mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-07-11 19:15:56 +00:00
19 lines
507 B
Bash
19 lines
507 B
Bash
|
#!/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"
|