Skip to main content

viparse-llamaindex

LlamaIndex integration for viparse — read Vietnamese documents, including files written in the pre-Unicode TCVN3 / VNI / VISCII / VPS encodings that generic loaders return as B¸o c¸o tµi chÝnh.

pip install viparse-llamaindex
from viparse_llamaindex import ViparseReader

documents = ViparseReader().load_data("bao_cao_cu.doc")

Takes the same options as viparse.load()encoding, ocr, output, chunk — and streams rather than materialising a whole document first.

What it is

A thin, deliberately empty package. The code lives in viparse.integrations and ships with pip install "viparse[llamaindex]"; this distribution exists so that a LlamaIndex user can find it, because LlamaIndex no longer accepts third-party integrations into its own repositories.

Why not llama-index-readers-viparse

That prefix belongs to LlamaIndex's own packages. Using it would imply an official integration that does not exist, and a PyPI name cannot be given back.

Accuracy

0.986 diacritic accuracy over 96 hand-transcribed Vietnamese government documents, against 0.019 for the same reader with conversion switched off — same documents, same published command, one flag apart. The corpus, the metric and every raw result are public, including a written account of the ways the number is weaker than it looks.

MIT © 2026 Đinh Minh Trí (Kayden)

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

viparse_llamaindex-0.1.0.tar.gz (3.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

viparse_llamaindex-0.1.0-py3-none-any.whl (3.8 kB view details)

Uploaded Python 3

File details

Details for the file viparse_llamaindex-0.1.0.tar.gz.

File metadata

  • Download URL: viparse_llamaindex-0.1.0.tar.gz
  • Upload date:
  • Size: 3.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for viparse_llamaindex-0.1.0.tar.gz
Algorithm Hash digest
SHA256 e984df201556f47bf3a93590227c4f8579c7fb7e8ef14f1e03d97a0218a05de4
MD5 3321d727e83c476d49c386246b2c0dbd
BLAKE2b-256 7d792d1597b373475b82c141f6c777946f8a3dc00cc96ed629b9c0d082a8f847

See more details on using hashes here.

Provenance

The following attestation bundles were made for viparse_llamaindex-0.1.0.tar.gz:

Publisher: publish-integrations.yml on TrizenX/viparse

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file viparse_llamaindex-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for viparse_llamaindex-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 ec55f6200a5583904e99f01007ab5a1dff867d6202cd8a181eeea0106e5c57e0
MD5 ff30587d2b6e86d61a670d12c2ab860b
BLAKE2b-256 fac6a4afdb1bddc1d86d563161821bff72d9b3636cf5988b7a3f7be865b5c2db

See more details on using hashes here.

Provenance

The following attestation bundles were made for viparse_llamaindex-0.1.0-py3-none-any.whl:

Publisher: publish-integrations.yml on TrizenX/viparse

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page