mirror of
https://github.com/hwchase17/langchain
synced 2024-11-06 03:20:49 +00:00
373ad49157
# docs: `ecosystem_integrations` update 3 Next cycle of updating the `ecosystem/integrations` * Added an integration `template` file * Added missed integration files * Fixed several document_loaders/notebooks ## Who can review? Is it possible to assign somebody to review PRs on docs? Thanks.
32 lines
948 B
Markdown
32 lines
948 B
Markdown
# MediaWikiDump
|
|
|
|
>[MediaWiki XML Dumps](https://www.mediawiki.org/wiki/Manual:Importing_XML_dumps) contain the content of a wiki
|
|
> (wiki pages with all their revisions), without the site-related data. A XML dump does not create a full backup
|
|
> of the wiki database, the dump does not contain user accounts, images, edit logs, etc.
|
|
|
|
|
|
## Installation and Setup
|
|
|
|
We need to install several python packages.
|
|
|
|
The `mediawiki-utilities` supports XML schema 0.11 in unmerged branches.
|
|
```bash
|
|
pip install -qU git+https://github.com/mediawiki-utilities/python-mwtypes@updates_schema_0.11
|
|
```
|
|
|
|
The `mediawiki-utilities mwxml` has a bug, fix PR pending.
|
|
|
|
```bash
|
|
pip install -qU git+https://github.com/gdedrouas/python-mwxml@xml_format_0.11
|
|
pip install -qU mwparserfromhell
|
|
```
|
|
|
|
## Document Loader
|
|
|
|
See a [usage example](../modules/indexes/document_loaders/examples/mediawikidump.ipynb).
|
|
|
|
|
|
```python
|
|
from langchain.document_loaders import MWDumpLoader
|
|
```
|