Feature/add acreom loader (#5780)

adding new loader for [acreom](https://acreom.com) vaults. It's based on
the Obsidian loader with some additional text processing for acreom
specific markdown elements.

 @eyurtsev please take a look!

---------

Co-authored-by: rlm <pexpresss31@gmail.com>
This commit is contained in:
Martin Antos 2023-06-15 20:53:00 +02:00 committed by GitHub
parent ae76e473e1
commit 1913320cbe
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 150 additions and 0 deletions

View File

@ -0,0 +1,75 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "e310c8dc-acd0-48d2-801c-f37ce99acd2d",
"metadata": {},
"source": [
"# acreom"
]
},
{
"cell_type": "markdown",
"id": "04a2c95d-4114-431e-904a-32d79005c28b",
"metadata": {},
"source": [
"[acreom](https://acreom.com) is a dev-first knowledge base with tasks running on local markdown files.\n",
"\n",
"Below is an example on how to load a local acreom vault into Langchain. As the local vault in acreom is a folder of plain text .md files, the loader requires the path to the directory. \n",
"\n",
"Vault files may contain some metadata which is stored as a YAML header. These values will be added to the documents metadata if `collect_metadata` is set to true. "
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0169bee5-aa7a-4ec7-b7e7-b3bb2e58f3bb",
"metadata": {},
"outputs": [],
"source": [
"from langchain.document_loaders import AcreomLoader"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c1b49ab3-616b-4149-bef5-7559d65d3d2b",
"metadata": {},
"outputs": [],
"source": [
"loader = AcreomLoader('<path-to-acreom-vault>', collect_metadata=False)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "3127a018-9c1c-4886-8321-f5666d970a95",
"metadata": {},
"outputs": [],
"source": [
"docs = loader.load()"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.10"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

View File

@ -1,5 +1,6 @@
"""All different types of document loaders."""
from langchain.document_loaders.acreom import AcreomLoader
from langchain.document_loaders.airbyte_json import AirbyteJSONLoader
from langchain.document_loaders.airtable import AirtableLoader
from langchain.document_loaders.apify_dataset import ApifyDatasetLoader
@ -136,6 +137,7 @@ PagedPDFSplitter = PyPDFLoader
TelegramChatLoader = TelegramChatFileLoader
__all__ = [
"AcreomLoader",
"AZLyricsLoader",
"AirbyteJSONLoader",
"AirtableLoader",

View File

@ -0,0 +1,73 @@
"""Loader that loads acreom vault from a directory."""
import re
from pathlib import Path
from typing import Iterator, List
from langchain.docstore.document import Document
from langchain.document_loaders.base import BaseLoader
class AcreomLoader(BaseLoader):
FRONT_MATTER_REGEX = re.compile(r"^---\n(.*?)\n---\n", re.MULTILINE | re.DOTALL)
def __init__(
self, path: str, encoding: str = "UTF-8", collect_metadata: bool = True
):
"""Initialize with path."""
self.file_path = path
self.encoding = encoding
self.collect_metadata = collect_metadata
def _parse_front_matter(self, content: str) -> dict:
"""Parse front matter metadata from the content and return it as a dict."""
if not self.collect_metadata:
return {}
match = self.FRONT_MATTER_REGEX.search(content)
front_matter = {}
if match:
lines = match.group(1).split("\n")
for line in lines:
if ":" in line:
key, value = line.split(":", 1)
front_matter[key.strip()] = value.strip()
else:
# Skip lines without a colon
continue
return front_matter
def _remove_front_matter(self, content: str) -> str:
"""Remove front matter metadata from the given content."""
if not self.collect_metadata:
return content
return self.FRONT_MATTER_REGEX.sub("", content)
def _process_acreom_content(self, content: str) -> str:
# remove acreom specific elements from content that
# do not contribute to the context of current document
content = re.sub("\s*-\s\[\s\]\s.*|\s*\[\s\]\s.*", "", content) # rm tasks
content = re.sub("#", "", content) # rm hashtags
content = re.sub("\[\[.*?\]\]", "", content) # rm doclinks
return content
def lazy_load(self) -> Iterator[Document]:
ps = list(Path(self.file_path).glob("**/*.md"))
for p in ps:
with open(p, encoding=self.encoding) as f:
text = f.read()
front_matter = self._parse_front_matter(text)
text = self._remove_front_matter(text)
text = self._process_acreom_content(text)
metadata = {
"source": str(p.name),
"path": str(p),
**front_matter,
}
yield Document(page_content=text, metadata=metadata)
def load(self) -> List[Document]:
return list(self.lazy_load())