Skip to content

README.md

Latest commit

 

History

History
62 lines (44 loc) · 3.49 KB

README.md

File metadata and controls

62 lines (44 loc) · 3.49 KB

Dataprep Microservice

The Dataprep Microservice aims to preprocess the data from various sources (either structured or unstructured data) to text data, and convert the text data to embedding vectors then store them in the database.

Table of contents

  1. Install Requirements
  2. Summarizing Image Data with LVM
  3. Dataprep Microservice on Various Databases
  4. Running in the air gapped environment

Install Requirements

apt-get update
apt-get install libreoffice

Summarizing Image Data with LVM

Occasionally unstructured data will contain image data, to convert the image data to the text data, LVM (Large Vision Model) can be used to summarize the image. To leverage LVM, please refer to this readme to start the LVM microservice first and then set the below environment variable, before starting any dataprep microservice.

export SUMMARIZE_IMAGE_VIA_LVM=1

Dataprep Microservice on Various Databases

Dataprep microservice are supported on various databases, as shown in the table below, for details, please refer to the respective readme listed below.

Databases Readme
Redis Dataprep Microservice with Redis
Milvus Dataprep Microservice with Milvus
Qdrant Dataprep Microservice with Qdrant
Pinecone Dataprep Microservice with Pinecone
PGVector Dataprep Microservice with PGVector
VDMS Dataprep Microservice with VDMS
Multimodal Dataprep Microservice with Multimodal
ElasticSearch Dataprep Microservice with ElasticSearch
OpenSearch Dataprep Microservice with OpenSearch
neo4j Dataprep Microservice with neo4j
financial domain data Dataprep Microservice for financial domain data
MariaDB Dataprep Microservice with MariaDB Vector
ArangoDB Dataprep Microservice with ArangoDB Vector

Running in the air gapped environment

The following steps are common for running the dataprep microservice in an air gapped environment (a.k.a. environment with no internet access), for all DB backends.

  1. Download the following models, e.g. huggingface-cli download --cache-dir <model data directory> <model>
  • microsoft/table-transformer-structure-recognition
  • timm/resnet18.a1_in1k
  • unstructuredio/yolo_x_layout
  1. launch the dataprep microservice with the following settings:
  • mount the model data directory as the /data directory within the dataprep container
  • set environment variable HF_HUB_OFFLINE to 1 when launching the dataprep microservice

e.g. docker run -d -v <model data directory>:/data -e HF_HUB_OFFLINE=1 ... ...