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

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

Fixes #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 <dev.dev2049@gmail.com>

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 @@ class BigQueryLoader(BaseLoader):
         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 @@ class BigQueryLoader(BaseLoader):
                 "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

@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 1.4.1 and should not be changed by hand.
+# This file is automatically @generated by Poetry 1.4.2 and should not be changed by hand.
 
 [[package]]
 name = "absl-py"
@@ -6950,7 +6950,6 @@ files = [
     {file = "pylance-0.4.12-cp38-abi3-macosx_10_15_x86_64.whl", hash = "sha256:2b86fb8dccc03094c0db37bef0d91bda60e8eb0d1eddf245c6971450c8d8a53f"},
     {file = "pylance-0.4.12-cp38-abi3-macosx_11_0_arm64.whl", hash = "sha256:0bc82914b13204187d673b5f3d45f93219c38a0e9d0542ba251074f639669789"},
     {file = "pylance-0.4.12-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5a4bcce77f99ecd4cbebbadb01e58d5d8138d40eb56bdcdbc3b20b0475e7a472"},
-    {file = "pylance-0.4.12-cp38-abi3-win_amd64.whl", hash = "sha256:9616931c5300030adb9626d22515710a127d1e46a46737a7a0f980b52f13627c"},
 ]
 
 [package.dependencies]
@@ -10949,7 +10948,7 @@ cffi = {version = ">=1.11", markers = "platform_python_implementation == \"PyPy\
 cffi = ["cffi (>=1.11)"]
 
 [extras]
-all = ["O365", "aleph-alpha-client", "anthropic", "arxiv", "atlassian-python-api", "azure-ai-formrecognizer", "azure-ai-vision", "azure-cognitiveservices-speech", "azure-cosmos", "azure-identity", "beautifulsoup4", "clickhouse-connect", "cohere", "deeplake", "docarray", "duckduckgo-search", "elasticsearch", "faiss-cpu", "google-api-python-client", "google-search-results", "gptcache", "html2text", "huggingface_hub", "jina", "jinja2", "jq", "lancedb", "langkit", "lark", "lxml", "manifest-ml", "momento", "neo4j", "networkx", "nlpcloud", "nltk", "nomic", "openai", "openlm", "opensearch-py", "pdfminer-six", "pexpect", "pgvector", "pinecone-client", "pinecone-text", "psycopg2-binary", "pymongo", "pyowm", "pypdf", "pytesseract", "pyvespa", "qdrant-client", "redis", "requests-toolbelt", "sentence-transformers", "spacy", "steamship", "tensorflow-text", "tiktoken", "torch", "transformers", "weaviate-client", "wikipedia", "wolframalpha"]
+all = ["O365", "aleph-alpha-client", "anthropic", "arxiv", "atlassian-python-api", "azure-ai-formrecognizer", "azure-ai-vision", "azure-cognitiveservices-speech", "azure-cosmos", "azure-identity", "beautifulsoup4", "clickhouse-connect", "cohere", "deeplake", "docarray", "duckduckgo-search", "elasticsearch", "faiss-cpu", "google-api-python-client", "google-auth", "google-search-results", "gptcache", "html2text", "huggingface_hub", "jina", "jinja2", "jq", "lancedb", "langkit", "lark", "lxml", "manifest-ml", "momento", "neo4j", "networkx", "nlpcloud", "nltk", "nomic", "openai", "openlm", "opensearch-py", "pdfminer-six", "pexpect", "pgvector", "pinecone-client", "pinecone-text", "psycopg2-binary", "pymongo", "pyowm", "pypdf", "pytesseract", "pyvespa", "qdrant-client", "redis", "requests-toolbelt", "sentence-transformers", "spacy", "steamship", "tensorflow-text", "tiktoken", "torch", "transformers", "weaviate-client", "wikipedia", "wolframalpha"]
 azure = ["azure-ai-formrecognizer", "azure-ai-vision", "azure-cognitiveservices-speech", "azure-core", "azure-cosmos", "azure-identity", "openai"]
 cohere = ["cohere"]
 docarray = ["docarray"]
@@ -10963,4 +10962,4 @@ text-helpers = ["chardet"]
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.8.1,<4.0"
-content-hash = "6a28a31679ae3bdb156121ff7c09bfb1f691345f445196eb0384f08e031c84d3"
+content-hash = "379bfcf130acc24f2f8408e2bb7e3ae9d769070e6bf5f66868491bddb1b2fc53"

pyproject.toml

@@ -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",