Knowledge Bases

API Reference

Knowledge Bases

Create a Knowledge Base

post/v2/gen-ai/knowledge_bases

Delete a Knowledge Base

delete/v2/gen-ai/knowledge_bases/{uuid}

List Knowledge Bases

get/v2/gen-ai/knowledge_bases

Retrieve Information About an Existing Knowledge Base

get/v2/gen-ai/knowledge_bases/{uuid}

Update a Knowledge Base

put/v2/gen-ai/knowledge_bases/{uuid}

ModelsExpand Collapse

APIKnowledgeBase = object { added_to_agent_at, created_at, database_id, 10 more }

Knowledgebase Description

added_to_agent_at: optional string

Time when the knowledge base was added to the agent

formatdate-time

created_at: optional string

Creation date / time

formatdate-time

database_id: optional string

embedding_model_uuid: optional string

is_public: optional boolean

Whether the knowledge base is public or not

last_indexing_job: optional APIIndexingJob

IndexingJob description

name: optional string

Name of knowledge base

project_id: optional string

region: optional string

Region code

tags: optional array of string

Tags to organize related resources

updated_at: optional string

Last modified

formatdate-time

user_id: optional string

Id of user that created the knowledge base

formatint64

uuid: optional string

Unique id for knowledge base

Knowledge BasesData Sources

Add Data Source to a Knowledge Base

post/v2/gen-ai/knowledge_bases/{knowledge_base_uuid}/data_sources

Delete a Data Source from a Knowledge Base

delete/v2/gen-ai/knowledge_bases/{knowledge_base_uuid}/data_sources/{data_source_uuid}

List Data Sources for a Knowledge Base

get/v2/gen-ai/knowledge_bases/{knowledge_base_uuid}/data_sources

ModelsExpand Collapse

APIFileUploadDataSource = object { original_file_name, size_in_bytes, stored_object_key }

File to upload as data source for knowledge base.

original_file_name: optional string

The original file name

size_in_bytes: optional string

The size of the file in bytes

formatuint64

stored_object_key: optional string

The object key the file was stored as

APIKnowledgeBaseDataSource = object { aws_data_source, bucket_name, created_at, 10 more }

Data Source configuration for Knowledge Bases

aws_data_source: optional object { bucket_name, item_path, region }

AWS S3 Data Source for Display

bucket_name: optional string

Spaces bucket name

item_path: optional string

region: optional string

Region of bucket

bucket_name: optional string

Name of storage bucket - Deprecated, moved to data_source_details

created_at: optional string

Creation date / time

formatdate-time

dropbox_data_source: optional object { folder }

Dropbox Data Source for Display

folder: optional string

file_upload_data_source: optional APIFileUploadDataSource

File to upload as data source for knowledge base.

item_path: optional string

Path of folder or object in bucket - Deprecated, moved to data_source_details

last_datasource_indexing_job: optional APIIndexedDataSource

last_indexing_job: optional APIIndexingJob

IndexingJob description

region: optional string

Region code - Deprecated, moved to data_source_details

spaces_data_source: optional APISpacesDataSource

Spaces Bucket Data Source

updated_at: optional string

Last modified

formatdate-time

uuid: optional string

Unique id of knowledge base

web_crawler_data_source: optional APIWebCrawlerDataSource

WebCrawlerDataSource

APISpacesDataSource = object { bucket_name, item_path, region }

Spaces Bucket Data Source

bucket_name: optional string

Spaces bucket name

item_path: optional string

region: optional string

Region of bucket

APIWebCrawlerDataSource = object { base_url, crawling_option, embed_media }

WebCrawlerDataSource

base_url: optional string

The base url to crawl.

crawling_option: optional "UNKNOWN" or "SCOPED" or "PATH" or 2 more

Options for specifying how URLs found on pages should be handled.

• UNKNOWN: Default unknown value
• SCOPED: Only include the base URL.
• PATH: Crawl the base URL and linked pages within the URL path.
• DOMAIN: Crawl the base URL and linked pages within the same domain.
• SUBDOMAINS: Crawl the base URL and linked pages for any subdomain.

Accepts one of the following:

"UNKNOWN"

"SCOPED"

"PATH"

"DOMAIN"

"SUBDOMAINS"

embed_media: optional boolean

Whether to ingest and index media (images, etc.) on web pages.

AwsDataSource = object { bucket_name, item_path, key_id, 2 more }

AWS S3 Data Source

bucket_name: optional string

Spaces bucket name

item_path: optional string

key_id: optional string

The AWS Key ID

region: optional string

Region of bucket

secret_key: optional string

The AWS Secret Key

Knowledge BasesIndexing Jobs

Start Indexing Job for a Knowledge Base

post/v2/gen-ai/indexing_jobs

List Indexing Jobs for a Knowledge Base

get/v2/gen-ai/indexing_jobs

Retrieve Status of Indexing Job for a Knowledge Base

get/v2/gen-ai/indexing_jobs/{uuid}

List Data Sources for Indexing Job for a Knowledge Base

get/v2/gen-ai/indexing_jobs/{indexing_job_uuid}/data_sources

Cancel Indexing Job for a Knowledge Base

put/v2/gen-ai/indexing_jobs/{uuid}/cancel

ModelsExpand Collapse

APIIndexedDataSource = object { completed_at, data_source_uuid, error_details, 11 more }

completed_at: optional string

Timestamp when data source completed indexing

formatdate-time

data_source_uuid: optional string

Uuid of the indexed data source

error_details: optional string

A detailed error description

error_msg: optional string

A string code provinding a hint which part of the system experienced an error

failed_item_count: optional string

Total count of files that have failed

formatuint64

indexed_file_count: optional string

Total count of files that have been indexed

formatuint64

indexed_item_count: optional string

Total count of files that have been indexed

formatuint64

removed_item_count: optional string

Total count of files that have been removed

formatuint64

skipped_item_count: optional string

Total count of files that have been skipped

formatuint64

started_at: optional string

Timestamp when data source started indexing

formatdate-time

status: optional "DATA_SOURCE_STATUS_UNKNOWN" or "DATA_SOURCE_STATUS_IN_PROGRESS" or "DATA_SOURCE_STATUS_UPDATED" or 3 more

Accepts one of the following:

"DATA_SOURCE_STATUS_UNKNOWN"

"DATA_SOURCE_STATUS_IN_PROGRESS"

"DATA_SOURCE_STATUS_UPDATED"

"DATA_SOURCE_STATUS_PARTIALLY_UPDATED"

"DATA_SOURCE_STATUS_NOT_UPDATED"

"DATA_SOURCE_STATUS_FAILED"

total_bytes: optional string

Total size of files in data source in bytes

formatuint64

total_bytes_indexed: optional string

Total size of files in data source in bytes that have been indexed

formatuint64

total_file_count: optional string

Total file count in the data source

formatuint64

APIIndexingJob = object { completed_datasources, created_at, data_source_uuids, 12 more }

IndexingJob description

completed_datasources: optional number

Number of datasources indexed completed

formatint64

created_at: optional string

Creation date / time

formatdate-time

data_source_uuids: optional array of string

finished_at: optional string

knowledge_base_uuid: optional string

Knowledge base id

phase: optional "BATCH_JOB_PHASE_UNKNOWN" or "BATCH_JOB_PHASE_PENDING" or "BATCH_JOB_PHASE_RUNNING" or 4 more

Accepts one of the following:

"BATCH_JOB_PHASE_UNKNOWN"

"BATCH_JOB_PHASE_PENDING"

"BATCH_JOB_PHASE_RUNNING"

"BATCH_JOB_PHASE_SUCCEEDED"

"BATCH_JOB_PHASE_FAILED"

"BATCH_JOB_PHASE_ERROR"

"BATCH_JOB_PHASE_CANCELLED"

started_at: optional string

status: optional "INDEX_JOB_STATUS_UNKNOWN" or "INDEX_JOB_STATUS_PARTIAL" or "INDEX_JOB_STATUS_IN_PROGRESS" or 4 more

Accepts one of the following:

"INDEX_JOB_STATUS_UNKNOWN"

"INDEX_JOB_STATUS_PARTIAL"

"INDEX_JOB_STATUS_IN_PROGRESS"

"INDEX_JOB_STATUS_COMPLETED"

"INDEX_JOB_STATUS_FAILED"

"INDEX_JOB_STATUS_NO_CHANGES"

"INDEX_JOB_STATUS_PENDING"

tokens: optional number

Number of tokens

formatint64

total_datasources: optional number

Number of datasources being indexed

formatint64

total_items_failed: optional string

Total Items Failed

formatuint64

total_items_indexed: optional string

Total Items Indexed

formatuint64

total_items_skipped: optional string

Total Items Skipped

formatuint64

updated_at: optional string

Last modified

formatdate-time

uuid: optional string

Unique id