|
| 1 | +```python Python Ingest v2 |
| 2 | +import os |
| 3 | + |
| 4 | +from unstructured_ingest.v2.pipeline.pipeline import Pipeline |
| 5 | +from unstructured_ingest.v2.interfaces import ProcessorConfig |
| 6 | + |
| 7 | +from unstructured_ingest.v2.processes.connectors.local import ( |
| 8 | + LocalIndexerConfig, |
| 9 | + LocalDownloaderConfig, |
| 10 | + LocalConnectionConfig |
| 11 | +) |
| 12 | +from unstructured_ingest.v2.processes.partitioner import PartitionerConfig |
| 13 | +from unstructured_ingest.v2.processes.chunker import ChunkerConfig |
| 14 | +from unstructured_ingest.v2.processes.embedder import EmbedderConfig |
| 15 | + |
| 16 | +# For LanceDB OSS with local data storage: |
| 17 | +# from unstructured_ingest.v2.processes.connectors.lancedb.local import ( |
| 18 | +# LanceDBLocalConnectionConfig, |
| 19 | +# LanceDBLocalAccessConfig, |
| 20 | +# LanceDBUploadStagerConfig, |
| 21 | +# LanceDBUploaderConfig |
| 22 | +# ) |
| 23 | + |
| 24 | +# For LanceDB OSS with data storage in an Amazon S3 bucket: |
| 25 | +from unstructured_ingest.v2.processes.connectors.lancedb.aws import ( |
| 26 | + LanceDBS3ConnectionConfig, |
| 27 | + LanceDBS3AccessConfig, |
| 28 | + LanceDBUploadStagerConfig, |
| 29 | + LanceDBUploaderConfig |
| 30 | +) |
| 31 | + |
| 32 | +# For LanceDB OSS with data storage in an Azure Blob Storage account: |
| 33 | +# from unstructured_ingest.v2.processes.connectors.lancedb.azure import ( |
| 34 | +# LanceDBAzureConnectionConfig, |
| 35 | +# LanceDBAzureAccessConfig, |
| 36 | +# LanceDBUploadStagerConfig, |
| 37 | +# LanceDBUploaderConfig |
| 38 | +# ) |
| 39 | + |
| 40 | +# For LanceDB OSS with data storage in a Google Cloud Storage bucket: |
| 41 | +# from unstructured_ingest.v2.processes.connectors.lancedb.gcp import ( |
| 42 | +# LanceDBGCSConnectionConfig, |
| 43 | +# LanceDBGCSAccessConfig, |
| 44 | +# LanceDBUploadStagerConfig, |
| 45 | +# LanceDBUploaderConfig |
| 46 | +# ) |
| 47 | + |
| 48 | +# Chunking and embedding are optional. |
| 49 | + |
| 50 | +if __name__ == "__main__": |
| 51 | + Pipeline.from_configs( |
| 52 | + context=ProcessorConfig(), |
| 53 | + indexer_config=LocalIndexerConfig(input_path=os.getenv("LOCAL_FILE_INPUT_DIR")), |
| 54 | + downloader_config=LocalDownloaderConfig(), |
| 55 | + source_connection_config=LocalConnectionConfig(), |
| 56 | + partitioner_config=PartitionerConfig( |
| 57 | + partition_by_api=True, |
| 58 | + api_key=os.getenv("UNSTRUCTURED_API_KEY"), |
| 59 | + partition_endpoint=os.getenv("UNSTRUCTURED_API_URL"), |
| 60 | + additional_partition_args={ |
| 61 | + "split_pdf_page": True, |
| 62 | + "split_pdf_allow_failed": True, |
| 63 | + "split_pdf_concurrency_level": 15 |
| 64 | + } |
| 65 | + ), |
| 66 | + chunker_config=ChunkerConfig(chunking_strategy="by_title"), |
| 67 | + embedder_config=EmbedderConfig(embedding_provider="huggingface"), |
| 68 | + |
| 69 | + # For LanceDB OSS with local data storage: |
| 70 | + # destination_connection_config=LanceDBLocalConnectionConfig( |
| 71 | + # access_config=LanceDBLocalAccessConfig(), |
| 72 | + # uri=os.getenv("LANCEDB_URI") |
| 73 | + # ), |
| 74 | + |
| 75 | + # For LanceDB OSS with data storage in an Amazon S3 bucket: |
| 76 | + destination_connection_config=LanceDBS3ConnectionConfig( |
| 77 | + access_config=LanceDBS3AccessConfig( |
| 78 | + aws_access_key_id=os.getenv("AWS_ACCESS_KEY_ID"), |
| 79 | + aws_secret_access_key=os.getenv("AWS_SECRET_ACCESS_KEY") |
| 80 | + ), |
| 81 | + uri=os.getenv("LANCEDB_URI"), |
| 82 | + timeout="30s" |
| 83 | + ), |
| 84 | + |
| 85 | + # For LanceDB OSS with data storage in an Azure Blob Storage account: |
| 86 | + # destination_connection_config=LanceDBAzureConnectionConfig( |
| 87 | + # access_config=LanceDBAzureAccessConfig( |
| 88 | + # azure_storage_account_name=os.getenv("AZURE_STORAGE_ACCOUNT_NAME"), |
| 89 | + # azure_storage_account_key=os.getenv("AZURE_STORAGE_ACCOUNT_KEY") |
| 90 | + # ), |
| 91 | + # uri=os.getenv("LANCEDB_URI"), |
| 92 | + # timeout="30s" |
| 93 | + # ), |
| 94 | + |
| 95 | + # For LanceDB OSS with data storage in a Google Cloud Storage bucket: |
| 96 | + # destination_connection_config=LanceDBGCSConnectionConfig( |
| 97 | + # access_config=LanceDBGCSAccessConfig( |
| 98 | + # google_service_account_key=os.getenv("GCS_SERVICE_ACCOUNT_KEY") |
| 99 | + # ), |
| 100 | + # uri=os.getenv("LANCEDB_URI"), |
| 101 | + # timeout="30s" |
| 102 | + # ), |
| 103 | + |
| 104 | + stager_config=LanceDBUploadStagerConfig(), |
| 105 | + uploader_config=LanceDBUploaderConfig(table_name=os.gentenv("LANCEDB_TABLE")) |
| 106 | + ).run() |
| 107 | +``` |
0 commit comments