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

Add optional id_field to VertexRank #217

Merged
merged 7 commits into from
May 15, 2024
Merged

Add optional id_field to VertexRank #217

Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
488dad2
Add optional id_field to VertexRank
shenghann May 12, 2024
5e64709
Add missing comma
shenghann May 12, 2024
5116f5b
Add check for `id_field` in metadata and raise error if not
shenghann May 13, 2024
d3d2963
catch KeyError and raise warning
shenghann May 14, 2024
1ba8cc3
Merge branch 'main' into patch-1
shenghann May 14, 2024
36337b1
reorg imports for linting
shenghann May 15, 2024
5aae863
formatted
May 15, 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
35 changes: 21 additions & 14 deletions libs/community/langchain_google_community/vertex_rank.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
import warnings
from typing import TYPE_CHECKING, Any, Optional, Sequence

from google.api_core import exceptions as core_exceptions # type: ignore
Expand Down Expand Up @@ -42,6 +43,8 @@ class VertexAIRank(BaseDocumentCompressor):
If true, the response will contain only
record ID and score. By default, it is false,
the response will contain record details.
id_field (Optional[str]): Specifies a unique document metadata field
to use as an id.
title_field (Optional[str]): Specifies the document metadata field
to use as title.
credentials (Optional[Credentials]): Google Cloud credentials object.
Expand All @@ -55,6 +58,7 @@ class VertexAIRank(BaseDocumentCompressor):
model: str = Field(default="semantic-ranker-512@latest")
top_n: int = Field(default=10)
ignore_record_details_in_response: bool = Field(default=False)
id_field: Optional[str] = Field(default=None)
title_field: Optional[str] = Field(default=None)
credentials: Optional[Credentials] = Field(default=None)
credentials_path: Optional[str] = Field(default=None)
Expand Down Expand Up @@ -112,20 +116,23 @@ def _rerank_documents(
"""
from google.cloud import discoveryengine_v1alpha # type: ignore

records = [
discoveryengine_v1alpha.RankingRecord(
id=str(idx),
content=doc.page_content,
**(
{"title": doc.metadata.get(self.title_field)}
if self.title_field
else {}
),
)
for idx, doc in enumerate(documents)
if doc.page_content
or (self.title_field and doc.metadata.get(self.title_field))
]
try:
records = [
discoveryengine_v1alpha.RankingRecord(
id=(doc.metadata.get(self.id_field) if self.id_field else str(idx)),
content=doc.page_content,
**(
{"title": doc.metadata.get(self.title_field)}
if self.title_field
else {}
),
)
for idx, doc in enumerate(documents)
if doc.page_content
or (self.title_field and doc.metadata.get(self.title_field))
]
except KeyError:
warnings.warn(f"id_field '{self.id_field}' not found in document metadata.")

ranking_config_path = (
f"projects/{self.project_id}/locations/{self.location_id}"
Expand Down
Loading