mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-07-18 22:46:44 +00:00
4b8352e0f5
Adds Chroma (also known as ChromaDB) as a vector destination. Currently Chroma is an in-memory single-process oriented library with plans of a hosted and/or more production ready solution -https://docs.trychroma.com/deployment Though they now claim to support multiple Clients hitting the database at once, I found that it was inconsistent. Sometimes multiprocessing worked (maybe 1 out of 3 times) But the other times I would get different errors. So I kept it single process. --------- Co-authored-by: potter-potter <david.potter@gmail.com>
35 lines
1.4 KiB
Bash
35 lines
1.4 KiB
Bash
#!/usr/bin/env bash
|
|
|
|
# Processes example-docs/book-war-and-peace-1p.txt/,
|
|
# embeds the processed document and writes to results to a Chroma collection.
|
|
|
|
# Structured outputs are stored in local-to-chroma/
|
|
|
|
SCRIPT_DIR=$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" &>/dev/null && pwd)
|
|
cd "$SCRIPT_DIR"/../../.. || exit 1
|
|
|
|
# As an example we're using the local source connector,
|
|
# however ingesting from any supported source connector is possible.
|
|
# shellcheck disable=2094
|
|
PYTHONPATH=. ./unstructured/ingest/main.py \
|
|
local \
|
|
--input-path example-docs/book-war-and-peace-1p.txt \
|
|
--output-dir local-to-chroma \
|
|
--strategy fast \
|
|
--chunk-elements \
|
|
--embedding-provider "<an unstructured embedding provider, ie. langchain-huggingface>" \
|
|
--num-processes 2 \
|
|
--verbose \
|
|
--work-dir "<directory for intermediate outputs to be saved>" \
|
|
chroma \
|
|
--path "<Location where Chroma is persisted, if not connecting via http>" \
|
|
--settings "<Dictionary of settings to communicate with the chroma server>" \
|
|
--tenant "<Tenant to use for this client>" \
|
|
--database "<Database to use for this client>" \
|
|
--host "<Hostname of the Chroma server>" \
|
|
--port "<Port of the Chroma server>" \
|
|
--ssl "<Whether to use SSL to connect to the Chroma server>" \
|
|
--headers "<Dictionary of headers to send to the Chroma server>" \
|
|
--collection-name "<Name of the Chroma collection to write into>" \
|
|
--batch-size "<Number of elements to be uploaded in a single batch, ie. 80>"
|