mirror of
https://github.com/hwchase17/langchain
synced 2024-11-10 01:10:59 +00:00
8799b028a6
## Description
In this update, I addressed the missing implementation for
atransform_document, which is the asynchronous counterpart of
transform_document in Doctran.
### Usage Example:
```py
# Instantiate DoctranPropertyExtractor with specified properties
property_extractor = DoctranPropertyExtractor(properties=properties)
# Asynchronously extract properties from a list of documents
extracted_document = await property_extractor.atransform_documents(
documents, properties=properties
)
# Display metadata of the first extracted document
print(json.dumps(extracted_document[0].metadata, indent=2))
```
## Issue
- Pull request #14525 has caused a break in the aforementioned code.
Instead of removing an asynchronous implementation of a function,
consider implementing a synchronous version alongside it.
|
||
|---|---|---|
| .. | ||
| xsl | ||
| __init__.py | ||
| beautiful_soup_transformer.py | ||
| doctran_text_extract.py | ||
| doctran_text_qa.py | ||
| doctran_text_translate.py | ||
| embeddings_redundant_filter.py | ||
| google_translate.py | ||
| html2text.py | ||
| long_context_reorder.py | ||
| nuclia_text_transform.py | ||
| openai_functions.py | ||