API Documentation
Health
Files
Web Scrape
Data Source
SharePoint
GitHub
Chunks / Embeddings
Retrieval
List Chunks and Embeddings
curl --request POST \
--url https://api.carbon.ai/list_chunks_and_embeddings \
--header 'Content-Type: application/json' \
--header 'authorization: <api-key>' \
--data '{
"pagination": {
"limit": 10,
"offset": 0,
"starting_id": 0
},
"order_by": "updated_at",
"order_dir": "asc",
"filters": {
"source": "GOOGLE_CLOUD_STORAGE",
"name": "<string>",
"tags": {},
"tags_v2": {},
"ids": [
123
],
"external_file_ids": [
"<string>"
],
"sync_statuses": [
"DELAYED"
],
"parent_file_ids": [
123
],
"organization_user_data_source_id": [
123
],
"embedding_generators": [
"OPENAI"
],
"root_files_only": true,
"include_all_children": false,
"non_synced_only": false,
"request_ids": [
"<string>"
],
"upload_ids": [
"<string>"
],
"sync_error_message": "<string>",
"include_containers": true,
"external_urls": [
"<string>"
],
"file_types_at_source": [
"TICKET"
]
},
"include_vectors": false
}'{
"results": [
{
"user_file_id": 123,
"chunk_index": 123,
"source_content": "<string>",
"embedding": [
123
],
"content_metadata": {}
}
],
"count": 123
}Authorizations
token <token>, corresponds to temporary access tokens.
Body
The source of the file. If a list is provided, the query will return files from any of the sources in the list.
GOOGLE_CLOUD_STORAGE, GOOGLE_DRIVE, NOTION, NOTION_DATABASE, INTERCOM, DROPBOX, ONEDRIVE, SHAREPOINT, CONFLUENCE, BOX, ZENDESK, ZOTERO, S3, AZURE_BLOB_STORAGE, GMAIL, OUTLOOK, SERVICENOW, TEXT, CSV, TSV, PDF, DOCX, PPTX, XLSX, XLSM, MD, RTF, JSON, HTML, RAW_TEXT, WEB_SCRAPE, RSS_FEED, FRESHDESK, GITBOOK, SALESFORCE, GITHUB, SLACK, GURU, GONG, DOCUMENT360, JPG, PNG, JPEG, MP3, MP2, AAC, WAV, FLAC, PCM, M4A, OGG, OPUS, MPEG, MPG, MP4, WMV, AVI, MOV, MKV, FLV, WEBM, EML, MSG The name of the file. The query will return files with names that contain this string.
Tags to filter by. Supports logical AND and OR operations. Input should be like below:
{
"OR": [
{
"key": "subject",
"value": "holy-bible",
"negate": false
},
{
"key": "person-of-interest",
"value": "jesus christ",
"negate": false
},
{
"key": "genre",
"value": "fiction",
"negate": true
}
{
"AND": [
{
"key": "subject",
"value": "tao-te-ching",
"negate": true
},
{
"key": "author",
"value": "lao-tzu",
"negate": false
}
]
}
]
}
For a single filter, the filter block can be placed within either an "AND" or "OR" block.
The IDs of the files. The query will return files with these IDs.
The external file IDs of the files. The query will return files with these external file IDs.
The sync statuses of the files. The query will return files with these sync statuses.
DELAYED, QUEUED_FOR_SYNC, SYNCING, READY, SYNC_ERROR, EVALUATING_RESYNC, RATE_LIMITED, SYNC_ABORTED, QUEUED_FOR_OCR, READY_TO_SYNC The organization user data source IDs of the files. The query will return files with these organization user data source IDs.
The embedding generators of the files. The query will return files with these embedding generators.
OPENAI, AZURE_OPENAI, AZURE_ADA_LARGE_256, AZURE_ADA_LARGE_1024, AZURE_ADA_LARGE_3072, AZURE_ADA_SMALL_512, AZURE_ADA_SMALL_1536, COHERE_MULTILINGUAL_V3, VERTEX_MULTIMODAL, OPENAI_ADA_LARGE_256, OPENAI_ADA_LARGE_1024, OPENAI_ADA_LARGE_3072, OPENAI_ADA_SMALL_512, OPENAI_ADA_SMALL_1536, SOLAR_1_MINI If true, the query will return only root files. Cannot be true if parent_file_ids or include_all_children is specified.
If true, the query will return all descendents of the specified parent_file_ids.
If true, the query will return only files that have not been synced yet.
Filter by request ID(s) which were used to sync the files
Filter by upload ID(s) which were used to sync the files
The error message of the file. The query will return files with error messages that contain this string. To search for files with no error message, use an empty string.
If true, the query will return containers in the response. Containers are files that group other files together and have no content themselves. Default behavior is to include containers.
The external URLs of the files. The query will return files with these external URLs.
Filter files based on their type at the source (for example help center tickets and articles)
TICKET, ARTICLE, CONVERSATION created_at, updated_at, name, last_sync, file_size, id desc, asc curl --request POST \
--url https://api.carbon.ai/list_chunks_and_embeddings \
--header 'Content-Type: application/json' \
--header 'authorization: <api-key>' \
--data '{
"pagination": {
"limit": 10,
"offset": 0,
"starting_id": 0
},
"order_by": "updated_at",
"order_dir": "asc",
"filters": {
"source": "GOOGLE_CLOUD_STORAGE",
"name": "<string>",
"tags": {},
"tags_v2": {},
"ids": [
123
],
"external_file_ids": [
"<string>"
],
"sync_statuses": [
"DELAYED"
],
"parent_file_ids": [
123
],
"organization_user_data_source_id": [
123
],
"embedding_generators": [
"OPENAI"
],
"root_files_only": true,
"include_all_children": false,
"non_synced_only": false,
"request_ids": [
"<string>"
],
"upload_ids": [
"<string>"
],
"sync_error_message": "<string>",
"include_containers": true,
"external_urls": [
"<string>"
],
"file_types_at_source": [
"TICKET"
]
},
"include_vectors": false
}'{
"results": [
{
"user_file_id": 123,
"chunk_index": 123,
"source_content": "<string>",
"embedding": [
123
],
"content_metadata": {}
}
],
"count": 123
}