carbon-python-sdk 0.1.0

`carbon.auth.get_white_labeling`

Returns 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

🛠️ Usage

get_white_labeling_response = carbon.auth.get_white_labeling()

🔄 Return

WhiteLabelingResponse

🌐 Endpoint

/auth/v1/white_labeling get

OrganizationUserDataSourceQueryInput

`carbon.data_sources.query_user_data_sources`

User Data Sources

🛠️ Usage

query_user_data_sources_response = carbon.data_sources.query_user_data_sources(
    pagination={
        "limit": 10,
        "offset": 0,
    },
    order_by="created_at",
    order_dir="desc",
    filters={
        "source": "GOOGLE_DRIVE",
    },
)

⚙️ Parameters

pagination: `Pagination`

order_by: `OrganizationUserDataSourceOrderByColumns`

order_dir: `OrderDir`

filters: `OrganizationUserDataSourceFilters`

⚙️ Request Body

🔄 Return

OrganizationUserDataSourceResponse

🌐 Endpoint

/user_data_sources post

`carbon.data_sources.revoke_access_token`

Revoke Access Token

🛠️ Usage

revoke_access_token_response = carbon.data_sources.revoke_access_token(
    data_source_id=1,
)

⚙️ Parameters

data_source_id: `int`

⚙️ Request Body

RevokeAccessTokenInput

🔄 Return

🌐 Endpoint

/revoke_access_token post

GetEmbeddingDocumentsBody

`carbon.embeddings.get_documents`

For 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:

"subject" = "holy-bible" OR
"person-of-interest" = "jesus christ" OR
"genre" != "religion" OR
"subject" = "tao-te-ching" AND "author" = "lao-tzu"

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:

"key" isn't optional and must be a string
"value" isn't optional and can be any or list[any]
"negate" is optional and must be 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 search
weight_b: weight to assign to keyword search

You 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:

Use the /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
  }
}

Make sure hybrid search is enabled for the documents across which you want to perform the search. For the /uploadfile endpoint, this can be done by setting the following query parameter: generate_sparse_vectors=true

Carbon 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.

🛠️ Usage

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],
    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",
)

⚙️ Parameters

query: `str`

Query for which to get related chunks and embeddings.

k: `int`

Number of related chunks to return.

tags: `GetEmbeddingDocumentsBodyTags`

query_vector: `GetEmbeddingDocumentsBodyQueryVector`

file_ids: `GetEmbeddingDocumentsBodyFileIds`

parent_file_ids: `GetEmbeddingDocumentsBodyParentFileIds`

tags_v2: `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.

include_tags: `Optional[bool]`

Flag to control whether or not to include tags for each chunk in the response.

include_vectors: `Optional[bool]`

Flag to control whether or not to include embedding vectors in the response.

include_raw_file: `Optional[bool]`

Flag to control whether or not to include a signed URL to the raw file containing each chunk in the response.

hybrid_search: `Optional[bool]`

Flag to control whether or not to perform hybrid search.

hybrid_search_tuning_parameters: `HybridSearchTuningParamsNullable`

media_type: `FileContentTypesNullable`

embedding_model: `EmbeddingGeneratorsNullable`

⚙️ Request Body

🔄 Return

DocumentResponseList

🌐 Endpoint

/embeddings post

EmbeddingsAndChunksQueryInput

`carbon.embeddings.get_embeddings_and_chunks`

Retrieve Embeddings And Content

🛠️ Usage

get_embeddings_and_chunks_response = carbon.embeddings.get_embeddings_and_chunks(
    filters={
        "user_file_id": 1,
        "embedding_model": "OPENAI",
    },
    pagination={
        "limit": 10,
        "offset": 0,
    },
    order_by="created_at",
    order_dir="desc",
    include_vectors=False,
)

⚙️ Parameters

filters: `EmbeddingsAndChunksFilters`

pagination: `Pagination`

order_by: `EmbeddingsAndChunksOrderByColumns`

order_dir: `OrderDir`

include_vectors: `bool`

⚙️ Request Body

🔄 Return

EmbeddingsAndChunksResponse

🌐 Endpoint

/text_chunks post

ChunksAndEmbeddingsUploadInput

`carbon.embeddings.upload_chunks_and_embeddings`

Upload Chunks And Embeddings

🛠️ Usage

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",
                    "embedding": [3.14],
                }
            ],
        }
    ],
    overwrite_existing=False,
)

⚙️ Parameters

embedding_model: `EmbeddingGenerators`

chunks_and_embeddings: List[`SingleChunksAndEmbeddingsUploadInput`]

overwrite_existing: `bool`

⚙️ Request Body

🔄 Return

🌐 Endpoint

/upload_chunks_and_embeddings post

OrganizationUserFileTagCreate

`carbon.files.create_user_file_tags`

A 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:

db_embedding_id
organization_id
user_id
organization_user_file_id

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").

🛠️ Usage

create_user_file_tags_response = carbon.files.create_user_file_tags(
    tags={
        "key": "string_example",
    },
    organization_user_file_id=1,
)

⚙️ Parameters

tags: `OrganizationUserFileTagCreateTags`

organization_user_file_id: `int`

⚙️ Request Body

🔄 Return

🌐 Endpoint

/create_user_file_tags post

`carbon.files.delete`

Delete File Endpoint

🛠️ Usage

delete_response = carbon.files.delete(
    file_id=1,
)

⚙️ Parameters

file_id: `int`

🔄 Return

🌐 Endpoint

/deletefile/{file_id} delete

OrganizationUserFileTagsRemove

`carbon.files.delete_file_tags`

Delete File Tags

🛠️ Usage

delete_file_tags_response = carbon.files.delete_file_tags(
    tags=["string_example"],
    organization_user_file_id=1,
)

⚙️ Parameters

tags: `OrganizationUserFileTagsRemoveTags`

organization_user_file_id: `int`

⚙️ Request Body

🔄 Return

🌐 Endpoint

/delete_user_file_tags post

`carbon.files.delete_many`

Delete Files Endpoint

🛠️ Usage

delete_many_response = carbon.files.delete_many(
    file_ids=[1],
    sync_statuses=["string_example"],
    delete_non_synced_only=False,
)

⚙️ Parameters

file_ids: `DeleteFilesQueryInputFileIds`

sync_statuses: List[`ExternalFileSyncStatuses`]

delete_non_synced_only: `bool`

⚙️ Request Body

DeleteFilesQueryInput

🔄 Return

🌐 Endpoint

/delete_files post

`carbon.files.get_parsed_file`

This route is deprecated. Use /user_files_v2 instead.

🛠️ Usage

get_parsed_file_response = carbon.files.get_parsed_file(
    file_id=1,
)

⚙️ Parameters

file_id: `int`

🔄 Return

PresignedURLResponse

🌐 Endpoint

/parsed_file/{file_id} get

`carbon.files.get_raw_file`

This route is deprecated. Use /user_files_v2 instead.

🛠️ Usage

get_raw_file_response = carbon.files.get_raw_file(
    file_id=1,
)

⚙️ Parameters

file_id: `int`

🔄 Return

PresignedURLResponse

🌐 Endpoint

/raw_file/{file_id} get

OrganizationUserFilesToSyncQueryInput

`carbon.files.query_user_files`

{
    "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:

"subject" = "holy-bible" OR
"person-of-interest" = "jesus christ" OR
"genre" != "religion" OR
"subject" = "tao-te-ching" AND "author" = "lao-tzu"

"key" isn't optional and must be a string
"value" isn't optional and can be any or list[any]
"negate" is optional and must be true or false. If present and true, then the filter block is negated in the resulting query. It is false by default.

🛠️ Usage

query_user_files_response = carbon.files.query_user_files(
    pagination={
        "limit": 10,
        "offset": 0,
    },
    order_by="created_at",
    order_dir="desc",
    filters={},
    include_raw_file=True,
    include_parsed_text_file=True,
    include_additional_files=True,
)

⚙️ Parameters

pagination: `Pagination`

order_by: `OrganizationUserFilesToSyncOrderByTypes`

order_dir: `OrderDir`

filters: `OrganizationUserFilesToSyncFilters`

include_raw_file: `Optional[bool]`

include_parsed_text_file: `Optional[bool]`

include_additional_files: `Optional[bool]`

⚙️ Request Body

🔄 Return

UserFilesV2

🌐 Endpoint

/user_files_v2 post

OrganizationUserFilesToSyncQueryInput

`carbon.files.query_user_files_deprecated`

This route is deprecated. Use /user_files_v2 instead.

🛠️ Usage

query_user_files_deprecated_response = carbon.files.query_user_files_deprecated(
    pagination={
        "limit": 10,
        "offset": 0,
    },
    order_by="created_at",
    order_dir="desc",
    filters={},
    include_raw_file=True,
    include_parsed_text_file=True,
    include_additional_files=True,
)

⚙️ Parameters

pagination: `Pagination`

order_by: `OrganizationUserFilesToSyncOrderByTypes`

order_dir: `OrderDir`

filters: `OrganizationUserFilesToSyncFilters`

include_raw_file: `Optional[bool]`

include_parsed_text_file: `Optional[bool]`

include_additional_files: `Optional[bool]`

⚙️ Request Body

🔄 Return

FilesQueryUserFilesDeprecatedResponse

🌐 Endpoint

/user_files post

`carbon.files.resync`

Resync File

🛠️ Usage

resync_response = carbon.files.resync(
    file_id=1,
    chunk_size=1,
    chunk_overlap=1,
)

⚙️ Parameters

file_id: `int`

chunk_size: `Optional[int]`

chunk_overlap: `Optional[int]`

⚙️ Request Body

ResyncFileQueryInput

🔄 Return

🌐 Endpoint

/resync_file post

BodyCreateUploadFileUploadfilePost

`carbon.files.upload`

This 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 document
chunk_overlap: the chunk overlap (in tokens) applied when splitting the document
skip_embedding_generation: whether or not to skip the generation of chunks and embeddings
set_page_as_boundary: described above
embedding_model: the model used to generate embeddings for the document chunks
use_ocr: whether or not to use OCR as a preprocessing step prior to generating chunks (only valid for PDFs currently)
generate_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 text

🛠️ Usage

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="OPENAI",
    use_ocr=False,
    generate_sparse_vectors=False,
    prepend_filename_to_chunks=False,
    max_items_per_chunk=1,
)

⚙️ Parameters

file: `IO`

chunk_size: `Optional[int]`

Chunk size in tiktoken tokens to be used when processing file.

chunk_overlap: `Optional[int]`

Chunk overlap in tiktoken tokens to be used when processing file.

skip_embedding_generation: `bool`

Flag to control whether or not embeddings should be generated and stored when processing file.

set_page_as_boundary: `bool`

Flag 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.

embedding_model: `TextEmbeddingGenerators`

Embedding model that will be used to embed file chunks.

use_ocr: `bool`

Whether or not to use OCR when processing files. Only valid for PDFs. Useful for documents with tables, images, and/or scanned text.

generate_sparse_vectors: `bool`

Whether or not to generate sparse vectors for the file. This is required for the file to be a candidate for hybrid search.

prepend_filename_to_chunks: `bool`

Whether or not to prepend the file's name to chunks.

max_items_per_chunk: `Optional[int]`

Number of objects per chunk. For json files only.

⚙️ Request Body

🔄 Return

🌐 Endpoint

/uploadfile post

`carbon.files.upload_from_url`

Create Upload File From Url

🛠️ Usage

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,
)

⚙️ Parameters

url: `str`

file_name: `Optional[str]`

chunk_size: `Optional[int]`

chunk_overlap: `Optional[int]`

skip_embedding_generation: `bool`

set_page_as_boundary: `bool`

embedding_model: `EmbeddingGenerators`

generate_sparse_vectors: `bool`

use_textract: `bool`

prepend_filename_to_chunks: `bool`

max_items_per_chunk: `Optional[int]`

⚙️ Request Body

UploadFileFromUrlInput

🔄 Return

🌐 Endpoint

/upload_file_from_url post

`carbon.files.upload_text`

🛠️ Usage

upload_text_response = carbon.files.upload_text(
    contents="string_example",
    name="string_example",
    chunk_size=1,
    chunk_overlap=1,
    skip_embedding_generation=False,
    overwrite_file_id=1,
    embedding_model="OPENAI",
    generate_sparse_vectors=False,
)

⚙️ Parameters

contents: `str`

name: `Optional[str]`

chunk_size: `Optional[int]`

chunk_overlap: `Optional[int]`

skip_embedding_generation: `bool`

overwrite_file_id: `Optional[int]`

embedding_model: `EmbeddingGeneratorsNullable`

generate_sparse_vectors: `Optional[bool]`

⚙️ Request Body

RawTextInput

🔄 Return

🌐 Endpoint

/upload_text post

`carbon.health.check`

Health

🛠️ Usage

check_response = carbon.health.check()

🌐 Endpoint

/health get

FreshDeskConnectRequest

`carbon.integrations.connect_freshdesk`

Refer 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.

🛠️ Usage

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,
)

⚙️ Parameters

domain: `str`

api_key: `str`

tags: `Optional[Dict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]]`

chunk_size: `Optional[int]`

chunk_overlap: `Optional[int]`

skip_embedding_generation: `Optional[bool]`

embedding_model: `EmbeddingGeneratorsNullable`

generate_sparse_vectors: `Optional[bool]`

prepend_filename_to_chunks: `Optional[bool]`

⚙️ Request Body

🔄 Return

🌐 Endpoint

/integrations/freshdesk post

OrganizationUserDataSourceAPI

`carbon.integrations.create_aws_iam_user`

Create a new IAM user with permissions to:

List all buckets.
Read from the specific buckets and objects to sync with Carbon. Ensure any future buckets or objects carry the same permissions.

Once created, generate an access key for this user and share the credentials with us. We recommend testing this key beforehand.

🛠️ Usage

create_aws_iam_user_response = carbon.integrations.create_aws_iam_user(
    access_key="string_example",
    access_key_secret="string_example",
)

⚙️ Parameters

access_key: `str`

access_key_secret: `str`

⚙️ Request Body

S3AuthRequest

🔄 Return

🌐 Endpoint

/integrations/s3 post

`carbon.integrations.get_oauth_url`

Get Oauth Url

🛠️ Usage

get_oauth_url_response = carbon.integrations.get_oauth_url(
    service="GOOGLE_DRIVE",
    tags=None,
    scope="string_example",
    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,
)

⚙️ Parameters

service: `DataSourceType`

tags: `Union[bool, date, datetime, dict, float, int, list, str, None]`

scope: `Optional[str]`

chunk_size: `Optional[int]`

chunk_overlap: `Optional[int]`

skip_embedding_generation: `Optional[bool]`

embedding_model: `EmbeddingGeneratorsNullable`

zendesk_subdomain: `Optional[str]`

microsoft_tenant: `Optional[str]`

sharepoint_site_name: `Optional[str]`

confluence_subdomain: `Optional[str]`

generate_sparse_vectors: `Optional[bool]`

prepend_filename_to_chunks: `Optional[bool]`

max_items_per_chunk: `Optional[int]`

⚙️ Request Body

OAuthURLRequest

🌐 Endpoint

/integrations/oauth_url post

`carbon.integrations.list_confluence_pages`

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.

🛠️ Usage

list_confluence_pages_response = carbon.integrations.list_confluence_pages(
    data_source_id=1,
    parent_id="string_example",
)

⚙️ Parameters

data_source_id: `int`

parent_id: `Optional[str]`

⚙️ Request Body

ListRequest

🔄 Return

ListResponse

🌐 Endpoint

/integrations/confluence/list post

ListDataSourceItemsRequest

`carbon.integrations.list_data_source_items`

List Data Source Items

🛠️ Usage

list_data_source_items_response = carbon.integrations.list_data_source_items(
    data_source_id=1,
    parent_id="string_example",
    pagination={
        "limit": 10,
        "offset": 0,
    },
)

⚙️ Parameters

data_source_id: `int`

parent_id: `Optional[str]`

pagination: `Pagination`

⚙️ Request Body

🔄 Return

ListDataSourceItemsResponse

🌐 Endpoint

/integrations/items/list post

`carbon.integrations.list_folders`

After 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.

🛠️ Usage

list_folders_response = carbon.integrations.list_folders()

🌐 Endpoint

/integrations/outlook/user_folders get

`carbon.integrations.list_labels`

After 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"

🛠️ Usage

list_labels_response = carbon.integrations.list_labels()

🌐 Endpoint

/integrations/gmail/user_labels get

`carbon.integrations.sync_confluence`

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.

🛠️ Usage

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,
)

⚙️ Parameters

data_source_id: `int`

ids: `SyncFilesRequestIds`

tags: `Optional[Dict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]]`

chunk_size: `Optional[int]`

chunk_overlap: `Optional[int]`

skip_embedding_generation: `Optional[bool]`

embedding_model: `EmbeddingGeneratorsNullable`

generate_sparse_vectors: `Optional[bool]`

prepend_filename_to_chunks: `Optional[bool]`

max_items_per_chunk: `Optional[int]`

⚙️ Request Body

SyncFilesRequest

🔄 Return

🌐 Endpoint

/integrations/confluence/sync post

OrganizationUserDataSourceAPI

`carbon.integrations.sync_data_source_items`

Sync Data Source Items

🛠️ Usage

sync_data_source_items_response = carbon.integrations.sync_data_source_items(
    data_source_id=1,
)

⚙️ Parameters

data_source_id: `int`

⚙️ Request Body

SyncDirectoryRequest

🔄 Return

🌐 Endpoint

/integrations/items/sync post

`carbon.integrations.sync_files`

Sync Files

🛠️ Usage

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,
)

⚙️ Parameters

data_source_id: `int`

ids: `SyncFilesRequestIds`

tags: `Optional[Dict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]]`

chunk_size: `Optional[int]`

chunk_overlap: `Optional[int]`

skip_embedding_generation: `Optional[bool]`

embedding_model: `EmbeddingGeneratorsNullable`

generate_sparse_vectors: `Optional[bool]`

prepend_filename_to_chunks: `Optional[bool]`

max_items_per_chunk: `Optional[int]`

⚙️ Request Body

SyncFilesRequest

🔄 Return

🌐 Endpoint

/integrations/files/sync post

`carbon.integrations.sync_gmail`

Once 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

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.

🛠️ Usage

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,
)

⚙️ Parameters

filters: `Dict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]`

tags: `Optional[Dict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]]`

chunk_size: `Optional[int]`

chunk_overlap: `Optional[int]`

skip_embedding_generation: `Optional[bool]`

embedding_model: `EmbeddingGenerators`

generate_sparse_vectors: `Optional[bool]`

prepend_filename_to_chunks: `Optional[bool]`

⚙️ Request Body

GmailSyncInput

🔄 Return

🌐 Endpoint

/integrations/gmail/sync post

`carbon.integrations.sync_outlook`

Once 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

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.

🛠️ Usage

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,
)

⚙️ Parameters

filters: `Dict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]`

tags: `Optional[Dict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]]`

folder: `Optional[str]`

chunk_size: `Optional[int]`

chunk_overlap: `Optional[int]`

skip_embedding_generation: `Optional[bool]`

embedding_model: `EmbeddingGenerators`

generate_sparse_vectors: `Optional[bool]`

prepend_filename_to_chunks: `Optional[bool]`

⚙️ Request Body

OutlookSyncInput

🔄 Return

🌐 Endpoint

/integrations/outlook/sync post

`carbon.integrations.sync_rss_feed`

Rss Feed

🛠️ Usage

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,
)

⚙️ Parameters

url: `str`

tags: `Optional[Dict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]]`

chunk_size: `Optional[int]`

chunk_overlap: `Optional[int]`

skip_embedding_generation: `Optional[bool]`

embedding_model: `EmbeddingGenerators`

generate_sparse_vectors: `Optional[bool]`

prepend_filename_to_chunks: `Optional[bool]`

⚙️ Request Body

RSSFeedInput

🔄 Return

🌐 Endpoint

/integrations/rss_feed post

`carbon.integrations.sync_s3_files`

After 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

🛠️ Usage

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,
)

⚙️ Parameters

ids: List[`S3GetFileInput`]

tags: `Optional[Dict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]]`

chunk_size: `Optional[int]`

chunk_overlap: `Optional[int]`

skip_embedding_generation: `Optional[bool]`

embedding_model: `EmbeddingGenerators`

generate_sparse_vectors: `Optional[bool]`

prepend_filename_to_chunks: `Optional[bool]`

max_items_per_chunk: `Optional[int]`

⚙️ Request Body

S3FileSyncInput

🔄 Return

🌐 Endpoint

/integrations/s3/files post

`carbon.organizations.get`

Get Organization

🛠️ Usage

get_response = carbon.organizations.get()

🔄 Return

OrganizationResponse

🌐 Endpoint

/organization get

`carbon.users.get`

User Endpoint

🛠️ Usage

get_response = carbon.users.get(
    customer_id="string_example",
)

⚙️ Parameters

customer_id: `str`

⚙️ Request Body

UserRequestContent

🔄 Return

UserResponse

🌐 Endpoint

/user post

ModifyUserConfigurationInput

`carbon.users.toggle_user_features`

Toggle User Features

🛠️ Usage

toggle_user_features_response = carbon.users.toggle_user_features(
    configuration_key_name="string_example",
    value={},
)

⚙️ Parameters

configuration_key_name: `str`

value: `Dict[str, Union[bool, date, datetime, dict, float, int, list, str, None]]`

⚙️ Request Body

🔄 Return

🌐 Endpoint

/modify_user_configuration post

`carbon.utilities.fetch_urls`

Extracts 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.

🛠️ Usage

fetch_urls_response = carbon.utilities.fetch_urls(
    url="url_example",
)

⚙️ Parameters

url: `str`

🔄 Return

FetchURLsResponse

🌐 Endpoint

/fetch_urls get

YoutubeTranscriptResponse

`carbon.utilities.fetch_youtube_transcripts`

Fetches 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.

🛠️ Usage

fetch_youtube_transcripts_response = carbon.utilities.fetch_youtube_transcripts(
    id="id_example",
    raw=False,
)

⚙️ Parameters

id: `str`

raw: `bool`

🔄 Return

🌐 Endpoint

/fetch_youtube_transcript get

`carbon.utilities.process_sitemap`

Retrieves all URLs from a sitemap, which can subsequently be utilized with our web_scrape endpoint.

🛠️ Usage

process_sitemap_response = carbon.utilities.process_sitemap(
    url="url_example",
)

⚙️ Parameters

url: `str`

🌐 Endpoint

/process_sitemap get

`carbon.utilities.scrape_sitemap`

Extracts 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.-->

🛠️ Usage

scrape_sitemap_response = carbon.utilities.scrape_sitemap(
    url="string_example",
    tags={
        "key": "string_example",
    },
    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=[],
)

⚙️ Parameters

url: `str`

tags: `SitemapScrapeRequestTags`

max_pages_to_scrape: `Optional[int]`

chunk_size: `Optional[int]`

chunk_overlap: `Optional[int]`

skip_embedding_generation: `Optional[bool]`

enable_auto_sync: `Optional[bool]`

generate_sparse_vectors: `Optional[bool]`

prepend_filename_to_chunks: `Optional[bool]`

html_tags_to_skip: `SitemapScrapeRequestHtmlTagsToSkip`

css_classes_to_skip: `SitemapScrapeRequestCssClassesToSkip`

css_selectors_to_skip: `SitemapScrapeRequestCssSelectorsToSkip`

⚙️ Request Body

SitemapScrapeRequest

🌐 Endpoint

/scrape_sitemap post

UtilitiesScrapeWebRequest

`carbon.utilities.scrape_web`

Conduct 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.

🛠️ Usage

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": [],
        }
    ],
)

⚙️ Request Body

🌐 Endpoint

/web_scrape post

`carbon.utilities.search_urls`

Perform 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.

🛠️ Usage

search_urls_response = carbon.utilities.search_urls(
    query="query_example",
)

⚙️ Parameters

query: `str`

🔄 Return

FetchURLsResponse

🌐 Endpoint

/search_urls get

`carbon.webhooks.add_url`

Add Webhook Url

🛠️ Usage

add_url_response = carbon.webhooks.add_url(
    url="string_example",
)

⚙️ Parameters

url: `str`

⚙️ Request Body

AddWebhookProps

🔄 Return

Webhook

🌐 Endpoint

/add_webhook post

`carbon.webhooks.delete_url`

Delete Webhook Url

🛠️ Usage

delete_url_response = carbon.webhooks.delete_url(
    webhook_id=1,
)

⚙️ Parameters

webhook_id: `int`

🔄 Return

🌐 Endpoint

/delete_webhook/{webhook_id} delete

`carbon.webhooks.urls`

Webhook Urls

🛠️ Usage

urls_response = carbon.webhooks.urls(
    pagination={
        "limit": 10,
        "offset": 0,
    },
    order_by="created_at",
    order_dir="desc",
    filters={
        "ids": [],
    },
)

⚙️ Parameters

pagination: `Pagination`

order_by: `WebhookOrderByColumns`

order_dir: `OrderDir`

filters: `WebhookFilters`

⚙️ Request Body

WebhookQueryInput

🔄 Return

WebhookQueryResponse

🌐 Endpoint

/webhooks post