Skip to content
LlamaIndex API Docs
Framework Docs
API Reference

Shared

ModelsExpand Collapse
class CloudAstraDbVectorStore:

Cloud AstraDB Vector Store.

This class is used to store the configuration for an AstraDB vector store, so that it can be created and used in LlamaCloud.

Args: token (str): The Astra DB Application Token to use. api_endpoint (str): The Astra DB JSON API endpoint for your database. collection_name (str): Collection name to use. If not existing, it will be created. embedding_dimension (int): Length of the embedding vectors in use. keyspace (optional[str]): The keyspace to use. If not provided, ‘default_keyspace’

String token

The Astra DB Application Token to use

formatpassword
String apiEndpoint

The Astra DB JSON API endpoint for your database

String collectionName

Collection name to use. If not existing, it will be created

long embeddingDimension

Length of the embedding vectors in use

Optional<String> className
Optional<String> keyspace

The keyspace to use. If not provided, ‘default_keyspace’

Optional<SupportsNestedMetadataFilters> supportsNestedMetadataFilters
class CloudAzStorageBlobDataSource:
String accountUrl

The Azure Storage Blob account URL to use for authentication.

String containerName

The name of the Azure Storage Blob container to read from.

Optional<String> accountKey

The Azure Storage Blob account key to use for authentication.

formatpassword
Optional<String> accountName

The Azure Storage Blob account name to use for authentication.

Optional<String> blob

The blob name to read from.

Optional<String> className
Optional<String> clientId

The Azure AD client ID to use for authentication.

Optional<String> clientSecret

The Azure AD client secret to use for authentication.

formatpassword
Optional<String> prefix

The prefix of the Azure Storage Blob objects to read from.

Optional<Boolean> supportsAccessControl
Optional<String> tenantId

The Azure AD tenant ID to use for authentication.

class CloudAzureAiSearchVectorStore:

Cloud Azure AI Search Vector Store.

String searchServiceApiKey
String searchServiceEndpoint
Optional<String> className
Optional<String> clientId
Optional<String> clientSecret
Optional<Long> embeddingDimension
Optional<FilterableMetadataFieldKeys> filterableMetadataFieldKeys
Optional<String> indexName
Optional<String> searchServiceApiVersion
Optional<SupportsNestedMetadataFilters> supportsNestedMetadataFilters
Optional<String> tenantId
class CloudBoxDataSource:
AuthenticationMechanism authenticationMechanism

The type of authentication to use (Developer Token or CCG)

One of the following:
DEVELOPER_TOKEN("developer_token")
CCG("ccg")
Optional<String> className
Optional<String> clientId

Box API key used for identifying the application the user is authenticating with

Optional<String> clientSecret

Box API secret used for making auth requests.

formatpassword
Optional<String> developerToken

Developer token for authentication if authentication_mechanism is ‘developer_token’.

formatpassword
Optional<String> enterpriseId

Box Enterprise ID, if provided authenticates as service.

Optional<String> folderId

The ID of the Box folder to read from.

Optional<Boolean> supportsAccessControl
Optional<String> userId

Box User ID, if provided authenticates as user.

class CloudConfluenceDataSource:
String authenticationMechanism

Type of Authentication for connecting to Confluence APIs.

String serverUrl

The server URL of the Confluence instance.

Optional<String> apiToken

The API token to use for authentication.

formatpassword
Optional<String> className
Optional<String> cql

The CQL query to use for fetching pages.

Optional<FailureHandlingConfig> failureHandling

Configuration for handling failures during processing. Key-value object controlling failure handling behaviors.

Example: { “skip_list_failures”: true }

Currently supports:

  • skip_list_failures: Skip failed batches/lists and continue processing
Optional<Boolean> skipListFailures

Whether to skip failed batches/lists and continue processing

Optional<Boolean> indexRestrictedPages

Whether to index restricted pages.

Optional<Boolean> keepMarkdownFormat

Whether to keep the markdown format.

Optional<String> label

The label to use for fetching pages.

Optional<String> pageIds

The page IDs of the Confluence to read from.

Optional<String> spaceKey

The space key to read from.

Optional<Boolean> supportsAccessControl
Optional<String> userName

The username to use for authentication.

class CloudGoogleDriveDataSource:
String folderId

The ID of the Google Drive folder to read from.

Optional<String> className
Optional<ServiceAccountKey> serviceAccountKey

A dictionary containing secret values

Optional<Boolean> supportsAccessControl
class CloudJiraDataSource:

Cloud Jira Data Source integrating JiraReader.

String authenticationMechanism

Type of Authentication for connecting to Jira APIs.

String query

JQL (Jira Query Language) query to search.

Optional<String> apiToken

The API/ Access Token used for Basic, PAT and OAuth2 authentication.

formatpassword
Optional<String> className
Optional<String> cloudId

The cloud ID, used in case of OAuth2.

Optional<String> email

The email address to use for authentication.

Optional<String> serverUrl

The server url for Jira Cloud.

Optional<Boolean> supportsAccessControl
class CloudJiraDataSourceV2:

Cloud Jira Data Source integrating JiraReaderV2.

String authenticationMechanism

Type of Authentication for connecting to Jira APIs.

String query

JQL (Jira Query Language) query to search.

String serverUrl

The server url for Jira Cloud.

Optional<String> apiToken

The API Access Token used for Basic, PAT and OAuth2 authentication.

formatpassword
Optional<ApiVersion> apiVersion

Jira REST API version to use (2 or 3). 3 supports Atlassian Document Format (ADF).

One of the following:
_2("2")
_3("3")
Optional<String> className
Optional<String> cloudId

The cloud ID, used in case of OAuth2.

Optional<String> email

The email address to use for authentication.

Optional<String> expand

Fields to expand in the response.

Optional<List<String>> fields

List of fields to retrieve from Jira. If None, retrieves all fields.

Optional<Boolean> getPermissions

Whether to fetch project role permissions and issue-level security

Optional<Long> requestsPerMinute

Rate limit for Jira API requests per minute.

Optional<Boolean> supportsAccessControl
class CloudMilvusVectorStore:

Cloud Milvus Vector Store.

String uri
Optional<String> token
Optional<String> className
Optional<String> collectionName
Optional<Long> embeddingDimension
Optional<Boolean> supportsNestedMetadataFilters

Cloud MongoDB Atlas Vector Store.

This class is used to store the configuration for a MongoDB Atlas vector store, so that it can be created and used in LlamaCloud.

Args: mongodb_uri (str): URI for connecting to MongoDB Atlas db_name (str): name of the MongoDB database collection_name (str): name of the MongoDB collection vector_index_name (str): name of the MongoDB Atlas vector index fulltext_index_name (str): name of the MongoDB Atlas full-text index

class CloudNotionPageDataSource:
String integrationToken

The integration token to use for authentication.

formatpassword
Optional<String> className
Optional<String> databaseIds

The Notion Database Id to read content from.

Optional<String> pageIds

The Page ID’s of the Notion to read from.

Optional<Boolean> supportsAccessControl
class CloudOneDriveDataSource:
String clientId

The client ID to use for authentication.

String clientSecret

The client secret to use for authentication.

formatpassword
String tenantId

The tenant ID to use for authentication.

String userPrincipalName

The user principal name to use for authentication.

Optional<String> className
Optional<String> folderId

The ID of the OneDrive folder to read from.

Optional<String> folderPath

The path of the OneDrive folder to read from.

Optional<List<String>> requiredExts

The list of required file extensions.

Optional<SupportsAccessControl> supportsAccessControl
class CloudPineconeVectorStore:

Cloud Pinecone Vector Store.

This class is used to store the configuration for a Pinecone vector store, so that it can be created and used in LlamaCloud.

Args: api_key (str): API key for authenticating with Pinecone index_name (str): name of the Pinecone index namespace (optional[str]): namespace to use in the Pinecone index insert_kwargs (optional[dict]): additional kwargs to pass during insertion

String apiKey

The API key for authenticating with Pinecone

formatpassword
String indexName
Optional<String> className
Optional<InsertKwargs> insertKwargs
Optional<String> namespace
Optional<SupportsNestedMetadataFilters> supportsNestedMetadataFilters
class CloudPostgresVectorStore:
String database
long embedDim
String host
String password
long port
String schemaName
String tableName
String user
Optional<String> className
Optional<PgVectorHnswSettings> hnswSettings

HNSW settings for PGVector.

Optional<DistanceMethod> distanceMethod

The distance method to use.

One of the following:
L2("l2")
IP("ip")
COSINE("cosine")
L1("l1")
HAMMING("hamming")
JACCARD("jaccard")
Optional<Long> efConstruction

The number of edges to use during the construction phase.

minimum1

The number of edges to use during the search phase.

minimum1
Optional<Long> m

The number of bi-directional links created for each new element.

minimum1
Optional<VectorType> vectorType

The type of vector to use.

One of the following:
VECTOR("vector")
HALF_VEC("half_vec")
BIT("bit")
SPARSE_VEC("sparse_vec")
Optional<Boolean> performSetup
Optional<Boolean> supportsNestedMetadataFilters
class CloudQdrantVectorStore:

Cloud Qdrant Vector Store.

This class is used to store the configuration for a Qdrant vector store, so that it can be created and used in LlamaCloud.

Args: collection_name (str): name of the Qdrant collection url (str): url of the Qdrant instance api_key (str): API key for authenticating with Qdrant max_retries (int): maximum number of retries in case of a failure. Defaults to 3 client_kwargs (dict): additional kwargs to pass to the Qdrant client

String apiKey
String collectionName
String url
Optional<String> className
Optional<ClientKwargs> clientKwargs
Optional<Long> maxRetries
Optional<SupportsNestedMetadataFilters> supportsNestedMetadataFilters
class CloudS3DataSource:
String bucket

The name of the S3 bucket to read from.

Optional<String> awsAccessId

The AWS access ID to use for authentication.

Optional<String> awsAccessSecret

The AWS access secret to use for authentication.

formatpassword
Optional<String> className
Optional<String> prefix

The prefix of the S3 objects to read from.

Optional<String> regexPattern

The regex pattern to filter S3 objects. Must be a valid regex pattern.

Optional<String> s3EndpointUrl

The S3 endpoint URL to use for authentication.

Optional<Boolean> supportsAccessControl
class CloudSharepointDataSource:
String clientId

The client ID to use for authentication.

String clientSecret

The client secret to use for authentication.

formatpassword
String tenantId

The tenant ID to use for authentication.

Optional<String> className
Optional<String> driveName

The name of the Sharepoint drive to read from.

Optional<List<String>> excludePathPatterns

List of regex patterns for file paths to exclude. Files whose paths (including filename) match any pattern will be excluded. Example: [‘/temp/’, ‘/backup/’, ‘.git/’, ‘.tmp$’, ’^~’]

Optional<String> folderId

The ID of the Sharepoint folder to read from.

Optional<String> folderPath

The path of the Sharepoint folder to read from.

Optional<Boolean> getPermissions

Whether to get permissions for the sharepoint site.

Optional<List<String>> includePathPatterns

List of regex patterns for file paths to include. Full paths (including filename) must match at least one pattern to be included. Example: [‘/reports/’, ‘/docs/..pdf$’, ‘^Report..pdf$’]

Optional<List<String>> requiredExts

The list of required file extensions.

Optional<String> siteId

The ID of the SharePoint site to download from.

Optional<String> siteName

The name of the SharePoint site to download from.

Optional<SupportsAccessControl> supportsAccessControl
class CloudSlackDataSource:
String slackToken

Slack Bot Token.

formatpassword
Optional<String> channelIds

Slack Channel.

Optional<String> channelPatterns

Slack Channel name pattern.

Optional<String> className
Optional<String> earliestDate

Earliest date.

Optional<Double> earliestDateTimestamp

Earliest date timestamp.

Optional<String> latestDate

Latest date.

Optional<Double> latestDateTimestamp

Latest date timestamp.

Optional<Boolean> supportsAccessControl
class FailureHandlingConfig:

Configuration for handling different types of failures during data source processing.

Optional<Boolean> skipListFailures

Whether to skip failed batches/lists and continue processing

class PgVectorHnswSettings:

HNSW settings for PGVector.

Optional<DistanceMethod> distanceMethod

The distance method to use.

One of the following:
L2("l2")
IP("ip")
COSINE("cosine")
L1("l1")
HAMMING("hamming")
JACCARD("jaccard")
Optional<Long> efConstruction

The number of edges to use during the construction phase.

minimum1

The number of edges to use during the search phase.

minimum1
Optional<Long> m

The number of bi-directional links created for each new element.

minimum1
Optional<VectorType> vectorType

The type of vector to use.

One of the following:
VECTOR("vector")
HALF_VEC("half_vec")
BIT("bit")
SPARSE_VEC("sparse_vec")