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

Jump to bottom

Support hdf5 files in bulk operation #620

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Support hdf5 files in bulk operation #620

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
15 changes: 14 additions & 1 deletion osbenchmark/utils/dataset.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,6 @@
from abc import ABC, ABCMeta, abstractmethod
from enum import Enum
from typing import cast

import h5py
import numpy as np

Expand Down Expand Up @@ -159,6 +158,20 @@ def parse_context(context: Context) -> str:

raise Exception("Unsupported context")

def context_string_to_context(context_string: str) -> Context:
if context_string == "neighbors":
return Context.NEIGHBORS
elif context_string == "train":
return Context.INDEX
elif context_string == "test":
return Context.QUERY
elif context_string == "max_distance_neighbors":
return Context.MAX_DISTANCE_NEIGHBORS
elif context_string == "min_score_neighbors":
return Context.MIN_SCORE_NEIGHBORS
else:
raise ValueError(f"Invalid context string: {context_string}")


class BigANNDataSet(DataSet):

Expand Down
1 change: 0 additions & 1 deletion osbenchmark/worker_coordinator/runner.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -515,7 +515,6 @@ async def __call__(self, opensearch, params):
if not detailed_results:
opensearch.return_raw_response()
request_context_holder.on_client_request_start()

if with_action_metadata:
api_kwargs.pop("index", None)
# only half of the lines are documents
Expand Down
15 changes: 15 additions & 0 deletions osbenchmark/workload/loader.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1477,6 +1477,12 @@ def _create_corpora(self, corpora_specs, indices, data_streams):
default_value=workload.Documents.SOURCE_FORMAT_BULK)
default_action_and_meta_data = self._r(corpus_spec, "includes-action-and-meta-data", mandatory=False,
default_value=False)
default_generate_increasing_vector_ids = self._r(corpus_spec, "generate-increasing-vector-ids", mandatory=False,
default_value=False)
default_id_field_name = self._r(corpus_spec, "id-field-name", mandatory=False,
default_value=None)
default_vector_field_name = self._r(corpus_spec, "vector-field-name", mandatory=False,
default_value=None)
corpus_target_idx = None
corpus_target_ds = None
corpus_target_type = None
Expand Down Expand Up @@ -1518,6 +1524,12 @@ def _create_corpora(self, corpora_specs, indices, data_streams):

includes_action_and_meta_data = self._r(doc_spec, "includes-action-and-meta-data", mandatory=False,
default_value=default_action_and_meta_data)
generate_increasing_vector_ids = self._r(doc_spec, "generate-increasing-vector-ids", mandatory=False,
default_value=default_generate_increasing_vector_ids)
id_field_name = self._r(doc_spec, "id-field-name", mandatory=False,
default_value=default_id_field_name)
vector_field_name = self._r(doc_spec, "vector-field-name", mandatory=False,
default_value=default_vector_field_name)
if includes_action_and_meta_data:
target_idx = None
target_type = None
Expand Down Expand Up @@ -1558,6 +1570,9 @@ def _create_corpora(self, corpora_specs, indices, data_streams):
base_url=base_url,
source_url=source_url,
includes_action_and_meta_data=includes_action_and_meta_data,
generate_increasing_vector_ids=generate_increasing_vector_ids,
id_field_name = id_field_name,
vector_field_name = vector_field_name,
number_of_documents=num_docs,
compressed_size_in_bytes=compressed_bytes,
uncompressed_size_in_bytes=uncompressed_bytes,
Expand Down
Loading
Loading