> ## 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. # Submit Upload Job ## OpenAPI ````yaml https://app.stainlessapi.com/api/spec/documented/sgp/openapi.yml post /v4/knowledge-bases/{knowledge_base_id}/uploads 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-bases/{knowledge_base_id}/uploads: post: tags: - Knowledge Bases summary: Submit Upload Job operationId: POST-V4-/v2/knowledge-bases/{knowledge_base_id}/uploads parameters: - name: knowledge_base_id in: path required: true schema: type: string title: Knowledge Base Id - name: x-selected-account-id in: header required: false schema: anyOf: - type: string - type: 'null' title: Account ID Header requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/CreateKnowledgeBaseV2UploadRequest' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/CreateKnowledgeBaseV2UploadResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - APIKeyHeader: [] 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 ) create_knowledge_base_upload_response = client.knowledge_bases.uploads.create( knowledge_base_id="knowledge_base_id", data_source_config={ "aws_account_id": "aws_account_id", "aws_region": "aws_region", "s3_bucket": "s3_bucket", "source": "S3", }, ) print(create_knowledge_base_upload_response.upload_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\tcreateKnowledgeBaseUploadResponse, err := client.KnowledgeBases.Uploads.New(\n\t\tcontext.TODO(),\n\t\t\"knowledge_base_id\",\n\t\tsgp.KnowledgeBaseUploadNewParams{\n\t\t\tBody: sgp.KnowledgeBaseUploadNewParamsBodyDataSourceUploadRequest{\n\t\t\t\tDataSourceConfig: sgp.F[sgp.KnowledgeBaseUploadNewParamsBodyDataSourceUploadRequestDataSourceConfigUnion](sgp.S3DataSourceConfigParam{\n\t\t\t\t\tAwsAccountID: sgp.F(\"aws_account_id\"),\n\t\t\t\t\tAwsRegion: sgp.F(\"aws_region\"),\n\t\t\t\t\tS3Bucket: sgp.F(\"s3_bucket\"),\n\t\t\t\t\tSource: sgp.F(sgp.S3DataSourceConfigSourceS3),\n\t\t\t\t}),\n\t\t\t},\n\t\t},\n\t)\n\tif err != nil {\n\t\tpanic(err.Error())\n\t}\n\tfmt.Printf(\"%+v\\n\", createKnowledgeBaseUploadResponse.UploadID)\n}\n" components: schemas: CreateKnowledgeBaseV2UploadRequest: anyOf: - $ref: >- #/components/schemas/CreateKnowledgeBaseV2UploadFromDataSourceRequest - $ref: >- #/components/schemas/CreateKnowledgeBaseV2UploadFromLocalChunksRequest - $ref: >- #/components/schemas/CreateKnowledgeBaseV2UploadFromDataSourceIdRequest title: CreateKnowledgeBaseV2UploadRequest CreateKnowledgeBaseV2UploadResponse: properties: upload_id: type: string title: Upload Id description: ID of the created knowledge base upload job. type: object required: - upload_id title: CreateKnowledgeBaseV2UploadResponse HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError CreateKnowledgeBaseV2UploadFromDataSourceRequest: properties: data_source_config: $ref: '#/components/schemas/RemoteDataSourceConfig' description: >- Configuration for the data source which describes where to find the data. data_source_auth_config: $ref: '#/components/schemas/DataSourceAuthConfig' description: >- Configuration for the data source which describes how to authenticate to the data source. chunking_strategy_config: $ref: '#/components/schemas/ChunkingStrategyConfig' description: >- Configuration for the chunking strategy which describes how to chunk the data. force_reupload: title: Force Reupload description: Force reingest, regardless the change of the source file. default: false type: boolean tagging_information: $ref: '#/components/schemas/TaggingInformation' description: >- A dictionary of tags to apply to all artifacts added from the data source. type: object required: - data_source_config title: DataSource Upload Request CreateKnowledgeBaseV2UploadFromLocalChunksRequest: properties: data_source_config: $ref: '#/components/schemas/LocalChunksSourceConfig' description: >- Configuration for the data source which describes where to find the data. chunks: items: $ref: '#/components/schemas/ArtifactChunkUpload' type: array title: Chunks description: List of chunks. force_reupload: title: Force Reupload description: Force reingest, regardless the change of the source file. default: false type: boolean tagging_information: $ref: '#/components/schemas/TaggingInformation' description: >- A dictionary of tags to apply to all artifacts added from the data source. type: object required: - data_source_config title: Local Chunks Upload Request CreateKnowledgeBaseV2UploadFromDataSourceIdRequest: properties: data_source_id: type: string title: Data Source Id description: Id of the data source to fetch. chunking_strategy_config: $ref: '#/components/schemas/ChunkingStrategyConfig' description: >- Configuration for the chunking strategy which describes how to chunk the data. force_reupload: title: Force Reupload description: Force reingest, regardless the change of the source file. default: false type: boolean tagging_information: $ref: '#/components/schemas/TaggingInformation' description: >- A dictionary of tags to apply to all artifacts added from the data source. type: object required: - data_source_id - chunking_strategy_config title: DataSource Upload Request 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 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' ChunkingStrategyConfig: oneOf: - $ref: '#/components/schemas/CharacterChunkingStrategyConfig' - $ref: '#/components/schemas/TokenChunkingStrategyConfig' - $ref: '#/components/schemas/CustomChunkingStrategyConfig' - $ref: '#/components/schemas/PreChunkedStrategyConfig' - $ref: '#/components/schemas/EnhancedChunkingStrategyConfig' title: ChunkingStrategyConfig discriminator: propertyName: strategy mapping: character: $ref: '#/components/schemas/CharacterChunkingStrategyConfig' custom: $ref: '#/components/schemas/CustomChunkingStrategyConfig' enhanced: $ref: '#/components/schemas/EnhancedChunkingStrategyConfig' pre_chunked: $ref: '#/components/schemas/PreChunkedStrategyConfig' token: $ref: '#/components/schemas/TokenChunkingStrategyConfig' TaggingInformation: oneOf: - $ref: '#/components/schemas/TaggingInformationPerFile' - $ref: '#/components/schemas/TaggingInformationAll' title: TaggingInformation discriminator: propertyName: type mapping: all: $ref: '#/components/schemas/TaggingInformationAll' per_file: $ref: '#/components/schemas/TaggingInformationPerFile' LocalChunksSourceConfig: properties: source: type: string const: LocalChunks title: Source artifact_name: type: string title: Artifact Name description: >- The file name assigned to the artifact, containing a file extension. Adding an extension is mandatory, to allow detecting file types for text extraction. artifact_uri: type: string title: Artifact Uri description: >- A unique identifier for an artifact within the knowledge base, such as full path in a directory or file system. deduplication_strategy: $ref: '#/components/schemas/DeduplicationStrategy' description: >- Action to take if an artifact with the same name already exists in the knowledge base. Can be either Overwrite (default) or Fail. default: Overwrite type: object required: - source - artifact_name - artifact_uri title: LocalChunksSourceConfig ArtifactChunkUpload: properties: text: type: string title: Text description: Associated text of the chunk. chunk_position: type: integer title: Chunk Position description: Position of the chunk in the artifact. metadata: additionalProperties: true type: object title: Metadata description: Additional metadata associated with the chunk. default: {} type: object required: - text - chunk_position title: ArtifactChunkUpload S3DataSourceConfig: properties: source: type: string const: S3 title: Source s3_bucket: type: string title: S3 Bucket description: Name of the S3 bucket where the data is stored. s3_prefix: type: string title: S3 Prefix description: >- Prefix of the S3 bucket where the data is stored. If not specified, the entire bucket will be used. default: '' aws_region: type: string title: Aws Region description: AWS region where the S3 bucket is located. aws_account_id: type: string pattern: ^\d{12}$ 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 CharacterChunkingStrategyConfig: properties: strategy: type: string const: character title: Strategy separator: title: Separator description: >- Character designating breaks in input data. Text data will first be split into sections by this separator, then each section will be split into chunks of size `chunk_size`. default: |+ type: string chunk_size: title: Chunk Size description: >- Maximum number of characters in each chunk. If not specified, a chunk size of 1000 will be used. default: 1000 type: integer minimum: 1 chunk_overlap: title: Chunk Overlap description: >- Number of characters to overlap between chunks. If not specified, an overlap of 200 will be used. For example if the chunk size is 3 and the overlap size is 1, and the text to chunk is 'abcde', the chunks will be 'abc', 'cde'. default: 200 type: integer minimum: 0 type: object required: - strategy title: CharacterChunkingStrategyConfig TokenChunkingStrategyConfig: properties: strategy: type: string const: token title: Strategy separator: title: Separator description: >- Character designating breaks in input data. Text data will first be split into sections by this separator, then each section will be split into chunks of size `chunk_size`. default: |+ type: string target_chunk_size: title: Target Chunk Size description: >- Target number of tokens in each chunk. If not specified, a target chunk size of 200 will be used. default: 200 type: integer minimum: 1 max_chunk_size: title: Max Chunk Size description: >- Maximum number of tokens in each chunk. If not specified, a maximum chunk size of 600 will be used. default: 600 type: integer minimum: 1 chunk_overlap: title: Chunk Overlap description: >- Number of tokens to overlap between chunks. If not specified, an overlap of 0 will be used. Not this if only followed approximately. default: 0 type: integer minimum: 0 type: object required: - strategy title: TokenChunkingStrategyConfig CustomChunkingStrategyConfig: properties: strategy: type: string const: custom title: Strategy endpoint: type: string title: Endpoint description: Endpoint path to call for custom chunking params: title: Params description: >- Parameters that will be appended to the body of the request for the chunk. default: {} additionalProperties: true type: object type: object required: - strategy - endpoint title: CustomChunkingStrategyConfig PreChunkedStrategyConfig: properties: strategy: type: string const: pre_chunked title: Strategy type: object required: - strategy title: PreChunkedStrategyConfig description: Only compliant with the .chunks file type EnhancedChunkingStrategyConfig: properties: strategy: type: string const: enhanced title: Strategy default: enhanced chunk_mode: type: string enum: - variable - section - page - page_sections - block title: Chunk Mode description: Enhanced internal chunking method default: section options: title: Options description: Options for enhanced parsing additionalProperties: true type: object advanced_options: title: Advanced Options description: Advanced options for enhanced parsing additionalProperties: true type: object experimental_options: title: Experimental Options description: Experimental options for enhanced parsing additionalProperties: true type: object use_async_parsing: type: boolean title: Use Async Parsing default: false type: object title: EnhancedChunkingStrategyConfig description: Enhanced document parsing and chunking TaggingInformationPerFile: properties: type: type: string const: per_file title: Type default: per_file tags_to_apply: title: Tags To Apply additionalProperties: anyOf: - additionalProperties: true type: object - type: 'null' type: object type: object title: TaggingInformationPerFile 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 DeduplicationStrategy: type: string enum: - Overwrite - Fail title: DeduplicationStrategy securitySchemes: APIKeyHeader: type: apiKey in: header name: x-api-key ````