visual-parser 1.0.0__tar.gz → 1.0.2__tar.gz

{visual_parser-1.0.0 → visual_parser-1.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: visual-parser
-Version: 1.0.0
+Version: 1.0.2
 Summary: Standalone Visual-RAG PDF Parser — text extraction + Vision-LLM figure descriptions → JSONL
 License: MIT
 Project-URL: Homepage, https://github.com/SmartLabNuclear/RADIANT_LLM
@@ -30,6 +30,8 @@ Requires-Dist: openai==1.78.1
 Requires-Dist: google-generativeai==0.8.5
 Requires-Dist: python-dotenv==1.1.0
 Requires-Dist: tqdm==4.67.1
+Requires-Dist: nltk>=3.8
+Requires-Dist: python-Levenshtein>=0.20
 Provides-Extra: ocr
 Requires-Dist: pytesseract==0.3.13; extra == "ocr"
 Provides-Extra: dev
@@ -52,7 +54,7 @@ Requires-Dist: mypy; extra == "dev"
 
 By default, the pipeline writes:
 - `01_chunks_kb.jsonl`: chunked text extracted from PDFs (Nougat by default).
-- `02_figures_kb.jsonl`: figure/page visual descriptions (Vision LLM).
+- `02_visuals_kb.jsonl`: figure/page visual descriptions (Vision LLM).
 - `03_metadata_kb.jsonl`: document metadata rows (title/author/etc.).
 - `04_processed_pdfs.txt`: a tracker so re-runs only process new PDFs (unless `--rebuild`).
 

{visual_parser-1.0.0 → visual_parser-1.0.2}/README.md

@@ -13,7 +13,7 @@
 
 By default, the pipeline writes:
 - `01_chunks_kb.jsonl`: chunked text extracted from PDFs (Nougat by default).
-- `02_figures_kb.jsonl`: figure/page visual descriptions (Vision LLM).
+- `02_visuals_kb.jsonl`: figure/page visual descriptions (Vision LLM).
 - `03_metadata_kb.jsonl`: document metadata rows (title/author/etc.).
 - `04_processed_pdfs.txt`: a tracker so re-runs only process new PDFs (unless `--rebuild`).
 

{visual_parser-1.0.0 → visual_parser-1.0.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name        = "visual-parser"
-version     = "1.0.0"
+version     = "1.0.2"
 description = "Standalone Visual-RAG PDF Parser — text extraction + Vision-LLM figure descriptions → JSONL"
 readme      = "README.md"
 requires-python = ">=3.10"
@@ -40,6 +40,8 @@ dependencies = [
     "google-generativeai==0.8.5",
     "python-dotenv==1.1.0",
     "tqdm==4.67.1",
+    "nltk>=3.8",
+    "python-Levenshtein>=0.20",
 ]
 
 [project.optional-dependencies]

{visual_parser-1.0.0 → visual_parser-1.0.2}/visual_parser/__init__.py

@@ -7,7 +7,7 @@ a Vision LLM (OpenAI GPT-4o or Google Gemini), and writes three JSONL knowledge
 bases ready for any downstream RAG system:
 
     01_chunks_kb.jsonl   – text chunks with stable IDs
-    02_visuals_kb.jsonl  – per-figure visual descriptions
+    02_visuals_kb.jsonl  – per-figure visual descriptions
     03_metadata_kb.jsonl – document-level metadata (title, authors, DOI …)
 
 No chatbot, no vector store, no retrieval – just a robust parser.
@@ -17,4 +17,4 @@ from visual_parser.config import ParserConfig
 from visual_parser.pipeline import run_pipeline
 
 __all__ = ["ParserConfig", "run_pipeline"]
-__version__ = "1.0.0"
+__version__ = "1.0.2"

{visual_parser-1.0.0 → visual_parser-1.0.2}/visual_parser/cli.py

@@ -17,8 +17,8 @@ import sys
 USAGE_EXAMPLES = """
 Examples
 --------
-# Nougat (default) + GPT-5.5 vision
-python visual-parser.py --input-dir ./my_pdfs
+# Nougat (default) + GPT-5.4 vision
+python visual-parser.py --input-dir ./my_pdfs
 
 # Fast lightweight extraction + Gemini
 python visual-parser.py --input-dir ./my_pdfs \\
@@ -47,7 +47,7 @@ def _build_arg_parser() -> argparse.ArgumentParser:
             "Visual-RAG PDF Parser — detects new PDFs, extracts text and "
             "figure descriptions, and writes three JSONL knowledge bases:\n"
             "  01_chunks_kb.jsonl   text chunks\n"
-            "  02_visuals_kb.jsonl  visual descriptions\n"
+            "  02_visuals_kb.jsonl  visual descriptions\n"
             "  03_metadata_kb.jsonl document metadata"
         ),
         formatter_class=argparse.RawDescriptionHelpFormatter,
@@ -108,20 +108,20 @@ def _build_arg_parser() -> argparse.ArgumentParser:
         choices=["gpt", "gemini"],
         default="gpt",
         help=(
-            "gpt    — OpenAI GPT-5.5  (set OPENAI_API_KEY in .env).\n"
-            "gemini — Google Gemini   (set GEMINI_API_KEY in .env)."
-        ),
-    )
+            "gpt    — OpenAI GPT-5.4  (set OPENAI_API_KEY in .env).\n"
+            "gemini — Google Gemini   (set GEMINI_API_KEY in .env)."
+        ),
+    )
     vision_group.add_argument(
         "--vision-model",
         default=None,
         metavar="MODEL_NAME",
-        help=(
-            "Vision model name. Omit to use the latest for each provider:\n"
-            "  gpt    → gpt-5.5            (also: gpt-5.4, gpt-5.3-chat-latest, gpt-5.2, gpt-5.1, gpt-5, gpt-4o, gpt-4.1)\n"
-            "  gemini → gemini-3-pro-preview (also: gemini-2.5-flash, gemini-1.5-pro)"
-        ),
-    )
+        help=(
+            "Vision model name. Omit to use the latest for each provider:\n"
+            "  gpt    → gpt-5.4            (also: gpt-5.5, gpt-5.3-chat-latest, gpt-5.2, gpt-5.1, gpt-5, gpt-4o, gpt-4.1)\n"
+            "  gemini → gemini-3-pro-preview (also: gemini-2.5-flash, gemini-1.5-pro)"
+        ),
+    )
     vision_group.add_argument(
         "--vision-detail",
         choices=["low", "high", "auto"],
@@ -134,17 +134,17 @@ def _build_arg_parser() -> argparse.ArgumentParser:
     )
     vision_group.add_argument(
         "--reasoning-effort",
-        choices=["minimal", "none", "low", "medium", "high", "xhigh"],
+        choices=["minimal", "none", "low", "medium", "high", "xhigh"],
         default="medium",
-        help=(
-            "Reasoning effort for GPT-5.x models (ignored for Gemini and older GPT).\n"
-            "  minimal/none — minimum reasoning, depending on model.\n"
-            "  low          — light reasoning.\n"
-            "  medium       — balanced (default).\n"
-            "  high         — deeper reasoning, slower.\n"
-            "  xhigh        — maximum depth (gpt-5.2, gpt-5.4, and gpt-5.5)."
-        ),
-    )
+        help=(
+            "Reasoning effort for GPT-5.x models (ignored for Gemini and older GPT).\n"
+            "  minimal/none — minimum reasoning, depending on model.\n"
+            "  low          — light reasoning.\n"
+            "  medium       — balanced (default).\n"
+            "  high         — deeper reasoning, slower.\n"
+            "  xhigh        — maximum depth (gpt-5.2, gpt-5.4, and gpt-5.5)."
+        ),
+    )
     vision_group.add_argument(
         "--metadata-pages",
         type=int,
@@ -194,10 +194,10 @@ def main(argv=None) -> int:
     args   = parser.parse_args(argv)
 
     # Default vision model per provider when not explicitly set
-    if args.vision_model is None:
-        args.vision_model = (
-            "gpt-5.5" if args.vision_provider == "gpt" else "gemini-3-pro-preview"
-        )
+    if args.vision_model is None:
+        args.vision_model = (
+            "gpt-5.4" if args.vision_provider == "gpt" else "gemini-3-pro-preview"
+        )
 
     from visual_parser.config import ParserConfig
 
@@ -209,7 +209,7 @@ def main(argv=None) -> int:
         chunk_size            = args.chunk_size,
         chunk_overlap         = args.chunk_overlap,
         vision_provider       = args.vision_provider,
-        gpt_vision_model      = args.vision_model if args.vision_provider == "gpt"    else "gpt-5.5",
+        gpt_vision_model      = args.vision_model if args.vision_provider == "gpt"    else "gpt-5.4",
         gemini_vision_model   = args.vision_model if args.vision_provider == "gemini" else "gemini-3-pro-preview",
         gpt_reasoning_effort  = args.reasoning_effort,
         vision_detail         = args.vision_detail,

{visual_parser-1.0.0 → visual_parser-1.0.2}/visual_parser/cli_main.py

@@ -15,7 +15,7 @@ import sys
 USAGE_EXAMPLES = """
 Examples
 --------
-# Nougat (default) + GPT-5.5 vision
+# Nougat (default) + GPT-5.4 vision
 python visual-parser.py --input-dir ./my_pdfs
 
 # Fast lightweight extraction + Gemini

{visual_parser-1.0.0 → visual_parser-1.0.2}/visual_parser.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: visual-parser
-Version: 1.0.0
+Version: 1.0.2
 Summary: Standalone Visual-RAG PDF Parser — text extraction + Vision-LLM figure descriptions → JSONL
 License: MIT
 Project-URL: Homepage, https://github.com/SmartLabNuclear/RADIANT_LLM
@@ -30,6 +30,8 @@ Requires-Dist: openai==1.78.1
 Requires-Dist: google-generativeai==0.8.5
 Requires-Dist: python-dotenv==1.1.0
 Requires-Dist: tqdm==4.67.1
+Requires-Dist: nltk>=3.8
+Requires-Dist: python-Levenshtein>=0.20
 Provides-Extra: ocr
 Requires-Dist: pytesseract==0.3.13; extra == "ocr"
 Provides-Extra: dev
@@ -52,7 +54,7 @@ Requires-Dist: mypy; extra == "dev"
 
 By default, the pipeline writes:
 - `01_chunks_kb.jsonl`: chunked text extracted from PDFs (Nougat by default).
-- `02_figures_kb.jsonl`: figure/page visual descriptions (Vision LLM).
+- `02_visuals_kb.jsonl`: figure/page visual descriptions (Vision LLM).
 - `03_metadata_kb.jsonl`: document metadata rows (title/author/etc.).
 - `04_processed_pdfs.txt`: a tracker so re-runs only process new PDFs (unless `--rebuild`).
 

{visual_parser-1.0.0 → visual_parser-1.0.2}/visual_parser.egg-info/requires.txt

@@ -10,6 +10,8 @@ openai==1.78.1
 google-generativeai==0.8.5
 python-dotenv==1.1.0
 tqdm==4.67.1
+nltk>=3.8
+python-Levenshtein>=0.20
 
 [dev]
 pytest