deepresearch-flow 0.4.0__tar.gz → 0.4.1__tar.gz

{deepresearch_flow-0.4.0/python/deepresearch_flow.egg-info → deepresearch_flow-0.4.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deepresearch-flow
-Version: 0.4.0
+Version: 0.4.1
 Summary: Workflow tools for paper extraction, review, and research automation.
 Author-email: DengQi <dengqi935@gmail.com>
 License: MIT License
@@ -51,9 +51,10 @@ Requires-Dist: jsonschema>=4.21.1
 Requires-Dist: markdown-it-py>=3.0.0
 Requires-Dist: mdit-py-plugins>=0.4.0
 Requires-Dist: pypdf>=3.0.0
+Requires-Dist: pylatexenc>=2.10
 Requires-Dist: pybtex>=0.24.0
 Requires-Dist: rich>=13.7.1
-Requires-Dist: rumdl>=0.0.214
+Requires-Dist: rumdl>=0.0.218
 Requires-Dist: starlette>=0.37.2
 Requires-Dist: tqdm>=4.66.4
 Requires-Dist: uvicorn>=0.27.1
@@ -172,7 +173,36 @@ uv run deepresearch-flow translator translate \
   --fix-level moderate
 ```
 
-#### Step 3: Serve Your Database
+#### Step 3: Repair OCR Outputs (Recommended)
+
+Recommended sequence to stabilize markdown before serving:
+
+```bash
+# 1) Fix OCR markdown (auto-detects JSON if inputs are .json)
+uv run deepresearch-flow recognize fix \
+  --input ./docs \
+  --in-place
+
+# 2) Fix LaTeX formulas
+uv run deepresearch-flow recognize fix-math \
+  --input ./docs \
+  --model openai/gpt-4o-mini \
+  --in-place
+
+# 3) Fix Mermaid diagrams
+uv run deepresearch-flow recognize fix-mermaid \
+  --input ./paper_outputs \
+  --json \
+  --model openai/gpt-4o-mini \
+  --in-place
+
+# 4) Fix again to normalize formatting
+uv run deepresearch-flow recognize fix \
+  --input ./docs \
+  --in-place
+```
+
+#### Step 4: Serve Your Database
 
 Launch a local UI to read and manage your papers.
 
@@ -275,6 +305,10 @@ Tools to clean up raw outputs from OCR engines like MinerU.
 - Unpack Images: extract Base64 images back to files.
 - Organize: flatten nested OCR output directories.
 - Fix: apply OCR fixes and rumdl formatting during organize, or as a standalone step.
+- Fix JSON: apply the same fixes to markdown fields inside paper JSON outputs.
+- Fix Math: validate and repair LaTeX formulas with optional LLM assistance.
+- Fix Mermaid: validate and repair Mermaid diagrams (requires `mmdc` from mermaid-cli).
+- Recommended order: `fix` -> `fix-math` -> `fix-mermaid` -> `fix`.
 
 ```bash
 uv run deepresearch-flow recognize md embed --input ./raw_ocr --output ./clean_md
@@ -296,6 +330,25 @@ uv run deepresearch-flow recognize fix \
 uv run deepresearch-flow recognize fix \
   --input ./ocr_md \
   --in-place
+
+# Fix JSON outputs in place
+uv run deepresearch-flow recognize fix \
+  --json \
+  --input ./paper_outputs \
+  --in-place
+
+# Fix LaTeX formulas in markdown
+uv run deepresearch-flow recognize fix-math \
+  --input ./docs \
+  --model openai/gpt-4o-mini \
+  --in-place
+
+# Fix Mermaid diagrams in JSON outputs
+uv run deepresearch-flow recognize fix-mermaid \
+  --json \
+  --input ./paper_outputs \
+  --model openai/gpt-4o-mini \
+  --in-place
 ```
 
 </details>

{deepresearch_flow-0.4.0 → deepresearch_flow-0.4.1}/README.md

@@ -111,7 +111,36 @@ uv run deepresearch-flow translator translate \
   --fix-level moderate
 ```
 
-#### Step 3: Serve Your Database
+#### Step 3: Repair OCR Outputs (Recommended)
+
+Recommended sequence to stabilize markdown before serving:
+
+```bash
+# 1) Fix OCR markdown (auto-detects JSON if inputs are .json)
+uv run deepresearch-flow recognize fix \
+  --input ./docs \
+  --in-place
+
+# 2) Fix LaTeX formulas
+uv run deepresearch-flow recognize fix-math \
+  --input ./docs \
+  --model openai/gpt-4o-mini \
+  --in-place
+
+# 3) Fix Mermaid diagrams
+uv run deepresearch-flow recognize fix-mermaid \
+  --input ./paper_outputs \
+  --json \
+  --model openai/gpt-4o-mini \
+  --in-place
+
+# 4) Fix again to normalize formatting
+uv run deepresearch-flow recognize fix \
+  --input ./docs \
+  --in-place
+```
+
+#### Step 4: Serve Your Database
 
 Launch a local UI to read and manage your papers.
 
@@ -214,6 +243,10 @@ Tools to clean up raw outputs from OCR engines like MinerU.
 - Unpack Images: extract Base64 images back to files.
 - Organize: flatten nested OCR output directories.
 - Fix: apply OCR fixes and rumdl formatting during organize, or as a standalone step.
+- Fix JSON: apply the same fixes to markdown fields inside paper JSON outputs.
+- Fix Math: validate and repair LaTeX formulas with optional LLM assistance.
+- Fix Mermaid: validate and repair Mermaid diagrams (requires `mmdc` from mermaid-cli).
+- Recommended order: `fix` -> `fix-math` -> `fix-mermaid` -> `fix`.
 
 ```bash
 uv run deepresearch-flow recognize md embed --input ./raw_ocr --output ./clean_md
@@ -235,6 +268,25 @@ uv run deepresearch-flow recognize fix \
 uv run deepresearch-flow recognize fix \
   --input ./ocr_md \
   --in-place
+
+# Fix JSON outputs in place
+uv run deepresearch-flow recognize fix \
+  --json \
+  --input ./paper_outputs \
+  --in-place
+
+# Fix LaTeX formulas in markdown
+uv run deepresearch-flow recognize fix-math \
+  --input ./docs \
+  --model openai/gpt-4o-mini \
+  --in-place
+
+# Fix Mermaid diagrams in JSON outputs
+uv run deepresearch-flow recognize fix-mermaid \
+  --json \
+  --input ./paper_outputs \
+  --model openai/gpt-4o-mini \
+  --in-place
 ```
 
 </details>

{deepresearch_flow-0.4.0 → deepresearch_flow-0.4.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "deepresearch-flow"
-version = "0.4.0"
+version = "0.4.1"
 description = "Workflow tools for paper extraction, review, and research automation."
 readme = { file = "README.md", content-type = "text/markdown" }
 license = { file = "LICENSE" }
@@ -20,9 +20,10 @@ dependencies = [
     "markdown-it-py>=3.0.0",
     "mdit-py-plugins>=0.4.0",
     "pypdf>=3.0.0",
+    "pylatexenc>=2.10",
     "pybtex>=0.24.0",
     "rich>=13.7.1",
-    "rumdl>=0.0.214",
+    "rumdl>=0.0.218",
     "starlette>=0.37.2",
     "tqdm>=4.66.4",
     "uvicorn>=0.27.1",
@@ -60,3 +61,4 @@ include-package-data = true
 "deepresearch_flow.paper.prompt_templates" = ["*.j2"]
 "deepresearch_flow.paper.examples" = ["*.toml"]
 "deepresearch_flow.paper.web" = ["pdfjs/**/*", "templates/**/*", "static/**/*"]
+"deepresearch_flow.recognize" = ["*.js"]

{deepresearch_flow-0.4.0 → deepresearch_flow-0.4.1}/python/deepresearch_flow/paper/web/constants.py

@@ -4,10 +4,10 @@ from pathlib import Path
 
 # CDN URLs for external libraries
 CDN_ECHARTS = "https://cdn.jsdelivr.net/npm/echarts@5/dist/echarts.min.js"
-CDN_MERMAID = "https://cdn.jsdelivr.net/npm/mermaid@10/dist/mermaid.min.js"
-CDN_KATEX = "https://cdn.jsdelivr.net/npm/katex@0.16.10/dist/katex.min.css"
-CDN_KATEX_JS = "https://cdn.jsdelivr.net/npm/katex@0.16.10/dist/katex.min.js"
-CDN_KATEX_AUTO = "https://cdn.jsdelivr.net/npm/katex@0.16.10/dist/contrib/auto-render.min.js"
+CDN_MERMAID = "https://cdn.jsdelivr.net/npm/mermaid@11/dist/mermaid.min.js"
+CDN_KATEX = "https://cdn.jsdelivr.net/npm/katex@0.16.27/dist/katex.min.css"
+CDN_KATEX_JS = "https://cdn.jsdelivr.net/npm/katex@0.16.27/dist/katex.min.js"
+CDN_KATEX_AUTO = "https://cdn.jsdelivr.net/npm/katex@0.16.27/dist/contrib/auto-render.min.js"
 
 # Use legacy builds to ensure `pdfjsLib` is available as a global.
 CDN_PDFJS = "https://cdn.jsdelivr.net/npm/pdfjs-dist@3.11.174/legacy/build/pdf.min.js"

{deepresearch_flow-0.4.0 → deepresearch_flow-0.4.1}/python/deepresearch_flow/paper/web/templates/detail.html

@@ -1,7 +1,7 @@
 {% extends "base.html" %}
 
 {% block extra_head %}
-<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/katex@0.16.10/dist/katex.min.css" />
+<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/katex@0.16.27/dist/katex.min.css" />
 <style>
   #content img {
     max-width: 100%;
@@ -251,8 +251,8 @@
 
 {% block extra_scripts %}
 {# CDN scripts for markdown rendering #}
-<script src="https://cdn.jsdelivr.net/npm/katex@0.16.10/dist/katex.min.js"></script>
-<script src="https://cdn.jsdelivr.net/npm/katex@0.16.10/dist/contrib/auto-render.min.js"></script>
+<script src="https://cdn.jsdelivr.net/npm/katex@0.16.27/dist/katex.min.js"></script>
+<script src="https://cdn.jsdelivr.net/npm/katex@0.16.27/dist/contrib/auto-render.min.js"></script>
 <script src="https://cdn.jsdelivr.net/npm/mermaid@10.6.1/dist/mermaid.min.js"></script>
 <script src="https://cdn.jsdelivr.net/npm/markmap-lib@0.15.4/dist/browser/index.min.js"></script>
 <script src="https://cdn.jsdelivr.net/npm/markmap-view@0.15.4/dist/index.min.js"></script>

{deepresearch_flow-0.4.0 → deepresearch_flow-0.4.1}/python/deepresearch_flow/paper/web/templates/index.html

@@ -1,7 +1,7 @@
 {% extends "base.html" %}
 
 {% block extra_head %}
-<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/katex@0.16.10/dist/katex.min.css" />
+<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/katex@0.16.27/dist/katex.min.css" />
 <style>
   #content img {
     max-width: 100%;
@@ -108,7 +108,7 @@
 {% endblock %}
 
 {% block extra_scripts %}
-<script src="https://cdn.jsdelivr.net/npm/katex@0.16.10/dist/katex.min.js"></script>
-<script src="https://cdn.jsdelivr.net/npm/katex@0.16.10/dist/contrib/auto-render.min.js"></script>
+<script src="https://cdn.jsdelivr.net/npm/katex@0.16.27/dist/katex.min.js"></script>
+<script src="https://cdn.jsdelivr.net/npm/katex@0.16.27/dist/contrib/auto-render.min.js"></script>
 <script src="/static/js/index.js"></script>
 {% endblock %}