mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-07-10 18:45:54 +00:00
c100ce28a7
Thanks to Ofer at Vectara, we now have a Vectara destination connector. - There are no dependencies since it is all REST calls to API - --------- Co-authored-by: potter-potter <david.potter@gmail.com>
20 lines
545 B
Bash
20 lines
545 B
Bash
#!/usr/bin/env bash
|
|
|
|
unstructured-ingest \
|
|
local \
|
|
--input-path example-docs/book-war-and-peace-1p.txt \
|
|
--output-dir local-to-chroma \
|
|
--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" \
|
|
--tenant "default_tenant" \
|
|
--database "default_database" \
|
|
--batch-size 80
|