Ability to specify credentials wihen using Google BigQuery as a data loader (langchain-ai#5466)

# Adds ability to specify credentials when using Google BigQuery as a
data loader

Fixes langchain-ai#5465 . Adds ability to set credentials which must be of the
`google.auth.credentials.Credentials` type. This argument is optional
and will default to `None.

Co-authored-by: Dev 2049 <[email protected]>

Author: nsheils

langchain/document_loaders/bigquery.py

@@ -1,8 +1,13 @@
-from typing import List, Optional
+from __future__ import annotations
+
+from typing import TYPE_CHECKING, List, Optional
 
 from langchain.docstore.document import Document
 from langchain.document_loaders.base import BaseLoader
 
+if TYPE_CHECKING:
+    from google.auth.credentials import Credentials
+
 
 class BigQueryLoader(BaseLoader):
     """Loads a query result from BigQuery into a list of documents.
@@ -11,6 +16,7 @@ class BigQueryLoader(BaseLoader):
     are written into the `page_content` of the document. The `metadata_columns`
     are written into the `metadata` of the document. By default, all columns
     are written into the `page_content` and none into the `metadata`.
+
     """
 
     def __init__(
@@ -19,11 +25,28 @@ def __init__(
         project: Optional[str] = None,
         page_content_columns: Optional[List[str]] = None,
         metadata_columns: Optional[List[str]] = None,
+        credentials: Optional[Credentials] = None,
     ):
+        """Initialize BigQuery document loader.
+
+        Args:
+            query: The query to run in BigQuery.
+            project: Optional. The project to run the query in.
+            page_content_columns: Optional. The columns to write into the `page_content`
+                of the document.
+            metadata_columns: Optional. The columns to write into the `metadata` of the
+                document.
+            credentials : google.auth.credentials.Credentials, optional
+            Credentials for accessing Google APIs. Use this parameter to override
+                default credentials, such as to use Compute Engine
+                (`google.auth.compute_engine.Credentials`) or Service Account
+                (`google.oauth2.service_account.Credentials`) credentials directly.
+        """
         self.query = query
         self.project = project
         self.page_content_columns = page_content_columns
         self.metadata_columns = metadata_columns
+        self.credentials = credentials
 
     def load(self) -> List[Document]:
         try:
@@ -34,7 +57,7 @@ def load(self) -> List[Document]:
                 "Please install it with `pip install google-cloud-bigquery`."
             ) from ex
 
-        bq_client = bigquery.Client(self.project)
+        bq_client = bigquery.Client(credentials=self.credentials, project=self.project)
         query_result = bq_client.query(self.query).result()
         docs: List[Document] = []
 

poetry.lock

@@ -40,6 +40,7 @@ pymongo = {version = "^4.3.3", optional = true}
 clickhouse-connect = {version="^0.5.14", optional=true}
 weaviate-client = {version = "^3", optional = true}
 google-api-python-client = {version = "2.70.0", optional = true}
+google-auth = {version = "^2.18.1", optional = true}
 wolframalpha = {version = "5.0.0", optional = true}
 anthropic = {version = "^0.2.6", optional = true}
 qdrant-client = {version = "^1.1.2", optional = true, python = ">=3.8.1,<3.12"}
@@ -239,6 +240,7 @@ all = [
     "weaviate-client",
     "redis",
     "google-api-python-client",
+    "google-auth",
     "wolframalpha",
     "qdrant-client",
     "tensorflow-text",