu129", source = { registry = "https://download.pytorch.org/whl/cu129" }, marker = "sys_platform == 'linux'" },
@@ -1513,6 +1518,7 @@ requires-dist = [
     { name = "fastapi", marker = "extra == 'serve'", specifier = ">=0.115.0" },
     { name = "huggingface-hub", marker = "extra == 'eval'", specifier = ">=0.20" },
     { name = "libzim", marker = "extra == 'kiwix'", specifier = ">=3.6.0" },
+    { name = "markdown", marker = "extra == 'index'", specifier = ">=3.4" },
     { name = "numpy", marker = "extra == 'embed'", specifier = ">=1.26.0" },
     { name = "numpy", marker = "extra == 'serve'", specifier = ">=1.26.0" },
     { name = "openai", marker = "extra == 'eval'", specifier = ">=1.0" },
@@ -2429,10 +2435,7 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/8a/85/237e446c25abced71e9c53d269f2cef5bab8a82b3f88a12e00c5368e7368/xxhash-3.7.0-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:44fba4a5f1d179b7ddc7b3dc40f56f9209046421679b57025d4d8821b376fd8d", size = 275345, upload-time = "2026-04-25T11:06:42.525Z" },
     { url = "https://files.pythonhosted.org/packages/62/34/c2c26c0a6a9cc739bc2a5f0ae03ba8b87deb12b8bce35f7ac495e790dc6d/xxhash-3.7.0-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:31e3516a0f829d06ded4a2c0f3c7c5561993256bfa1c493975fb9dc7bfa828a1", size = 414056, upload-time = "2026-04-25T11:06:44.343Z" },
     { url = "https://files.pythonhosted.org/packages/a0/aa/5c58e9bc8071b8afd8dcf297ff362f723c4892168faba149f19904132bf4/xxhash-3.7.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:b59ee2ac81de57771a09ecad09191e840a1d2fae1ef684208320591055768f83", size = 191485, upload-time = "2026-04-25T11:06:46.262Z" },
-    { url = "https://files.pythonhosted.org/packages/c1/ca/d5174b4c36d10f64d4ca7050563138c5a599efb01a765858ddefc9c1202a/xxhash-3.7.0-cp313-cp313-android_21_arm64_v8a.whl", hash = "sha256:4b6d6b33f141158692bd4eafbb96edbc5aa0dabdb593a962db01a91983d4f8fa", size = 36813, upload-time = "2026-04-25T11:06:51.73Z" },
-    { url = "https://files.pythonhosted.org/packages/bf/11/4cc834eb3d79f2f2b3a6ef7324195208bcdfbdcf7534d2b17267aa5f3a8f/xxhash-3.7.0-cp313-cp313-ios_13_0_arm64_iphoneos.whl", hash = "sha256:fddbbb69a6fff4f421e7a0d1fa28f894b20112e9e3fab306af451e2dfd0e459b", size = 29624, upload-time = "2026-04-25T11:06:54.311Z" },
-    { url = "https://files.pythonhosted.org/packages/23/83/e97d3e7b635fe73a1dfb1e91f805324dd6d930bb42041cbf18f183bc0b6d/xxhash-3.7.0-cp313-cp313-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:54876a4e45101cec2bf8f31a973cda073a23e2e108538dad224ba07f85f22487", size = 30638, upload-time = "2026-04-25T11:06:55.864Z" },
-    { url = "https://files.pythonhosted.org/packages/f4/40/d84951d80c35db1f4c40a29a64a8520eea5d56e764c603906b4fe763580f/xxhash-3.7.0-cp313-cp313-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:0c72fe9c7e3d6dfd7f1e21e224a877917fa09c465694ba4e06464b9511b65544", size = 33323, upload-time = "2026-04-25T11:06:57.336Z" },
+    { url = "https://files.pythonhosted.org/packages/41/d0/abc6c9d347ba1f1e1e1d98125d0881a0452c7f9a76a9dd03a7b5d2197f23/xxhash-3.7.0-cp313-cp313-android_21_x86_64.whl", hash = "sha256:845d347df254d6c619f616afa921331bada8614b8d373d58725c663ba97c3605", size = 35121, upload-time = "2026-04-25T11:06:53.048Z" },
     { url = "https://files.pythonhosted.org/packages/89/cc/c7dc6558d97e9ab023f663d69ab28b340ed9bf4d2d94f2c259cf896bb354/xxhash-3.7.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:a6d73a830b17ef49bc04e00182bd839164c1b3c59c127cd7c54fcb10c7ed8ee8", size = 33362, upload-time = "2026-04-25T11:06:58.656Z" },
     { url = "https://files.pythonhosted.org/packages/2a/6e/46b84017b1301d54091430353d4ad5901654a3e0871649877a416f7f1644/xxhash-3.7.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:91c3b07cf3362086d8f126c6aecd8e5e9396ad8b2f2219ea7e49a8250c318acd", size = 30874, upload-time = "2026-04-25T11:06:59.834Z" },
     { url = "https://files.pythonhosted.org/packages/df/5e/8f9158e3ab906ad3fec51e09b5ea0093e769f12207bfa42a368ca204e7ab/xxhash-3.7.0-cp313-cp313-manylinux1_i686.manylinux_2_28_i686.manylinux_2_5_i686.whl", hash = "sha256:50e879ebbac351c81565ca108db766d7832f5b8b6a5b14b8c0151f7190028e3d", size = 194185, upload-time = "2026-04-25T11:07:01.658Z" },
@@ -2465,10 +2468,7 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/a1/7e/106d4067130c59f1e18a55ffadcd876d8c68534883a1e02685b29d3d8153/xxhash-3.7.0-cp313-cp313t-musllinux_1_2_riscv64.whl", hash = "sha256:1910df4756a5ab58cfad8744fc2d0f23926e3efcc346ee76e87b974abab922f4", size = 277600, upload-time = "2026-04-25T11:07:51.745Z" },
     { url = "https://files.pythonhosted.org/packages/c5/86/a081dd30da71d720b2612a792bfd55e45fa9a07ac76a0507f60487473c25/xxhash-3.7.0-cp313-cp313t-musllinux_1_2_s390x.whl", hash = "sha256:d006faf3b491957efcb433489be3c149efe4787b7063d5cddb8ddaefdc60e0c1", size = 416980, upload-time = "2026-04-25T11:07:53.504Z" },
     { url = "https://files.pythonhosted.org/packages/35/29/1a95221a029a3c1293773869e1ab47b07cbbdd82444a42809e8c60156626/xxhash-3.7.0-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:abb65b4e947e958f7b3b0d71db3ce447d1bc5f37f5eab871ce7223bda8768a04", size = 193840, upload-time = "2026-04-25T11:07:55.103Z" },
-    { url = "https://files.pythonhosted.org/packages/0e/cc/431db584f6fbb9312e40a173af027644e5580d39df1f73603cbb9dca4d6b/xxhash-3.7.0-cp314-cp314-android_24_arm64_v8a.whl", hash = "sha256:8c5fcfd806c335bfa2adf1cd0b3110a44fc7b6995c3a648c27489bae85801465", size = 36644, upload-time = "2026-04-25T11:08:00.658Z" },
-    { url = "https://files.pythonhosted.org/packages/68/70/c55fc33c93445b44d8fc5a17b41ed99e3cebe92bcf8396809e63fc9a1165/xxhash-3.7.0-cp314-cp314-ios_13_0_arm64_iphoneos.whl", hash = "sha256:ec68dbba21532c0173a9872298e65c89749f7c9d21538c3a78b5bb6105871568", size = 29655, upload-time = "2026-04-25T11:08:03.701Z" },
-    { url = "https://files.pythonhosted.org/packages/c2/72/ff8de73df000d74467d12a59ce6d6e2b2a368b978d41ab7b1fba5ed442be/xxhash-3.7.0-cp314-cp314-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:fa77e7ec1450d415d20129961814787c9abd9a07f98872f070b1fe96c5084611", size = 30664, upload-time = "2026-04-25T11:08:05.011Z" },
-    { url = "https://files.pythonhosted.org/packages/b6/91/08416d9bd9bc3bf39d831abe8a5631ac2db5141dfd6fe81c3fe59a1f9264/xxhash-3.7.0-cp314-cp314-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:fe32736295ea38e43e7d9424053c8c47c9f64fecfc7c895fb3da9b30b131c9ee", size = 33317, upload-time = "2026-04-25T11:08:06.413Z" },
+    { url = "https://files.pythonhosted.org/packages/bc/01/255ec513e0a705d1f9a61413e78dfce4e3235203f0ed525a24c2b4b56345/xxhash-3.7.0-cp314-cp314-android_24_x86_64.whl", hash = "sha256:506a0b488f190f0a06769575e30caf71615c898ed93ab18b0dbcb6dec5c3713c", size = 35003, upload-time = "2026-04-25T11:08:02.338Z" },
     { url = "https://files.pythonhosted.org/packages/0e/3b/86b1caa4dee10a99f4bf9521e623359341c5e50d05158fa10c275b2bd079/xxhash-3.7.0-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:ab9dd2c83c4bbd63e422181a76f13502d049d3ddcac9a1bdc29196263d692bb8", size = 33457, upload-time = "2026-04-25T11:08:08.099Z" },
     { url = "https://files.pythonhosted.org/packages/ed/38/98ea14ad1517e1461292a65906951458d520689782bfbae111050145bdba/xxhash-3.7.0-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:3afec3a336a2286601a437cb07562ab0227685e6fbb9ec17e8c18457ff348ecf", size = 30894, upload-time = "2026-04-25T11:08:09.429Z" },
     { url = "https://files.pythonhosted.org/packages/61/a2/074654d0b893606541199993c7db70067d9fc63b748e0d60020a52a1bd36/xxhash-3.7.0-cp314-cp314-manylinux1_i686.manylinux_2_28_i686.manylinux_2_5_i686.whl", hash = "sha256:565df64437a9390f84465dcca33e7377114c7ede8d05cd2cf20081f831ea788e", size = 194409, upload-time = "2026-04-25T11:08:10.91Z" },

From ebbdf53db010a5c5e0aa120f678e1f0de2664a42 Mon Sep 17 00:00:00 2001
From: yichuan520030910320 <yichuan_wang@berkeley.edu>
Date: Sat, 27 Jun 2026 00:55:33 -0700
Subject: [PATCH 2/3] style: ruff format pipelines.py

---
 index/src/pixelrag_index/pipelines.py | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/index/src/pixelrag_index/pipelines.py b/index/src/pixelrag_index/pipelines.py
index 5fc7d611..2d517969 100644
--- a/index/src/pixelrag_index/pipelines.py
+++ b/index/src/pixelrag_index/pipelines.py
@@ -123,12 +123,14 @@ def build(config: dict, limit: int | None = None, force: bool = False) -> Path:
 
         def _resolve_relative_paths(html_str: str, base_dir: str) -> str:
             """Rewrite relative src/href paths to file:// so the browser can load them."""
+
             def _repl(m: re.Match) -> str:
                 attr, quote, url = m.group(1), m.group(2), m.group(3)
                 if url.startswith(("http://", "https://", "file://", "data:", "#")):
                     return m.group(0)
                 resolved = (Path(base_dir) / url).resolve()
-                return f'{attr}={quote}{resolved.as_uri()}{quote}'
+                return f"{attr}={quote}{resolved.as_uri()}{quote}"
+
             return re.sub(r'(src|href)=(["\'])([^"\']+)\2', _repl, html_str)
 
         text_urls = []
@@ -142,7 +144,9 @@ def _repl(m: re.Match) -> str:
                 content = src_path.read_text(errors="replace")
                 ext = (doc.metadata or {}).get("extension", src_path.suffix.lower())
                 if ext == ".md":
-                    body = md_lib.markdown(content, extensions=["tables", "fenced_code"])
+                    body = md_lib.markdown(
+                        content, extensions=["tables", "fenced_code"]
+                    )
                 else:
                     body = f"<pre>{html_mod.escape(content)}</pre>"
                 body = _resolve_relative_paths(body, str(src_path.parent))
@@ -155,7 +159,11 @@ def _repl(m: re.Match) -> str:
             if text_urls:
                 text_ingest = {k: v for k, v in ingest_cfg.items() if k != "backend"}
                 render_urls(
-                    text_urls, str(tiles_dir), backend="cdp", stems=text_stems, **text_ingest
+                    text_urls,
+                    str(tiles_dir),
+                    backend="cdp",
+                    stems=text_stems,
+                    **text_ingest,
                 )
         logger.info("  Rendered %d text files (.md/.txt)", len(text_docs))
 

From d84720178bc46c92fd129c392cdbfab8c1d25648 Mon Sep 17 00:00:00 2001
From: yichuan520030910320 <yichuan_wang@berkeley.edu>
Date: Sat, 27 Jun 2026 00:58:05 -0700
Subject: [PATCH 3/3] style: ruff format test_local_source_text.py

---
 tests/test_local_source_text.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/test_local_source_text.py b/tests/test_local_source_text.py
index 160a7beb..48aac6a4 100644
--- a/tests/test_local_source_text.py
+++ b/tests/test_local_source_text.py
@@ -26,7 +26,7 @@ def test_local_source_discovers_text_files(text_dir):
     names = {d.id for d in docs}
     assert "guide" in names  # .md
     assert "notes" in names  # .txt
-    assert "page" in names   # .html
+    assert "page" in names  # .html
     assert "photo" in names  # .png
     assert "ignored" not in names  # .csv not supported