MBCDN

Run a local cluster

docker run --rm -p 9200:9200 -p 9600:9600 -e "discovery.type=single-node" opensearchproject/opensearch:2.6.0

Create a python script

from opensearchpy import OpenSearch
 
client = OpenSearch(
    hosts = [{"host": "localhost", "port": 9200}],
    http_auth = ("admin", "admin"),
    use_ssl = True,
    verify_certs = False,
    ssl_assert_hostname = False,
    ssl_show_warn = False,
)
client.info()

Get some random data for e.g wikipedia-movie-plots. Read the data into a pandas array.

import pandas as pd
 
df = (
    pd.read_csv("wiki_movie_plots_deduped.csv")
    .dropna()
    .sample(5000, random_state=42)
    .reset_index(drop=True)
)

Create an index

body = {
    "mappings":{
        "properties": {
            "title": {"type": "text", "analyzer": "english"},
            "ethnicity": {"type": "text", "analyzer": "standard"},
            "director": {"type": "text", "analyzer": "standard"},
            "cast": {"type": "text", "analyzer": "standard"},
            "genre": {"type": "text", "analyzer": "standard"},
            "plot": {"type": "text", "analyzer": "english"},
            "year": {"type": "integer"},
            "wiki_page": {"type": "keyword"}
        }
    }
}
response = client.indices.create("movies", body=body)

Push the data into the index

for i, row in df.iterrows():
    body = {
            "title": row["Title"],
            "ethnicity": row["Origin/Ethnicity"],
            "director": row["Director"],
            "cast": row["Cast"],
            "genre": row["Genre"],
            "plot": row["Plot"],
            "year": row["Release Year"],
            "wiki_page": row["Wiki Page"]
    }
    client.index(index="movies", id=i, body=body)

More data in a bulk

from opensearchpy.helpers import bulk
 
bulk_data = []
for i,row in df.iterrows():
    bulk_data.append(
        {
            "_index": "movies",
            "_id": i,
            "_source": {
                "title": row["Title"],
                "ethnicity": row["Origin/Ethnicity"],
                "director": row["Director"],
                "cast": row["Cast"],
                "genre": row["Genre"],
                "plot": row["Plot"],
                "year": row["Release Year"],
                "wiki_page": row["Wiki Page"],
            }
        }
    )
bulk(client, bulk_data)

Count the inserted data

client.indices.refresh(index="movies")
client.cat.count(index="movies", format="json")

Search the data

resp = client.search(
    index="movies",
    body={
        "query": {
            "bool": {
                "must": {
                    "match_phrase": {
                        "cast": "jack nicholson",
                    }
                },
                "filter": {"bool": {"must_not": {"match_phrase": {"director": "tim burton"}}}},
            },
        },
    }
)
resp