2023-12-19 08:58:23 -08:00
|
|
|
#!/usr/bin/env bash
|
|
|
|
|
|
|
|
unstructured-ingest \
|
|
|
|
local \
|
|
|
|
--input-path example-docs/book-war-and-peace-1p.txt \
|
2024-02-01 06:38:34 -08:00
|
|
|
--output-dir local-to-chroma \
|
2023-12-19 08:58:23 -08:00
|
|
|
--strategy fast \
|
|
|
|
--chunk-elements \
|
|
|
|
--embedding-provider "<unstructured embedding provider, ie. langchain-huggingface>" \
|
|
|
|
--num-processes 2 \
|
|
|
|
--verbose \
|
|
|
|
--work-dir "<directory for intermediate outputs to be saved>" \
|
|
|
|
chroma \
|
|
|
|
--host "localhost" \
|
|
|
|
--port 8000 \
|
|
|
|
--collection-name "collection name" \
|
2024-01-16 17:53:52 -08:00
|
|
|
--tenant "default_tenant" \
|
|
|
|
--database "default_database" \
|
2023-12-19 08:58:23 -08:00
|
|
|
--batch-size 80
|