> ## Documentation Index > Fetch the complete documentation index at: https://docs.gp.scale.com/llms.txt > Use this file to discover all available pages before exploring further. # Create Knowledge Base Data Source > ### Description Creates a knowledge base data source ### Details This API can be used to create a knowledge base data source. To use this API, review the request schema and pass in all fields that are required to create a knowledge base data source. ## OpenAPI ````yaml https://app.stainlessapi.com/api/spec/documented/sgp/openapi.yml post /v4/knowledge-base-data-sources openapi: 3.1.0 info: title: EGP API V4 description: >- This is the parent API for all EGP APIs. If you are looking for the EGP API, please go to https://api.egp.scale.com/docs. contact: name: Scale Generative AI Platform url: https://scale.com/genai-platform version: 0.1.0 servers: - url: https://api.egp.scale.com security: [] tags: - name: Models description: Model API. paths: /v4/knowledge-base-data-sources: post: tags: - Knowledge Base Data Sources summary: Create Knowledge Base Data Source description: >- ### Description Creates a knowledge base data source ### Details This API can be used to create a knowledge base data source. To use this API, review the request schema and pass in all fields that are required to create a knowledge base data source. operationId: POST-V4-/knowledge-base-data-sources requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/KnowledgeBaseDataSourceRequest' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/KnowledgeBaseDataSourceResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' x-codeSamples: - lang: Python source: >- import os from scale_gp import SGPClient client = SGPClient( api_key=os.environ.get("SGP_API_KEY"), # This is the default and can be omitted ) knowledge_base_data_source = client.knowledge_base_data_sources.create( account_id="account_id", data_source_config={ "aws_account_id": "aws_account_id", "aws_region": "aws_region", "s3_bucket": "s3_bucket", "source": "S3", }, name="name", ) print(knowledge_base_data_source.id) - lang: Go source: "package main\n\nimport (\n\t\"context\"\n\t\"fmt\"\n\n\t\"github.com/stainless-sdks/sgp-go\"\n\t\"github.com/stainless-sdks/sgp-go/option\"\n)\n\nfunc main() {\n\tclient := sgp.NewClient(\n\t\toption.WithAPIKey(\"My API Key\"),\n\t)\n\tknowledgeBaseDataSource, err := client.KnowledgeBaseDataSources.New(context.TODO(), sgp.KnowledgeBaseDataSourceNewParams{\n\t\tAccountID: sgp.F(\"account_id\"),\n\t\tDataSourceConfig: sgp.F[sgp.KnowledgeBaseDataSourceNewParamsDataSourceConfigUnion](sgp.S3DataSourceConfigParam{\n\t\t\tAwsAccountID: sgp.F(\"aws_account_id\"),\n\t\t\tAwsRegion: sgp.F(\"aws_region\"),\n\t\t\tS3Bucket: sgp.F(\"s3_bucket\"),\n\t\t\tSource: sgp.F(sgp.S3DataSourceConfigSourceS3),\n\t\t}),\n\t\tName: sgp.F(\"name\"),\n\t})\n\tif err != nil {\n\t\tpanic(err.Error())\n\t}\n\tfmt.Printf(\"%+v\\n\", knowledgeBaseDataSource.ID)\n}\n" components: schemas: KnowledgeBaseDataSourceRequest: properties: name: type: string title: Name description: title: Description type: string data_source_config: $ref: '#/components/schemas/RemoteDataSourceConfig' can_patch: false data_source_auth_config: $ref: '#/components/schemas/DataSourceAuthConfig' tagging_information: $ref: '#/components/schemas/TaggingInformationAll' can_patch: true account_id: type: string title: Account Id description: The ID of the account that owns the given entity. can_patch: false type: object required: - name - data_source_config - account_id title: KnowledgeBaseDataSourceRequest KnowledgeBaseDataSourceResponse: properties: name: type: string title: Name description: title: Description type: string data_source_config: $ref: '#/components/schemas/RemoteDataSourceConfig' can_patch: false tagging_information: $ref: '#/components/schemas/TaggingInformationAll' can_patch: true id: type: string title: Id description: The unique identifier of the entity. created_at: type: string format: date-time title: Created At description: The date and time when the entity was created in ISO format. updated_at: type: string format: date-time title: Updated At description: The date and time when the entity was last updated in ISO format. created_by_user_id: type: string title: Created By User Id description: The user who originally created the entity. created_by_identity_type: $ref: '#/components/schemas/IdentifierTypeEnum' description: The type of identity that created the entity. account_id: type: string title: Account Id description: The ID of the account that owns the given entity. can_patch: false type: object required: - name - data_source_config - id - created_at - updated_at - created_by_user_id - created_by_identity_type - account_id title: KnowledgeBaseDataSourceResponse HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError RemoteDataSourceConfig: oneOf: - $ref: '#/components/schemas/S3DataSourceConfig' - $ref: '#/components/schemas/SharePointDataSourceConfig' - $ref: '#/components/schemas/SharePointPageDataSourceConfig' - $ref: '#/components/schemas/GoogleDriveDataSourceConfig' - $ref: '#/components/schemas/AzureBlobStorageDataSourceConfig' - $ref: '#/components/schemas/GoogleCloudStorageDataSourceConfig' - $ref: '#/components/schemas/ConfluenceDataSourceConfig' - $ref: '#/components/schemas/SlackDataSourceConfig' - $ref: '#/components/schemas/SnowflakeDataSourceConfig' - $ref: '#/components/schemas/DatabricksDataSourceConfig' - $ref: '#/components/schemas/SQLDatabaseDataSourceConfig' - $ref: '#/components/schemas/MongoDBDataSourceConfig' - $ref: '#/components/schemas/BigQueryDataSourceConfig' title: RemoteDataSourceConfig discriminator: propertyName: source mapping: AzureBlobStorage: $ref: '#/components/schemas/AzureBlobStorageDataSourceConfig' BigQuery: $ref: '#/components/schemas/BigQueryDataSourceConfig' Confluence: $ref: '#/components/schemas/ConfluenceDataSourceConfig' Databricks: $ref: '#/components/schemas/DatabricksDataSourceConfig' GoogleCloudStorage: $ref: '#/components/schemas/GoogleCloudStorageDataSourceConfig' GoogleDrive: $ref: '#/components/schemas/GoogleDriveDataSourceConfig' MongoDB: $ref: '#/components/schemas/MongoDBDataSourceConfig' S3: $ref: '#/components/schemas/S3DataSourceConfig' SQLDatabase: $ref: '#/components/schemas/SQLDatabaseDataSourceConfig' SharePoint: $ref: '#/components/schemas/SharePointDataSourceConfig' SharePointPage: $ref: '#/components/schemas/SharePointPageDataSourceConfig' Slack: $ref: '#/components/schemas/SlackDataSourceConfig' Snowflake: $ref: '#/components/schemas/SnowflakeDataSourceConfig' DataSourceAuthConfig: oneOf: - $ref: '#/components/schemas/SharePointDataSourceAuthConfig' - $ref: '#/components/schemas/SharePointPageDataSourceAuthConfig' - $ref: '#/components/schemas/AzureBlobStorageDataSourceAuthConfig' - $ref: '#/components/schemas/GoogleCloudStorageDataSourceAuthConfig' - $ref: '#/components/schemas/GoogleDriveDataSourceAuthConfig' - $ref: '#/components/schemas/S3DataSourceAuthConfig' - $ref: '#/components/schemas/ConfluenceDataSourceAuthConfig' - $ref: '#/components/schemas/SlackDataSourceAuthConfig' - $ref: '#/components/schemas/SnowflakeDataSourceAuthConfig' - $ref: '#/components/schemas/DatabricksDataSourceAuthConfig' - $ref: '#/components/schemas/SQLDatabaseDataSourceAuthConfig' - $ref: '#/components/schemas/MongoDBDataSourceAuthConfig' - $ref: '#/components/schemas/BigQueryDataSourceAuthConfig' title: DataSourceAuthConfig discriminator: propertyName: source mapping: AzureBlobStorage: $ref: '#/components/schemas/AzureBlobStorageDataSourceAuthConfig' BigQuery: $ref: '#/components/schemas/BigQueryDataSourceAuthConfig' Confluence: $ref: '#/components/schemas/ConfluenceDataSourceAuthConfig' Databricks: $ref: '#/components/schemas/DatabricksDataSourceAuthConfig' GoogleCloudStorage: $ref: '#/components/schemas/GoogleCloudStorageDataSourceAuthConfig' GoogleDrive: $ref: '#/components/schemas/GoogleDriveDataSourceAuthConfig' MongoDB: $ref: '#/components/schemas/MongoDBDataSourceAuthConfig' S3: $ref: '#/components/schemas/S3DataSourceAuthConfig' SQLDatabase: $ref: '#/components/schemas/SQLDatabaseDataSourceAuthConfig' SharePoint: $ref: '#/components/schemas/SharePointDataSourceAuthConfig' SharePointPage: $ref: '#/components/schemas/SharePointPageDataSourceAuthConfig' Slack: $ref: '#/components/schemas/SlackDataSourceAuthConfig' Snowflake: $ref: '#/components/schemas/SnowflakeDataSourceAuthConfig' TaggingInformationAll: properties: type: type: string const: all title: Type default: all tags_to_apply: title: Tags To Apply additionalProperties: true type: object type: object title: TaggingInformationAll IdentifierTypeEnum: type: string enum: - user - service_account title: IdentifierTypeEnum ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type input: title: Input ctx: type: object title: Context additionalProperties: true type: object required: - loc - msg - type title: ValidationError S3DataSourceConfig: properties: source: type: string const: S3 title: Source s3_bucket: type: string title: S3 Bucket description: Name of the S3 bucket where the data is stored. s3_prefix: type: string title: S3 Prefix description: >- Prefix of the S3 bucket where the data is stored. If not specified, the entire bucket will be used. default: '' aws_region: type: string title: Aws Region description: AWS region where the S3 bucket is located. aws_account_id: type: string pattern: ^\d{12}$ title: Aws Account Id description: AWS account ID that owns the S3 bucket. type: object required: - source - s3_bucket - aws_region - aws_account_id title: S3 DataSource Config SharePointDataSourceConfig: properties: source: type: string const: SharePoint title: Source client_id: type: string title: Client Id description: Client ID associated with this SharePoint site tenant_id: type: string title: Tenant Id description: Tenant ID that the SharePoint site is within site_id: type: string title: Site Id description: >- Site ID for this SharePoint site, can be found at https://[hostname].sharepoint.com/sites/[site name]/_api/site/id folder_path: title: Folder Path description: >- Nested folder path to read files from the root of the site. Please omit the leading slash. Example: 'Documents/sub_directory' default: '' type: string recursive: title: Recursive description: Recurse through the folder contents, default is True. default: true type: boolean type: object required: - source - client_id - tenant_id - site_id title: SharePoint DataSource Config SharePointPageDataSourceConfig: properties: source: type: string const: SharePointPage title: Source client_id: type: string title: Client Id description: Client ID associated with this SharePoint site tenant_id: type: string title: Tenant Id description: Tenant ID that the SharePoint site is within site_id: type: string title: Site Id description: Site ID for this SharePoint site type: object required: - source - client_id - tenant_id - site_id title: SharePoint Page DataSource Config GoogleDriveDataSourceConfig: properties: source: type: string const: GoogleDrive title: Source drive_id: type: string title: Drive Id description: ID associated with the Google Drive to retrieve contents from type: object required: - source - drive_id title: Google Drive DataSource Config AzureBlobStorageDataSourceConfig: properties: source: type: string const: AzureBlobStorage title: Source container_url: type: string title: Container Url description: >- The full URL of the container such as 'https://your-account-name.blob.core.windows.net/your-container-name' type: object required: - source - container_url title: Azure Blob Storage DataSource Config GoogleCloudStorageDataSourceConfig: properties: source: type: string const: GoogleCloudStorage title: Source bucket: type: string title: Bucket description: Name of the Google Cloud Storage bucket where the data is stored. prefix: title: Prefix description: >- Prefix path within the Google Cloud Storage bucket. If not specified, the entire bucket will be used. type: string project_id: title: Project Id description: >- GCP project ID that owns the Google Cloud Storage bucket. If not specified, uses the default project. type: string type: object required: - source - bucket title: Google Cloud Storage DataSource Config ConfluenceDataSourceConfig: properties: source: type: string const: Confluence title: Source space_key: type: string title: Space Key description: >- Confluence space key to retrieve contents from. See https://support.atlassian.com/confluence-cloud/docs/choose-a-space-key type: object required: - source - space_key title: Confluence DataSource Config SlackDataSourceConfig: properties: source: type: string const: Slack title: Source channel_id: type: string title: Channel Id description: >- Slack Channel or Conversation ID to retrieve history from. Open channel details and find the ID at bottom of 'About' section. type: object required: - source - channel_id title: Slack DataSource Config SnowflakeDataSourceConfig: properties: source: type: string const: Snowflake title: Source account: type: string title: Account description: Snowflake account identifier user: type: string title: User description: Snowflake user name type: object required: - source - account - user title: Snowflake DataSource Config DatabricksDataSourceConfig: properties: source: type: string const: Databricks title: Source server_hostname: type: string title: Server Hostname description: Databricks server hostname http_path: type: string title: Http Path description: HTTP path for the Databricks cluster or SQL warehouse type: object required: - source - server_hostname - http_path title: Databricks DataSource Config SQLDatabaseDataSourceConfig: properties: source: type: string const: SQLDatabase title: Source dialect: type: string enum: - postgresql - mssql - sqlite - snowflake title: Dialect description: SQL dialect to use for connection host: title: Host description: Database server hostname or IP address type: string port: title: Port description: Database server port type: integer database: type: string title: Database description: Name of the database to connect to. username: title: Username description: Username for authentication type: string driver: title: Driver description: >- ODBC driver name for MSSQL connections. Defaults to 'ODBC Driver 18 for SQL Server' if not specified. type: string ssl_mode: title: Ssl Mode description: SSL mode for PostgreSQL connections (e.g., 'require', 'verify-full') type: string connect_timeout: title: Connect Timeout description: Connection timeout in seconds default: 30 type: integer connection_options: title: Connection Options description: >- Additional connection parameters appended to the URL (e.g., {'sslrootcert': '/path/to/ca.pem', 'application_name': 'myapp'}) additionalProperties: type: string type: object account: title: Account description: >- Snowflake account identifier (e.g., 'xy12345' or 'xy12345.us-east-2.azure'). Do NOT include the '.snowflakecomputing.com' suffix. type: string warehouse: title: Warehouse description: >- Snowflake warehouse name for query execution. Required for Snowflake. type: string schema_name: title: Schema Name description: Snowflake schema name. Defaults to 'PUBLIC' if not specified. type: string role: title: Role description: >- Snowflake role for authentication. Uses the default role for the user if not specified. type: string type: object required: - source - dialect - database title: SQL Database DataSource Config MongoDBDataSourceConfig: properties: source: type: string const: MongoDB title: Source database: type: string title: Database description: Database name to connect to connect_timeout: title: Connect Timeout description: Connection timeout in seconds default: 30 type: integer type: object required: - source - database title: MongoDB DataSource Config BigQueryDataSourceConfig: properties: source: type: string const: BigQuery title: Source project_id: type: string title: Project Id description: GCP project ID containing the BigQuery dataset(s) to query. location: title: Location description: >- BigQuery dataset location (e.g. 'US', 'EU', 'us-central1'). When omitted the client uses the project's default location. type: string connect_timeout: title: Connect Timeout description: Connection timeout in seconds for BigQuery API calls. default: 30 type: integer type: object required: - source - project_id title: BigQuery DataSource Config SharePointDataSourceAuthConfig: properties: encrypted: type: boolean title: Encrypted default: false source: type: string const: SharePoint title: Source client_secret: type: string title: Client Secret description: Secret for the app registration associated with this SharePoint site type: object required: - source - client_secret title: SharePoint DataSource Auth Config SharePointPageDataSourceAuthConfig: properties: encrypted: type: boolean title: Encrypted default: false source: type: string const: SharePointPage title: Source client_secret: type: string title: Client Secret description: Secret for the app registration associated with this SharePoint site type: object required: - source - client_secret title: SharePoint Page DataSource Auth Config AzureBlobStorageDataSourceAuthConfig: properties: encrypted: type: boolean title: Encrypted default: false source: type: string const: AzureBlobStorage title: Source blob_sas_token: type: string title: Blob Sas Token description: Shared Access Signature token for the Azure Blob Storage container type: object required: - source - blob_sas_token title: Azure DataSource Auth Config GoogleCloudStorageDataSourceAuthConfig: properties: encrypted: type: boolean title: Encrypted default: false source: type: string const: GoogleCloudStorage title: Source impersonated_service_account_email: title: Impersonated Service Account Email description: >- Service account email to impersonate for Google Cloud Storage authentication. Similar to AWS AssumeRole. If provided, Scale will impersonate this service account using default credentials. If not provided, uses default credentials directly. type: string type: object required: - source title: Google Cloud Storage DataSource Auth Config GoogleDriveDataSourceAuthConfig: properties: encrypted: type: boolean title: Encrypted default: false source: type: string const: GoogleDrive title: Source client_email: type: string title: Client Email description: >- Client email to use for google drive, set to override client email set in env vars private_key: type: string title: Private Key description: >- Private key to use for google drive, set to override private key set in env vars token_uri: type: string title: Token Uri description: >- Token uri to use for google drive, set to override token uri set in env vars client_id: type: string title: Client Id description: >- Client id to use for google drive, set to override client id set in env vars type: object required: - source - client_email - private_key - token_uri - client_id title: Google Drive DataSource Auth Config S3DataSourceAuthConfig: properties: encrypted: type: boolean title: Encrypted default: false source: type: string const: S3 title: Source s3_role: title: S3 Role description: >- Name of the role that a client will be initialized via AssumeRole of AWS sts type: string external_id: title: External Id description: External ID defined by the customer for the IAM role type: string type: object required: - source title: S3 DataSource Auth Config ConfluenceDataSourceAuthConfig: properties: encrypted: type: boolean title: Encrypted default: false source: type: string const: Confluence title: Source client_email: type: string title: Client Email description: >- Client email to use for Confluence, set to override client email set in env vars. api_key: type: string title: Api Key description: >- API key to use for Confluence, set this to override api key configured in env vars. atlassian_domain: type: string title: Atlassian Domain description: >- Your Confluence API server's full domain, set to override domain configured in env vars. E.g. 'https://[your-company].atlassian.net' type: object required: - source - client_email - api_key - atlassian_domain title: Confluence DataSource Auth Config SlackDataSourceAuthConfig: properties: encrypted: type: boolean title: Encrypted default: false source: type: string const: Slack title: Source bot_token: type: string title: Bot Token description: >- Your Slack app's Bot OAuth token. See https://api.slack.com/quickstart type: object required: - source - bot_token title: Slack DataSource Auth Config SnowflakeDataSourceAuthConfig: properties: encrypted: type: boolean title: Encrypted default: false source: type: string const: Snowflake title: Source password: type: string title: Password description: Password for Snowflake authentication type: object required: - source - password title: Snowflake DataSource Auth Config DatabricksDataSourceAuthConfig: properties: encrypted: type: boolean title: Encrypted default: false source: type: string const: Databricks title: Source access_token: type: string title: Access Token description: Databricks access token for authentication type: object required: - source - access_token title: Databricks DataSource Auth Config SQLDatabaseDataSourceAuthConfig: properties: encrypted: type: boolean title: Encrypted default: false source: type: string const: SQLDatabase title: Source password: type: string title: Password description: Password for database authentication type: object required: - source - password title: SQL Database DataSource Auth Config MongoDBDataSourceAuthConfig: properties: encrypted: type: boolean title: Encrypted default: false source: type: string const: MongoDB title: Source connection_uri: type: string title: Connection Uri description: MongoDB connection URI type: object required: - source - connection_uri title: MongoDB DataSource Auth Config BigQueryDataSourceAuthConfig: properties: encrypted: type: boolean title: Encrypted default: false source: type: string const: BigQuery title: Source impersonated_service_account_email: type: string title: Impersonated Service Account Email description: >- Service account email to impersonate for BigQuery authentication. When provided, Scale will impersonate this service account using default credentials (no secret material crosses the boundary). Mutually exclusive with service_account_json. NOTE: the host service account that ADC resolves on the EGP service must have roles/iam.serviceAccountTokenCreator on this target service account, otherwise BigQuery calls will fail with a 403 at query time. default: '' service_account_json: type: string title: Service Account Json description: >- Service account JSON key blob (the full contents of the downloaded key file). Used in environments where impersonation is not available. Mutually exclusive with impersonated_service_account_email. default: '' type: object required: - source title: BigQuery DataSource Auth Config ````