github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-08 06:23:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

community[major], core[patch], langchain[patch], experimental[patch]: Create langchain-community (#14463)

Browse Source 
Moved the following modules to new package langchain-community in a backwards compatible fashion:

```
mv langchain/langchain/adapters community/langchain_community
mv langchain/langchain/callbacks community/langchain_community/callbacks
mv langchain/langchain/chat_loaders community/langchain_community
mv langchain/langchain/chat_models community/langchain_community
mv langchain/langchain/document_loaders community/langchain_community
mv langchain/langchain/docstore community/langchain_community
mv langchain/langchain/document_transformers community/langchain_community
mv langchain/langchain/embeddings community/langchain_community
mv langchain/langchain/graphs community/langchain_community
mv langchain/langchain/llms community/langchain_community
mv langchain/langchain/memory/chat_message_histories community/langchain_community
mv langchain/langchain/retrievers community/langchain_community
mv langchain/langchain/storage community/langchain_community
mv langchain/langchain/tools community/langchain_community
mv langchain/langchain/utilities community/langchain_community
mv langchain/langchain/vectorstores community/langchain_community
mv langchain/langchain/agents/agent_toolkits community/langchain_community
mv langchain/langchain/cache.py community/langchain_community
mv langchain/langchain/adapters community/langchain_community
mv langchain/langchain/callbacks community/langchain_community/callbacks
mv langchain/langchain/chat_loaders community/langchain_community
mv langchain/langchain/chat_models community/langchain_community
mv langchain/langchain/document_loaders community/langchain_community
mv langchain/langchain/docstore community/langchain_community
mv langchain/langchain/document_transformers community/langchain_community
mv langchain/langchain/embeddings community/langchain_community
mv langchain/langchain/graphs community/langchain_community
mv langchain/langchain/llms community/langchain_community
mv langchain/langchain/memory/chat_message_histories community/langchain_community
mv langchain/langchain/retrievers community/langchain_community
mv langchain/langchain/storage community/langchain_community
mv langchain/langchain/tools community/langchain_community
mv langchain/langchain/utilities community/langchain_community
mv langchain/langchain/vectorstores community/langchain_community
mv langchain/langchain/agents/agent_toolkits community/langchain_community
mv langchain/langchain/cache.py community/langchain_community
```

Moved the following to core
```
mv langchain/langchain/utils/json_schema.py core/langchain_core/utils
mv langchain/langchain/utils/html.py core/langchain_core/utils
mv langchain/langchain/utils/strings.py core/langchain_core/utils
cat langchain/langchain/utils/env.py >> core/langchain_core/utils/env.py
rm langchain/langchain/utils/env.py
```

See .scripts/community_split/script_integrations.sh for all changes
This commit is contained in:
Bagatur
2023-12-11 13:53:30 -08:00
committed by GitHub
parent c0f4b95aa9
commit ed58eeb9c5
2446 changed files with 171805 additions and 137118 deletions
Download Patch File Download Diff File Expand all files Collapse all files

49
libs/community/langchain_community/document_loaders/docusaurus.py Normal file
View File

@@ -0,0 +1,49 @@
"""Load Documents from Docusarus Documentation"""
from typing import Any, List, Optional
from langchain_community.document_loaders.sitemap import SitemapLoader
class DocusaurusLoader(SitemapLoader):
"""
Loader that leverages the SitemapLoader to loop through the generated pages of a
Docusaurus Documentation website and extracts the content by looking for specific
HTML tags. By default, the parser searches for the main content of the Docusaurus
page, which is normally the <article>. You also have the option to define your own
custom HTML tags by providing them as a list, for example: ["div", ".main", "a"].
"""
def __init__(
self,
url: str,
custom_html_tags: Optional[List[str]] = None,
**kwargs: Any,
):
"""
Initialize DocusaurusLoader
Args:
url: The base URL of the Docusaurus website.
custom_html_tags: Optional custom html tags to extract content from pages.
kwargs: Additional args to extend the underlying SitemapLoader, for example:
filter_urls, blocksize, meta_function, is_local, continue_on_failure
"""
if not kwargs.get("is_local"):
url = f"{url}/sitemap.xml"
self.custom_html_tags = custom_html_tags or ["main article"]
super().__init__(
url,
parsing_function=kwargs.get("parsing_function") or self._parsing_function,
**kwargs,
)
def _parsing_function(self, content: Any) -> str:
"""Parses specific elements from a Docusarus page."""
relevant_elements = content.select(",".join(self.custom_html_tags))
for element in relevant_elements:
if element not in relevant_elements:
element.decompose()
return str(content.get_text())