mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-07-04 07:27:34 +00:00
48 lines
1.4 KiB
Python
48 lines
1.4 KiB
Python
from unstructured.ingest.connector.fsspec.s3 import S3AccessConfig, S3WriteConfig, SimpleS3Config
|
|
from unstructured.ingest.connector.local import SimpleLocalConfig
|
|
from unstructured.ingest.interfaces import (
|
|
ChunkingConfig,
|
|
EmbeddingConfig,
|
|
PartitionConfig,
|
|
ProcessorConfig,
|
|
ReadConfig,
|
|
)
|
|
from unstructured.ingest.runner import LocalRunner
|
|
from unstructured.ingest.runner.writers.base_writer import Writer
|
|
from unstructured.ingest.runner.writers.fsspec.s3 import (
|
|
S3Writer,
|
|
)
|
|
|
|
|
|
def get_writer() -> Writer:
|
|
return S3Writer(
|
|
connector_config=SimpleS3Config(
|
|
access_config=S3AccessConfig(anon=True),
|
|
remote_url="s3://unstructured/war-and-peace-output",
|
|
),
|
|
write_config=S3WriteConfig(),
|
|
)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
writer = get_writer()
|
|
runner = LocalRunner(
|
|
processor_config=ProcessorConfig(
|
|
verbose=True,
|
|
output_dir="local-output-to-s3",
|
|
num_processes=2,
|
|
),
|
|
connector_config=SimpleLocalConfig(
|
|
input_path="example-docs/book-war-and-peace-1225p.txt",
|
|
),
|
|
read_config=ReadConfig(),
|
|
partition_config=PartitionConfig(),
|
|
chunking_config=ChunkingConfig(chunk_elements=True),
|
|
embedding_config=EmbeddingConfig(
|
|
provider="langchain-huggingface",
|
|
),
|
|
writer=writer,
|
|
writer_kwargs={},
|
|
)
|
|
runner.run()
|