Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Adding semantic search with hybrid query workload #292

Merged
merged 9 commits into from
May 24, 2024
Merged

Adding semantic search with hybrid query workload #292

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
fb8a140
Init version of workload for semantic search and hybrid query
martin-gaievski Apr 29, 2024
010e3ec
Added medium dataset to profiler procedure
martin-gaievski May 17, 2024
9631f12
Addressing review comments: rename workload, fix readme
martin-gaievski May 21, 2024
479db39
Use eventdata for throughput and client parameters per operation
martin-gaievski May 21, 2024
34498f4
Add details to workload description
martin-gaievski May 21, 2024
b7919a8
Change version back to 1, add more aggs queries for medium subset
martin-gaievski May 21, 2024
7c69ca0
Remove unused methods from workload.py
martin-gaievski May 22, 2024
22a501f
Delete workload.py as it's not needed
martin-gaievski May 22, 2024
8bdd9af
Delete files.txt as it's not needed
martin-gaievski May 23, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
440 changes: 440 additions & 0 deletions semanticsearch/README.md
View file
Open in desktop

Large diffs are not rendered by default.

2 changes: 2 additions & 0 deletions semanticsearch/files.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
documents.json.bz2
documents-1k.json.bz2
273 changes: 273 additions & 0 deletions semanticsearch/index.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,273 @@
{
"settings": {
"index.number_of_shards": {{number_of_shards | default(1)}},
"index.number_of_replicas": {{number_of_replicas | default(0)}},
"index.queries.cache.enabled": {{query_cache_enabled | default(false) | tojson}},
"index.requests.cache.enable": {{requests_cache_enabled | default(false) | tojson}},
"index.merge.policy.max_merged_segment": "100GB"
},
"mappings": {
"dynamic": "strict",
"_source": {
"enabled": {{ source_enabled | default(true) | tojson }}
},
"properties": {
"AWDR": {
"type": "keyword"
},
"AWND": {
"type": "float"
},
"DAPR": {
"type": "keyword"
},
"DASF": {
"type": "keyword"
},
"DATN": {
"type": "keyword"
},
"DATX": {
"type": "keyword"
},
"DWPR": {
"type": "keyword"
},
"EVAP": {
"type": "float"
},
"MDPR": {
"type": "float"
},
"MDSF": {
"type": "keyword"
},
"MDTN": {
"type": "float"
},
"MDTRANGE": {
"type": "double_range"
},
"MDTX": {
"type": "float"
},
"MNPN": {
"type": "float"
},
"MXPN": {
"type": "float"
},
"PGTM": {
"type": "keyword"
},
"PRCP": {
"type": "float"
},
"PSUN": {
"type": "keyword"
},
"SN31": {
"type": "keyword"
},
"SN32": {
"type": "keyword"
},
"SN33": {
"type": "keyword"
},
"SN35": {
"type": "keyword"
},
"SN36": {
"type": "keyword"
},
"SN51": {
"type": "keyword"
},
"SN52": {
"type": "keyword"
},
"SN53": {
"type": "keyword"
},
"SN55": {
"type": "keyword"
},
"SN56": {
"type": "keyword"
},
"SN57": {
"type": "keyword"
},
"SNOW": {
"type": "keyword"
},
"SNWD": {
"type": "keyword"
},
"SX31": {
"type": "keyword"
},
"SX32": {
"type": "keyword"
},
"SX33": {
"type": "keyword"
},
"SX35": {
"type": "keyword"
},
"SX36": {
"type": "keyword"
},
"SX51": {
"type": "keyword"
},
"SX52": {
"type": "keyword"
},
"SX53": {
"type": "keyword"
},
"SX55": {
"type": "keyword"
},
"SX56": {
"type": "keyword"
},
"SX57": {
"type": "keyword"
},
"TAVG": {
"type": "float"
},
"THIC": {
"type": "float"
},
"TMAX": {
"type": "float"
},
"TMIN": {
"type": "float"
},
"TOBS": {
"type": "float"
},
"TRANGE": {
"type": "double_range"
},
"TSUN": {
"type": "keyword"
},
"WDF2": {
"type": "keyword"
},
"WDF5": {
"type": "keyword"
},
"WDFG": {
"type": "keyword"
},
"WDMV": {
"type": "keyword"
},
"WESD": {
"type": "float"
},
"WESF": {
"type": "float"
},
"WSF2": {
"type": "float"
},
"WSF5": {
"type": "float"
},
"WSFG": {
"type": "float"
},
"WSFI": {
"type": "float"
},
"WT01": {
"type": "keyword"
},
"WT02": {
"type": "keyword"
},
"WT03": {
"type": "keyword"
},
"WT04": {
"type": "keyword"
},
"WT05": {
"type": "keyword"
},
"WT06": {
"type": "keyword"
},
"WT07": {
"type": "keyword"
},
"WT08": {
"type": "keyword"
},
"WT09": {
"type": "keyword"
},
"WT10": {
"type": "keyword"
},
"WT11": {
"type": "keyword"
},
"WT17": {
"type": "keyword"
},
"WT18": {
"type": "keyword"
},
"date": {
"type": "date"
},
"station": {
"properties": {
"country": {
"type": "keyword"
},
"country_code": {
"type": "keyword"
},
"elevation": {
"type": "float"
},
"gsn_flag": {
"type": "keyword"
},
"hcn_crn_flag": {
"type": "keyword"
},
"id": {
"type": "keyword"
},
"location": {
"type": "geo_point"
},
"name": {
"type": "keyword"
},
"state": {
"type": "keyword"
},
"state_code": {
"type": "keyword"
},
"wmo_id": {
"type": "keyword"
}
}
}
}
}
}
6 changes: 6 additions & 0 deletions semanticsearch/operations/default.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,6 @@
{
"name": "index",
"operation-type": "bulk",
"bulk-size": {{bulk_size | default(5000)}},
"ingest-percentage": {{ingest_percentage | default(100)}}
}
Loading