mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-08-18 13:45:45 +00:00
ce905dd098
Closes #1781. - Adds a Weaviate destination connector - The connector receives a host for the weaviate instance and a weaviate class name. - Defines a weaviate schema for json elements. - Defines the pre-processing to conform unstructured's schema to the proposed weaviate schema.
27 lines
879 B
Bash
27 lines
879 B
Bash
#!/usr/bin/env bash
|
|
|
|
# Uploads the structured output of the files within the given S3 path to a Weaviate index.
|
|
|
|
# Structured outputs are stored in s3-small-batch-output-to-weaviate/
|
|
|
|
SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
|
|
cd "$SCRIPT_DIR"/../../.. || exit 1
|
|
|
|
PYTHONPATH=. ./unstructured/ingest/main.py \
|
|
local \
|
|
--num-processes 2 \
|
|
--output-dir weaviate-output \
|
|
--strategy fast \
|
|
--verbose \
|
|
--reprocess \
|
|
--input-path example-docs/book-war-and-peace-1225p.txt \
|
|
--work-dir weaviate-work-dir \
|
|
--chunk-elements \
|
|
--chunk-new-after-n-chars 2500\
|
|
--chunk-multipage-sections \
|
|
--embedding-provider "langchain-huggingface" \
|
|
weaviate \
|
|
--host-url http://localhost:8080 \
|
|
--class-name elements \
|
|
--batch-size 100
|