Astra

Batch process all your records using unstructured-ingest to store structured outputs and embeddings locally on your filesystem and upload those to a Astra DB index.

First you’ll need to install the Astra dependencies as shown here.

pip install "unstructured[astra]"

Run Locally

The upstream connector can be any of the ones supported, but for convenience here, showing a sample command using the upstream local connector.

#!/usr/bin/env bash

EMBEDDING_PROVIDER=${EMBEDDING_PROVIDER:-"langchain-huggingface"}

unstructured-ingest \
  local \
  --input-path example-docs/book-war-and-peace-1p.txt \
  --output-dir local-output-to-astra \
  --strategy fast \
  --chunk-elements \
  --embedding-provider "$EMBEDDING_PROVIDER" \
  --num-processes 2 \
  --verbose \
  astra \
  --token "$ASTRA_DB_TOKEN" \
  --api-endpoint "$ASTRA_DB_ENDPOINT" \
  --collection-name "$COLLECTION_NAME" \
  --embedding-dimension "$EMBEDDING_DIMENSION"

import os

from unstructured.ingest.connector.astra import (
    AstraAccessConfig,
    AstraWriteConfig,
    SimpleAstraConfig,
)
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.astra import (
    AstraWriter,
)
from unstructured.ingest.runner.writers.base_writer import Writer


def get_writer() -> Writer:
    return AstraWriter(
        connector_config=SimpleAstraConfig(
            access_config=AstraAccessConfig(
                token=os.getenv("ASTRA_DB_TOKEN"), api_endpoint=os.getenv("ASTRA_DB_ENDPOINT")
            ),
            collection_name="test_collection",
            embedding_dimension=384,
        ),
        write_config=AstraWriteConfig(batch_size=80),
    )


if __name__ == "__main__":
    writer = get_writer()
    runner = LocalRunner(
        processor_config=ProcessorConfig(
            verbose=True,
            output_dir="local-output-to-astra",
            num_processes=2,
        ),
        connector_config=SimpleLocalConfig(
            input_path="example-docs/book-war-and-peace-1p.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()

For a full list of the options the CLI accepts check unstructured-ingest <upstream connector> astra --help.

NOTE: Keep in mind that you will need to have all the appropriate extras and dependencies for the file types of the documents contained in your data storage platform if you’re running this locally. You can find more information about this in the installation guide.