Add vertex feature store integration #250
Conversation
...ertexai/tests/integration_tests/vectorstores/feature_store/test_feature_store_bf_executor.py
Outdated
Show resolved
Hide resolved
libs/vertexai/langchain_google_vertexai/vectorstores/feature_store/executors.py
Outdated
Show resolved
Hide resolved
|
/gcbrun |
1 similar comment
|
/gcbrun |
eliasecchig
force-pushed
the
add-fs
branch
3 times, most recently
from
127d024
to
b96cecf
Compare
|
/gcbrun |
|
/gcbrun |
1 similar comment
|
/gcbrun |
|
In integration tests could you please add a check for already created datasets in BQ. |
|
@gmogr Added teardown for feature view. |
|
/gcbrun |
|
/gcbrun |
| gca_resource = self._online_store.gca_resource | ||
| endpoint = gca_resource.dedicated_serving_endpoint.public_endpoint_domain_name | ||
| return FeatureOnlineStoreServiceClient( | ||
| client_options={"api_endpoint": endpoint} |
There was a problem hiding this comment.
it looks like telemetry is missing here too
| self._bq_client = bigquery.Client( | ||
| project=self.project_id, | ||
| location=self.location, | ||
| credentials=self.credentials, |
There was a problem hiding this comment.
same here, client_info is not set
| authentication. | ||
|
|
||
| To use, you need the following packages installed: | ||
| google-cloud-bigquery |
There was a problem hiding this comment.
can we hint a specific langchain-google-vertexai dep group instead, please?
|
|
||
| def sync(self): | ||
| """Sync the data from the Big Query source into the Executor source""" | ||
| self._df = self._query_table_to_df() |
There was a problem hiding this comment.
can we at least add a warning if the amount of records it too large for an in-memory bfs, please?
| self._env_config = env_config | ||
|
|
||
|
|
||
| class BruteForceExecutor(BaseExecutor): |
There was a problem hiding this comment.
why do we need our own in-memory implementation if LC already has a few? can we just write an adapter that will load data into it?
| The FeatureStore aims to facilitate similarity search using different | ||
| methodologies on Google Cloud including Big Query, Feature Store and a | ||
| local bruteforce search engine. | ||
| Big Query is the data source of truth and also the default search |
There was a problem hiding this comment.
nit: BigQuery one word instead of Big Query
Authors: @lspataroG @eliasecchig
Add VertexAI Langchain integration
Example usage