mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-08-31 12:23:49 +00:00
e8ec09c8b9
Thanks to Eric Hare @erichare at DataStax we have a new destination connector. This Pull Request implements an integration with [Astra DB](https://datastax.com) which allows for the Astra DB Vector Database to be compatible with Unstructured's set of integrations. To create your Astra account and authenticate with your `ASTRA_DB_APPLICATION_TOKEN`, and `ASTRA_DB_API_ENDPOINT`, follow these steps: 1. Create an account at https://astra.datastax.com 2. Login and create a new database 3. From the database page, in the right hand panel, you will find your API Endpoint 4. Beneath that, you can create a Token to be used Some notes about Astra DB: - Astra DB is a Vector Database which allows for high-performance database transactions, and enables modern GenAI apps [See here](https://docs.datastax.com/en/astra/astra-db-vector/get-started/concepts.html) - It supports similarity search via a number of methods [See here](https://docs.datastax.com/en/astra/astra-db-vector/get-started/concepts.html#metrics) - It also supports non-vector tables / collections
56 lines
1.6 KiB
Bash
Executable File
56 lines
1.6 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
|
|
set -e
|
|
|
|
SRC_PATH=$(dirname "$(realpath "$0")")
|
|
SCRIPT_DIR=$(dirname "$SRC_PATH")
|
|
cd "$SCRIPT_DIR"/.. || exit 1
|
|
OUTPUT_FOLDER_NAME=astra-dest
|
|
OUTPUT_DIR=$SCRIPT_DIR/structured-output/$OUTPUT_FOLDER_NAME
|
|
WORK_DIR=$SCRIPT_DIR/workdir/$OUTPUT_FOLDER_NAME
|
|
max_processes=${MAX_PROCESSES:=$(python3 -c "import os; print(os.cpu_count())")}
|
|
|
|
if [ -z "$ASTRA_DB_TOKEN" ]; then
|
|
echo "Skipping Astra DB ingest test because ASTRA_DB_TOKEN env var is not set."
|
|
exit 0
|
|
fi
|
|
|
|
if [ -z "$ASTRA_DB_ENDPOINT" ]; then
|
|
echo "Skipping Astra DB ingest test because ASTRA_DB_ENDPOINT env var is not set."
|
|
exit 0
|
|
fi
|
|
|
|
RANDOM_SUFFIX=$((RANDOM % 100000 + 1))
|
|
COLLECTION_NAME="astra_test_output_$RANDOM_SUFFIX"
|
|
EMBEDDING_DIMENSION=384
|
|
|
|
# shellcheck disable=SC1091
|
|
source "$SCRIPT_DIR"/cleanup.sh
|
|
|
|
function cleanup() {
|
|
cleanup_dir "$OUTPUT_DIR"
|
|
cleanup_dir "$WORK_DIR"
|
|
}
|
|
|
|
trap cleanup EXIT
|
|
|
|
PYTHONPATH=. ./unstructured/ingest/main.py \
|
|
local \
|
|
--num-processes "$max_processes" \
|
|
--output-dir "$OUTPUT_DIR" \
|
|
--strategy fast \
|
|
--verbose \
|
|
--input-path example-docs/book-war-and-peace-1p.txt \
|
|
--work-dir "$WORK_DIR" \
|
|
--chunk-elements \
|
|
--chunk-max-characters 1500 \
|
|
--chunk-multipage-sections \
|
|
--embedding-provider "langchain-huggingface" \
|
|
astra \
|
|
--token "$ASTRA_DB_TOKEN" \
|
|
--api-endpoint "$ASTRA_DB_ENDPOINT" \
|
|
--collection-name "$COLLECTION_NAME" \
|
|
--embedding-dimension "$EMBEDDING_DIMENSION"
|
|
|
|
python "$SCRIPT_DIR"/python/test-ingest-astra-output.py --token "$ASTRA_DB_TOKEN" --api-endpoint "$ASTRA_DB_ENDPOINT" --collection-name "$COLLECTION_NAME"
|