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

Serialize query strings to avoid Ray Dataset column imputation #1171

Merged
merged 2 commits into from
Feb 11, 2025
Merged

Serialize query strings to avoid Ray Dataset column imputation #1171

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f9be43f
Serialize query strings to avoid Ray Dataset column imputation
austintlee Feb 11, 2025
c4372fd
Fix non reconstruct case, ensure all integ tests pass
austintlee Feb 11, 2025
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
9 changes: 6 additions & 3 deletions lib/sycamore/sycamore/connectors/opensearch/opensearch_reader.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
import json
import logging
from copy import deepcopy

Expand Down Expand Up @@ -288,7 +289,7 @@ def __init__(
logger.info(f"OpenSearchReader using PIT: {self.use_pit}")

@timetrace("OpenSearchReader")
def _to_parent_doc(self, slice_query: dict[str, Any]) -> List[dict[str, Any]]:
def _to_parent_doc(self, doc: dict[str, Any]) -> List[dict[str, Any]]:
"""
Get all parent documents from a given slice.
"""
Expand All @@ -304,6 +305,7 @@ def _to_parent_doc(self, slice_query: dict[str, Any]) -> List[dict[str, Any]]:
raise ValueError("Target is not present\n" f"Parameters: {self._query_params}\n")

os_client = client._client
slice_query = json.loads(doc["doc"])

assert (
get_doc_count_for_slice(os_client, slice_query) < 10000
Expand Down Expand Up @@ -341,7 +343,7 @@ def _to_parent_doc(self, slice_query: dict[str, Any]) -> List[dict[str, Any]]:
logger.info(f"Read {len(results)} documents from {self._query_params.index_name}")

except Exception as e:
raise ValueError(f"Error reading from target: {e}")
raise ValueError(f"Error reading from target: {e}, query: {slice_query}")
finally:
if client is not None:
client.close()
Expand Down Expand Up @@ -547,7 +549,8 @@ def _execute_pit(self, **kwargs) -> "Dataset":
}
if "query" in query:
_query["query"] = query["query"]
docs.append(_query)

docs.append({"doc": json.dumps(_query)})
logger.debug(f"Added slice {i} to the query {_query}")
except Exception as e:
raise ValueError(f"Error reading from target: {e}")
Expand Down
Loading