carbon.auth.get_access_tokencarbon.auth.get_white_labelingcarbon.crm.get_accountcarbon.crm.get_accountscarbon.crm.get_contactcarbon.crm.get_contactscarbon.crm.get_leadcarbon.crm.get_leadscarbon.crm.get_opportunitiescarbon.crm.get_opportunitycarbon.data_sources.add_tagscarbon.data_sources.querycarbon.data_sources.query_user_data_sourcescarbon.data_sources.remove_tagscarbon.data_sources.revoke_access_tokencarbon.embeddings.get_documentscarbon.embeddings.get_embeddings_and_chunkscarbon.embeddings.listcarbon.embeddings.upload_chunks_and_embeddingscarbon.files.create_user_file_tagscarbon.files.delete_file_tagscarbon.files.delete_manycarbon.files.delete_v2carbon.files.get_parsed_filecarbon.files.get_raw_filecarbon.files.modify_cold_storage_parameterscarbon.files.move_to_hot_storagecarbon.files.query_user_filescarbon.files.query_user_files_deprecatedcarbon.files.resynccarbon.files.uploadcarbon.files.upload_from_urlcarbon.files.upload_textcarbon.github.get_issuecarbon.github.get_issuescarbon.github.get_prcarbon.github.get_pr_commentscarbon.github.get_pr_commitscarbon.github.get_pr_filescarbon.github.get_pull_requestscarbon.integrations.cancelcarbon.integrations.connect_data_sourcecarbon.integrations.connect_document360carbon.integrations.connect_freshdeskcarbon.integrations.connect_gitbookcarbon.integrations.connect_gurucarbon.integrations.create_aws_iam_usercarbon.integrations.get_oauth_urlcarbon.integrations.list_confluence_pagescarbon.integrations.list_conversationscarbon.integrations.list_data_source_itemscarbon.integrations.list_folderscarbon.integrations.list_gitbook_spacescarbon.integrations.list_labelscarbon.integrations.list_outlook_categoriescarbon.integrations.list_reposcarbon.integrations.list_sharepoint_sitescarbon.integrations.sync_azure_blob_filescarbon.integrations.sync_azure_blob_storagecarbon.integrations.sync_confluencecarbon.integrations.sync_data_source_itemscarbon.integrations.sync_filescarbon.integrations.sync_git_hubcarbon.integrations.sync_gitbookcarbon.integrations.sync_gmailcarbon.integrations.sync_outlookcarbon.integrations.sync_reposcarbon.integrations.sync_rss_feedcarbon.integrations.sync_s3_filescarbon.integrations.sync_slackcarbon.organizations.getcarbon.organizations.updatecarbon.organizations.update_statscarbon.users.deletecarbon.users.getcarbon.users.listcarbon.users.toggle_user_featurescarbon.users.update_userscarbon.users.who_am_icarbon.utilities.fetch_urlscarbon.utilities.fetch_webpagecarbon.utilities.fetch_youtube_transcriptscarbon.utilities.process_sitemapcarbon.utilities.scrape_sitemapcarbon.utilities.scrape_webcarbon.utilities.search_urlscarbon.utilities.user_webpagescarbon.webhooks.add_urlcarbon.webhooks.delete_urlcarbon.webhooks.urlscarbon.white_label.createcarbon.white_label.deletecarbon.white_label.listcarbon.white_label.updatePython >=3.7
pip install carbon-python-sdk==0.2.56
from carbon import Carbon
# 1) Get an access token for a customer
carbon = Carbon(
api_key="YOUR_API_KEY",
customer_id="YOUR_CUSTOMER_ID",
)
token = carbon.auth.get_access_token()
# 2) Use the access token to authenticate moving forward
carbon = Carbon(access_token=token.access_token)
# use SDK as usual
white_labeling = carbon.auth.get_white_labeling()
# etc.
async support is available by prepending a to any method.
import asyncio
from pprint import pprint
from carbon import Carbon, ApiException
carbon = Carbon(
access_token="YOUR_API_KEY",
api_key="YOUR_API_KEY",
customer_id="YOUR_API_KEY",
)
async def main():
try:
# Get Access Token
get_access_token_response = await carbon.auth.aget_access_token()
print(get_access_token_response)
except ApiException as e:
print("Exception when calling AuthApi.get_access_token: %s\n" % e)
pprint(e.body)
if e.status == 422:
pprint(e.body["detail"])
pprint(e.headers)
pprint(e.status)
pprint(e.reason)
pprint(e.round_trip_time)
asyncio.run(main())
To access raw HTTP response values, use the .raw namespace.
from pprint import pprint
from carbon import Carbon, ApiException
carbon = Carbon(
access_token="YOUR_API_KEY",
api_key="YOUR_API_KEY",
customer_id="YOUR_API_KEY",
)
try:
# Get Access Token
get_access_token_response = carbon.auth.raw.get_access_token()
pprint(get_access_token_response.body)
pprint(get_access_token_response.body["access_token"])
pprint(get_access_token_response.body["refresh_token"])
pprint(get_access_token_response.headers)
pprint(get_access_token_response.status)
pprint(get_access_token_response.round_trip_time)
except ApiException as e:
print("Exception when calling AuthApi.get_access_token: %s\n" % e)
pprint(e.body)
if e.status == 422:
pprint(e.body["detail"])
pprint(e.headers)
pprint(e.status)
pprint(e.reason)
pprint(e.round_trip_time)
carbon.auth.get_access_tokenGet Access Token
get_access_token_response = carbon.auth.get_access_token()
/auth/v1/access_token get
carbon.auth.get_white_labelingReturns whether or not the organization is white labeled and which integrations are white labeled
:param current_user: the current user :param db: the database session :return: a WhiteLabelingResponse
get_white_labeling_response = carbon.auth.get_white_labeling()
/auth/v1/white_labeling get
carbon.crm.get_accountGet Account
get_account_response = carbon.crm.get_account(
id="id_example",
data_source_id=1,
include_remote_data=False,
includes=["string_example"],
)
strintboolBaseIncludes]/integrations/data/crm/accounts/{id} get
carbon.crm.get_accountsGet Accounts
get_accounts_response = carbon.crm.get_accounts(
data_source_id=1,
include_remote_data=False,
next_cursor="string_example",
page_size=1,
order_dir="asc",
includes=[],
filters={},
order_by="created_at",
)
intboolOptional[str]Optional[int]OrderDirV2NullableBaseIncludes]AccountFiltersAccountsOrderByNullable/integrations/data/crm/accounts post
carbon.crm.get_contactGet Contact
get_contact_response = carbon.crm.get_contact(
id="id_example",
data_source_id=1,
include_remote_data=False,
includes=["string_example"],
)
strintboolBaseIncludes]/integrations/data/crm/contacts/{id} get
carbon.crm.get_contactsGet Contacts
get_contacts_response = carbon.crm.get_contacts(
data_source_id=1,
include_remote_data=False,
next_cursor="string_example",
page_size=1,
order_dir="asc",
includes=[],
filters={},
order_by="created_at",
)
intboolOptional[str]Optional[int]OrderDirV2NullableBaseIncludes]ContactFiltersContactsOrderByNullable/integrations/data/crm/contacts post
carbon.crm.get_leadGet Lead
get_lead_response = carbon.crm.get_lead(
id="id_example",
data_source_id=1,
include_remote_data=False,
includes=["string_example"],
)
strintboolBaseIncludes]/integrations/data/crm/leads/{id} get
carbon.crm.get_leadsGet Leads
get_leads_response = carbon.crm.get_leads(
data_source_id=1,
include_remote_data=False,
next_cursor="string_example",
page_size=1,
order_dir="asc",
includes=[],
filters={},
order_by="created_at",
)
intboolOptional[str]Optional[int]OrderDirV2NullableBaseIncludes]LeadFiltersLeadsOrderByNullable/integrations/data/crm/leads post
carbon.crm.get_opportunitiesGet Opportunities
get_opportunities_response = carbon.crm.get_opportunities(
data_source_id=1,
include_remote_data=False,
next_cursor="string_example",
page_size=1,
order_dir="asc",
includes=[],
filters={
"status": "WON",
},
order_by="created_at",
)
intboolOptional[str]Optional[int]OrderDirV2NullableBaseIncludes]OpportunityFiltersOpportunitiesOrderByNullable/integrations/data/crm/opportunities post
carbon.crm.get_opportunityGet Opportunity
get_opportunity_response = carbon.crm.get_opportunity(
id="id_example",
data_source_id=1,
include_remote_data=False,
includes=["string_example"],
)
strintboolBaseIncludes]/integrations/data/crm/opportunities/{id} get
carbon.data_sources.add_tagsAdd Data Source Tags
add_tags_response = carbon.data_sources.add_tags(
tags={},
data_source_id=1,
)
Dict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]int/data_sources/tags/add post
carbon.data_sources.queryData Sources
query_response = carbon.data_sources.query(
pagination={
"limit": 10,
"offset": 0,
"starting_id": 0,
},
order_by="created_at",
order_dir="desc",
filters={
"source": "GOOGLE_CLOUD_STORAGE",
},
)
PaginationOrganizationUserDataSourceOrderByColumnsOrderDirOrganizationUserDataSourceFiltersOrganizationUserDataSourceQueryInput
OrganizationUserDataSourceResponse
/data_sources post
carbon.data_sources.query_user_data_sourcesUser Data Sources
query_user_data_sources_response = carbon.data_sources.query_user_data_sources(
pagination={
"limit": 10,
"offset": 0,
"starting_id": 0,
},
order_by="created_at",
order_dir="desc",
filters={
"source": "GOOGLE_CLOUD_STORAGE",
},
)
PaginationOrganizationUserDataSourceOrderByColumnsOrderDirOrganizationUserDataSourceFiltersOrganizationUserDataSourceQueryInput
OrganizationUserDataSourceResponse
/user_data_sources post
carbon.data_sources.remove_tagsRemove Data Source Tags
remove_tags_response = carbon.data_sources.remove_tags(
data_source_id=1,
tags_to_remove=[],
remove_all_tags=False,
)
intRemoveDataSourceTagsInputTagsToRemovebool/data_sources/tags/remove post
carbon.data_sources.revoke_access_tokenRevoke Access Token
revoke_access_token_response = carbon.data_sources.revoke_access_token(
data_source_id=1,
)
int/revoke_access_token post
carbon.embeddings.get_documentsFor pre-filtering documents, using tags_v2 is preferred to using tags (which is now deprecated). If both tags_v2
and tags are specified, tags is ignored. tags_v2 enables
building complex filters through the use of "AND", "OR", and negation logic. Take the below input as an example:
{
"OR": [
{
"key": "subject",
"value": "holy-bible",
"negate": false
},
{
"key": "person-of-interest",
"value": "jesus christ",
"negate": false
},
{
"key": "genre",
"value": "religion",
"negate": true
}
{
"AND": [
{
"key": "subject",
"value": "tao-te-ching",
"negate": false
},
{
"key": "author",
"value": "lao-tzu",
"negate": false
}
]
}
]
}
In this case, files will be filtered such that:
Note that the top level of the query must be either an "OR" or "AND" array. Currently, nesting is limited to 3. For tag blocks (those with "key", "value", and "negate" keys), the following typing rules apply:
stringany or list[any]true or false. If present and true, then the filter block is negated in
the resulting query. It is false by default.When querying embeddings, you can optionally specify the media_type parameter in your request. By default (if
not set), it is equal to "TEXT". This means that the query will be performed over files that have
been parsed as text (for now, this covers all files except image files). If it is equal to "IMAGE",
the query will be performed over image files (for now, .jpg and .png files). You can think of this
field as an additional filter on top of any filters set in file_ids and
When hybrid_search is set to true, a combination of keyword search and semantic search are used to rank
and select candidate embeddings during information retrieval. By default, these search methods are weighted
equally during the ranking process. To adjust the weight (or "importance") of each search method, you can use
the hybrid_search_tuning_parameters property. The description for the different tuning parameters are:
weight_a: weight to assign to semantic searchweight_b: weight to assign to keyword searchYou must ensure that sum(weight_a, weight_b,..., weight_n) for all n weights is equal to 1. The equality
has an error tolerance of 0.001 to account for possible floating point issues.
In order to use hybrid search for a customer across a set of documents, two flags need to be enabled:
/modify_user_configuration endpoint to to enable sparse_vectors for the customer. The payload
body for this request is below:{
"configuration_key_name": "sparse_vectors",
"value": {
"enabled": true
}
}
/uploadfile endpoint, this can be done by setting the following query parameter: generate_sparse_vectors=trueCarbon supports multiple models for use in generating embeddings for files. For images, we support Vertex AI's
multimodal model; for text, we support OpenAI's text-embedding-ada-002 and Cohere's embed-multilingual-v3.0.
The model can be specified via the embedding_model parameter (in the POST body for /embeddings, and a query
parameter in /uploadfile). If no model is supplied, the text-embedding-ada-002 is used by default. When performing
embedding queries, embeddings from files that used the specified model will be considered in the query.
For example, if files A and B have embeddings generated with OPENAI, and files C and D have embeddings generated with
COHERE_MULTILINGUAL_V3, then by default, queries will only consider files A and B. If COHERE_MULTILINGUAL_V3 is
specified as the embedding_model in /embeddings, then only files C and D will be considered. Make sure that
the set of all files you want considered for a query have embeddings generated via the same model. For now, do not
set VERTEX_MULTIMODAL as an embedding_model. This model is used automatically by Carbon when it detects an image file.
get_documents_response = carbon.embeddings.get_documents(
query="a",
k=1,
tags={
"key": "string_example",
},
query_vector=[3.14],
file_ids=[1],
parent_file_ids=[1],
include_all_children=False,
tags_v2={},
include_tags=True,
include_vectors=True,
include_raw_file=True,
hybrid_search=True,
hybrid_search_tuning_parameters={
"weight_a": 0.5,
"weight_b": 0.5,
},
media_type="TEXT",
embedding_model="OPENAI",
include_file_level_metadata=False,
high_accuracy=False,
rerank={
"model": "model_example",
},
file_types_at_source=["string_example"],
exclude_cold_storage_files=False,
)
strQuery for which to get related chunks and embeddings.
intNumber of related chunks to return.
GetEmbeddingDocumentsBodyTagsGetEmbeddingDocumentsBodyQueryVectorGetEmbeddingDocumentsBodyFileIdsGetEmbeddingDocumentsBodyParentFileIdsboolFlag to control whether or not to include all children of filtered files in the embedding search.
Optional[Dict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]]A set of tags to limit the search to. Use this instead of tags, which is deprecated.
Optional[bool]Flag to control whether or not to include tags for each chunk in the response.
Optional[bool]Flag to control whether or not to include embedding vectors in the response.
Optional[bool]Flag to control whether or not to include a signed URL to the raw file containing each chunk in the response.
Optional[bool]Flag to control whether or not to perform hybrid search.
HybridSearchTuningParamsNullableFileContentTypesNullableEmbeddingGeneratorsNullableOptional[bool]Flag to control whether or not to include file-level metadata in the response. This metadata will be included in the content_metadata field of each document along with chunk/embedding level metadata.
Optional[bool]Flag to control whether or not to perform a high accuracy embedding search. By default, this is set to false. If true, the search may return more accurate results, but may take longer to complete.
RerankParamsNullableGetEmbeddingDocumentsBodyFileTypesAtSourceboolFlag to control whether or not to exclude files that are not in hot storage. If set to False, then an error will be returned if any filtered files are in cold storage.
/embeddings post
carbon.embeddings.get_embeddings_and_chunksRetrieve Embeddings And Content
get_embeddings_and_chunks_response = carbon.embeddings.get_embeddings_and_chunks(
filters={
"user_file_id": 1,
"embedding_model": "OPENAI",
},
pagination={
"limit": 10,
"offset": 0,
"starting_id": 0,
},
order_by="created_at",
order_dir="desc",
include_vectors=False,
)
EmbeddingsAndChunksFiltersPaginationEmbeddingsAndChunksOrderByColumnsOrderDirbool/text_chunks post
carbon.embeddings.listRetrieve Embeddings And Content V2
list_response = carbon.embeddings.list(
filters={
"include_all_children": False,
"non_synced_only": False,
},
pagination={
"limit": 10,
"offset": 0,
"starting_id": 0,
},
order_by="created_at",
order_dir="desc",
include_vectors=False,
)
OrganizationUserFilesToSyncFiltersPaginationOrganizationUserFilesToSyncOrderByTypesOrderDirboolEmbeddingsAndChunksQueryInputV2
/list_chunks_and_embeddings post
carbon.embeddings.upload_chunks_and_embeddingsUpload Chunks And Embeddings
upload_chunks_and_embeddings_response = carbon.embeddings.upload_chunks_and_embeddings(
embedding_model="OPENAI",
chunks_and_embeddings=[
{
"file_id": 1,
"chunks_and_embeddings": [
{
"chunk_number": 1,
"chunk": "chunk_example",
}
],
}
],
overwrite_existing=False,
chunks_only=False,
custom_credentials={
"key": {},
},
)
EmbeddingGeneratorsSingleChunksAndEmbeddingsUploadInput]boolboolChunksAndEmbeddingsUploadInputCustomCredentialsChunksAndEmbeddingsUploadInput
/upload_chunks_and_embeddings post
carbon.files.create_user_file_tagsA tag is a key-value pair that can be added to a file. This pair can then be used for searches (e.g. embedding searches) in order to narrow down the scope of the search. A file can have any number of tags. The following are reserved keys that cannot be used:
Carbon currently supports two data types for tag values - string and list<string>.
Keys can only be string. If values other than string and list<string> are used,
they're automatically converted to strings (e.g. 4 will become "4").
create_user_file_tags_response = carbon.files.create_user_file_tags(
tags={
"key": "string_example",
},
organization_user_file_id=1,
)
OrganizationUserFileTagCreateTagsint/create_user_file_tags post
carbon.files.delete_file_tagsDelete File Tags
delete_file_tags_response = carbon.files.delete_file_tags(
tags=["string_example"],
organization_user_file_id=1,
)
OrganizationUserFileTagsRemoveTagsintOrganizationUserFileTagsRemove
/delete_user_file_tags post
carbon.files.delete_manyDelete Files Endpoint
delete_many_response = carbon.files.delete_many(
file_ids=[1],
sync_statuses=["string_example"],
delete_non_synced_only=False,
send_webhook=False,
delete_child_files=False,
)
DeleteFilesQueryInputFileIdsExternalFileSyncStatuses]boolboolbool/delete_files post
carbon.files.delete_v2Delete Files V2 Endpoint
delete_v2_response = carbon.files.delete_v2(
filters={
"include_all_children": False,
"non_synced_only": False,
},
send_webhook=False,
preserve_file_record=False,
)
OrganizationUserFilesToSyncFiltersboolboolWhether or not to delete all data related to the file from the database, BUT to preserve the file metadata, allowing for resyncs. By default preserve_file_record is false, which means that all data related to the file as well as its metadata will be deleted. Note that even if preserve_file_record is true, raw files uploaded via the uploadfile endpoint still cannot be resynced.
/delete_files_v2 post
carbon.files.get_parsed_fileThis route is deprecated. Use /user_files_v2 instead.
get_parsed_file_response = carbon.files.get_parsed_file(
file_id=1,
)
int/parsed_file/{file_id} get
carbon.files.get_raw_fileThis route is deprecated. Use /user_files_v2 instead.
get_raw_file_response = carbon.files.get_raw_file(
file_id=1,
)
int/raw_file/{file_id} get
carbon.files.modify_cold_storage_parametersModify Cold Storage Parameters
modify_cold_storage_parameters_response = carbon.files.modify_cold_storage_parameters(
filters={
"include_all_children": False,
"non_synced_only": False,
},
enable_cold_storage=True,
hot_storage_time_to_live=1,
)
OrganizationUserFilesToSyncFiltersOptional[bool]Optional[int]ModifyColdStorageParametersQueryInput
/modify_cold_storage_parameters post
carbon.files.move_to_hot_storageMove To Hot Storage
move_to_hot_storage_response = carbon.files.move_to_hot_storage(
filters={
"include_all_children": False,
"non_synced_only": False,
},
)
OrganizationUserFilesToSyncFilters/move_to_hot_storage post
carbon.files.query_user_filesFor pre-filtering documents, using tags_v2 is preferred to using tags (which is now deprecated). If both tags_v2
and tags are specified, tags is ignored. tags_v2 enables
building complex filters through the use of "AND", "OR", and negation logic. Take the below input as an example:
{
"OR": [
{
"key": "subject",
"value": "holy-bible",
"negate": false
},
{
"key": "person-of-interest",
"value": "jesus christ",
"negate": false
},
{
"key": "genre",
"value": "religion",
"negate": true
}
{
"AND": [
{
"key": "subject",
"value": "tao-te-ching",
"negate": false
},
{
"key": "author",
"value": "lao-tzu",
"negate": false
}
]
}
]
}
In this case, files will be filtered such that:
Note that the top level of the query must be either an "OR" or "AND" array. Currently, nesting is limited to 3. For tag blocks (those with "key", "value", and "negate" keys), the following typing rules apply:
stringany or list[any]true or false. If present and true, then the filter block is negated in
the resulting query. It is false by default.query_user_files_response = carbon.files.query_user_files(
pagination={
"limit": 10,
"offset": 0,
"starting_id": 0,
},
order_by="created_at",
order_dir="desc",
filters={
"include_all_children": False,
"non_synced_only": False,
},
include_raw_file=True,
include_parsed_text_file=True,
include_additional_files=True,
presigned_url_expiry_time_seconds=3600,
)
PaginationOrganizationUserFilesToSyncOrderByTypesOrderDirOrganizationUserFilesToSyncFiltersOptional[bool]If true, the query will return presigned URLs for the raw file. Only relevant for the /user_files_v2 endpoint.
Optional[bool]If true, the query will return presigned URLs for the parsed text file. Only relevant for the /user_files_v2 endpoint.
Optional[bool]If true, the query will return presigned URLs for additional files. Only relevant for the /user_files_v2 endpoint.
intThe expiry time for the presigned URLs. Only relevant for the /user_files_v2 endpoint.
OrganizationUserFilesToSyncQueryInput
/user_files_v2 post
carbon.files.query_user_files_deprecatedThis route is deprecated. Use /user_files_v2 instead.
query_user_files_deprecated_response = carbon.files.query_user_files_deprecated(
pagination={
"limit": 10,
"offset": 0,
"starting_id": 0,
},
order_by="created_at",
order_dir="desc",
filters={
"include_all_children": False,
"non_synced_only": False,
},
include_raw_file=True,
include_parsed_text_file=True,
include_additional_files=True,
presigned_url_expiry_time_seconds=3600,
)
PaginationOrganizationUserFilesToSyncOrderByTypesOrderDirOrganizationUserFilesToSyncFiltersOptional[bool]If true, the query will return presigned URLs for the raw file. Only relevant for the /user_files_v2 endpoint.
Optional[bool]If true, the query will return presigned URLs for the parsed text file. Only relevant for the /user_files_v2 endpoint.
Optional[bool]If true, the query will return presigned URLs for additional files. Only relevant for the /user_files_v2 endpoint.
intThe expiry time for the presigned URLs. Only relevant for the /user_files_v2 endpoint.
OrganizationUserFilesToSyncQueryInput
FilesQueryUserFilesDeprecatedResponse
/user_files post
carbon.files.resyncResync File
resync_response = carbon.files.resync(
file_id=1,
chunk_size=1,
chunk_overlap=1,
force_embedding_generation=False,
skip_file_processing=False,
)
intOptional[int]Optional[int]boolOptional[bool]/resync_file post
carbon.files.uploadThis endpoint is used to directly upload local files to Carbon. The POST request should be a multipart form request.
Note that the set_page_as_boundary query parameter is applicable only to PDFs for now. When this value is set,
PDF chunks are at most one page long. Additional information can be retrieved for each chunk, however, namely the coordinates
of the bounding box around the chunk (this can be used for things like text highlighting). Following is a description
of all possible query parameters:
chunk_size: the chunk size (in tokens) applied when splitting the documentchunk_overlap: the chunk overlap (in tokens) applied when splitting the documentskip_embedding_generation: whether or not to skip the generation of chunks and embeddingsset_page_as_boundary: described aboveembedding_model: the model used to generate embeddings for the document chunksuse_ocr: whether or not to use OCR as a preprocessing step prior to generating chunks. Valid for PDFs, JPEGs, and PNGsgenerate_sparse_vectors: whether or not to generate sparse vectors for the file. Required for hybrid search.prepend_filename_to_chunks: whether or not to prepend the filename to the chunk textCarbon supports multiple models for use in generating embeddings for files. For images, we support Vertex AI's
multimodal model; for text, we support OpenAI's text-embedding-ada-002 and Cohere's embed-multilingual-v3.0.
The model can be specified via the embedding_model parameter (in the POST body for /embeddings, and a query
parameter in /uploadfile). If no model is supplied, the text-embedding-ada-002 is used by default. When performing
embedding queries, embeddings from files that used the specified model will be considered in the query.
For example, if files A and B have embeddings generated with OPENAI, and files C and D have embeddings generated with
COHERE_MULTILINGUAL_V3, then by default, queries will only consider files A and B. If COHERE_MULTILINGUAL_V3 is
specified as the embedding_model in /embeddings, then only files C and D will be considered. Make sure that
the set of all files you want considered for a query have embeddings generated via the same model. For now, do not
set VERTEX_MULTIMODAL as an embedding_model. This model is used automatically by Carbon when it detects an image file.
upload_response = carbon.files.upload(
file=open("/path/to/file", "rb"),
chunk_size=1,
chunk_overlap=1,
skip_embedding_generation=False,
set_page_as_boundary=False,
embedding_model="string_example",
use_ocr=False,
generate_sparse_vectors=False,
prepend_filename_to_chunks=False,
max_items_per_chunk=1,
parse_pdf_tables_with_ocr=False,
detect_audio_language=False,
transcription_service="assemblyai",
include_speaker_labels=False,
media_type="TEXT",
split_rows=False,
enable_cold_storage=False,
hot_storage_time_to_live=1,
generate_chunks_only=False,
store_file_only=False,
)
IOOptional[int]Chunk size in tiktoken tokens to be used when processing file.
Optional[int]Chunk overlap in tiktoken tokens to be used when processing file.
boolFlag to control whether or not embeddings should be generated and stored when processing file.
boolFlag to control whether or not to set the a page's worth of content as the maximum amount of content that can appear in a chunk. Only valid for PDFs. See description route description for more information.
TextEmbeddingGenerators, MultiModalEmbeddingGenerators]Embedding model that will be used to embed file chunks.
boolWhether or not to use OCR when processing files. Valid for PDFs, JPEGs, and PNGs. Useful for documents with tables, images, and/or scanned text.
boolWhether or not to generate sparse vectors for the file. This is required for the file to be a candidate for hybrid search.
boolWhether or not to prepend the file's name to chunks.
Optional[int]Number of objects per chunk. For csv, tsv, xlsx, and json files only.
boolWhether to use rich table parsing when use_ocr is enabled.
boolWhether to automatically detect the language of the uploaded audio file.
TranscriptionServiceNullableThe transcription service to use for audio files. If no service is specified, 'deepgram' will be used.
boolDetect multiple speakers and label segments of speech by speaker for audio files.
FileContentTypesNullableThe media type of the file. If not provided, it will be inferred from the file extension.
boolWhether to split tabular rows into chunks. Currently only valid for CSV, TSV, and XLSX files.
boolEnable cold storage for the file. If set to true, the file will be moved to cold storage after a certain period of inactivity. Default is false.
Optional[int]Time in days after which the file will be moved to cold storage. Must be one of [1, 3, 7, 14, 30].
boolIf this flag is enabled, the file will be chunked and stored with Carbon, but no embeddings will be generated. This overrides the skip_embedding_generation flag.
boolIf this flag is enabled, the file will be stored with Carbon, but no processing will be done.
BodyCreateUploadFileUploadfilePost
/uploadfile post
carbon.files.upload_from_urlCreate Upload File From Url
upload_from_url_response = carbon.files.upload_from_url(
url="string_example",
file_name="string_example",
chunk_size=1,
chunk_overlap=1,
skip_embedding_generation=False,
set_page_as_boundary=False,
embedding_model="OPENAI",
generate_sparse_vectors=False,
use_textract=False,
prepend_filename_to_chunks=False,
max_items_per_chunk=1,
parse_pdf_tables_with_ocr=False,
detect_audio_language=False,
transcription_service="assemblyai",
include_speaker_labels=False,
media_type="TEXT",
split_rows=False,
cold_storage_params={
"enable_cold_storage": False,
},
generate_chunks_only=False,
store_file_only=False,
)
strOptional[str]Optional[int]Optional[int]boolboolEmbeddingGeneratorsboolboolboolOptional[int]Number of objects per chunk. For csv, tsv, xlsx, and json files only.
boolboolTranscriptionServiceNullableboolFileContentTypesNullableboolColdStoragePropsboolIf this flag is enabled, the file will be chunked and stored with Carbon, but no embeddings will be generated. This overrides the skip_embedding_generation flag.
boolIf this flag is enabled, the file will be stored with Carbon, but no processing will be done.
/upload_file_from_url post
carbon.files.upload_textCarbon supports multiple models for use in generating embeddings for files. For images, we support Vertex AI's
multimodal model; for text, we support OpenAI's text-embedding-ada-002 and Cohere's embed-multilingual-v3.0.
The model can be specified via the embedding_model parameter (in the POST body for /embeddings, and a query
parameter in /uploadfile). If no model is supplied, the text-embedding-ada-002 is used by default. When performing
embedding queries, embeddings from files that used the specified model will be considered in the query.
For example, if files A and B have embeddings generated with OPENAI, and files C and D have embeddings generated with
COHERE_MULTILINGUAL_V3, then by default, queries will only consider files A and B. If COHERE_MULTILINGUAL_V3 is
specified as the embedding_model in /embeddings, then only files C and D will be considered. Make sure that
the set of all files you want considered for a query have embeddings generated via the same model. For now, do not
set VERTEX_MULTIMODAL as an embedding_model. This model is used automatically by Carbon when it detects an image file.
upload_text_response = carbon.files.upload_text(
contents="aaaaa",
name="string_example",
chunk_size=1,
chunk_overlap=1,
skip_embedding_generation=False,
overwrite_file_id=1,
embedding_model="OPENAI",
generate_sparse_vectors=False,
cold_storage_params={
"enable_cold_storage": False,
},
generate_chunks_only=False,
store_file_only=False,
)
strOptional[str]Optional[int]Optional[int]boolOptional[int]EmbeddingGeneratorsNullableOptional[bool]ColdStoragePropsboolIf this flag is enabled, the file will be chunked and stored with Carbon, but no embeddings will be generated. This overrides the skip_embedding_generation flag.
boolIf this flag is enabled, the file will be stored with Carbon, but no processing will be done.
/upload_text post
carbon.github.get_issueIssue
get_issue_response = carbon.github.get_issue(
issue_number=1,
include_remote_data=False,
data_source_id=1,
repository="string_example",
)
intboolintstr/integrations/data/github/issues/{issue_number} get
carbon.github.get_issuesIssues
get_issues_response = carbon.github.get_issues(
data_source_id=1,
repository="string_example",
include_remote_data=False,
page=1,
page_size=30,
next_cursor="string_example",
filters={
"state": "closed",
},
order_by="created",
order_dir="asc",
)
intstrFull name of the repository, denoted as {owner}/{repo}
boolintintOptional[str]IssuesFilterIssuesOrderByOrderDirV2Nullable/integrations/data/github/issues post
carbon.github.get_prGet Pr
get_pr_response = carbon.github.get_pr(
pull_number=1,
include_remote_data=False,
data_source_id=1,
repository="string_example",
)
intboolintstr/integrations/data/github/pull_requests/{pull_number} get
carbon.github.get_pr_commentsPr Comments
get_pr_comments_response = carbon.github.get_pr_comments(
data_source_id=1,
repository="string_example",
pull_number=1,
include_remote_data=False,
page=1,
page_size=30,
next_cursor="string_example",
order_by="created",
order_dir="asc",
)
intstrFull name of the repository, denoted as {owner}/{repo}
intboolintintOptional[str]CommentsOrderByOrderDirV2Nullable/integrations/data/github/pull_requests/comments post
carbon.github.get_pr_commitsPr Commits
get_pr_commits_response = carbon.github.get_pr_commits(
data_source_id=1,
repository="string_example",
pull_number=1,
include_remote_data=False,
page=1,
page_size=30,
next_cursor="string_example",
)
intstrFull name of the repository, denoted as {owner}/{repo}
intboolintintOptional[str]/integrations/data/github/pull_requests/commits post
carbon.github.get_pr_filesPr Files
get_pr_files_response = carbon.github.get_pr_files(
data_source_id=1,
repository="string_example",
pull_number=1,
include_remote_data=False,
page=1,
page_size=30,
next_cursor="string_example",
)
intstrFull name of the repository, denoted as {owner}/{repo}
intboolintintOptional[str]/integrations/data/github/pull_requests/files post
carbon.github.get_pull_requestsGet Prs
get_pull_requests_response = carbon.github.get_pull_requests(
data_source_id=1,
repository="string_example",
include_remote_data=False,
page=1,
page_size=30,
next_cursor="string_example",
filters={
"state": "closed",
},
order_by="created",
order_dir="asc",
)
intstrFull name of the repository, denoted as {owner}/{repo}
boolintintOptional[str]PullRequestFiltersPROrderByOrderDirV2Nullable/integrations/data/github/pull_requests post
carbon.integrations.cancelCancel Data Source Items Sync
cancel_response = carbon.integrations.cancel(
data_source_id=1,
)
int/integrations/items/sync/cancel post
carbon.integrations.connect_data_sourceConnect Data Source
connect_data_source_response = carbon.integrations.connect_data_source(
authentication={
"source": "GOOGLE_DRIVE",
"access_token": "access_token_example",
},
sync_options={
"chunk_size": 1500,
"chunk_overlap": 20,
"skip_embedding_generation": False,
"embedding_model": "OPENAI",
"generate_sparse_vectors": False,
"prepend_filename_to_chunks": False,
"sync_files_on_connection": True,
"set_page_as_boundary": False,
"enable_file_picker": True,
"sync_source_items": True,
"incremental_sync": False,
},
)
OAuthAuthentication, NotionAuthentication, OneDriveAuthentication, SharepointAuthentication, ConfluenceAuthentication, ZendeskAuthentication, ZoteroAuthentication, GitbookAuthetication, SalesforceAuthentication, FreskdeskAuthentication, S3Authentication, AzureBlobStorageAuthentication, GithubAuthentication, ServiceNowAuthentication, GuruAuthentication, GongAuthentication]SyncOptions/integrations/connect post
carbon.integrations.connect_document360You will need an access token to connect your Document360 account. To obtain an access token, follow the steps highlighted here https://apidocs.document360.com/apidocs/api-token.
connect_document360_response = carbon.integrations.connect_document360(
account_email="string_example",
access_token="string_example",
tags={},
chunk_size=1500,
chunk_overlap=20,
skip_embedding_generation=False,
embedding_model="OPENAI",
generate_sparse_vectors=False,
prepend_filename_to_chunks=False,
sync_files_on_connection=True,
request_id="string_example",
sync_source_items=True,
file_sync_config={
"auto_synced_source_types": ["ARTICLE"],
"sync_attachments": False,
"detect_audio_language": False,
"transcription_service": "assemblyai",
"include_speaker_labels": False,
"split_rows": False,
"generate_chunks_only": False,
"store_file_only": False,
"skip_file_processing": False,
"parsed_text_format": "PLAIN_TEXT",
},
data_source_tags={},
)
strThis email will be used to identify your carbon data source. It should have access to the Document360 account you wish to connect.
strOptional[Dict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]]Optional[int]Optional[int]Optional[bool]EmbeddingGeneratorsOptional[bool]Optional[bool]Optional[bool]Optional[str]boolEnabling this flag will fetch all available content from the source to be listed via list items endpoint
FileSyncConfigNullableDict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]Tags to be associated with the data source. If the data source already has tags set, then an upsert will be performed.
/integrations/document360 post
carbon.integrations.connect_freshdeskRefer this article to obtain an API key https://support.freshdesk.com/en/support/solutions/articles/215517. Make sure that your API key has the permission to read solutions from your account and you are on a paid plan. Once you have an API key, you can make a request to this endpoint along with your freshdesk domain. This will trigger an automatic sync of the articles in your "solutions" tab. Additional parameters below can be used to associate data with the synced articles or modify the sync behavior.
connect_freshdesk_response = carbon.integrations.connect_freshdesk(
domain="string_example",
api_key="string_example",
tags={},
chunk_size=1500,
chunk_overlap=20,
skip_embedding_generation=False,
embedding_model="OPENAI",
generate_sparse_vectors=False,
prepend_filename_to_chunks=False,
sync_files_on_connection=True,
request_id="string_example",
sync_source_items=True,
file_sync_config={
"auto_synced_source_types": ["ARTICLE"],
"sync_attachments": False,
"detect_audio_language": False,
"transcription_service": "assemblyai",
"include_speaker_labels": False,
"split_rows": False,
"generate_chunks_only": False,
"store_file_only": False,
"skip_file_processing": False,
"parsed_text_format": "PLAIN_TEXT",
},
data_source_tags={},
)
strstrOptional[Dict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]]Optional[int]Optional[int]Optional[bool]EmbeddingGeneratorsNullableOptional[bool]Optional[bool]Optional[bool]Optional[str]boolEnabling this flag will fetch all available content from the source to be listed via list items endpoint
FileSyncConfigNullableDict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]Tags to be associated with the data source. If the data source already has tags set, then an upsert will be performed.
/integrations/freshdesk post
carbon.integrations.connect_gitbookYou will need an access token to connect your Gitbook account. Note that the permissions will be defined by the user generating access token so make sure you have the permission to access spaces you will be syncing. Refer this article for more details https://developer.gitbook.com/gitbook-api/authentication. Additionally, you need to specify the name of organization you will be syncing data from.
connect_gitbook_response = carbon.integrations.connect_gitbook(
organization="string_example",
access_token="string_example",
tags={},
chunk_size=1500,
chunk_overlap=20,
skip_embedding_generation=False,
embedding_model="OPENAI",
generate_sparse_vectors=False,
prepend_filename_to_chunks=False,
sync_files_on_connection=True,
request_id="string_example",
sync_source_items=True,
file_sync_config={
"auto_synced_source_types": ["ARTICLE"],
"sync_attachments": False,
"detect_audio_language": False,
"transcription_service": "assemblyai",
"include_speaker_labels": False,
"split_rows": False,
"generate_chunks_only": False,
"store_file_only": False,
"skip_file_processing": False,
"parsed_text_format": "PLAIN_TEXT",
},
data_source_tags={},
)
strstrOptional[Dict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]]Optional[int]Optional[int]Optional[bool]EmbeddingGeneratorsOptional[bool]Optional[bool]Optional[bool]Optional[str]boolEnabling this flag will fetch all available content from the source to be listed via list items endpoint
FileSyncConfigNullableDict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]Tags to be associated with the data source. If the data source already has tags set, then an upsert will be performed.
/integrations/gitbook post
carbon.integrations.connect_guruYou will need an access token to connect your Guru account. To obtain an access token, follow the steps highlighted here https://help.getguru.com/docs/gurus-api#obtaining-a-user-token. The username should be your Guru username.
connect_guru_response = carbon.integrations.connect_guru(
username="string_example",
access_token="string_example",
tags={},
chunk_size=1500,
chunk_overlap=20,
skip_embedding_generation=False,
embedding_model="OPENAI",
generate_sparse_vectors=False,
prepend_filename_to_chunks=False,
sync_files_on_connection=True,
request_id="string_example",
sync_source_items=True,
file_sync_config={
"auto_synced_source_types": ["ARTICLE"],
"sync_attachments": False,
"detect_audio_language": False,
"transcription_service": "assemblyai",
"include_speaker_labels": False,
"split_rows": False,
"generate_chunks_only": False,
"store_file_only": False,
"skip_file_processing": False,
"parsed_text_format": "PLAIN_TEXT",
},
data_source_tags={},
)
strstrOptional[Dict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]]Optional[int]Optional[int]Optional[bool]EmbeddingGeneratorsOptional[bool]Optional[bool]Optional[bool]Optional[str]boolEnabling this flag will fetch all available content from the source to be listed via list items endpoint
FileSyncConfigNullableDict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]Tags to be associated with the data source. If the data source already has tags set, then an upsert will be performed.
/integrations/guru post
carbon.integrations.create_aws_iam_userThis endpoint can be used to connect S3 as well as Digital Ocean Spaces (S3 compatible)
For S3, create a new IAM user with permissions to:
create_aws_iam_user_response = carbon.integrations.create_aws_iam_user(
access_key="string_example",
access_key_secret="string_example",
sync_source_items=True,
endpoint_url="string_example",
data_source_tags={},
)
strstrboolEnabling this flag will fetch all available content from the source to be listed via list items endpoint
Optional[str]You can specify a Digital Ocean endpoint URL to connect a Digital Ocean Space through this endpoint. The URL should be of format .digitaloceanspaces.com. It's not required for S3 buckets.
Dict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]Tags to be associated with the data source. If the data source already has tags set, then an upsert will be performed.
/integrations/s3 post
carbon.integrations.get_oauth_urlThis endpoint can be used to generate the following URLs
get_oauth_url_response = carbon.integrations.get_oauth_url(
service="BOX",
tags=None,
scope="string_example",
scopes=[],
chunk_size=1500,
chunk_overlap=20,
skip_embedding_generation=False,
embedding_model="OPENAI",
zendesk_subdomain="string_example",
microsoft_tenant="string_example",
sharepoint_site_name="string_example",
confluence_subdomain="string_example",
generate_sparse_vectors=False,
prepend_filename_to_chunks=False,
max_items_per_chunk=1,
salesforce_domain="string_example",
sync_files_on_connection=True,
set_page_as_boundary=False,
data_source_id=1,
connecting_new_account=False,
request_id="string_example",
use_ocr=False,
parse_pdf_tables_with_ocr=False,
enable_file_picker=True,
sync_source_items=True,
incremental_sync=False,
file_sync_config={
"auto_synced_source_types": ["ARTICLE"],
"sync_attachments": False,
"detect_audio_language": False,
"transcription_service": "assemblyai",
"include_speaker_labels": False,
"split_rows": False,
"generate_chunks_only": False,
"store_file_only": False,
"skip_file_processing": False,
"parsed_text_format": "PLAIN_TEXT",
},
automatically_open_file_picker=True,
gong_account_email="string_example",
servicenow_credentials={
"instance_subdomain": "instance_subdomain_example",
"client_id": "client_id_example",
"client_secret": "client_secret_example",
"redirect_uri": "redirect_uri_example",
},
data_source_tags={},
)
OauthBasedConnectorsUnion[bool, date, datetime, dict, float, int, list, str, None]Optional[str]OAuthURLRequestScopesOptional[int]Optional[int]Optional[bool]EmbeddingGeneratorsNullableOptional[str]Optional[str]Optional[str]Optional[str]Optional[bool]Optional[bool]Optional[int]Number of objects per chunk. For csv, tsv, xlsx, and json files only.
Optional[str]Optional[bool]Used to specify whether Carbon should attempt to sync all your files automatically when authorization is complete. This is only supported for a subset of connectors and will be ignored for the rest. Supported connectors: Intercom, Zendesk, Gitbook, Confluence, Salesforce, Freshdesk
boolOptional[int]Used to specify a data source to sync from if you have multiple connected. It can be skipped if you only have one data source of that type connected or are connecting a new account.
Optional[bool]Used to connect a new data source. If not specified, we will attempt to create a sync URL for an existing data source based on type and ID.
Optional[str]This request id will be added to all files that get synced using the generated OAuth URL
Optional[bool]Enable OCR for files that support it. Supported formats: pdf, png, jpg
Optional[bool]boolEnable integration's file picker for sources that support it. Supported sources: BOX, DROPBOX, GOOGLE_DRIVE, ONEDRIVE, SHAREPOINT
boolEnabling this flag will fetch all available content from the source to be listed via list items endpoint
boolOnly sync files if they have not already been synced or if the embedding properties have changed. This flag is currently supported by ONEDRIVE, GOOGLE_DRIVE, BOX, DROPBOX, INTERCOM, GMAIL, OUTLOOK, ZENDESK, CONFLUENCE, NOTION, SHAREPOINT, SERVICENOW. It will be ignored for other data sources.
FileSyncConfigNullableOptional[bool]Automatically open source file picker after the OAuth flow is complete. This flag is currently supported by BOX, DROPBOX, GOOGLE_DRIVE, ONEDRIVE, SHAREPOINT. It will be ignored for other data sources.
Optional[str]If you are connecting a Gong account, you need to input the email of the account you wish to connect. This email will be used to identify your carbon data source.
ServiceNowCredentialsNullableDict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]Tags to be associated with the data source. If the data source already has tags set, then an upsert will be performed.
/integrations/oauth_url post
carbon.integrations.list_confluence_pagesThis endpoint has been deprecated. Use /integrations/items/list instead.
To begin listing a user's Confluence pages, at least a data_source_id of a connected
Confluence account must be specified. This base request returns a list of root pages for
every space the user has access to in a Confluence instance. To traverse further down
the user's page directory, additional requests to this endpoint can be made with the same
data_source_id and with parent_id set to the id of page from a previous request. For
convenience, the has_children property in each directory item in the response list will
flag which pages will return non-empty lists of pages when set as the parent_id.
list_confluence_pages_response = carbon.integrations.list_confluence_pages(
data_source_id=1,
parent_id="string_example",
)
intOptional[str]/integrations/confluence/list post
carbon.integrations.list_conversationsList all of your public and private channels, DMs, and Group DMs. The ID from response
can be used as a filter to sync messages to Carbon
types: Comma separated list of types. Available types are im (DMs), mpim (group DMs), public_channel, and private_channel.
Defaults to public_channel.
cursor: Used for pagination. If next_cursor is returned in response, you need to pass it as the cursor in the next request
data_source_id: Data source needs to be specified if you have linked multiple slack accounts
exclude_archived: Should archived conversations be excluded, defaults to true
list_conversations_response = carbon.integrations.list_conversations(
types="public_channel",
cursor="string_example",
data_source_id=1,
exclude_archived=True,
)
strOptional[str]Optional[int]bool/integrations/slack/conversations get
carbon.integrations.list_data_source_itemsList Data Source Items
list_data_source_items_response = carbon.integrations.list_data_source_items(
data_source_id=1,
parent_id="string_example",
filters={},
pagination={
"limit": 10,
"offset": 0,
"starting_id": 0,
},
order_by="name",
order_dir="asc",
)
intOptional[str]ListItemsFiltersNullablePaginationExternalSourceItemsOrderByOrderDirV2/integrations/items/list post
carbon.integrations.list_foldersAfter connecting your Outlook account, you can use this endpoint to list all of your folders on outlook. This includes both system folders like "inbox" and user created folders.
list_folders_response = carbon.integrations.list_folders(
data_source_id=1,
)
Optional[int]/integrations/outlook/user_folders get
carbon.integrations.list_gitbook_spacesAfter connecting your Gitbook account, you can use this endpoint to list all of your spaces under current organization.
list_gitbook_spaces_response = carbon.integrations.list_gitbook_spaces(
data_source_id=1,
)
int/integrations/gitbook/spaces get
carbon.integrations.list_labelsAfter connecting your Gmail account, you can use this endpoint to list all of your labels. User created labels will have the type "user" and Gmail's default labels will have the type "system"
list_labels_response = carbon.integrations.list_labels(
data_source_id=1,
)
Optional[int]/integrations/gmail/user_labels get
carbon.integrations.list_outlook_categoriesAfter connecting your Outlook account, you can use this endpoint to list all of your categories on outlook. We currently support listing up to 250 categories.
list_outlook_categories_response = carbon.integrations.list_outlook_categories(
data_source_id=1,
)
Optional[int]/integrations/outlook/user_categories get
carbon.integrations.list_reposOnce you have connected your GitHub account, you can use this endpoint to list the repositories your account has access to. You can use a data source ID or username to fetch from a specific account.
list_repos_response = carbon.integrations.list_repos(
per_page=30,
page=1,
data_source_id=1,
)
intintOptional[int]/integrations/github/repos get
carbon.integrations.list_sharepoint_sitesList all Sharepoint sites in the connected tenant. The site names from the response can be used as the site name when connecting a Sharepoint site. If site name is null in the response, then site name should be left null when connecting to the site.
This endpoint requires an additional Sharepoint scope: "Sites.Read.All". Include this scope along with the default Sharepoint scopes to list Sharepoint sites, connect to a site, and finally sync files from the site. The default Sharepoint scopes are: [o, p, e, n, i, d, , o, f, f, l, i, n, e, _, a, c, c, e, s, s, , U, s, e, r, ., R, e, a, d, , F, i, l, e, s, ., R, e, a, d, ., A, l, l].
data_soure_id: Data source needs to be specified if you have linked multiple Sharepoint accounts cursor: Used for pagination. If next_cursor is returned in response, you need to pass it as the cursor in the next request
list_sharepoint_sites_response = carbon.integrations.list_sharepoint_sites(
data_source_id=1,
cursor="string_example",
)
Optional[int]Optional[str]/integrations/sharepoint/sites/list get
carbon.integrations.sync_azure_blob_filesAfter optionally loading the items via /integrations/items/sync and integrations/items/list, use the container name and file name as the ID in this endpoint to sync them into Carbon. Additional parameters below can associate data with the selected items or modify the sync behavior
sync_azure_blob_files_response = carbon.integrations.sync_azure_blob_files(
ids=[{}],
tags={},
chunk_size=1500,
chunk_overlap=20,
skip_embedding_generation=False,
embedding_model="OPENAI",
generate_sparse_vectors=False,
prepend_filename_to_chunks=False,
max_items_per_chunk=1,
set_page_as_boundary=False,
data_source_id=1,
request_id="string_example",
use_ocr=False,
parse_pdf_tables_with_ocr=False,
file_sync_config={
"auto_synced_source_types": ["ARTICLE"],
"sync_attachments": False,
"detect_audio_language": False,
"transcription_service": "assemblyai",
"include_speaker_labels": False,
"split_rows": False,
"generate_chunks_only": False,
"store_file_only": False,
"skip_file_processing": False,
"parsed_text_format": "PLAIN_TEXT",
},
)
AzureBlobGetFileInput]Optional[Dict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]]Optional[int]Optional[int]Optional[bool]EmbeddingGeneratorsOptional[bool]Optional[bool]Optional[int]Number of objects per chunk. For csv, tsv, xlsx, and json files only.
boolOptional[int]Optional[str]Optional[bool]Optional[bool]FileSyncConfigNullable/integrations/azure_blob_storage/files post
carbon.integrations.sync_azure_blob_storageThis endpoint can be used to connect Azure Blob Storage.
For Azure Blob Storage, follow these steps:
Once created, provide us with the following details to generate the connection URL:
sync_azure_blob_storage_response = carbon.integrations.sync_azure_blob_storage(
account_name="string_example",
account_key="string_example",
sync_source_items=True,
data_source_tags={},
)
strstrboolDict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]Tags to be associated with the data source. If the data source already has tags set, then an upsert will be performed.
/integrations/azure_blob_storage post
carbon.integrations.sync_confluenceThis endpoint has been deprecated. Use /integrations/files/sync instead.
After listing pages in a user's Confluence account, the set of selected page ids and the
connected account's data_source_id can be passed into this endpoint to sync them into
Carbon. Additional parameters listed below can be used to associate data to the selected
pages or alter the behavior of the sync.
sync_confluence_response = carbon.integrations.sync_confluence(
data_source_id=1,
ids=["string_example"],
tags={},
chunk_size=1500,
chunk_overlap=20,
skip_embedding_generation=False,
embedding_model="OPENAI",
generate_sparse_vectors=False,
prepend_filename_to_chunks=False,
max_items_per_chunk=1,
set_page_as_boundary=False,
request_id="string_example",
use_ocr=False,
parse_pdf_tables_with_ocr=False,
incremental_sync=False,
file_sync_config={
"auto_synced_source_types": ["ARTICLE"],
"sync_attachments": False,
"detect_audio_language": False,
"transcription_service": "assemblyai",
"include_speaker_labels": False,
"split_rows": False,
"generate_chunks_only": False,
"store_file_only": False,
"skip_file_processing": False,
"parsed_text_format": "PLAIN_TEXT",
},
)
intList[str], List[SyncFilesIds]]Optional[Dict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]]Optional[int]Optional[int]Optional[bool]EmbeddingGeneratorsNullableOptional[bool]Optional[bool]Optional[int]Number of objects per chunk. For csv, tsv, xlsx, and json files only.
boolOptional[str]Optional[bool]Optional[bool]boolOnly sync files if they have not already been synced or if the embedding properties have changed. This flag is currently supported by ONEDRIVE, GOOGLE_DRIVE, BOX, DROPBOX, INTERCOM, GMAIL, OUTLOOK, ZENDESK, CONFLUENCE, NOTION, SHAREPOINT, SERVICENOW. It will be ignored for other data sources.
FileSyncConfigNullable/integrations/confluence/sync post
carbon.integrations.sync_data_source_itemsSync Data Source Items
sync_data_source_items_response = carbon.integrations.sync_data_source_items(
data_source_id=1,
)
int/integrations/items/sync post
carbon.integrations.sync_filesAfter listing files and folders via /integrations/items/sync and integrations/items/list, use the selected items' external ids as the ids in this endpoint to sync them into Carbon. Sharepoint items take an additional parameter root_id, which identifies the drive the file or folder is in and is stored in root_external_id. That additional paramter is optional and excluding it will tell the sync to assume the item is stored in the default Documents drive.
sync_files_response = carbon.integrations.sync_files(
data_source_id=1,
ids=["string_example"],
tags={},
chunk_size=1500,
chunk_overlap=20,
skip_embedding_generation=False,
embedding_model="OPENAI",
generate_sparse_vectors=False,
prepend_filename_to_chunks=False,
max_items_per_chunk=1,
set_page_as_boundary=False,
request_id="string_example",
use_ocr=False,
parse_pdf_tables_with_ocr=False,
incremental_sync=False,
file_sync_config={
"auto_synced_source_types": ["ARTICLE"],
"sync_attachments": False,
"detect_audio_language": False,
"transcription_service": "assemblyai",
"include_speaker_labels": False,
"split_rows": False,
"generate_chunks_only": False,
"store_file_only": False,
"skip_file_processing": False,
"parsed_text_format": "PLAIN_TEXT",
},
)
intList[str], List[SyncFilesIds]]Optional[Dict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]]Optional[int]Optional[int]Optional[bool]EmbeddingGeneratorsNullableOptional[bool]Optional[bool]Optional[int]Number of objects per chunk. For csv, tsv, xlsx, and json files only.
boolOptional[str]Optional[bool]Optional[bool]boolOnly sync files if they have not already been synced or if the embedding properties have changed. This flag is currently supported by ONEDRIVE, GOOGLE_DRIVE, BOX, DROPBOX, INTERCOM, GMAIL, OUTLOOK, ZENDESK, CONFLUENCE, NOTION, SHAREPOINT, SERVICENOW. It will be ignored for other data sources.
FileSyncConfigNullable/integrations/files/sync post
carbon.integrations.sync_git_hubRefer this article to obtain an access token https://docs.github.com/en/authentication/keeping-your-account-and-data-secure/managing-your-personal-access-tokens. Make sure that your access token has the permission to read content from your desired repos. Note that if your access token expires you will need to manually update it through this endpoint.
sync_git_hub_response = carbon.integrations.sync_git_hub(
username="string_example",
access_token="string_example",
sync_source_items=False,
data_source_tags={},
)
strstrboolEnabling this flag will fetch all available content from the source to be listed via list items endpoint
Dict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]Tags to be associated with the data source. If the data source already has tags set, then an upsert will be performed.
/integrations/github post
carbon.integrations.sync_gitbookYou can sync upto 20 Gitbook spaces at a time using this endpoint. Additional parameters below can be used to associate data with the synced pages or modify the sync behavior.
sync_gitbook_response = carbon.integrations.sync_gitbook(
space_ids=["string_example"],
data_source_id=1,
tags={},
chunk_size=1500,
chunk_overlap=20,
skip_embedding_generation=False,
embedding_model="OPENAI",
generate_sparse_vectors=False,
prepend_filename_to_chunks=False,
request_id="string_example",
file_sync_config={
"auto_synced_source_types": ["ARTICLE"],
"sync_attachments": False,
"detect_audio_language": False,
"transcription_service": "assemblyai",
"include_speaker_labels": False,
"split_rows": False,
"generate_chunks_only": False,
"store_file_only": False,
"skip_file_processing": False,
"parsed_text_format": "PLAIN_TEXT",
},
)
GitbookSyncRequestSpaceIdsintOptional[Dict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]]Optional[int]Optional[int]Optional[bool]EmbeddingGeneratorsOptional[bool]Optional[bool]Optional[str]FileSyncConfigNullable/integrations/gitbook/sync post
carbon.integrations.sync_gmailOnce you have successfully connected your gmail account, you can choose which emails to sync with us using the filters parameter. Filters is a JSON object with key value pairs. It also supports AND and OR operations. For now, we support a limited set of keys listed below.
label: Inbuilt Gmail labels, for example "Important" or a custom label you created.
after or before: A date in YYYY/mm/dd format (example 2023/12/31). Gets emails after/before a certain date.
You can also use them in combination to get emails from a certain period.
is: Can have the following values - starred, important, snoozed, and unread
from: Email address of the sender
to: Email address of the recipient
in: Can have the following values - sent (sync emails sent by the user)
has: Can have the following values - attachment (sync emails that have attachments)
Using keys or values outside of the specified values can lead to unexpected behaviour.
An example of a basic query with filters can be
{
"filters": {
"key": "label",
"value": "Test"
}
}
Which will list all emails that have the label "Test".
You can use AND and OR operation in the following way:
{
"filters": {
"AND": [
{
"key": "after",
"value": "2024/01/07"
},
{
"OR": [
{
"key": "label",
"value": "Personal"
},
{
"key": "is",
"value": "starred"
}
]
}
]
}
}
This will return emails after 7th of Jan that are either starred or have the label "Personal". Note that this is the highest level of nesting we support, i.e. you can't add more AND/OR filters within the OR filter in the above example.
sync_gmail_response = carbon.integrations.sync_gmail(
filters={},
tags={},
chunk_size=1500,
chunk_overlap=20,
skip_embedding_generation=False,
embedding_model="OPENAI",
generate_sparse_vectors=False,
prepend_filename_to_chunks=False,
data_source_id=1,
request_id="string_example",
sync_attachments=False,
file_sync_config={
"auto_synced_source_types": ["ARTICLE"],
"sync_attachments": False,
"detect_audio_language": False,
"transcription_service": "assemblyai",
"include_speaker_labels": False,
"split_rows": False,
"generate_chunks_only": False,
"store_file_only": False,
"skip_file_processing": False,
"parsed_text_format": "PLAIN_TEXT",
},
incremental_sync=False,
)
Dict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]Optional[Dict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]]Optional[int]Optional[int]Optional[bool]EmbeddingGeneratorsOptional[bool]Optional[bool]Optional[int]Optional[str]Optional[bool]FileSyncConfigNullablebool/integrations/gmail/sync post
carbon.integrations.sync_outlookOnce you have successfully connected your Outlook account, you can choose which emails to sync with us
using the filters and folder parameter. "folder" should be the folder you want to sync from Outlook. By default
we get messages from your inbox folder.
Filters is a JSON object with key value pairs. It also supports AND and OR operations.
For now, we support a limited set of keys listed below.
category: Custom categories that you created in Outlook.
after or before: A date in YYYY/mm/dd format (example 2023/12/31). Gets emails after/before a certain date. You can also use them in combination to get emails from a certain period.
is: Can have the following values: flagged
from: Email address of the sender
An example of a basic query with filters can be
{
"filters": {
"key": "category",
"value": "Test"
}
}
Which will list all emails that have the category "Test".
Specifying a custom folder in the same query
{
"folder": "Folder Name",
"filters": {
"key": "category",
"value": "Test"
}
}
You can use AND and OR operation in the following way:
{
"filters": {
"AND": [
{
"key": "after",
"value": "2024/01/07"
},
{
"OR": [
{
"key": "category",
"value": "Personal"
},
{
"key": "category",
"value": "Test"
},
]
}
]
}
}
This will return emails after 7th of Jan that have either Personal or Test as category. Note that this is the highest level of nesting we support, i.e. you can't add more AND/OR filters within the OR filter in the above example.
sync_outlook_response = carbon.integrations.sync_outlook(
filters={},
tags={},
folder="Inbox",
chunk_size=1500,
chunk_overlap=20,
skip_embedding_generation=False,
embedding_model="OPENAI",
generate_sparse_vectors=False,
prepend_filename_to_chunks=False,
data_source_id=1,
request_id="string_example",
sync_attachments=False,
file_sync_config={
"auto_synced_source_types": ["ARTICLE"],
"sync_attachments": False,
"detect_audio_language": False,
"transcription_service": "assemblyai",
"include_speaker_labels": False,
"split_rows": False,
"generate_chunks_only": False,
"store_file_only": False,
"skip_file_processing": False,
"parsed_text_format": "PLAIN_TEXT",
},
incremental_sync=False,
)
Dict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]Optional[Dict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]]Optional[str]Optional[int]Optional[int]Optional[bool]EmbeddingGeneratorsOptional[bool]Optional[bool]Optional[int]Optional[str]Optional[bool]FileSyncConfigNullablebool/integrations/outlook/sync post
carbon.integrations.sync_reposYou can retreive repos your token has access to using /integrations/github/repos and sync their content. You can also pass full name of any public repository (username/repo-name). This will store the repo content with carbon which can be accessed through /integrations/items/list endpoint. Maximum of 25 repositories are accepted per request.
sync_repos_response = carbon.integrations.sync_repos(
repos=["string_example"],
data_source_id=1,
)
GithubFetchReposRequestReposOptional[int]/integrations/github/sync_repos post
carbon.integrations.sync_rss_feedRss Feed
sync_rss_feed_response = carbon.integrations.sync_rss_feed(
url="string_example",
tags={},
chunk_size=1500,
chunk_overlap=20,
skip_embedding_generation=False,
embedding_model="OPENAI",
generate_sparse_vectors=False,
prepend_filename_to_chunks=False,
request_id="string_example",
data_source_tags={},
)
strOptional[Dict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]]Optional[int]Optional[int]Optional[bool]EmbeddingGeneratorsOptional[bool]Optional[bool]Optional[str]Dict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]Tags to be associated with the data source. If the data source already has tags set, then an upsert will be performed.
/integrations/rss_feed post
carbon.integrations.sync_s3_filesAfter optionally loading the items via /integrations/items/sync and integrations/items/list, use the bucket name and object key as the ID in this endpoint to sync them into Carbon. Additional parameters below can associate data with the selected items or modify the sync behavior
sync_s3_files_response = carbon.integrations.sync_s3_files(
ids=[{}],
tags={},
chunk_size=1500,
chunk_overlap=20,
skip_embedding_generation=False,
embedding_model="OPENAI",
generate_sparse_vectors=False,
prepend_filename_to_chunks=False,
max_items_per_chunk=1,
set_page_as_boundary=False,
data_source_id=1,
request_id="string_example",
use_ocr=False,
parse_pdf_tables_with_ocr=False,
file_sync_config={
"auto_synced_source_types": ["ARTICLE"],
"sync_attachments": False,
"detect_audio_language": False,
"transcription_service": "assemblyai",
"include_speaker_labels": False,
"split_rows": False,
"generate_chunks_only": False,
"store_file_only": False,
"skip_file_processing": False,
"parsed_text_format": "PLAIN_TEXT",
},
)
S3GetFileInput]Each input should be one of the following: A bucket name, a bucket name and a prefix, or a bucket name and an object key. A prefix is the common path for all objects you want to sync. Paths should end with a forward slash.
Optional[Dict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]]Optional[int]Optional[int]Optional[bool]EmbeddingGeneratorsOptional[bool]Optional[bool]Optional[int]Number of objects per chunk. For csv, tsv, xlsx, and json files only.
boolOptional[int]Optional[str]Optional[bool]Optional[bool]FileSyncConfigNullable/integrations/s3/files post
carbon.integrations.sync_slackYou can list all conversations using the endpoint /integrations/slack/conversations. The ID of conversation will be used as an input for this endpoint with timestamps as optional filters.
sync_slack_response = carbon.integrations.sync_slack(
filters={
"conversation_id": "conversation_id_example",
},
tags={},
chunk_size=1500,
chunk_overlap=20,
skip_embedding_generation=False,
embedding_model="OPENAI",
generate_sparse_vectors=False,
prepend_filename_to_chunks=False,
data_source_id=1,
request_id="string_example",
)
SlackFiltersOptional[Dict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]]Optional[int]Optional[int]Optional[bool]EmbeddingGeneratorsOptional[bool]Optional[bool]Optional[int]Optional[str]/integrations/slack/sync post
carbon.organizations.getGet Organization
get_response = carbon.organizations.get()
/organization get
carbon.organizations.updateUpdate Organization
update_response = carbon.organizations.update(
global_user_config={},
data_source_configs={
"key": {
"allowed_file_formats": [],
},
},
)
UserConfigurationNullableUpdateOrganizationInputDataSourceConfigs/organization/update post
carbon.organizations.update_statsUse this endpoint to reaggregate the statistics for an organization, for example aggregate_file_size. The reaggregation process is asyncronous so a webhook will be sent with the event type being FILE_STATISTICS_AGGREGATED to notify when the process is complee. After this aggregation is complete, the updated statistics can be retrieved using the /organization endpoint. The response of /organization willalso contain a timestamp of the last time the statistics were reaggregated.
update_stats_response = carbon.organizations.update_stats()
/organization/statistics post
carbon.users.deleteDelete Users
delete_response = carbon.users.delete(
customer_ids=["string_example"],
)
DeleteUsersInputCustomerIds/delete_users post
carbon.users.getUser Endpoint
get_response = carbon.users.get(
customer_id="string_example",
)
str/user post
carbon.users.listList users within an organization
list_response = carbon.users.list(
pagination={
"limit": 10,
"offset": 0,
"starting_id": 0,
},
filters={},
order_by="created_at",
order_dir="asc",
include_count=False,
)
PaginationListUsersFiltersListUsersOrderByTypesOrderDirV2bool/list_users post
carbon.users.toggle_user_featuresToggle User Features
toggle_user_features_response = carbon.users.toggle_user_features(
configuration_key_name="sparse_vectors",
value={},
)
ConfigurationKeysDict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]/modify_user_configuration post
carbon.users.update_usersUpdate Users
update_users_response = carbon.users.update_users(
customer_ids=["string_example"],
auto_sync_enabled_sources=["string_example"],
max_files=-1,
max_files_per_upload=-1,
max_characters=-1,
max_characters_per_file=-1,
max_characters_per_upload=-1,
auto_sync_interval=-1,
)
UpdateUsersInputCustomerIdsDataSourceType], DataSourceExtendedInput]List of data source types to enable auto sync for. Empty array will remove all sources and the string \"ALL\" will enable it for all data sources
Optional[int]Custom file upload limit for the user over all user's files across all uploads. If set, then the user will not be allowed to upload more files than this limit. If not set, or if set to -1, then the user will have no limit.
Optional[int]Custom file upload limit for the user across a single upload. If set, then the user will not be allowed to upload more files than this limit in a single upload. If not set, or if set to -1, then the user will have no limit.
Optional[int]Custom character upload limit for the user over all user's files across all uploads. If set, then the user will not be allowed to upload more characters than this limit. If not set, or if set to -1, then the user will have no limit.
Optional[int]A single file upload from the user can not exceed this character limit. If set, then the file will not be synced if it exceeds this limit. If not set, or if set to -1, then the user will have no limit.
Optional[int]Custom character upload limit for the user across a single upload. If set, then the user won't be able to sync more than this many characters in one upload. If not set, or if set to -1, then the user will have no limit.
Optional[int]The interval in hours at which the user's data sources should be synced. If not set or set to -1, the user will be synced at the organization level interval or default interval if that is also not set. Must be one of [3, 6, 12, 24]
/update_users post
carbon.users.who_am_iMe Endpoint
who_am_i_response = carbon.users.who_am_i()
/whoami get
carbon.utilities.fetch_urlsExtracts all URLs from a webpage.
Args: url (str): URL of the webpage
Returns: FetchURLsResponse: A response object with a list of URLs extracted from the webpage and the webpage content.
fetch_urls_response = carbon.utilities.fetch_urls(
url="url_example",
)
str/fetch_urls get
carbon.utilities.fetch_webpageFetch Urls V2
fetch_webpage_response = carbon.utilities.fetch_webpage(
url="string_example",
)
str/fetch_webpage post
carbon.utilities.fetch_youtube_transcriptsFetches english transcripts from YouTube videos.
Args: id (str): The ID of the YouTube video. raw (bool): Whether to return the raw transcript or not. Defaults to False.
Returns: dict: A dictionary with the transcript of the YouTube video.
fetch_youtube_transcripts_response = carbon.utilities.fetch_youtube_transcripts(
id="id_example",
raw=False,
)
strbool/fetch_youtube_transcript get
carbon.utilities.process_sitemapRetrieves all URLs from a sitemap, which can subsequently be utilized with our web_scrape endpoint.
process_sitemap_response = carbon.utilities.process_sitemap(
url="url_example",
)
str/process_sitemap get
carbon.utilities.scrape_sitemapExtracts all URLs from a sitemap and performs a web scrape on each of them.
Args: sitemap_url (str): URL of the sitemap
Returns: dict: A response object with the status of the scraping job message.-->
scrape_sitemap_response = carbon.utilities.scrape_sitemap(
url="string_example",
tags={
"key": "string_example",
},
max_pages_to_scrape=1,
chunk_size=1500,
chunk_overlap=20,
skip_embedding_generation=False,
enable_auto_sync=False,
generate_sparse_vectors=False,
prepend_filename_to_chunks=False,
html_tags_to_skip=[],
css_classes_to_skip=[],
css_selectors_to_skip=[],
embedding_model="OPENAI",
url_paths_to_include=[],
url_paths_to_exclude=[],
urls_to_scrape=[],
download_css_and_media=False,
generate_chunks_only=False,
store_file_only=False,
use_premium_proxies=False,
)
strSitemapScrapeRequestTagsOptional[int]Optional[int]Optional[int]Optional[bool]Optional[bool]Optional[bool]Optional[bool]SitemapScrapeRequestHtmlTagsToSkipSitemapScrapeRequestCssClassesToSkipSitemapScrapeRequestCssSelectorsToSkipEmbeddingGeneratorsSitemapScrapeRequestUrlPathsToIncludeSitemapScrapeRequestUrlPathsToExcludeSitemapScrapeRequestUrlsToScrapeOptional[bool]Whether the scraper should download css and media from the page (images, fonts, etc). Scrapes might take longer to finish with this flag enabled, but the success rate is improved.
boolIf this flag is enabled, the file will be chunked and stored with Carbon, but no embeddings will be generated. This overrides the skip_embedding_generation flag.
boolIf this flag is enabled, the file will be stored with Carbon, but no processing will be done.
boolIf the default proxies are blocked and not returning results, this flag can be enabled to use alternate proxies (residential and office). Scrapes might take longer to finish with this flag enabled.
/scrape_sitemap post
carbon.utilities.scrape_webConduct a web scrape on a given webpage URL. Our web scraper is fully compatible with JavaScript and supports recursion depth, enabling you to efficiently extract all content from the target website.
scrape_web_response = carbon.utilities.scrape_web(
body=[
{
"url": "url_example",
"recursion_depth": 3,
"max_pages_to_scrape": 100,
"chunk_size": 1500,
"chunk_overlap": 20,
"skip_embedding_generation": False,
"enable_auto_sync": False,
"generate_sparse_vectors": False,
"prepend_filename_to_chunks": False,
"html_tags_to_skip": [],
"css_classes_to_skip": [],
"css_selectors_to_skip": [],
"embedding_model": "OPENAI",
"url_paths_to_include": [],
"download_css_and_media": False,
"generate_chunks_only": False,
"store_file_only": False,
"use_premium_proxies": False,
}
],
)
/web_scrape post
carbon.utilities.search_urlsPerform a web search and obtain a list of relevant URLs.
As an illustration, when you perform a search for “content related to MRNA,” you will receive a list of links such as the following:
- https://tomrenz.substack.com/p/mrna-and-why-it-matters
- https://www.statnews.com/2020/11/10/the-story-of-mrna-how-a-once-dismissed-idea-became-a-leading-technology-in-the-covid-vaccine-race/
- https://www.statnews.com/2022/11/16/covid-19-vaccines-were-a-success-but-mrna-still-has-a-delivery-problem/
- https://joomi.substack.com/p/were-still-being-misled-about-how
Subsequently, you can submit these links to the web_scrape endpoint in order to retrieve the content of the respective web pages.
Args: query (str): Query to search for
Returns: FetchURLsResponse: A response object with a list of URLs for a given search query.
search_urls_response = carbon.utilities.search_urls(
query="query_example",
)
str/search_urls get
carbon.utilities.user_webpagesUser Web Pages
user_webpages_response = carbon.utilities.user_webpages(
filters={},
pagination={
"limit": 10,
"offset": 0,
"starting_id": 0,
},
order_by="created_at",
order_dir="asc",
)
UserWebPagesFiltersPaginationUserWebPageOrderByTypesOrderDirV2/user_webpages post
carbon.webhooks.add_urlAdd Webhook Url
add_url_response = carbon.webhooks.add_url(
url="string_example",
)
str/add_webhook post
carbon.webhooks.delete_urlDelete Webhook Url
delete_url_response = carbon.webhooks.delete_url(
webhook_id=1,
)
int/delete_webhook/{webhook_id} delete
carbon.webhooks.urlsWebhook Urls
urls_response = carbon.webhooks.urls(
pagination={
"limit": 10,
"offset": 0,
"starting_id": 0,
},
order_by="created_at",
order_dir="desc",
filters={
"ids": [],
},
)
PaginationWebhookOrderByColumnsOrderDirWebhookFilters/webhooks post
carbon.white_label.createCreate White Labels
create_response = carbon.white_label.create(
body=[
{
"data_source_type": "GOOGLE_DRIVE",
"credentials": {
"client_id": "client_id_example",
"redirect_uri": "redirect_uri_example",
},
}
],
)
/white_label/create post
carbon.white_label.deleteDelete White Labels
delete_response = carbon.white_label.delete(
ids=[1],
)
DeleteWhiteLabelRequestIds/white_label/delete post
carbon.white_label.listList White Labels
list_response = carbon.white_label.list(
pagination={
"limit": 10,
"offset": 0,
"starting_id": 0,
},
order_by="created_at",
order_dir="desc",
filters={
"ids": [],
"data_source_type": [],
},
)
PaginationWhiteLabelOrderByColumnsOrderDirWhiteLabelFilters/white_label/list post
carbon.white_label.updateUpdate White Label
update_response = carbon.white_label.update(
body={
"data_source_type": "GOOGLE_DRIVE",
"credentials": {
"client_id": "client_id_example",
"redirect_uri": "redirect_uri_example",
},
},
data_source_type="INTERCOM",
credentials={
"client_id": "client_id_example",
"redirect_uri": "redirect_uri_example",
},
)
strCredentials/white_label/update post
This Python package is automatically generated by Konfig
FAQs
Client for Carbon
We found that carbon-python-sdk demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 2 open source maintainers collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Security News
Research
The Socket Research Team breaks down a malicious wrapper package that uses obfuscation to harvest credentials and exfiltrate sensitive data.
Research
Security News
Attackers used a malicious npm package typosquatting a popular ESLint plugin to steal sensitive data, execute commands, and exploit developer systems.
Security News
The Ultralytics' PyPI Package was compromised four times in one weekend through GitHub Actions cache poisoning and failure to rotate previously compromised API tokens.