How AI is applied across API Evangelist and APIs.io. Read my AI disclosure →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

LlamaParse Pipeline Data Sources API

The Pipeline Data Sources API from LlamaParse — 4 operation(s) for pipeline data sources.

LlamaParse Pipeline Data Sources API is one of 36 APIs that LlamaParse publishes on the APIs.io network, described by a machine-readable OpenAPI specification.

Tagged areas include Pipeline Data Sources. The published artifact set on APIs.io includes an OpenAPI specification, API documentation, an API reference, and a getting-started guide.

This API exposes 5 operations across 4 paths, and defines 83 schemas. It is described by OpenAPI 3.2.0, at version 0.1.0.

Requests are made against a single base URL, https://api.cloud.llamaindex.ai.

5 operations 4 paths 83 schemas 2 GET1 POST2 PUT

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.2.0
API Version
0.1.0
Base URL
https://api.cloud.llamaindex.ai
Authentication
HTTP Bearer
Resource Areas
1

Authentication & Security 1

LlamaParse Pipeline Data Sources API declares 1 security scheme for authenticating requests. It accepts HTTP bearer tokens (HTTPBearer).

Paths & Operations 5

Across 4 paths, the API surfaces 5 operations — 2 GET, 1 POST, 2 PUT. Each is listed below with its method, path, parameters, and response codes.

Pipeline Data Sources 5
GET
/api/v1/pipelines/{pipeline_id}/data-sources
List Pipeline Data Sources
list_pipeline_data_sources_api_v1_pipelines__pipeline_id__data_sources_get 2 params → 200422
PUT
/api/v1/pipelines/{pipeline_id}/data-sources
Add Data Sources To Pipeline
add_data_sources_to_pipeline_api_v1_pipelines__pipeline_id__data_sources_put 2 params body → 200422
PUT
/api/v1/pipelines/{pipeline_id}/data-sources/{data_source_id}
Update Pipeline Data Source
update_pipeline_data_source_api_v1_pipelines__pipeline_id__data_sources__data_source_id__put 3 params body → 200422
POST
/api/v1/pipelines/{pipeline_id}/data-sources/{data_source_id}/sync
Sync Pipeline Data Source
sync_pipeline_data_source_api_v1_pipelines__pipeline_id__data_sources__data_source_id__sync_post 3 params body → 200422
GET
/api/v1/pipelines/{pipeline_id}/data-sources/{data_source_id}/status
Get Pipeline Data Source Status
get_pipeline_data_source_status_api_v1_pipelines__pipeline_id__data_sources__data_source_id__status_get 3 params → 200422

Schemas 83

The contract defines 83 schemas that model the data the API accepts and returns. The most detailed are LlamaParseParameters (119 properties), Pipeline (18 properties), PipelineDataSource (16 properties), AzureOpenAIEmbedding (15 properties). Each schema is shown below with its type and property counts.

MetadataFilter
object
Comprehensive metadata filter for vector stores to support more operators. Value uses Strict types, as int, float and str are compatible types and were all con…
3 properties 2 required
AdvancedModeTransformConfig
object
3 properties
ManagedOpenAIEmbeddingConfig
object
2 properties
ManagedOpenAIEmbedding
object
4 properties
CloudBoxDataSource
object
9 properties 1 required
DataSourceSyncRequest
object
Request model for syncing pipeline data sources. Notes: - This endpoint pulls from the 3p data source and parses. - We accept pipelinefileids for now because c…
1 property
ElementSegmentationConfig
object
1 property
NoneChunkingConfig
object
1 property
PipelineConfigurationHashes
object
Hashes for the configuration of a pipeline.
3 properties
FailureHandlingConfig
object
Configuration for handling different types of failures during data source processing.
1 property
DataSink
object
Schema for a data sink.
7 properties 5 required
CloudJiraDataSource
object
Cloud Jira Data Source integrating JiraReader.
8 properties 2 required
ConfigurableDataSourceNames
string
PipelineDataSource
object
Schema for a data source in a pipeline.
16 properties 8 required
EmbeddingModelConfig
object
Schema for an embedding model config.
6 properties 4 required
JobNameMapping
string
Enum for mapping original job names to readable names.
CloudMilvusVectorStore
object
Cloud Milvus Vector Store.
6 properties 1 required
CloudAstraDBVectorStore
object
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:…
7 properties 4 required
HuggingFaceInferenceAPIEmbeddingConfig
object
2 properties
VertexAIEmbeddingConfig
object
2 properties
AzureOpenAIEmbeddingConfig
object
2 properties
CloudMongoDBAtlasVectorSearch
object
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 LlamaCl…
8 properties 3 required
PGVectorDistanceMethod
string
Distance methods for PGVector. Docs: https://github.com/pgvector/pgvector?tab=readme-ov-filequery-options
ParsingMode
string
Enum for representing the mode of parsing to be used.
SentenceChunkingConfig
object
5 properties
MetadataFilters
object
Metadata filters for vector stores.
2 properties 1 required
WebhookConfiguration
object
Configuration for a single outbound webhook endpoint.
4 properties
CohereEmbedding
object
8 properties 1 required
ParserLanguages
string
Enum for representing the languages supported by the parser.
CloudJiraDataSourceV2
object
Cloud Jira Data Source integrating JiraReaderV2.
13 properties 3 required
PGVectorHNSWSettings
object
HNSW settings for PGVector.
5 properties
FilterCondition
string
Vector store filter conditions to combine different filters.
IngestionErrorResponse
object
3 properties 3 required
CloudAzStorageBlobDataSource
object
11 properties 2 required
CharacterChunkingConfig
object
3 properties
RetrievalMode
string
SemanticChunkingConfig
object
3 properties
PageSegmentationConfig
object
2 properties
CloudSharepointDataSource
object
14 properties 3 required
AutoTransformConfig
object
3 properties
GeminiEmbeddingConfig
object
2 properties
PipelineType
string
Enum for representing the type of a pipeline
Pooling
string
Enum of possible pooling choices with pooling behaviors.
CloudPineconeVectorStore
object
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:…
6 properties 2 required
CloudOneDriveDataSource
object
9 properties 4 required
ManagedIngestionStatusResponse
object
5 properties 1 required
HTTPValidationError
object
1 property
Pipeline
object
Schema for a pipeline.
18 properties 4 required
BedrockEmbeddingConfig
object
2 properties
CloudConfluenceDataSource
object
13 properties 2 required
ConfigurableDataSinkNames
string
HuggingFaceInferenceAPIEmbedding
object
12 properties
PGVectorVectorType
string
Vector storage formats for PGVector. Docs: https://github.com/pgvector/pgvector?tab=readme-ov-filequery-options
PipelineDataSourceUpdate
object
Schema for updating an association between a data source and a pipeline.
1 property
VertexTextEmbedding
object
12 properties 6 required
FailPageMode
string
Enum for representing the different available page error handling modes.
PipelineDataSourceCreate
object
Schema for creating an association between a data source and a pipeline.
2 properties 1 required
OpenAIEmbeddingConfig
object
2 properties
NoneSegmentationConfig
object
1 property
SparseModelType
string
Enum for sparse model types supported in LlamaCloud. SPLADE: Uses HuggingFace Splade model for sparse embeddings BM25: Uses Qdrant's FastEmbed BM25 model for s…
FilterOperator
string
Vector store filter operator.
BedrockEmbedding
object
12 properties
CohereEmbeddingConfig
object
2 properties
TokenChunkingConfig
object
4 properties
OpenAIEmbedding
object
13 properties
CloudAzureAISearchVectorStore
object
Cloud Azure AI Search Vector Store.
11 properties 2 required
PipelineMetadataConfig
object
2 properties
DataSourceReaderVersionMetadata
object
1 property
CloudSlackDataSource
object
9 properties 1 required
GeminiEmbedding
object
10 properties
CloudPostgresVectorStore
object
13 properties 8 required
CloudGoogleDriveDataSource
object
4 properties 1 required
LlamaParseParameters
object
119 properties
CloudQdrantVectorStore
object
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: col…
7 properties 3 required
CloudNotionPageDataSource
object
5 properties 1 required
BoxAuthMechanism
string
VertexEmbeddingMode
string
Copied from llamaindex.embeddings.vertex.base.VertexEmbeddingMode since importing llamaindex.embeddings.vertex.base incurs a lot of memory usage.
AzureOpenAIEmbedding
object
15 properties
PresetRetrievalParams
object
Schema for the search params for an retrieval execution that can be preset for a pipeline.
14 properties
ValidationError
object
5 properties 3 required
SparseModelConfig
object
Configuration for sparse embedding models used in hybrid search. This allows users to choose between Splade and BM25 models for sparse retrieval in managed dat…
2 properties
CloudS3DataSource
object
8 properties 1 required
ManagedIngestionStatus
string
Status of managed ingestion with partial Updates.

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

llamaparse-pipeline-data-sources-api-openapi.yml Raw ↑

Other APIs LlamaParse publishes across the network.

LlamaParse Extract API
LlamaParse Classify API
LlamaCloud Index API
LlamaParse Agent Data API
LlamaParse Batch Processing API
LlamaParse Batches API
LlamaParse Beta API
LlamaParse Chat API
LlamaParse Classifier API
LlamaParse Classify API
LlamaParse Configurations API
LlamaParse Data Sinks API
Where this information came from

This is an independent, third-party profile of LlamaParse Pipeline Data Sources API, published by API Evangelist. We do not operate, host, resell, or support these APIs, and we are not affiliated with or endorsed by the company unless stated above. Everything here is built from publicly available information — the company's own site, developer portal, documentation, public repositories, and the specifications it publishes for public use. Nothing is obtained by breaching a system, defeating an access control, or using credentials.

The Kin Score and Agent Readiness rating are independently calculated assessments of a company's public API artifacts, scored against a published rubric. They are not certifications, endorsements, security assessments, or audits.

Corrections, re-scores, and removal are free — no partnership or purchase required, and you do not need to justify the request. A removed company is recorded as unrated, never scored zero for having asked. Acknowledgement within one business day; removal within two.

info@apievangelist.com · Read the full data-sourcing policy →
On a security or compliance team? Put security in the subject line and you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.