|
12 | 12 | "additionalProperties": true, |
13 | 13 | "properties": { |
14 | 14 | "big_query_client_buffer_size_mb": { |
15 | | - "title": "Google BigQuery client chunk size", |
16 | | - "description": "Google BigQuery client's chunk (buffer) size (MIN = 1, MAX = 15) for each table. The size that will be written by a single RPC. Written data will be buffered and only flushed upon reaching this size or closing the channel. It defaults to 15MiB. Smaller chunk size means less memory consumption, and is recommended for big data sets. For more details refer to the documentation <a href=\"https://googleapis.dev/python/bigquery/latest/generated/google.cloud.bigquery.client.Client.html\">here</a>", |
| 15 | + "title": "Google BigQuery Client Chunk Size (Optional)", |
| 16 | + "description": "Google BigQuery client's chunk (buffer) size (MIN=1, MAX = 15) for each table. The size that will be written by a single RPC. Written data will be buffered and only flushed upon reaching this size or closing the channel. The default 15MB value is used if not set explicitly. Read more <a href=\"https://googleapis.dev/python/bigquery/latest/generated/google.cloud.bigquery.client.Client.html\">here</a>.", |
17 | 17 | "type": "integer", |
18 | 18 | "minimum": 1, |
19 | 19 | "maximum": 15, |
|
22 | 22 | }, |
23 | 23 | "project_id": { |
24 | 24 | "type": "string", |
25 | | - "description": "The GCP project ID for the project containing the target BigQuery dataset.", |
| 25 | + "description": "The GCP project ID for the project containing the target BigQuery dataset. Read more <a href=\"https://cloud.google.com/resource-manager/docs/creating-managing-projects#identifying_projects\">here</a>.", |
26 | 26 | "title": "Project ID" |
27 | 27 | }, |
28 | 28 | "dataset_id": { |
29 | 29 | "type": "string", |
30 | | - "description": "Default BigQuery Dataset ID tables are replicated to if the source does not specify a namespace.", |
| 30 | + "description": "The default BigQuery Dataset ID that tables are replicated to if the source does not specify a namespace. Read more <a href=\"https://cloud.google.com/bigquery/docs/datasets#create-dataset\">here</a>.", |
31 | 31 | "title": "Default Dataset ID" |
32 | 32 | }, |
33 | 33 | "dataset_location": { |
34 | 34 | "type": "string", |
35 | | - "description": "The location of the dataset. Warning: Changes made after creation will not be applied.", |
36 | | - "title": "Dataset Location", |
| 35 | + "description": "The location of the dataset. Warning: Changes made after creation will not be applied. The default \"US\" value is used if not set explicitly. Read more <a href=\"https://cloud.google.com/bigquery/docs/locations\">here</a>.", |
| 36 | + "title": "Dataset Location (Optional)", |
37 | 37 | "default": "US", |
38 | 38 | "enum": [ |
39 | 39 | "US", |
|
71 | 71 | }, |
72 | 72 | "credentials_json": { |
73 | 73 | "type": "string", |
74 | | - "description": "The contents of the JSON service account key. Check out the <a href=\"https://docs.airbyte.io/integrations/destinations/bigquery\">docs</a> if you need help generating this key. Default credentials will be used if this field is left empty.", |
75 | | - "title": "Credentials JSON", |
| 74 | + "description": "The contents of the JSON service account key. Check out the <a href=\"https://docs.airbyte.com/integrations/destinations/bigquery#service-account-key\">docs</a> if you need help generating this key. Default credentials will be used if this field is left empty.", |
| 75 | + "title": "Service Account Key JSON (Optional)", |
76 | 76 | "airbyte_secret": true |
77 | 77 | }, |
78 | 78 | "loading_method": { |
79 | 79 | "type": "object", |
80 | | - "title": "Loading Method", |
81 | | - "description": "Select the way that data will be uploaded to BigQuery.", |
| 80 | + "title": "Loading Method *", |
| 81 | + "description": "Loading method used to send select the way data will be uploaded to BigQuery. <br><b>Standard Inserts</b> - Direct uploading using SQL INSERT statements. This method is extremely inefficient and provided only for quick testing. In almost all cases, you should use staging. <br><b>GCS Staging</b> - Writes large batches of records to a file, uploads the file to GCS, then uses <b>COPY INTO table</b> to upload the file. Recommended for most workloads for better speed and scalability. Read more about GCS Staging <a href=\"https://docs.airbyte.com/integrations/destinations/bigquery#gcs-staging\">here</a>.", |
82 | 82 | "oneOf": [ |
83 | 83 | { |
84 | 84 | "title": "Standard Inserts", |
85 | 85 | "additionalProperties": false, |
86 | | - "description": "Direct uploading using streams.", |
87 | 86 | "required": ["method"], |
88 | 87 | "properties": { |
89 | 88 | "method": { |
|
95 | 94 | { |
96 | 95 | "title": "GCS Staging", |
97 | 96 | "additionalProperties": false, |
98 | | - "description": "Writes large batches of records to a file, uploads the file to GCS, then uses <pre>COPY INTO table</pre> to upload the file. Recommended for large production workloads for better speed and scalability.", |
99 | 97 | "required": [ |
100 | 98 | "method", |
101 | 99 | "gcs_bucket_name", |
|
110 | 108 | "gcs_bucket_name": { |
111 | 109 | "title": "GCS Bucket Name", |
112 | 110 | "type": "string", |
113 | | - "description": "The name of the GCS bucket.", |
| 111 | + "description": "The name of the GCS bucket. Read more <a href=\"https://cloud.google.com/storage/docs/naming-buckets\">here</a>.", |
114 | 112 | "examples": ["airbyte_sync"] |
115 | 113 | }, |
116 | 114 | "gcs_bucket_path": { |
| 115 | + "title": "GCS Bucket Path", |
117 | 116 | "description": "Directory under the GCS bucket where data will be written.", |
118 | 117 | "type": "string", |
119 | 118 | "examples": ["data_sync/test"] |
120 | 119 | }, |
121 | 120 | "part_size_mb": { |
122 | | - "title": "Block Size (MB) for GCS multipart upload", |
| 121 | + "title": "Block Size (MB) for GCS Multipart Upload (Optional)", |
123 | 122 | "description": "This is the size of a \"Part\" being buffered in memory. It limits the memory usage when writing. Larger values will allow to upload a bigger files and improve the speed, but consumes more memory. Allowed values: min=5MB, max=525MB Default: 5MB.", |
124 | 123 | "type": "integer", |
125 | 124 | "default": 5, |
|
129 | 128 | }, |
130 | 129 | "keep_files_in_gcs-bucket": { |
131 | 130 | "type": "string", |
132 | | - "description": "This upload method is supposed to temporary store records in GCS bucket. What do you want to do with data in GCS bucket when migration has finished?", |
133 | | - "title": "GCS tmp files afterward processing", |
| 131 | + "description": "This upload method is supposed to temporary store records in GCS bucket. What do you want to do with data in GCS bucket when migration has finished? The default \"Delete all tmp files from GCS\" value is used if not set explicitly.", |
| 132 | + "title": "GCS Tmp Files Afterward Processing (Optional)", |
134 | 133 | "default": "Delete all tmp files from GCS", |
135 | 134 | "enum": [ |
136 | 135 | "Delete all tmp files from GCS", |
|
139 | 138 | }, |
140 | 139 | "credential": { |
141 | 140 | "title": "Credential", |
| 141 | + "description": "An HMAC key is a type of credential and can be associated with a service account or a user account in Cloud Storage. Read more <a href=\"https://cloud.google.com/storage/docs/authentication/hmackeys\">here</a>.", |
142 | 142 | "type": "object", |
143 | 143 | "oneOf": [ |
144 | 144 | { |
|
0 commit comments