mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-06-27 02:30:08 +00:00
fd293b3e78
Closes https://github.com/Unstructured-IO/unstructured/issues/1842
Closes https://github.com/Unstructured-IO/unstructured/issues/2202
Closes https://github.com/Unstructured-IO/unstructured/issues/2203
This PR:
- Adds Elasticsearch destination connector to be able to ingest
documents from any supported source, embed them and write the embeddings
/ documents into Elasticsearch.
- Defines an example unstructured elements schema for users to be able
to setup their unstructured elasticsearch indexes easily.
- Includes parallelized upload and lazy processing for elasticsearch
destination connector.
- Rearranges elasticsearch test helpers to source, destination, and
common folders.
- Adds util functions to be able to batch iterables in a lazy way for
uploads
- Fixes a bug where removing the optional parameter `--fields` broke the
connector due to an integer processing error.
- Fixes a bug where using an [elasticsearch
config](8fa5cbf036/unstructured/ingest/connector/elasticsearch.py (L26-L35))
for a destination connector resulted in a serialization issue when
optional parameter `--fields` was not provided.
36 lines
1.1 KiB
Python
Executable File
36 lines
1.1 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
|
|
import pandas as pd
|
|
from elasticsearch import Elasticsearch
|
|
from elasticsearch.helpers import bulk
|
|
from es_cluster_config import (
|
|
CLUSTER_URL,
|
|
DATA_PATH,
|
|
INDEX_NAME,
|
|
MAPPINGS,
|
|
PASSWORD,
|
|
USER,
|
|
form_elasticsearch_doc_dict,
|
|
)
|
|
|
|
print("Connecting to the Elasticsearch cluster.")
|
|
es = Elasticsearch(CLUSTER_URL, basic_auth=(USER, PASSWORD), request_timeout=30)
|
|
print(f"{es.info()}")
|
|
df = pd.read_csv(DATA_PATH).dropna().reset_index()
|
|
|
|
print("Creating an Elasticsearch index for testing elasticsearch ingest.")
|
|
response = es.options(max_retries=5).indices.create(index=INDEX_NAME, mappings=MAPPINGS)
|
|
if response.meta.status != 200:
|
|
raise RuntimeError("failed to create index")
|
|
|
|
print("Loading data into the index.")
|
|
bulk_data = []
|
|
for i, row in df.iterrows():
|
|
bulk_data.append(form_elasticsearch_doc_dict(i, row))
|
|
bulk(es, bulk_data)
|
|
|
|
es.indices.refresh(index=INDEX_NAME)
|
|
response = es.cat.count(index=INDEX_NAME, format="json")
|
|
|
|
print("Successfully created and filled an Elasticsearch index for testing elasticsearch ingest.")
|