mistocr 0.2.1__py3-none-any.whl → 0.2.5__py3-none-any.whl

mistocr/__init__.py

@@ -1 +1 @@
-__version__ = "0.2.1"
+__version__ = "0.2.5"

mistocr/refine.py

@@ -197,8 +197,8 @@ async def describe_imgs(
     imgs: list[Path], # List of image file paths to describe
     model: str = 'claude-sonnet-4-5', # Model to use for image description
     prompt: str = describe_img_prompt, # Prompt template for description
-    semaphore: int = 2, # Max concurrent API requests
-    delay: float = 1 # Delay in seconds between requests
+    semaphore: int = 10, # Max concurrent API requests
+    delay: float = 0.1 # Delay in seconds between requests
 ) -> dict[str, dict]: # Dict mapping filename to parsed description
     "Describe multiple images in parallel with rate limiting"
     sem = Semaphore(semaphore)

{mistocr-0.2.1.dist-info → mistocr-0.2.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mistocr
-Version: 0.2.1
+Version: 0.2.5
 Summary: Batch OCR for PDFs with heading restoration and visual content integration
 Home-page: https://github.com/franckalbinet/mistocr
 Author: Solveit
@@ -38,7 +38,7 @@ Dynamic: requires-dist
 Dynamic: requires-python
 Dynamic: summary
 
-# mistocr
+# Mistocr
 
 
 <!-- WARNING: THIS FILE WAS AUTOGENERATED! DO NOT EDIT! -->
@@ -69,12 +69,20 @@ fundamental challenges that raw OCR output leaves unsolved:
   markdown. This makes visual information searchable and accessible for
   downstream applications.
 
-- **Cost-efficient batch processing**: By exclusively using Mistral’s
-  batch API, mistocr cuts costs by 50% (\$0.50 vs \$1.00 per 1000 pages)
-  while eliminating the boilerplate code typically required.
+- **Cost-efficient batch processing**: The OCR step exclusively uses
+  Mistral’s batch API, cutting costs by 50% (\$0.50 vs \$1.00 per 1000
+  pages) while eliminating the boilerplate code typically required.
 
-**In short**: Production-ready batch OCR with intelligent postprocessing
-that ensures your documents are actually usable for AI systems.
+**In short**: Complete PDF OCR with heading hierarchy fixes and image
+descriptions for RAG and LLM pipelines.
+
+> [!NOTE]
+>
+> **Want to see mistocr in action?** This
+> [tutorial](https://share.solve.it.com/d/97f75412ca949af76a5945b4dfc443c7)
+> demonstrates real-world PDF processing and shows how clean markdown
+> enables structure-aware navigation through long documents—letting you
+> find exactly what you need, fast.
 
 ## Get Started
 
@@ -94,7 +102,10 @@ os.environ['ANTHROPIC_API_KEY'] = 'your-key-here'  # for refine features (see Ad
 
 ### Complete Pipeline
 
-Full pipeline with all features:
+#### Single File Processing
+
+Process a single PDF with OCR (using Mistral’s batch API for cost
+efficiency), heading fixes, and image descriptions:
 
 ``` python
 from mistocr.pipeline import pdf_to_md
@@ -171,12 +182,12 @@ instead.
 
 ### Advanced Usage
 
-**Batch process entire folders:**
+**Batch OCR for entire folders:**
 
 ``` python
 from mistocr.core import ocr_pdf
 
-# Process all PDFs in a folder
+# OCR all PDFs in a folder using Mistral's batch API
 output_dirs = ocr_pdf('path/to/pdf_folder', dst='output_folder')
 ```
 

mistocr-0.2.5.dist-info/RECORD

@@ -0,0 +1,11 @@
+mistocr/__init__.py,sha256=Xsa3ayOMVkhUWm4t06YeyHE0apjpZefxLH4ylp0CDtU,22
+mistocr/_modidx.py,sha256=JtXJb6ErVwyGFCWgeVz7N9JvybBp8Zyao4Ahn3smr90,4030
+mistocr/core.py,sha256=KH5ND6ZMmETj9m9A-Ivtw5N2L-qm9vGwYgvHAzg-BsA,7218
+mistocr/pipeline.py,sha256=k5rtr9ccxTgwQAzw533iMIL9qwiCofugWv0fhotLzaI,1639
+mistocr/refine.py,sha256=arJPOg1eP4MwtkD1zwnYY4EFrBfTTSP-mtR4AVnTiR8,11788
+mistocr-0.2.5.dist-info/licenses/LICENSE,sha256=xV8xoN4VOL0uw9X8RSs2IMuD_Ss_a9yAbtGNeBWZwnw,11337
+mistocr-0.2.5.dist-info/METADATA,sha256=uGim0pZ4V3-oolsihRFr4aOWh3ZDOO7u3d8Mn0n-gmc,8416
+mistocr-0.2.5.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+mistocr-0.2.5.dist-info/entry_points.txt,sha256=HjAiHozobM-alm_6bTF-ehRr2DD3KYE9PgRngelONOY,36
+mistocr-0.2.5.dist-info/top_level.txt,sha256=LelTYnSpSXLy1Hb1m2YP3gt8luwP-I8KV0NjP_ucdSs,8
+mistocr-0.2.5.dist-info/RECORD,,

mistocr-0.2.1.dist-info/RECORD

@@ -1,11 +0,0 @@
-mistocr/__init__.py,sha256=HfjVOrpTnmZ-xVFCYSVmX50EXaBQeJteUHG-PD6iQs8,22
-mistocr/_modidx.py,sha256=JtXJb6ErVwyGFCWgeVz7N9JvybBp8Zyao4Ahn3smr90,4030
-mistocr/core.py,sha256=KH5ND6ZMmETj9m9A-Ivtw5N2L-qm9vGwYgvHAzg-BsA,7218
-mistocr/pipeline.py,sha256=k5rtr9ccxTgwQAzw533iMIL9qwiCofugWv0fhotLzaI,1639
-mistocr/refine.py,sha256=zsPoxWD63bk1rzRVO9OPsevWeMNORHgT_y8H7T7CxYs,11785
-mistocr-0.2.1.dist-info/licenses/LICENSE,sha256=xV8xoN4VOL0uw9X8RSs2IMuD_Ss_a9yAbtGNeBWZwnw,11337
-mistocr-0.2.1.dist-info/METADATA,sha256=-y9Ze92RygrKGCfHbBjlGXlv-5iRYVAOyHtC9MHnplw,7990
-mistocr-0.2.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-mistocr-0.2.1.dist-info/entry_points.txt,sha256=HjAiHozobM-alm_6bTF-ehRr2DD3KYE9PgRngelONOY,36
-mistocr-0.2.1.dist-info/top_level.txt,sha256=LelTYnSpSXLy1Hb1m2YP3gt8luwP-I8KV0NjP_ucdSs,8
-mistocr-0.2.1.dist-info/RECORD,,