visual-parser 2.2.2__py3-none-any.whl → 2.2.3__py3-none-any.whl

visual_parser/__init__.py

@@ -1,14 +1,16 @@
 """
-visual_parser — Standalone Visual-RAG PDF Parser
-=================================================
-Detects new PDFs in a user-supplied directory, extracts text (via Nougat or
-lightweight PyMuPDF/PyPDFLoader), describes every figure/chart/schematic using
-a Vision LLM (OpenAI GPT, Google Gemini, or a local model via Ollama), and
-writes three JSONL knowledge bases ready for any downstream RAG system:
+visual_parser — Standalone Visual-RAG PDF & Image Parser
+=========================================================
+Detects new PDFs (and standalone images alongside them) in a user-supplied
+directory, extracts text (via Nougat or lightweight PyMuPDF/PyPDFLoader),
+describes every figure/chart/schematic and every standalone image using a
+Vision LLM (OpenAI GPT, Google Gemini, or a local model via Ollama), and
+writes 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
-    03_metadata_kb.jsonl – document-level metadata (title, authors, DOI …)
+    01_chunks_kb.jsonl          – text chunks with stable IDs
+    02_visuals_kb.jsonl         – per-figure visual descriptions
+    03_metadata_kb.jsonl        – document-level metadata (title, authors, DOI …)
+    image_descriptions_kb.jsonl – one holistic description per standalone image
 
 No chatbot, no vector store, no retrieval – just a robust parser.
 """
@@ -17,4 +19,4 @@ from visual_parser.config import ParserConfig
 from visual_parser.pipeline import run_pipeline
 
 __all__ = ["ParserConfig", "run_pipeline"]
-__version__ = "2.2.2"
+__version__ = "2.2.3"

visual_parser/cli.py

@@ -44,13 +44,13 @@ def _build_arg_parser() -> argparse.ArgumentParser:
     p = argparse.ArgumentParser(
         prog="visual-parser",
         description=(
-            "Visual-RAG PDF Parser — detects new PDFs and standalone images, "
+            "Visual-RAG PDF & Image Parser — detects new PDFs and standalone images, "
             "extracts text and figure/image descriptions, and writes JSONL "
             "knowledge bases:\n"
-            "  01_chunks_kb.jsonl       text chunks\n"
-            "  02_visuals_kb.jsonl      PDF figure descriptions\n"
-            "  03_metadata_kb.jsonl     document metadata\n"
-            "  image_descriptions.jsonl standalone image descriptions"
+            "  01_chunks_kb.jsonl            text chunks\n"
+            "  02_visuals_kb.jsonl           PDF figure descriptions\n"
+            "  03_metadata_kb.jsonl          document metadata\n"
+            "  image_descriptions_kb.jsonl   standalone image descriptions"
         ),
         formatter_class=argparse.RawDescriptionHelpFormatter,
         epilog=USAGE_EXAMPLES,

visual_parser/cli_main.py

@@ -1,5 +1,5 @@
 """
-cli_main.py - ASCII-safe CLI entry point for the Visual-RAG PDF Parser.
+cli_main.py - ASCII-safe CLI entry point for the Visual-RAG PDF & Image Parser.
 
 This module exists to keep Windows console help output stable for the
 installed ``visual-parser`` command and ``python -m visual_parser``.
@@ -42,13 +42,13 @@ def _build_arg_parser() -> argparse.ArgumentParser:
     parser = argparse.ArgumentParser(
         prog="visual-parser",
         description=(
-            "Visual-RAG PDF Parser - detects new PDFs and standalone images, "
+            "Visual-RAG PDF & Image Parser - detects new PDFs and standalone images, "
             "extracts text and figure/image descriptions, and writes JSONL "
             "knowledge bases:\n"
-            "  01_chunks_kb.jsonl       text chunks\n"
-            "  02_visuals_kb.jsonl      PDF figure descriptions\n"
-            "  03_metadata_kb.jsonl     document metadata\n"
-            "  image_descriptions.jsonl standalone image descriptions"
+            "  01_chunks_kb.jsonl            text chunks\n"
+            "  02_visuals_kb.jsonl           PDF figure descriptions\n"
+            "  03_metadata_kb.jsonl          document metadata\n"
+            "  image_descriptions_kb.jsonl   standalone image descriptions"
         ),
         formatter_class=argparse.RawDescriptionHelpFormatter,
         epilog=USAGE_EXAMPLES,

visual_parser/image_describer.py

@@ -10,7 +10,7 @@ supplied image files instead of PyMuPDF-rasterized PDF pages.
 
 Output
 ------
-One record per image is appended to ``image_descriptions.jsonl`` in
+One record per image is appended to ``image_descriptions_kb.jsonl`` in
 *output_dir*:
 
     {
@@ -40,7 +40,7 @@ from visual_parser.vision_llm import call_vision_llm
 
 logger = logging.getLogger(__name__)
 
-IMAGE_DESCRIPTIONS_FILE = "image_descriptions.jsonl"
+IMAGE_DESCRIPTIONS_FILE = "image_descriptions_kb.jsonl"
 
 # Decoupled from figure_describer.py's context-window-scaled formula (10 min
 # for 1 image there): IMAGE_DESCRIPTION_PROMPT's "Verbatim Text Content"
@@ -171,7 +171,7 @@ def describe_images(
     """
     For each image in *new_image_paths*, call the Vision LLM once (no
     context window -- a single standalone image per call), parse the
-    description, and append the result to ``image_descriptions.jsonl`` in
+    description, and append the result to ``image_descriptions_kb.jsonl`` in
     *output_dir*.
 
     Returns the basenames actually written a row for -- NOT the full input
@@ -183,7 +183,7 @@ def describe_images(
 
     Args:
         new_image_paths:  Full paths of images to describe.
-        output_dir:       Directory where ``image_descriptions.jsonl`` is written.
+        output_dir:       Directory where ``image_descriptions_kb.jsonl`` is written.
         vision_provider:  ``'gpt'``, ``'gemini'``, or ``'ollama'``.
         vision_api_key:   API key for the chosen provider (unused for ollama).
         vision_model:     Vision model name string.
@@ -191,7 +191,7 @@ def describe_images(
         image_prompt:     The instruction prompt sent with each image.
         max_workers:      Thread-pool size for concurrent vision-LLM calls.
 
-    Always resumes from image_descriptions.jsonl's existing content (via the
+    Always resumes from image_descriptions_kb.jsonl's existing content (via the
     done_images set below) -- callers that want an image redescribed must
     first remove its existing row and its basename from the processed-
     images registry (see kb_redo.redo_entries()), then pass it in here as if

visual_parser/kb_redo.py

@@ -14,7 +14,7 @@ dependency-free package and cannot depend on the sibling RADIANT-LLM repo)
 the proven basename-match + backup-once + atomic-rewrite pattern from
 RADIANT-LLM's knowledge_base_sanitizer() (radiant_lmm/RADIANT_LLM_ChatBot_
 Local/utils/pdf_helpers.py:1464-1607), extended to the 4th JSONL file
-(image_descriptions.jsonl) and both registries (04_processed_pdfs.txt,
+(image_descriptions_kb.jsonl) and both registries (04_processed_pdfs.txt,
 parsed_images.txt), which that function never touches at all.
 """
 
@@ -25,6 +25,7 @@ import os
 import shutil
 from typing import Any, Dict, Iterable, List
 
+from visual_parser.image_describer import IMAGE_DESCRIPTIONS_FILE
 from visual_parser.image_tracker import PROCESSED_IMAGES_REGISTRY
 from visual_parser.jsonl_writer import atomic_rewrite_jsonl
 from visual_parser.pdf_tracker import PROCESSED_REGISTRY, load_processed_pdfs, unmark_as_processed
@@ -33,12 +34,16 @@ logger = logging.getLogger(__name__)
 
 # Hardcoded, not glob("*.jsonl") like the RADIANT precedent -- output_dir
 # often equals input_dir (the documented default), so globbing risks
-# touching unrelated JSONL files a user happens to keep there.
+# touching unrelated JSONL files a user happens to keep there. The image
+# filename is imported (not hardcoded like the other three) because it was
+# renamed once already (image_descriptions.jsonl -> image_descriptions_kb.jsonl,
+# 2.2.3) with this exact file as a hardcoded duplicate that needed a manual
+# fix -- importing the constant means it can't drift out of sync again.
 KB_JSONL_FILENAMES = (
     "01_chunks_kb.jsonl",
     "02_visuals_kb.jsonl",
     "03_metadata_kb.jsonl",
-    "image_descriptions.jsonl",
+    IMAGE_DESCRIPTIONS_FILE,
 )
 REGISTRY_FILENAMES = (PROCESSED_REGISTRY, PROCESSED_IMAGES_REGISTRY)
 BACKUP_SUFFIX = "_backup_before_redo"

{visual_parser-2.2.2.dist-info → visual_parser-2.2.3.dist-info}/METADATA

@@ -1,14 +1,14 @@
 Metadata-Version: 2.4
 Name: visual-parser
-Version: 2.2.2
-Summary: Standalone Visual-RAG PDF Parser - text extraction and Vision-LLM figure descriptions to JSONL
+Version: 2.2.3
+Summary: Standalone Visual-RAG PDF & Image Parser - text extraction and Vision-LLM figure/image descriptions to JSONL
 Author: Zavier N. Ndum
 Author-email: zavier.ndum@tamu.edu
 License-Expression: Apache-2.0
 Project-URL: Homepage, https://github.com/SmartLabNuclear/RADIANT_LLM
 Project-URL: Repository, https://github.com/SmartLabNuclear/RADIANT_LLM
 Project-URL: Docker Hub, https://hub.docker.com/r/zev94/radiant-llm
-Keywords: pdf,rag,nougat,vision-llm,ocr,document-parsing,jsonl,knowledge-base
+Keywords: pdf,image,rag,nougat,vision-llm,ocr,document-parsing,jsonl,knowledge-base
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
@@ -43,16 +43,16 @@ Requires-Dist: ruff; extra == "dev"
 Requires-Dist: mypy; extra == "dev"
 Dynamic: license-file
 
-# visual-parser (Standalone Visual-RAG PDF Ingestion)
+# visual-parser (Standalone Visual-RAG PDF & Image Ingestion)
 
 ![Python 3.10+](https://img.shields.io/badge/Python-3.10%2B-brightgreen.svg)
 ![PyTorch](https://img.shields.io/badge/PyTorch-2.1%2B-ee4c2c.svg)
 ![LangChain](https://img.shields.io/badge/LangChain-0.1%2B-1C3C3C.svg)
 ![CUDA](https://img.shields.io/badge/CUDA-optional-76B900.svg)
 
-`visual-parser` converts PDFs (and standalone images alongside them) into a multi-modal JSONL knowledge base (text chunks, figure descriptions, standalone image descriptions, metadata). It was extracted from [RADIANT-LLM](https://github.com/SmartLabNuclear/RADIANT_LLM) as a standalone PDF-ingestion tool, independent of any chatbot.
+`visual-parser` converts PDFs (and standalone images alongside them) into a multi-modal JSONL knowledge base (text chunks, figure descriptions, standalone image descriptions, metadata). It was extracted from [RADIANT-LLM](https://github.com/SmartLabNuclear/RADIANT_LLM) as a standalone PDF-and-image ingestion tool, independent of any chatbot.
 
-1) Run `visual-parser` on curated PDFs to generate JSONL KB files.
+1) Run `visual-parser` on a directory of curated PDFs and/or standalone images to generate JSONL KB files.
 2) Point any downstream RAG system at the generated KB — RADIANT-LLM, AutoSAM, and AutoFLUKA all consume the identical JSONL/registry format, so the same KB works with any of them without re-parsing.
 
 ## Table of Contents
@@ -74,10 +74,12 @@ By default, the pipeline writes:
 - `01_chunks_kb.jsonl`: chunked text extracted from PDFs (Nougat by default).
 - `02_visuals_kb.jsonl`: figure/page visual descriptions (Vision LLM), one row per figure found in a PDF.
 - `03_metadata_kb.jsonl`: document metadata rows (title/author/etc.).
-- `image_descriptions.jsonl`: one holistic description per **standalone image** file found alongside your PDFs in `--input-dir` (not a PDF's own figures) — auto-detected by extension, no separate flag needed; disable with `--skip-images`.
+- `image_descriptions_kb.jsonl`: one holistic description per **standalone image** file found alongside your PDFs in `--input-dir` (not a PDF's own figures) — auto-detected by extension, no separate flag needed; disable with `--skip-images`.
 
 Alongside the KB, the pipeline also writes bookkeeping files: `04_processed_pdfs.txt` / `parsed_images.txt` (track which PDFs/images have already been processed, so re-runs skip them unless `--rebuild` or `--redo NAME`) and `05_pipeline.log` (run log at the verbosity set by `--log-level`, default `ERROR`).
 
+> **Breaking change in 2.2.3:** the standalone-image KB file was renamed from `image_descriptions.jsonl` to `image_descriptions_kb.jsonl` (matching the `NN_name_kb.jsonl` convention used by the other three KB files). Upgrading from an older version does **not** migrate existing data automatically — the resume check only looks at the new filename, so already-described images in an old `image_descriptions.jsonl` would otherwise appear "new" again and get re-described. If you have existing data, rename the file yourself before re-running: `image_descriptions.jsonl` → `image_descriptions_kb.jsonl`.
+
 ## API Keys (.env)
 
 Provide at least one provider:

{visual_parser-2.2.2.dist-info → visual_parser-2.2.3.dist-info}/RECORD

@@ -1,13 +1,13 @@
-visual_parser/__init__.py,sha256=A1YmiufPZJW4uHVo2hfds0NX0ixxg3fDU7DpfMnPU6E,858
+visual_parser/__init__.py,sha256=aM-Cb26eQC-P7KVTslxeUlts3SD8zvgFCh-oBHdAi_A,1039
 visual_parser/__main__.py,sha256=-p6rqjrnsjrtu71eFtmZdqFI1NgHXX9ASOnjuGqghNo,168
-visual_parser/cli.py,sha256=nU9SAnaWR9J3WzhKOgO1qHL-9kA1RKntR5L2pVz1zX8,16049
-visual_parser/cli_main.py,sha256=SdABWlUeGDNnVSzUZ8Nky5cxUvsxwJsMuzGliYJFYzk,11805
+visual_parser/cli.py,sha256=28u8JxiFwc6cHf-CGk3TiVFn7llQ0k_3smSH_KFR9tQ,16077
+visual_parser/cli_main.py,sha256=fZPCY6M_gMpp8rJ8U1F0-hJjiTRn3Ih03A-A_ZaPp1Q,11841
 visual_parser/config.py,sha256=mu52rGN1keQtho70IUP7kPuS6Wykpcc-gv3z0irg70c,12140
 visual_parser/figure_describer.py,sha256=q7Jsccsn5iGK4sCbsVOD4EzLuycbvBeBSYtHX0e9jPw,13470
-visual_parser/image_describer.py,sha256=nkwqK4aDcwYjuBLCjV2AmZShzCT_pdUkPZJLy2KaV9M,13859
+visual_parser/image_describer.py,sha256=JTmLuczGV8vx6o_G1_8JLgPpHCw5EsxPbpvbpzm7-yM,13874
 visual_parser/image_tracker.py,sha256=MyQiUyqnW6b7e7R7yIefJ0k15OO0WEkK5wMiRD2nmfU,2496
 visual_parser/jsonl_writer.py,sha256=klkDl_KKdCRtiWWjTNqecN2B6zXPc0e9f704Dvj8Fh0,6215
-visual_parser/kb_redo.py,sha256=xdp9Cd2xEz19x02ORsWvj5QlKzMyvxmM0pbSrPOla3k,5517
+visual_parser/kb_redo.py,sha256=5_FpHHaEYQCAXSAN-j-snaj6OlaL36Vqi97DMqPPROA,5897
 visual_parser/metadata_extractor.py,sha256=Z0jnA8Goo9R3SBThx5PQMetZkyrbevNvYCq36WsoQuQ,6579
 visual_parser/model_catalog.py,sha256=Voli3Wv0YYLWyocNCpiBCchzfCxX4IYFNR4eOIlFyIM,7739
 visual_parser/nougat_engine.py,sha256=o9u9XTxOL1EAo63mVARVt4z1IxfDMpvjhMD4URfTx1k,8369
@@ -18,9 +18,9 @@ visual_parser/pipeline.py,sha256=Bh03FO3ylIsC1bfRITvffGzL-e5r07dKVzgHEiNRK6Y,309
 visual_parser/prompts.py,sha256=hdjDUZjF0A9eugm6qt4K5E1qnqMO1JE9_mTDAGS7sgg,11186
 visual_parser/text_extractor.py,sha256=kMmjTvTnPJBsFTIv5qN49v88k1SJhQMtTob8_LT1tfE,17491
 visual_parser/vision_llm.py,sha256=TXiitsDAMIdo9fbzYVKqd-0sGt-hqiJryMU481eo1SM,17429
-visual_parser-2.2.2.dist-info/licenses/LICENSE,sha256=OEJRtZkWILIqPizQxk1m2CjYi1czEKW15RKX6WgLVBE,11344
-visual_parser-2.2.2.dist-info/METADATA,sha256=WJGuFZVprE2_nb1BdBpwDnDFpV1J78AJ_Ntz-mjYnK8,16422
-visual_parser-2.2.2.dist-info/WHEEL,sha256=YVMoNqKzERt-wjUZwJ33xBGAwnFl-4cqbYkTtWa4itE,91
-visual_parser-2.2.2.dist-info/entry_points.txt,sha256=yypghqnxA-nSiyoDyhlg99SK9vfOzloFwUiiwRw4EWI,62
-visual_parser-2.2.2.dist-info/top_level.txt,sha256=_aaZ41uFRN_WX-616YvmcXIroNq4k4m6Ph6FGetxLYY,14
-visual_parser-2.2.2.dist-info/RECORD,,
+visual_parser-2.2.3.dist-info/licenses/LICENSE,sha256=OEJRtZkWILIqPizQxk1m2CjYi1czEKW15RKX6WgLVBE,11344
+visual_parser-2.2.3.dist-info/METADATA,sha256=EM6UWzoRQlVeb93ier-LK3cQ2347HYsItXfm1skP5ZQ,17112
+visual_parser-2.2.3.dist-info/WHEEL,sha256=YVMoNqKzERt-wjUZwJ33xBGAwnFl-4cqbYkTtWa4itE,91
+visual_parser-2.2.3.dist-info/entry_points.txt,sha256=yypghqnxA-nSiyoDyhlg99SK9vfOzloFwUiiwRw4EWI,62
+visual_parser-2.2.3.dist-info/top_level.txt,sha256=_aaZ41uFRN_WX-616YvmcXIroNq4k4m6Ph6FGetxLYY,14
+visual_parser-2.2.3.dist-info/RECORD,,