Skip to content

Updated the SparseVectorStrategy class to use sparse_vector query #2657

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

Merged
merged 1 commit into from
Jan 27, 2025
Merged

Updated the SparseVectorStrategy class to use sparse_vector query #2657

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
24 changes: 12 additions & 12 deletions elasticsearch/helpers/vectorstore/_async/strategies.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -96,7 +96,7 @@ def needs_inference(self) -> bool:


class AsyncSparseVectorStrategy(AsyncRetrievalStrategy):
"""Sparse retrieval strategy using the `text_expansion` processor."""
"""Sparse retrieval strategy using the `sparse_vector` processor."""

def __init__(self, model_id: str = ".elser_model_2"):
self.model_id = model_id
Expand Down Expand Up @@ -127,11 +127,10 @@ def es_query(
"bool": {
"must": [
{
"text_expansion": {
f"{vector_field}.{self._tokens_field}": {
"model_id": self.model_id,
"model_text": query,
}
"sparse_vector": {
"field": f"{vector_field}.{self._tokens_field}",
"inference_id": self.model_id,
"query": query,
}
}
],
Expand All @@ -150,7 +149,7 @@ def es_mappings_settings(
mappings: Dict[str, Any] = {
"properties": {
vector_field: {
"properties": {self._tokens_field: {"type": "rank_features"}}
"properties": {self._tokens_field: {"type": "sparse_vector"}}
}
}
}
Expand All @@ -172,11 +171,12 @@ async def before_index_creation(
{
"inference": {
"model_id": self.model_id,
"target_field": vector_field,
"field_map": {text_field: "text_field"},
"inference_config": {
"text_expansion": {"results_field": self._tokens_field}
},
"input_output": [
{
"input_field": text_field,
"output_field": f"{vector_field}.{self._tokens_field}",
},
],
}
}
],
Expand Down
24 changes: 12 additions & 12 deletions elasticsearch/helpers/vectorstore/_sync/strategies.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -96,7 +96,7 @@ def needs_inference(self) -> bool:


class SparseVectorStrategy(RetrievalStrategy):
"""Sparse retrieval strategy using the `text_expansion` processor."""
"""Sparse retrieval strategy using the `sparse_vector` processor."""

def __init__(self, model_id: str = ".elser_model_2"):
self.model_id = model_id
Expand Down Expand Up @@ -127,11 +127,10 @@ def es_query(
"bool": {
"must": [
{
"text_expansion": {
f"{vector_field}.{self._tokens_field}": {
"model_id": self.model_id,
"model_text": query,
}
"sparse_vector": {
"field": f"{vector_field}.{self._tokens_field}",
"inference_id": self.model_id,
"query": query,
}
}
],
Expand All @@ -150,7 +149,7 @@ def es_mappings_settings(
mappings: Dict[str, Any] = {
"properties": {
vector_field: {
"properties": {self._tokens_field: {"type": "rank_features"}}
"properties": {self._tokens_field: {"type": "sparse_vector"}}
}
}
}
Expand All @@ -172,11 +171,12 @@ def before_index_creation(
{
"inference": {
"model_id": self.model_id,
"target_field": vector_field,
"field_map": {text_field: "text_field"},
"inference_config": {
"text_expansion": {"results_field": self._tokens_field}
},
"input_output": [
{
"input_field": text_field,
"output_field": f"{vector_field}.{self._tokens_field}",
},
],
}
}
],
Expand Down
Loading