Load BoardDocs Meeting Data
LlamaIndex reader that scrapes meeting agendas and materials from a public BoardDocs site.
Why it matters
Ingest and structure data from BoardDocs, enabling efficient retrieval and analysis of meeting agendas and associated materials for research and knowledge management.
Outcomes
What it gets done
Scrape agenda and material data from specified BoardDocs sites.
Extract relevant information from scraped BoardDocs content.
Index BoardDocs data for efficient querying and retrieval.
Load all or specific meeting content from BoardDocs.
Install
Add it to your toolbox
Run in your project directory:
curl -fsSL https://spark.entire.vc/get/li-reader-readers-boarddocs | bash Overview
BoardDocs Loader
The BoardDocs Loader scrapes meeting agendas and materials from a public BoardDocs site into LlamaIndex documents, given a site path and committee ID, optionally scoped to specific meeting IDs. Use it when you need public BoardDocs meeting agendas and materials loaded into LlamaIndex. Loading all meetings without meeting_ids involves scraping the whole site and can take a while.
What it does
The BoardDocs Loader retrieves an agenda and associated material from a BoardDocs site by scraping it -- given a site identifier (for example ca/redwood for https://go.boarddocs.com/ca/redwood/Board.nsf/Public) and a committee ID. It is not endorsed by, developed by, or affiliated with Diligent Corporation, BoardDocs' operator.
When to use - and when NOT to
Use it when you need meeting agendas and materials from a public BoardDocs site loaded into LlamaIndex -- either specific meetings by ID, or, if you omit meeting_ids, everything the loader can find, which involves scraping the whole site and can take a while. It requires knowing the site's path and committee ID in advance, so it is not usable without first identifying those from the BoardDocs URL structure.
Inputs and outputs
Install with:
pip install llama-index-readers-boarddocs
Specify the site and committee, then load meeting data:
from llama_index.readers.boarddocs import BoardDocsReader
### For a site URL https://go.boarddocs.com/ca/redwood/Board.nsf/Public
### your site should be set to 'ca/redwood'
### You'll also need to specify which committee on the site you want to index,
### in this case A4EP6J588C05 is the Board of Trustees meeting.
loader = BoardDocsReader(site="ca/redwood", committee_id="A4EP6J588C05")
### You can optionally specify to load a specific set of meetings; if you don't
### pass in meeting_ids, the loader will attempt to load *all* meeting content.
### Since we're actually scraping a site, this can take a little while.
documents = loader.load_data(meeting_ids=["CPSNV9612DF1"])
site and committee_id identify which BoardDocs site and committee to load; load_data optionally accepts a meeting_ids list to limit which meetings are scraped, otherwise it scrapes all of them.
Who it's for
Developers building LlamaIndex pipelines that need public governmental or organizational meeting agendas and materials from a BoardDocs site.
Source README
BoardDocs Loader
pip install llama-index-readers-boarddocs
This loader retrieves an agenda and associated material from a BoardDocs site.
This loader is not endorsed by, developed by, supported by, or in any way formally affiliated with Diligent Corporation.
Usage
To use this loader, you'll need to specify which BoardDocs site you want to load,
as well as the committee on the site you want to scrape.
from llama_index.readers.boarddocs import BoardDocsReader
### For a site URL https://go.boarddocs.com/ca/redwood/Board.nsf/Public
### your site should be set to 'ca/redwood'
### You'll also need to specify which committee on the site you want to index,
### in this case A4EP6J588C05 is the Board of Trustees meeting.
loader = BoardDocsReader(site="ca/redwood", committee_id="A4EP6J588C05")
### You can optionally specify to load a specific set of meetings; if you don't
### pass in meeting_ids, the loader will attempt to load *all* meeting content.
### Since we're actually scraping a site, this can take a little while.
documents = loader.load_data(meeting_ids=["CPSNV9612DF1"])
This loader is designed to be used as a way to load data into LlamaIndex.
FAQ
Common questions
Discussion
Questions & comments · 0
Sign In Sign in to leave a comment.