{
"ab_internal": {
"isEnterprise": false,
"ql": 300,
"requireVersionIncrementsInPullRequests": true,
"sl": 200
},
"allowedHosts": {
"hosts": [
"www.googleapis.com"
]
},
"connectorBuildOptions": {
"baseImage": "docker.io/airbyte/python-connector-base:4.1.1@sha256:a268b44c733ae699a60f5fbc06a324945dba98945c6e2ab7f8609f2f895b0d28"
},
"connectorTestSuitesOptions": [
{
"suite": "acceptanceTests",
"testSecrets": [
{
"fileName": "config.json",
"name": "SECRET_SOURCE_GOOGLE_DRIVE_CREDS",
"secretStore": {
"alias": "airbyte-connector-testing-secret-store",
"type": "GSM"
}
},
{
"fileName": "oauth_config.json",
"name": "SECRET_SOURCE_GOOGLE_DRIVE_OAUTH_CREDS",
"secretStore": {
"alias": "airbyte-connector-testing-secret-store",
"type": "GSM"
}
}
]
}
],
"custom": false,
"dockerImageTag": "0.5.28-preview.766c445",
"dockerRepository": "airbyte/source-google-drive",
"documentationUrl": "https://docs.airbyte.com/integrations/sources/google-drive",
"externalDocumentationUrls": [
{
"title": "Google Drive API reference",
"type": "api_reference",
"url": "https://developers.google.com/drive/api/reference/rest/v3"
},
{
"title": "Google Drive authentication",
"type": "authentication_guide",
"url": "https://developers.google.com/drive/api/guides/about-auth"
},
{
"title": "Google Drive quotas",
"type": "rate_limits",
"url": "https://developers.google.com/drive/api/guides/limits"
},
{
"title": "Google Workspace Status",
"type": "status_page",
"url": "https://www.google.com/appsstatus/"
}
],
"generated": {
"git": {
"commit_author": "Devin AI",
"commit_author_email": "158243242+devin-ai-integration[bot]@users.noreply.github.com",
"commit_sha": "766c445d406018610b25479a2c83892ce50845b5",
"commit_timestamp": "2026-08-04T11:35:15+00:00"
},
"sbomUrl": "https://connectors.airbyte.com/files/sbom/airbyte/source-google-drive/0.5.28-preview.766c445.spdx.json",
"source_file_info": {
"metadata_bucket_name": "prod-airbyte-cloud-connector-metadata-service",
"metadata_file_path": "metadata/airbyte/source-google-drive/0.5.28-preview.766c445/metadata.yaml",
"metadata_last_modified": "2026-08-04T18:15:55.613071+00:00",
"registry_entry_generated_at": "2026-08-04T18:15:55.613071+00:00"
}
},
"githubIssueLabel": "source-google-drive",
"icon": "google-drive.svg",
"iconUrl": "https://connectors.airbyte.com/files/metadata/airbyte/source-google-drive/latest/icon.svg",
"language": "python",
"license": "ELv2",
"maxSecondsBetweenMessages": 3600,
"name": "Google Drive",
"packageInfo": {
"cdk_version": "python:7.23.8"
},
"public": true,
"releaseStage": "alpha",
"releases": {
"rolloutConfiguration": {
"advanceDelayMinutes": 10,
"enableProgressiveRollout": false,
"initialPercentage": 0,
"maxPercentage": 50
}
},
"remoteRegistries": {
"pypi": {
"enabled": true,
"packageName": "airbyte-source-google-drive"
}
},
"sourceDefinitionId": "9f8dda77-1048-4368-815b-269bf54ee9b8",
"sourceType": "file",
"spec": {
"advanced_auth": {
"auth_flow_type": "oauth2.0",
"oauth_config_specification": {
"complete_oauth_output_specification": {
"additionalProperties": false,
"properties": {
"refresh_token": {
"path_in_connector_config": [
"credentials",
"refresh_token"
],
"path_in_oauth_response": [
"refresh_token"
],
"type": "string"
}
},
"type": "object"
},
"complete_oauth_server_input_specification": {
"additionalProperties": false,
"properties": {
"client_id": {
"type": "string"
},
"client_secret": {
"type": "string"
}
},
"type": "object"
},
"complete_oauth_server_output_specification": {
"additionalProperties": false,
"properties": {
"client_id": {
"path_in_connector_config": [
"credentials",
"client_id"
],
"type": "string"
},
"client_secret": {
"path_in_connector_config": [
"credentials",
"client_secret"
],
"type": "string"
}
},
"type": "object"
},
"oauth_connector_input_specification": {
"access_token_url": "https://oauth2.googleapis.com/token?{{client_id_param}}&{{client_secret_param}}&{{auth_code_param}}&{{redirect_uri_param}}&grant_type=authorization_code",
"consent_url": "https://accounts.google.com/o/oauth2/v2/auth?{{client_id_param}}&{{redirect_uri_param}}&response_type=code&{{scopes_param}}&access_type=offline&{{state_param}}&include_granted_scopes=true&prompt=consent",
"scopes": [
{
"scope": "https://www.googleapis.com/auth/drive.readonly"
},
{
"scope": "https://www.googleapis.com/auth/admin.directory.group.readonly"
},
{
"scope": "https://www.googleapis.com/auth/admin.directory.group.member.readonly"
},
{
"scope": "https://www.googleapis.com/auth/admin.directory.user.readonly"
}
]
}
},
"predicate_key": [
"credentials",
"auth_type"
],
"predicate_value": "Client"
},
"connectionSpecification": {
"description": "Used during spec; allows the developer to configure the cloud provider specific options\nthat are needed when users configure a file-based source.",
"properties": {
"credentials": {
"description": "Credentials for connecting to the Google Drive API",
"oneOf": [
{
"properties": {
"auth_type": {
"const": "Client",
"default": "Client",
"enum": [
"Client"
],
"title": "Auth Type",
"type": "string"
},
"client_id": {
"airbyte_secret": true,
"description": "Client ID for the Google Drive API",
"title": "Client ID",
"type": "string"
},
"client_secret": {
"airbyte_secret": true,
"description": "Client Secret for the Google Drive API",
"title": "Client Secret",
"type": "string"
},
"refresh_token": {
"airbyte_secret": true,
"description": "Refresh Token for the Google Drive API",
"title": "Refresh Token",
"type": "string"
}
},
"required": [
"client_id",
"client_secret",
"refresh_token",
"auth_type"
],
"title": "Authenticate via Google (OAuth)",
"type": "object"
},
{
"properties": {
"auth_type": {
"const": "Service",
"default": "Service",
"enum": [
"Service"
],
"title": "Auth Type",
"type": "string"
},
"service_account_info": {
"airbyte_secret": true,
"description": "The JSON key of the service account to use for authorization. Read more here.",
"title": "Service Account Information",
"type": "string"
}
},
"required": [
"service_account_info",
"auth_type"
],
"title": "Service Account Key Authentication",
"type": "object"
}
],
"title": "Authentication",
"type": "object"
},
"delivery_method": {
"default": "use_records_transfer",
"display_type": "radio",
"group": "advanced",
"oneOf": [
{
"description": "Recommended - Extract and load structured records into your destination of choice. This is the classic method of moving data in Airbyte. It allows for blocking and hashing individual fields or files from a structured schema. Data can be flattened, typed and deduped depending on the destination.",
"properties": {
"delivery_type": {
"const": "use_records_transfer",
"default": "use_records_transfer",
"enum": [
"use_records_transfer"
],
"title": "Delivery Type",
"type": "string"
}
},
"required": [
"delivery_type"
],
"title": "Replicate Records",
"type": "object"
},
{
"description": "Copy raw files without parsing their contents. Bits are copied into the destination exactly as they appeared in the source. Recommended for use with unstructured text data, non-text and compressed files.",
"properties": {
"delivery_type": {
"const": "use_file_transfer",
"default": "use_file_transfer",
"enum": [
"use_file_transfer"
],
"title": "Delivery Type",
"type": "string"
},
"preserve_directory_structure": {
"default": true,
"description": "If enabled, sends subdirectory folder structure along with source file names to the destination. Otherwise, files will be synced by their names only. This option is ignored when file-based replication is not enabled.",
"title": "Preserve Sub-Directories in File Paths",
"type": "boolean"
}
},
"required": [
"delivery_type"
],
"title": "Copy Raw Files",
"type": "object"
},
{
"description": "Sends one identity stream and one for more permissions (ACL) streams to the destination. This data can be used in downstream systems to recreate permission restrictions mirroring the original source.",
"properties": {
"delivery_type": {
"const": "use_permissions_transfer",
"default": "use_permissions_transfer",
"enum": [
"use_permissions_transfer"
],
"title": "Delivery Type",
"type": "string"
},
"domain": {
"airbyte_hidden": false,
"description": "The Google domain of the identities.",
"order": 1,
"title": "Domain",
"type": "string"
},
"include_identities_stream": {
"default": true,
"description": "This data can be used in downstream systems to recreate permission restrictions mirroring the original source",
"title": "Include Identity Stream",
"type": "boolean"
}
},
"required": [
"delivery_type"
],
"title": "Replicate Permissions ACL",
"type": "object"
}
],
"order": 1,
"title": "Delivery Method",
"type": "object"
},
"folder_url": {
"description": "URL for the folder you want to sync. Using individual streams and glob patterns, it's possible to only sync a subset of all files located in the folder.",
"examples": [
"https://drive.google.com/drive/folders/1Xaz0vXXXX2enKnNYU5qSt9NS70gvMyYn"
],
"order": 0,
"pattern": "^https://drive.google.com/.+",
"pattern_descriptor": "https://drive.google.com/drive/folders/MY-FOLDER-ID",
"title": "Folder Url",
"type": "string"
},
"start_date": {
"description": "UTC date and time in the format 2017-01-25T00:00:00.000000Z. Any file modified before this date will not be replicated.",
"examples": [
"2021-01-01",
"2021-01-01T00:00:00Z",
"2021-01-01T00:00:00.000Z",
"2021-01-01T00:00:00.000000Z"
],
"format": "date-time",
"order": 1,
"pattern": "^[0-9]{4}-[0-9]{2}-[0-9]{2}(T[0-9]{2}:[0-9]{2}:[0-9]{2}(\\.[0-9]+)?(Z|[+-][0-9]{2}:[0-9]{2})?)?$",
"pattern_descriptor": "YYYY-MM-DD, YYYY-MM-DDTHH:mm:ssZ, or YYYY-MM-DDTHH:mm:ss.SSSSSSZ",
"title": "Start Date",
"type": "string"
},
"streams": {
"description": "Each instance of this configuration defines a stream. Use this to define which files belong in the stream, their format, and how they should be parsed and validated. When sending data to warehouse destination such as Snowflake or BigQuery, each stream is a separate table.",
"items": {
"properties": {
"days_to_sync_if_history_is_full": {
"default": 3,
"description": "When the state history of the file store is full, syncs will only read files that were last modified in the provided day range.",
"title": "Days To Sync If History Is Full",
"type": "integer"
},
"format": {
"description": "The configuration options that are used to alter how to read incoming files that deviate from the standard formatting.",
"oneOf": [
{
"properties": {
"double_as_string": {
"default": false,
"description": "Whether to convert double fields to strings. This is recommended if you have decimal numbers with a high degree of precision because there can be a loss precision when handling floating point numbers.",
"title": "Convert Double Fields to Strings",
"type": "boolean"
},
"filetype": {
"const": "avro",
"default": "avro",
"title": "Filetype",
"type": "string"
}
},
"required": [
"filetype"
],
"title": "Avro Format",
"type": "object"
},
{
"properties": {
"delimiter": {
"default": ",",
"description": "The character delimiting individual cells in the CSV data. This may only be a 1-character string. For tab-delimited data enter '\\t'.",
"title": "Delimiter",
"type": "string"
},
"double_quote": {
"default": true,
"description": "Whether two quotes in a quoted CSV value denote a single quote in the data.",
"title": "Double Quote",
"type": "boolean"
},
"encoding": {
"default": "utf8",
"description": "The character encoding of the CSV data. Leave blank to default to UTF8. See list of python encodings for allowable options.",
"title": "Encoding",
"type": "string"
},
"escape_char": {
"description": "The character used for escaping special characters. To disallow escaping, leave this field blank.",
"title": "Escape Character",
"type": "string"
},
"false_values": {
"default": [
"n",
"no",
"f",
"false",
"off",
"0"
],
"description": "A set of case-sensitive strings that should be interpreted as false values.",
"items": {
"type": "string"
},
"title": "False Values",
"type": "array",
"uniqueItems": true
},
"filetype": {
"const": "csv",
"default": "csv",
"title": "Filetype",
"type": "string"
},
"header_definition": {
"default": {
"header_definition_type": "From CSV"
},
"description": "How headers will be defined. `User Provided` assumes the CSV does not have a header row and uses the headers provided and `Autogenerated` assumes the CSV does not have a header row and the CDK will generate headers using for `f{i}` where `i` is the index starting from 0. Else, the default behavior is to use the header from the CSV file. If a user wants to autogenerate or provide column names for a CSV having headers, they can skip rows.",
"oneOf": [
{
"properties": {
"header_definition_type": {
"const": "From CSV",
"default": "From CSV",
"title": "Header Definition Type",
"type": "string"
}
},
"required": [
"header_definition_type"
],
"title": "From CSV",
"type": "object"
},
{
"properties": {
"header_definition_type": {
"const": "Autogenerated",
"default": "Autogenerated",
"title": "Header Definition Type",
"type": "string"
}
},
"required": [
"header_definition_type"
],
"title": "Autogenerated",
"type": "object"
},
{
"properties": {
"column_names": {
"description": "The column names that will be used while emitting the CSV records",
"items": {
"type": "string"
},
"title": "Column Names",
"type": "array"
},
"header_definition_type": {
"const": "User Provided",
"default": "User Provided",
"title": "Header Definition Type",
"type": "string"
}
},
"required": [
"column_names",
"header_definition_type"
],
"title": "User Provided",
"type": "object"
}
],
"title": "CSV Header Definition",
"type": "object"
},
"ignore_errors_on_fields_mismatch": {
"default": false,
"description": "Whether to ignore errors that occur when the number of fields in the CSV does not match the number of columns in the schema.",
"title": "Ignore errors on field mismatch",
"type": "boolean"
},
"null_values": {
"default": [],
"description": "A set of case-sensitive strings that should be interpreted as null values. For example, if the value 'NA' should be interpreted as null, enter 'NA' in this field.",
"items": {
"type": "string"
},
"title": "Null Values",
"type": "array",
"uniqueItems": true
},
"quote_char": {
"default": "\"",
"description": "The character used for quoting CSV values. To disallow quoting, make this field blank.",
"title": "Quote Character",
"type": "string"
},
"skip_rows_after_header": {
"default": 0,
"description": "The number of rows to skip after the header row.",
"title": "Skip Rows After Header",
"type": "integer"
},
"skip_rows_before_header": {
"default": 0,
"description": "The number of rows to skip before the header row. For example, if the header row is on the 3rd row, enter 2 in this field.",
"title": "Skip Rows Before Header",
"type": "integer"
},
"strings_can_be_null": {
"default": true,
"description": "Whether strings can be interpreted as null values. If true, strings that match the null_values set will be interpreted as null. If false, strings that match the null_values set will be interpreted as the string itself.",
"title": "Strings Can Be Null",
"type": "boolean"
},
"true_values": {
"default": [
"y",
"yes",
"t",
"true",
"on",
"1"
],
"description": "A set of case-sensitive strings that should be interpreted as true values.",
"items": {
"type": "string"
},
"title": "True Values",
"type": "array",
"uniqueItems": true
}
},
"required": [
"filetype"
],
"title": "CSV Format",
"type": "object"
},
{
"properties": {
"filetype": {
"const": "jsonl",
"default": "jsonl",
"title": "Filetype",
"type": "string"
}
},
"required": [
"filetype"
],
"title": "Jsonl Format",
"type": "object"
},
{
"properties": {
"decimal_as_float": {
"default": false,
"description": "Whether to convert decimal fields to floats. There is a loss of precision when converting decimals to floats, so this is not recommended.",
"title": "Convert Decimal Fields to Floats",
"type": "boolean"
},
"filetype": {
"const": "parquet",
"default": "parquet",
"title": "Filetype",
"type": "string"
}
},
"required": [
"filetype"
],
"title": "Parquet Format",
"type": "object"
},
{
"description": "Extract text from document formats (.pdf, .docx, .md, .pptx) and emit as one record per file.",
"properties": {
"filetype": {
"const": "unstructured",
"default": "unstructured",
"title": "Filetype",
"type": "string"
},
"processing": {
"default": {
"mode": "local"
},
"description": "Processing configuration",
"oneOf": [
{
"description": "Process files locally, supporting `fast` and `ocr` modes. This is the default option.",
"properties": {
"mode": {
"const": "local",
"default": "local",
"enum": [
"local"
],
"title": "Mode",
"type": "string"
}
},
"required": [
"mode"
],
"title": "Local",
"type": "object"
}
],
"title": "Processing",
"type": "object"
},
"skip_unprocessable_files": {
"always_show": true,
"default": true,
"description": "If true, skip files that cannot be parsed and pass the error message along as the _ab_source_file_parse_error field. If false, fail the sync.",
"title": "Skip Unprocessable Files",
"type": "boolean"
},
"strategy": {
"always_show": true,
"default": "auto",
"description": "The strategy used to parse documents. `fast` extracts text directly from the document which doesn't work for all files. `ocr_only` is more reliable, but slower. `hi_res` is the most reliable, but requires an API key and a hosted instance of unstructured and can't be used with local mode. See the unstructured.io documentation for more details: https://unstructured-io.github.io/unstructured/core/partition.html#partition-pdf",
"enum": [
"auto",
"fast",
"ocr_only",
"hi_res"
],
"order": 0,
"title": "Parsing Strategy",
"type": "string"
}
},
"required": [
"filetype"
],
"title": "Unstructured Document Format",
"type": "object"
},
{
"properties": {
"filetype": {
"const": "excel",
"default": "excel",
"title": "Filetype",
"type": "string"
}
},
"required": [
"filetype"
],
"title": "Excel Format",
"type": "object"
}
],
"title": "Format",
"type": "object"
},
"globs": {
"default": [
"**"
],
"description": "The pattern used to specify which files should be selected from the file system. For more information on glob pattern matching look here.",
"items": {
"type": "string"
},
"order": 1,
"title": "Globs",
"type": "array"
},
"input_schema": {
"description": "The schema that will be used to validate records extracted from the file. This will override the stream schema that is auto-detected from incoming files.",
"title": "Input Schema",
"type": "string"
},
"name": {
"description": "The name of the stream.",
"title": "Name",
"type": "string"
},
"primary_key": {
"airbyte_hidden": true,
"description": "The column or columns (for a composite key) that serves as the unique identifier of a record. If empty, the primary key will default to the parser's default primary key.",
"title": "Primary Key",
"type": "string"
},
"recent_n_files_to_read_for_schema_discovery": {
"description": "The number of resent files which will be used to discover the schema for this stream.",
"exclusiveMinimum": 0,
"title": "Files To Read For Schema Discover",
"type": "integer"
},
"schemaless": {
"default": false,
"description": "When enabled, syncs will not validate or structure records against the stream's schema.",
"title": "Schemaless",
"type": "boolean"
},
"use_first_found_file_for_schema_discovery": {
"default": false,
"description": "When enabled, the source will use the first found file for schema discovery. Helps to avoid long discovery step.",
"title": "Use First Found File For Schema Discover",
"type": "boolean"
},
"validation_policy": {
"default": "Emit Record",
"description": "The name of the validation policy that dictates sync behavior when a record does not adhere to the stream schema.",
"enum": [
"Emit Record",
"Skip Record",
"Wait for Discover"
],
"title": "Validation Policy"
}
},
"required": [
"name",
"format"
],
"title": "FileBasedStreamConfig",
"type": "object"
},
"order": 10,
"title": "The list of streams to sync",
"type": "array"
}
},
"required": [
"streams",
"folder_url",
"credentials"
],
"title": "Google Drive Source Spec",
"type": "object"
},
"documentationUrl": "https://docs.airbyte.com/integrations/sources/google-drive",
"supportsDBT": false,
"supportsNormalization": false
},
"supportLevel": "certified",
"supportsDataActivation": false,
"supportsFileTransfer": true,
"tags": [
"language:python",
"cdk:python-file-based"
],
"tombstone": false
}