visual-parser 2.0.4__tar.gz → 2.1.0__tar.gz

visual_parser-2.1.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the
+      purposes of this License, Derivative Works shall not include works
+      that remain separable from, or merely link (or bind by name) to the
+      interfaces of, the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including the
+      original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 Zavier N. Ndum
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

{visual_parser-2.0.4 → visual_parser-2.1.0}/PKG-INFO

@@ -1,10 +1,10 @@
 Metadata-Version: 2.4
 Name: visual-parser
-Version: 2.0.4
+Version: 2.1.0
 Summary: Standalone Visual-RAG PDF Parser - text extraction and Vision-LLM figure descriptions to JSONL
 Author: Zavier N. Ndum
 Author-email: zavier.ndum@tamu.edu
-License: Apache-2.0
+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
@@ -13,43 +13,46 @@ Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
-Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Operating System :: OS Independent
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Classifier: Topic :: Text Processing :: Markup
 Classifier: Intended Audience :: Science/Research
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
-Requires-Dist: PyMuPDF==1.24.7
-Requires-Dist: Pillow==11.1.0
-Requires-Dist: torch==2.7.0
-Requires-Dist: transformers==4.45.2
-Requires-Dist: huggingface-hub==0.36.0
-Requires-Dist: langchain-community==0.3.3
-Requires-Dist: langchain==0.3.13
-Requires-Dist: langchain-text-splitters==0.3.4
-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
+License-File: LICENSE
+Requires-Dist: PyMuPDF>=1.23.0
+Requires-Dist: Pillow>=10.0.0
+Requires-Dist: torch>=2.1.0
+Requires-Dist: transformers>=4.38.0
+Requires-Dist: huggingface-hub>=0.36.0
+Requires-Dist: langchain-community>=0.0.20
+Requires-Dist: langchain>=0.1.0
+Requires-Dist: langchain-text-splitters>=0.0.1
+Requires-Dist: openai>=1.14.0
+Requires-Dist: google-generativeai>=0.5.0
+Requires-Dist: python-dotenv>=1.0.0
+Requires-Dist: tqdm>=4.66.0
 Requires-Dist: nltk>=3.8
 Requires-Dist: python-Levenshtein>=0.20
 Provides-Extra: ocr
-Requires-Dist: pytesseract==0.3.13; extra == "ocr"
+Requires-Dist: pytesseract>=0.3.10; extra == "ocr"
 Provides-Extra: dev
 Requires-Dist: pytest; extra == "dev"
 Requires-Dist: ruff; extra == "dev"
 Requires-Dist: mypy; extra == "dev"
+Dynamic: license-file
 
 # visual-parser (Standalone Visual-RAG PDF Ingestion)
 
 ![Python 3.12.10](https://img.shields.io/badge/Python-3.12.10-brightgreen.svg)
-<!-- ![PyTorch](https://img.shields.io/badge/PyTorch-2.0%2B-ee4c2c.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` is a standalone document-ingestion tool that converts PDFs into a multi-modal JSONL knowledge base (text chunks + figure descriptions + metadata). The intended workflow is:
+`visual-parser` is a standalone document-ingestion tool that converts PDFs into a multi-modal JSONL knowledge base (text chunks + figure descriptions + metadata). It was originally extracted from [RADIANT-LLM](https://github.com/SmartLabNuclear/RADIANT_LLM) — born out of the need for a fast, standalone PDF-ingestion path independent of any chatbot. The intended workflow is:
 
 1) Run `visual-parser` on curated PDFs to generate JSONL KB files.
-2) Run RADIANT-LLM Visual-RAG for QA over the generated KB.
+2) Point any downstream RAG system at the generated KB for QA over it — RADIANT-LLM, AutoSAM, and AutoFLUKA all consume the identical JSONL/registry format, so the same generated KB works with any of them without re-parsing.
 
 ## Outputs (JSONL KB)
 
@@ -59,6 +62,20 @@ By default, the pipeline writes:
 - `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`).
 
+## GPU support
+
+`--text-mode nougat` (the default) auto-detects and uses a CUDA GPU when one is available (`torch.cuda.is_available()`) — no flags or code changes needed. **The catch:** a plain `pip install visual-parser` (or `pip install torch`) resolves to PyPI's default **CPU-only** torch wheel, even on a machine with a real GPU. To actually get GPU acceleration, install the matching CUDA build from PyTorch's own index instead, e.g.:
+
+```bash
+pip install torch --index-url https://download.pytorch.org/whl/cu126
+```
+
+(pick the CUDA tag matching your driver — see [pytorch.org/get-started](https://pytorch.org/get-started/locally/)). Installing `visual-parser` again afterward won't silently downgrade this back to CPU, since the exact version you already have satisfies its own dependency requirement. Verify with:
+
+```bash
+python -c "import torch; print(torch.cuda.is_available(), torch.cuda.get_device_name(0) if torch.cuda.is_available() else None)"
+```
+
 ## API keys (`.env`)
 
 Provide at least one provider:
@@ -67,6 +84,7 @@ Provide at least one provider:
 
 Optional:
 - `HF_TOKEN` (if you use gated Hugging Face models)
+- `PORTKEY_API_KEY` + `PORTKEY_OPENAI_PROVIDER_SLUG` — routes OpenAI-family calls (vision LLM + `--list-models`) through a [Portkey](https://portkey.ai) gateway instead of OpenAI directly, exposing whatever models your Portkey account has access to. Only takes effect when `OPENAI_API_KEY` is absent/empty — direct OpenAI always wins when both are set. Set `VISUAL_PARSER_FORCE_PORTKEY=true` to force Portkey even when `OPENAI_API_KEY` is also present (e.g. set at the OS/system level, where commenting it out of `.env` alone can't disable it).
 
 ## Run with Docker (Docker Hub)
 
@@ -113,6 +131,17 @@ docker run --rm --env-file .env `
   --input-dir /data --output-dir /out
 ```
 
+### GPU acceleration (Docker)
+
+Add `--gpus all` to any of the run commands above to use an NVIDIA GPU for `--text-mode nougat` (the default) instead of CPU — confirmed working out of the box with Docker Desktop's WSL2 backend, no extra host setup needed on most machines. Omit it (or run on a machine with no GPU) and it falls back to CPU automatically:
+
+```powershell
+docker run --rm --gpus all --env-file .env `
+  -v "C:\path\to\pdfs:/data" `
+  zev94/radiant-llm:visual-parser-latest `
+  --input-dir /data --output-dir /data
+```
+
 ### Offline install (legacy `.tar`)
 
 ```powershell
@@ -167,6 +196,8 @@ Vision LLM:
 Performance / misc:
 - `--max-workers 4`
 - `--rebuild` (reprocess everything; ignore `04_processed_pdfs.txt`)
+- `--list-models` — print the live, currently-available vision models for whichever provider(s) you have a key configured for, then exit (no PDF processing). Reflects Portkey's catalog too when that's what's active.
+- `--version` / `-V`
 - `--log-level DEBUG|INFO|WARNING|ERROR`
 
 ---
@@ -195,6 +226,6 @@ Preprint: https://arxiv.org/abs/2604.22755
 
 Copyright 2026 Zavier N. Ndum
 
-This project is licensed under the Apache License 2.0. See the [LICENSE](https://github.com/SmartLabNuclear/RADIANT_LLM/blob/main/LICENSE) file in the RADIANT_LLM repository for the full license text.
+This project is licensed under the Apache License 2.0, the same license as its parent project, [RADIANT-LLM](https://github.com/SmartLabNuclear/RADIANT_LLM). See the [LICENSE](https://github.com/SmartLabNuclear/RADIANT_LLM/blob/main/LICENSE) file in the RADIANT_LLM repository, or the `LICENSE` file bundled with this package, for the full license text.
 
 

{visual_parser-2.0.4 → visual_parser-2.1.0}/README.md

@@ -1,12 +1,14 @@
 # visual-parser (Standalone Visual-RAG PDF Ingestion)
 
 ![Python 3.12.10](https://img.shields.io/badge/Python-3.12.10-brightgreen.svg)
-<!-- ![PyTorch](https://img.shields.io/badge/PyTorch-2.0%2B-ee4c2c.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` is a standalone document-ingestion tool that converts PDFs into a multi-modal JSONL knowledge base (text chunks + figure descriptions + metadata). The intended workflow is:
+`visual-parser` is a standalone document-ingestion tool that converts PDFs into a multi-modal JSONL knowledge base (text chunks + figure descriptions + metadata). It was originally extracted from [RADIANT-LLM](https://github.com/SmartLabNuclear/RADIANT_LLM) — born out of the need for a fast, standalone PDF-ingestion path independent of any chatbot. The intended workflow is:
 
 1) Run `visual-parser` on curated PDFs to generate JSONL KB files.
-2) Run RADIANT-LLM Visual-RAG for QA over the generated KB.
+2) Point any downstream RAG system at the generated KB for QA over it — RADIANT-LLM, AutoSAM, and AutoFLUKA all consume the identical JSONL/registry format, so the same generated KB works with any of them without re-parsing.
 
 ## Outputs (JSONL KB)
 
@@ -16,6 +18,20 @@ By default, the pipeline writes:
 - `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`).
 
+## GPU support
+
+`--text-mode nougat` (the default) auto-detects and uses a CUDA GPU when one is available (`torch.cuda.is_available()`) — no flags or code changes needed. **The catch:** a plain `pip install visual-parser` (or `pip install torch`) resolves to PyPI's default **CPU-only** torch wheel, even on a machine with a real GPU. To actually get GPU acceleration, install the matching CUDA build from PyTorch's own index instead, e.g.:
+
+```bash
+pip install torch --index-url https://download.pytorch.org/whl/cu126
+```
+
+(pick the CUDA tag matching your driver — see [pytorch.org/get-started](https://pytorch.org/get-started/locally/)). Installing `visual-parser` again afterward won't silently downgrade this back to CPU, since the exact version you already have satisfies its own dependency requirement. Verify with:
+
+```bash
+python -c "import torch; print(torch.cuda.is_available(), torch.cuda.get_device_name(0) if torch.cuda.is_available() else None)"
+```
+
 ## API keys (`.env`)
 
 Provide at least one provider:
@@ -24,6 +40,7 @@ Provide at least one provider:
 
 Optional:
 - `HF_TOKEN` (if you use gated Hugging Face models)
+- `PORTKEY_API_KEY` + `PORTKEY_OPENAI_PROVIDER_SLUG` — routes OpenAI-family calls (vision LLM + `--list-models`) through a [Portkey](https://portkey.ai) gateway instead of OpenAI directly, exposing whatever models your Portkey account has access to. Only takes effect when `OPENAI_API_KEY` is absent/empty — direct OpenAI always wins when both are set. Set `VISUAL_PARSER_FORCE_PORTKEY=true` to force Portkey even when `OPENAI_API_KEY` is also present (e.g. set at the OS/system level, where commenting it out of `.env` alone can't disable it).
 
 ## Run with Docker (Docker Hub)
 
@@ -70,6 +87,17 @@ docker run --rm --env-file .env `
   --input-dir /data --output-dir /out
 ```
 
+### GPU acceleration (Docker)
+
+Add `--gpus all` to any of the run commands above to use an NVIDIA GPU for `--text-mode nougat` (the default) instead of CPU — confirmed working out of the box with Docker Desktop's WSL2 backend, no extra host setup needed on most machines. Omit it (or run on a machine with no GPU) and it falls back to CPU automatically:
+
+```powershell
+docker run --rm --gpus all --env-file .env `
+  -v "C:\path\to\pdfs:/data" `
+  zev94/radiant-llm:visual-parser-latest `
+  --input-dir /data --output-dir /data
+```
+
 ### Offline install (legacy `.tar`)
 
 ```powershell
@@ -124,6 +152,8 @@ Vision LLM:
 Performance / misc:
 - `--max-workers 4`
 - `--rebuild` (reprocess everything; ignore `04_processed_pdfs.txt`)
+- `--list-models` — print the live, currently-available vision models for whichever provider(s) you have a key configured for, then exit (no PDF processing). Reflects Portkey's catalog too when that's what's active.
+- `--version` / `-V`
 - `--log-level DEBUG|INFO|WARNING|ERROR`
 
 ---
@@ -152,6 +182,6 @@ Preprint: https://arxiv.org/abs/2604.22755
 
 Copyright 2026 Zavier N. Ndum
 
-This project is licensed under the Apache License 2.0. See the [LICENSE](https://github.com/SmartLabNuclear/RADIANT_LLM/blob/main/LICENSE) file in the RADIANT_LLM repository for the full license text.
+This project is licensed under the Apache License 2.0, the same license as its parent project, [RADIANT-LLM](https://github.com/SmartLabNuclear/RADIANT_LLM). See the [LICENSE](https://github.com/SmartLabNuclear/RADIANT_LLM/blob/main/LICENSE) file in the RADIANT_LLM repository, or the `LICENSE` file bundled with this package, for the full license text.
 
 

{visual_parser-2.0.4 → visual_parser-2.1.0}/pyproject.toml

@@ -1,14 +1,14 @@
 [build-system]
-requires = ["setuptools>=61", "wheel"]
+requires = ["setuptools>=77.0.0", "wheel"]
 build-backend = "setuptools.build_meta"
 
 [project]
 name = "visual-parser"
-version = "2.0.4"
+version = "2.1.0"
 description = "Standalone Visual-RAG PDF Parser - text extraction and Vision-LLM figure descriptions to JSONL"
 readme = "README.md"
 requires-python = ">=3.10"
-license = { text = "Apache-2.0" }
+license = "Apache-2.0"
 # PEP 621: name+email in one entry -> Author-email only (Author stays empty on PyPI).
 # Split entries so PyPI/pip show both Author and Author-email.
 authors = [
@@ -26,7 +26,6 @@ classifiers = [
     "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
-    "License :: OSI Approved :: Apache Software License",
     "Operating System :: OS Independent",
     "Topic :: Scientific/Engineering :: Artificial Intelligence",
     "Topic :: Text Processing :: Markup",
@@ -34,24 +33,24 @@ classifiers = [
 ]
 
 dependencies = [
-    "PyMuPDF==1.24.7",
-    "Pillow==11.1.0",
-    "torch==2.7.0",
-    "transformers==4.45.2",
-    "huggingface-hub==0.36.0",
-    "langchain-community==0.3.3",
-    "langchain==0.3.13",
-    "langchain-text-splitters==0.3.4",
-    "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",
+    "PyMuPDF>=1.23.0",                 # fitz -- rasterisation & native text layer
+    "Pillow>=10.0.0",                  # image handling
+    "torch>=2.1.0",                    # CPU build is fine; GPU users install their own wheel -- see README's CUDA note
+    "transformers>=4.38.0",            # AutoProcessor + VisionEncoderDecoderModel
+    "huggingface-hub>=0.36.0",         # model download utilities (used by transformers/nougat)
+    "langchain-community>=0.0.20",     # PyPDFLoader fallback
+    "langchain>=0.1.0",
+    "langchain-text-splitters>=0.0.1", # RecursiveCharacterTextSplitter (split out from langchain in v0.2+)
+    "openai>=1.14.0",
+    "google-generativeai>=0.5.0",
+    "python-dotenv>=1.0.0",
+    "tqdm>=4.66.0",
+    "nltk>=3.8",                       # required by NougatTokenizerFast
+    "python-Levenshtein>=0.20",        # required by NougatTokenizerFast
 ]
 
 [project.optional-dependencies]
-ocr = ["pytesseract==0.3.13"]
+ocr = ["pytesseract>=0.3.10"]  # optional equation OCR, requires the Tesseract system binary
 dev = ["pytest", "ruff", "mypy"]
 
 [project.urls]

{visual_parser-2.0.4 → visual_parser-2.1.0}/visual_parser/__init__.py

@@ -17,4 +17,4 @@ from visual_parser.config import ParserConfig
 from visual_parser.pipeline import run_pipeline
 
 __all__ = ["ParserConfig", "run_pipeline"]
-__version__ = "1.0.2"
+__version__ = "2.1.0"

{visual_parser-2.0.4 → visual_parser-2.1.0}/visual_parser/cli.py

@@ -54,13 +54,21 @@ def _build_arg_parser() -> argparse.ArgumentParser:
         epilog=USAGE_EXAMPLES,
     )
 
+    from visual_parser import __version__
+    p.add_argument(
+        "--version", "-V",
+        action="version",
+        version=f"visual-parser {__version__}",
+    )
+
     # ---- Paths --------------------------------------------------------------
     io_group = p.add_argument_group("Paths")
     io_group.add_argument(
         "--input-dir", "-i",
-        required=True,
+        required=False,
         metavar="DIR",
-        help="Directory to scan for PDF files (searched recursively).",
+        help="Directory to scan for PDF files (searched recursively). "
+             "Required unless --list-models is given.",
     )
     io_group.add_argument(
         "--output-dir", "-o",
@@ -165,6 +173,17 @@ def _build_arg_parser() -> argparse.ArgumentParser:
 
     # ---- Misc ---------------------------------------------------------------
     misc_group = p.add_argument_group("Miscellaneous")
+    misc_group.add_argument(
+        "--list-models",
+        action="store_true",
+        help=(
+            "Print the live, currently-available vision models for gpt and/or "
+            "gemini (whichever of OPENAI_API_KEY / GEMINI_API_KEY is set in "
+            ".env), then exit -- no PDF processing. Replaces the static "
+            "example names shown in --vision-model's help text above, which "
+            "can go stale as providers add/retire models."
+        ),
+    )
     misc_group.add_argument(
         "--rebuild",
         action="store_true",
@@ -194,6 +213,55 @@ def _build_arg_parser() -> argparse.ArgumentParser:
     return p
 
 
+def _print_available_models() -> int:
+    """--list-models: print the live vision-model catalog for whichever
+    provider(s) have a key configured, then exit. No PDF processing."""
+    import os as _os
+
+    from visual_parser import config as _config  # noqa: F401  (triggers _load_env() on import)
+    from visual_parser.model_catalog import list_gemini_models, list_openai_models
+    from visual_parser.openai_gateway import resolve_openai_connection
+
+    conn = resolve_openai_connection()
+    gemini_key = _os.getenv("GEMINI_API_KEY", "").strip()
+
+    if not conn["api_key"] and not gemini_key:
+        print(
+            "[ERROR] None of OPENAI_API_KEY, PORTKEY_API_KEY, or GEMINI_API_KEY "
+            "is set (checked ~/.config/visual-parser/.env, the current "
+            "directory's .env, and $VISUAL_PARSER_ENV_FILE). Set at least one "
+            "to list models.",
+            file=sys.stderr,
+        )
+        return 1
+
+    if conn["api_key"]:
+        via = " (via Portkey)" if conn["base_url"] else ""
+        print(f"gpt (OpenAI){via} -- live, currently available:")
+        models = list_openai_models(
+            conn["api_key"], base_url=conn["base_url"], model_prefix=conn["model_prefix"], force_refresh=True
+        )
+        if models:
+            for model_id in models:
+                print(f"  {model_id}")
+        else:
+            print("  (none found -- check the configured key is valid)")
+        print()
+
+    if gemini_key:
+        print("gemini (Google) -- live, currently available:")
+        models = list_gemini_models(gemini_key, force_refresh=True)
+        if models:
+            for model_id in models:
+                print(f"  {model_id}")
+        else:
+            print("  (none found -- check GEMINI_API_KEY is valid)")
+        print()
+
+    print("Pass one of the above to --vision-model (with the matching --vision-provider).")
+    return 0
+
+
 def main(argv=None) -> int:
     """
     Parse CLI arguments, build a :class:`~visual_parser.config.ParserConfig`,
@@ -204,6 +272,12 @@ def main(argv=None) -> int:
     parser = _build_arg_parser()
     args   = parser.parse_args(argv)
 
+    if args.list_models:
+        return _print_available_models()
+
+    if not args.input_dir:
+        parser.error("--input-dir is required (unless --list-models is given).")
+
     # Default vision model per provider when not explicitly set
     if args.vision_model is None:
         args.vision_model = (

{visual_parser-2.0.4 → visual_parser-2.1.0}/visual_parser/cli_main.py

@@ -52,13 +52,21 @@ def _build_arg_parser() -> argparse.ArgumentParser:
         epilog=USAGE_EXAMPLES,
     )
 
+    from visual_parser import __version__
+    parser.add_argument(
+        "--version", "-V",
+        action="version",
+        version=f"visual-parser {__version__}",
+    )
+
     io_group = parser.add_argument_group("Paths")
     io_group.add_argument(
         "--input-dir",
         "-i",
-        required=True,
+        required=False,
         metavar="DIR",
-        help="Directory to scan for PDF files (searched recursively).",
+        help="Directory to scan for PDF files (searched recursively). "
+             "Required unless --list-models is given.",
     )
     io_group.add_argument(
         "--output-dir",
@@ -160,6 +168,17 @@ def _build_arg_parser() -> argparse.ArgumentParser:
     )
 
     misc_group = parser.add_argument_group("Miscellaneous")
+    misc_group.add_argument(
+        "--list-models",
+        action="store_true",
+        help=(
+            "Print the live, currently-available vision models for gpt and/or "
+            "gemini (whichever of OPENAI_API_KEY / GEMINI_API_KEY is set in "
+            ".env), then exit -- no PDF processing. Replaces the static "
+            "example names shown in --vision-model's help text above, which "
+            "can go stale as providers add/retire models."
+        ),
+    )
     misc_group.add_argument(
         "--rebuild",
         action="store_true",
@@ -193,6 +212,14 @@ def main(argv=None) -> int:
     parser = _build_arg_parser()
     args = parser.parse_args(argv)
 
+    if args.list_models:
+        from visual_parser.cli import _print_available_models
+
+        return _print_available_models()
+
+    if not args.input_dir:
+        parser.error("--input-dir is required (unless --list-models is given).")
+
     if args.vision_model is None:
         args.vision_model = (
             "gpt-5.4" if args.vision_provider == "gpt" else "gemini-3-pro-preview"