parsosaur
Convert academic PDFs to JSON, TEI XML, and HTML.
Synopsis
parsosaur [OPTIONS] DIR ...
Description
Parsosaur extracts text, tables, figures, and bibliographic metadata from
academic PDFs. Each input directory must contain exactly one PDF and at most
one GROBID TEI file with a .tei or .tei.xml suffix. The TEI file supplies
context for image interpretation and metadata for bibliographic merging.
New parses require Linux x86-64, Python 3.10–3.13, a CUDA GPU, and an OpenAI-compatible vision-model endpoint. Nemotron performs layout extraction locally. PDF crops and prompts are sent to the selected endpoint.
The NVIDIA runtime and model are downloaded from a fixed Hugging Face revision on first use. Allow several gigabytes of disk space for dependencies and model files.
Outputs are written to DIR/out/. Existing compatible results are reused;
complete cached results require neither GPU inference nor endpoint requests.
Use --force to regenerate results after changing inputs or options.
Installation
From a source checkout, install and run Parsosaur with uv:
uv sync --locked
uv run parsosaur --help
After publication to PyPI, run it without a checkout:
uvx parsosaur --help
Use uv tool install parsosaur to install a persistent parsosaur command.
Alternatively, install it with pip install parsosaur.
After publication, uv run URL [OPTIONS] DIR ... can run the launcher at a
raw URL for scripts/run_parsosaur.py. The launcher installs the library
version specified in that file.
Options
-h,--helpdisplays help and exits.--base-url URLselects the vision-model endpoint. It defaults toLLM_BASE_URL, orhttps://openrouter.ai/api/v1if that variable is unset. A URL without a path has/v1appended.--model MODELselects the endpoint's model. It is required for OpenRouter. Other endpoints default to the first model returned by their model list.--no-contextomits TEI prose from image interpretation requests.--no-mergeskips merging bibliographic metadata from the TEI file.--forcedeletes each input directory'sout/subdirectory and regenerates all results.
Environment
LLM_BASE_URLsets the default vision-model endpoint.LLM_API_KEYsupplies the endpoint's API key.OPENROUTER_API_KEYis used ifLLM_API_KEYis unset. OpenRouter requires a key.HF_HOMEsets the Hugging Face cache directory.HF_HUB_OFFLINE=1restricts model and runtime loading to cached files. It does not disable requests to the vision-model endpoint.
Files
All generated files reside in DIR/out/.
document.json,metadata.json, andfigures.jsoncontain the structured extraction results.document.tei.xmlcontains the document in TEI XML format.index.htmlprovides a reading view with source-page highlights.viewer.htmldisplays detected regions on the PDF.pages/,crops/, andraw/contain rendered pages, extracted images, and intermediate model outputs.merge_report.jsonrecords bibliographic merge decisions when merging is enabled and a TEI file is supplied.
Examples
Parse one paper using a local vision-model endpoint:
uvx parsosaur paper/ --base-url http://localhost:8000
Parse several papers using the same endpoint:
export LLM_BASE_URL=http://localhost:8000
uvx parsosaur papers/*/
Exit status
Parsosaur exits with status zero on success and a nonzero status on error. During batch processing, individual paper failures are reported and processing continues with the remaining papers.
License
Parsosaur is distributed under the MIT license. NVIDIA's runtime and model are subject to their upstream license and notices.
Please note that this is experimental research software, and is likely to be rapidly iterated on with no backwards compatibility guarantees. You should also carefully check the outputs to ensure that they are suitable for your usecases.
Metadata
Release files for parsosaur 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| parsosaur-0.1.0.tar.gz | 260.7 kB | Without provenance | Details for parsosaur-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| parsosaur-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for parsosaur-0.1.0-py3-none-any.whl |
Total release size: 341.2 kB
Release files / parsosaur-0.1.0.tar.gz
| Download URL | parsosaur-0.1.0.tar.gz |
|---|---|
| Size | 260.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
993e1861472067b679cd65397c114f1dc2ad0f255366347fbb9909778052d1ce
|
|
BLAKE2b-256 checksum How to use checksums |
25d2d40635af5897d6892a50dab0dc6f896c17b5eda921f02c551d081881759d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.13.6 {"installer":{"name":"uv","version":"0.13.6","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Release files / parsosaur-0.1.0-py3-none-any.whl
| Download URL | parsosaur-0.1.0-py3-none-any.whl |
|---|---|
| Size | 80.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
72e24ca8a40c362dc0195c69c44b4914e3d3811e1d8aaf5dc0876c47d02649b2
|
|
BLAKE2b-256 checksum How to use checksums |
ceb783847eb45ad5dcec65cfb6bcb9ef117a80cf9ea23300686cacbebf185957
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.13.6 {"installer":{"name":"uv","version":"0.13.6","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Security for parsosaur 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.