deepresearch-flow 0.4.0__py3-none-any.whl → 0.4.1__py3-none-any.whl

{deepresearch_flow-0.4.0.dist-info → deepresearch_flow-0.4.1.dist-info}/METADATA

@@ -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.dist-info → deepresearch_flow-0.4.1.dist-info}/RECORD

@@ -42,7 +42,7 @@ deepresearch_flow/paper/templates/eight_questions.md.j2,sha256=Ecz4CD3nd7jZ4Dg8h
 deepresearch_flow/paper/templates/three_pass.md.j2,sha256=ZRj-NkpZePnqp0gSE8OT1dN5Lr5RW4vdOYdeVejYJW0,1576
 deepresearch_flow/paper/web/__init__.py,sha256=eQBtBjvOYsNEdivHTI0aO286SCG2c86xI02tf-0jz5I,39
 deepresearch_flow/paper/web/app.py,sha256=rXnQjffyzH5b64oCwv6ucihU_y5zaFbpzdEB5PRUvHc,3063
-deepresearch_flow/paper/web/constants.py,sha256=DzE1TO5Sd-1pfy8ww71J6LnS6cta_Je84jmXyxJ6DNI,1085
+deepresearch_flow/paper/web/constants.py,sha256=HuuE_oZKckmisD3F_1RAqWzO7bnhNmMLyM8FqyM5Yfk,1085
 deepresearch_flow/paper/web/filters.py,sha256=OVMB4GfigP9GPD5dXytHyeLYtnVXEK-QjYfA_k7QbaA,8315
 deepresearch_flow/paper/web/markdown.py,sha256=QHrxUYKB-uAZjG5jVGmkQ6EIT2dSxQNzlibgjGIIKuA,18888
 deepresearch_flow/paper/web/query.py,sha256=vTegfm5zGVkYCd6_K3yNrXJEmKMccUUFKG9DePPcKMw,1938
@@ -427,12 +427,15 @@ deepresearch_flow/paper/web/static/js/index.js,sha256=bbQz8QAewmu3TT8ImAzUqNtTWQ
 deepresearch_flow/paper/web/static/js/outline.js,sha256=e9ydLcBqaTXOYULXt-1OKgKIzrZcZaH1RebPXWBbLvE,1882
 deepresearch_flow/paper/web/static/js/stats.js,sha256=USGIAx9cPQTMeyFwYu_bTYPJM7OoiqimhCYuAjoP0-s,1420
 deepresearch_flow/paper/web/templates/base.html,sha256=4gWJLvjOuDSnBYRpJqxhGKmKC6UuOl19q_Q_cOjhL-g,1806
-deepresearch_flow/paper/web/templates/detail.html,sha256=jM7rkMu1rQs-kx7LHfLwUvv4yJlhua4eE-wZoOJPufA,16332
-deepresearch_flow/paper/web/templates/index.html,sha256=eQJgjr-RuKPcDxdCJG_hM6KvlMYIp-OSG0oQEJHO7Is,6117
+deepresearch_flow/paper/web/templates/detail.html,sha256=VC5VbsaAONajZG8_WFSuURCViRXLdi4gH_wDAMt3EVI,16332
+deepresearch_flow/paper/web/templates/index.html,sha256=qNWwyQWa3QzmHdJbohSe5PJOZS3-KxWjk0RxoQSZiys,6117
 deepresearch_flow/paper/web/templates/stats.html,sha256=bcQBawoZ9KoRkM0NNo9WJBVeN_8O1WU2xNiye-Fugyo,671
 deepresearch_flow/recognize/__init__.py,sha256=yMAqbdCzpdRSiwFhq9j7yx9ZWxqz_Zq3vfYlTLFCWek,33
-deepresearch_flow/recognize/cli.py,sha256=zWUsqvou2h6c5zR_myGaySvK6cG9ItJp9cJFtqqJk7Y,21597
+deepresearch_flow/recognize/cli.py,sha256=QV0d9XhOdcWcr05427GPSSMheal06WvvmejV7wLVfz8,53460
+deepresearch_flow/recognize/katex_check.js,sha256=jKFLk0Y7y_XR0fBJe2xdfQhAMMuYRXo-pSpWqcEyAH0,735
 deepresearch_flow/recognize/markdown.py,sha256=y-PMJbGqrfWCNBVGanXK1M4OuMP9e1eqh7HDYye5a7Q,8757
+deepresearch_flow/recognize/math.py,sha256=qgI4WRsoWgLaue9OxIq1pcO18wUOlpCNBLKQgicN2hs,22623
+deepresearch_flow/recognize/mermaid.py,sha256=O8uQoEC9mG4mSdTpr-OnmP_vrThaFdUeqt6U00m6O-0,22545
 deepresearch_flow/recognize/organize.py,sha256=-KVzuwNjiT2bLwqwLwcguEMQYxnGiZXjLNlov_oXSTo,5237
 deepresearch_flow/translator/__init__.py,sha256=iaAkufvEELVKNbcs08Nh7bkTO4JlkT3rT_JIBP9jGfc,26
 deepresearch_flow/translator/cli.py,sha256=BceOZhQuN9s5kqhpvLJuwpbB5J0MY1ucWUKw0jXWUPc,16872
@@ -443,9 +446,9 @@ deepresearch_flow/translator/placeholder.py,sha256=mEgqA-dPdOsIhno0h_hzfpXpY2asb
 deepresearch_flow/translator/prompts.py,sha256=kl_9O2YvmtXC1w6WLnsLuVZKz4mcOtUF887SiTaOvc0,4754
 deepresearch_flow/translator/protector.py,sha256=sXwNJ1Y8tyPm7dgm8-7S8HkcPe23TGsBdwRxH6mKL70,11291
 deepresearch_flow/translator/segment.py,sha256=rBFMCLTrvm2GrPc_hNFymi-8Ih2DAtUQlZHCRE9nLaM,5146
-deepresearch_flow-0.4.0.dist-info/licenses/LICENSE,sha256=hT8F2Py1pe6flxq3Ufdm2UKFk0B8CBm0aAQfsLXfvjw,1063
-deepresearch_flow-0.4.0.dist-info/METADATA,sha256=FKueIvCHzloXlQk71dliJK29rxEC9tyMOMS7ISXdfAY,11476
-deepresearch_flow-0.4.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-deepresearch_flow-0.4.0.dist-info/entry_points.txt,sha256=1uIKscs0YRMg_mFsg9NjsaTt4CvQqQ_-zGERUKhhL_Y,65
-deepresearch_flow-0.4.0.dist-info/top_level.txt,sha256=qBl4RvPJNJUbL8CFfMNWxY0HpQLx5RlF_ko-z_aKpm0,18
-deepresearch_flow-0.4.0.dist-info/RECORD,,
+deepresearch_flow-0.4.1.dist-info/licenses/LICENSE,sha256=hT8F2Py1pe6flxq3Ufdm2UKFk0B8CBm0aAQfsLXfvjw,1063
+deepresearch_flow-0.4.1.dist-info/METADATA,sha256=bfOksObo91hopsY_NbQNce_FjC8MEW8kkYUjkQQi9Xo,12918
+deepresearch_flow-0.4.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+deepresearch_flow-0.4.1.dist-info/entry_points.txt,sha256=1uIKscs0YRMg_mFsg9NjsaTt4CvQqQ_-zGERUKhhL_Y,65
+deepresearch_flow-0.4.1.dist-info/top_level.txt,sha256=qBl4RvPJNJUbL8CFfMNWxY0HpQLx5RlF_ko-z_aKpm0,18
+deepresearch_flow-0.4.1.dist-info/RECORD,,