The LlamaCloud API is the central REST API for LlamaIndex's cloud platform, providing programmatic access to managed document processing, indexing, and retrieval services. It enables developers to build production-grade LLM applications by leveraging cloud-hosted infrastructure for document ingestion, knowledge management, and agent orchestration. The API supports authentication via API keys and is available in both US and EU regions.
openapi: 3.1.0
info:
title: LlamaIndex LlamaCloud API
description: >-
The LlamaCloud API is the central REST API for LlamaIndex's cloud platform,
providing programmatic access to managed document processing, indexing, and
retrieval services. It enables developers to build production-grade LLM
applications by leveraging cloud-hosted infrastructure for document
ingestion, knowledge management, and agent orchestration. The API supports
authentication via API keys and is available in both US and EU regions.
version: '1.0'
contact:
name: LlamaIndex Support
url: https://www.llamaindex.ai/contact
termsOfService: https://www.llamaindex.ai/terms-of-service
externalDocs:
description: LlamaCloud API Documentation
url: https://developers.api.llamaindex.ai/
servers:
- url: https://api.cloud.llamaindex.ai/api/v1
description: US Production Server
- url: https://api.cloud.llamaindex.eu/api/v1
description: EU Production Server
tags:
- name: Data Sources
description: >-
Manage data sources at the project level.
- name: Files
description: >-
Upload, list, and manage files for use in pipelines and parsing jobs.
- name: Pipeline Data Sinks
description: >-
Manage data sinks that receive processed data from a pipeline.
- name: Pipeline Data Sources
description: >-
Manage data sources connected to a pipeline for automatic ingestion.
- name: Pipeline Files
description: >-
Manage files associated with a specific pipeline.
- name: Pipeline Jobs
description: >-
Monitor and manage ingestion jobs for a pipeline.
- name: Pipelines
description: >-
Create, configure, sync, and manage document ingestion pipelines.
- name: Projects
description: >-
Manage projects that organize pipelines, files, and other resources.
- name: Retrieval
description: >-
Query and retrieve content from indexed pipelines.
security:
- bearerAuth: []
paths:
/projects:
get:
operationId: listProjects
summary: List projects
description: >-
Retrieve a list of all projects associated with the authenticated
account. Projects serve as organizational containers for pipelines,
files, and other resources.
tags:
- Projects
responses:
'200':
description: Successfully retrieved list of projects
content:
application/json:
schema:
type: array
items:
$ref: '#/components/schemas/Project'
'401':
description: Unauthorized - invalid or missing API key
post:
operationId: createProject
summary: Create a project
description: >-
Create a new project to organize pipelines, files, and other cloud
resources.
tags:
- Projects
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/CreateProjectRequest'
responses:
'201':
description: Project created successfully
content:
application/json:
schema:
$ref: '#/components/schemas/Project'
'400':
description: Bad request - invalid project parameters
'401':
description: Unauthorized - invalid or missing API key
/projects/{projectId}:
get:
operationId: getProject
summary: Get a project
description: >-
Retrieve details of a specific project by its identifier.
tags:
- Projects
parameters:
- $ref: '#/components/parameters/projectId'
responses:
'200':
description: Successfully retrieved project details
content:
application/json:
schema:
$ref: '#/components/schemas/Project'
'401':
description: Unauthorized - invalid or missing API key
'404':
description: Project not found
/files:
post:
operationId: uploadFile
summary: Upload a file
description: >-
Upload a file to the cloud platform using multipart form data. The file
can then be used in pipelines, parsing jobs, or extraction workflows.
tags:
- Files
parameters:
- name: project_id
in: query
description: >-
The project to associate the file with.
required: true
schema:
type: string
requestBody:
required: true
content:
multipart/form-data:
schema:
type: object
required:
- file
properties:
file:
type: string
format: binary
description: >-
The file to upload.
responses:
'200':
description: File uploaded successfully
content:
application/json:
schema:
$ref: '#/components/schemas/File'
'400':
description: Bad request - invalid file or missing parameters
'401':
description: Unauthorized - invalid or missing API key
/pipelines:
get:
operationId: listPipelines
summary: List pipelines
description: >-
Retrieve a list of all pipelines for the specified project. Pipelines
represent document ingestion workflows that process, embed, and index
documents.
tags:
- Pipelines
parameters:
- name: project_id
in: query
description: >-
Filter pipelines by project identifier.
required: true
schema:
type: string
responses:
'200':
description: Successfully retrieved list of pipelines
content:
application/json:
schema:
type: array
items:
$ref: '#/components/schemas/Pipeline'
'401':
description: Unauthorized - invalid or missing API key
post:
operationId: createPipeline
summary: Create a pipeline
description: >-
Create a new document ingestion pipeline with specified configuration
including parsing, embedding, and vector store settings.
tags:
- Pipelines
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/CreatePipelineRequest'
responses:
'201':
description: Pipeline created successfully
content:
application/json:
schema:
$ref: '#/components/schemas/Pipeline'
'400':
description: Bad request - invalid pipeline configuration
'401':
description: Unauthorized - invalid or missing API key
/pipelines/{pipelineId}:
get:
operationId: getPipeline
summary: Get a pipeline
description: >-
Retrieve detailed information about a specific pipeline including its
configuration, status, and associated resources.
tags:
- Pipelines
parameters:
- $ref: '#/components/parameters/pipelineId'
responses:
'200':
description: Successfully retrieved pipeline details
content:
application/json:
schema:
$ref: '#/components/schemas/Pipeline'
'401':
description: Unauthorized - invalid or missing API key
'404':
description: Pipeline not found
delete:
operationId: deletePipeline
summary: Delete a pipeline
description: >-
Delete a pipeline and optionally its associated resources.
tags:
- Pipelines
parameters:
- $ref: '#/components/parameters/pipelineId'
responses:
'200':
description: Pipeline deleted successfully
'401':
description: Unauthorized - invalid or missing API key
'404':
description: Pipeline not found
/pipelines/{pipelineId}/sync:
post:
operationId: syncPipeline
summary: Sync a pipeline
description: >-
Run ingestion for the pipeline by incrementally updating the data sink
with upstream changes from data sources and files. This triggers a
new ingestion job that processes any new or modified content.
tags:
- Pipelines
parameters:
- $ref: '#/components/parameters/pipelineId'
responses:
'200':
description: Pipeline sync initiated successfully
content:
application/json:
schema:
$ref: '#/components/schemas/PipelineJob'
'401':
description: Unauthorized - invalid or missing API key
'404':
description: Pipeline not found
/pipelines/{pipelineId}/retrieve:
post:
operationId: runSearch
summary: Run search
description: >-
Execute a retrieval query against the indexed content of a managed
pipeline. Returns ranked results matching the query with configurable
retrieval modes including fast, accurate, and advanced options.
tags:
- Retrieval
parameters:
- $ref: '#/components/parameters/pipelineId'
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/RetrievalRequest'
responses:
'200':
description: Search results returned successfully
content:
application/json:
schema:
$ref: '#/components/schemas/RetrievalResponse'
'400':
description: Bad request - invalid query parameters
'401':
description: Unauthorized - invalid or missing API key
'404':
description: Pipeline not found
/pipelines/{pipelineId}/files:
get:
operationId: listPipelineFiles
summary: List pipeline files
description: >-
Retrieve a list of files associated with a specific pipeline, including
their processing status and metadata.
tags:
- Pipeline Files
parameters:
- $ref: '#/components/parameters/pipelineId'
responses:
'200':
description: Successfully retrieved list of pipeline files
content:
application/json:
schema:
type: array
items:
$ref: '#/components/schemas/PipelineFile'
'401':
description: Unauthorized - invalid or missing API key
'404':
description: Pipeline not found
put:
operationId: addFilesToPipeline
summary: Add files to a pipeline
description: >-
Add one or more previously uploaded files to a pipeline for processing.
Files can include optional custom metadata.
tags:
- Pipeline Files
parameters:
- $ref: '#/components/parameters/pipelineId'
requestBody:
required: true
content:
application/json:
schema:
type: array
items:
$ref: '#/components/schemas/PipelineFileInput'
responses:
'200':
description: Files added to pipeline successfully
'400':
description: Bad request - invalid file references
'401':
description: Unauthorized - invalid or missing API key
'404':
description: Pipeline not found
/pipelines/{pipelineId}/data-sources:
get:
operationId: listPipelineDataSources
summary: List pipeline data sources
description: >-
Retrieve data sources connected to a specific pipeline. Data sources
provide automatic ingestion of documents from external systems.
tags:
- Pipeline Data Sources
parameters:
- $ref: '#/components/parameters/pipelineId'
responses:
'200':
description: Successfully retrieved list of pipeline data sources
content:
application/json:
schema:
type: array
items:
$ref: '#/components/schemas/DataSource'
'401':
description: Unauthorized - invalid or missing API key
'404':
description: Pipeline not found
put:
operationId: addDataSourcesToPipeline
summary: Add data sources to a pipeline
description: >-
Connect data sources to a pipeline for automatic document ingestion.
When data sources are connected, the pipeline will sync content from
these sources based on the configured schedule.
tags:
- Pipeline Data Sources
parameters:
- $ref: '#/components/parameters/pipelineId'
requestBody:
required: true
content:
application/json:
schema:
type: array
items:
$ref: '#/components/schemas/DataSourceInput'
responses:
'200':
description: Data sources added to pipeline successfully
'400':
description: Bad request - invalid data source configuration
'401':
description: Unauthorized - invalid or missing API key
'404':
description: Pipeline not found
/pipelines/{pipelineId}/data-sinks:
get:
operationId: listPipelineDataSinks
summary: List pipeline data sinks
description: >-
Retrieve data sinks configured for a specific pipeline. Data sinks
define where processed and embedded content is stored, such as
vector databases.
tags:
- Pipeline Data Sinks
parameters:
- $ref: '#/components/parameters/pipelineId'
responses:
'200':
description: Successfully retrieved list of pipeline data sinks
content:
application/json:
schema:
type: array
items:
$ref: '#/components/schemas/DataSink'
'401':
description: Unauthorized - invalid or missing API key
'404':
description: Pipeline not found
/pipelines/{pipelineId}/jobs:
get:
operationId: listPipelineJobs
summary: List pipeline jobs
description: >-
Retrieve a list of ingestion jobs for a specific pipeline, including
their status and processing details.
tags:
- Pipeline Jobs
parameters:
- $ref: '#/components/parameters/pipelineId'
responses:
'200':
description: Successfully retrieved list of pipeline jobs
content:
application/json:
schema:
type: array
items:
$ref: '#/components/schemas/PipelineJob'
'401':
description: Unauthorized - invalid or missing API key
'404':
description: Pipeline not found
/data-sources:
get:
operationId: listDataSources
summary: List data sources
description: >-
Retrieve a list of all data sources for the specified project.
tags:
- Data Sources
parameters:
- name: project_id
in: query
description: >-
Filter data sources by project identifier.
required: true
schema:
type: string
responses:
'200':
description: Successfully retrieved list of data sources
content:
application/json:
schema:
type: array
items:
$ref: '#/components/schemas/DataSource'
'401':
description: Unauthorized - invalid or missing API key
post:
operationId: createDataSource
summary: Create a data source
description: >-
Create a new data source that can be connected to one or more pipelines
for automatic document ingestion.
tags:
- Data Sources
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/DataSourceInput'
responses:
'201':
description: Data source created successfully
content:
application/json:
schema:
$ref: '#/components/schemas/DataSource'
'400':
description: Bad request - invalid data source configuration
'401':
description: Unauthorized - invalid or missing API key
components:
securitySchemes:
bearerAuth:
type: http
scheme: bearer
bearerFormat: API Key
description: >-
LlamaCloud API key obtained from the LlamaCloud dashboard. Include as
a Bearer token in the Authorization header.
parameters:
projectId:
name: projectId
in: path
description: >-
Unique identifier of the project.
required: true
schema:
type: string
pipelineId:
name: pipelineId
in: path
description: >-
Unique identifier of the pipeline.
required: true
schema:
type: string
schemas:
Project:
type: object
description: >-
A project that organizes pipelines, files, and other cloud resources.
properties:
id:
type: string
description: >-
Unique identifier of the project.
name:
type: string
description: >-
Human-readable name of the project.
created_at:
type: string
format: date-time
description: >-
Timestamp when the project was created.
updated_at:
type: string
format: date-time
description: >-
Timestamp when the project was last updated.
CreateProjectRequest:
type: object
description: >-
Request body for creating a new project.
required:
- name
properties:
name:
type: string
description: >-
Human-readable name for the new project.
File:
type: object
description: >-
A file uploaded to the LlamaCloud platform.
properties:
id:
type: string
description: >-
Unique identifier of the file.
name:
type: string
description: >-
Original file name.
project_id:
type: string
description: >-
Identifier of the project the file belongs to.
file_size:
type: integer
description: >-
Size of the file in bytes.
content_type:
type: string
description: >-
MIME type of the file.
created_at:
type: string
format: date-time
description: >-
Timestamp when the file was uploaded.
Pipeline:
type: object
description: >-
A document ingestion pipeline that processes, embeds, and indexes
documents for retrieval.
properties:
id:
type: string
description: >-
Unique identifier of the pipeline.
name:
type: string
description: >-
Human-readable name of the pipeline.
project_id:
type: string
description: >-
Identifier of the project the pipeline belongs to.
status:
type: string
enum:
- active
- syncing
- error
- idle
description: >-
Current status of the pipeline.
sync_interval:
type: integer
description: >-
Scheduled sync frequency in seconds, if configured.
created_at:
type: string
format: date-time
description: >-
Timestamp when the pipeline was created.
updated_at:
type: string
format: date-time
description: >-
Timestamp when the pipeline was last updated.
CreatePipelineRequest:
type: object
description: >-
Request body for creating a new pipeline.
required:
- name
- project_id
properties:
name:
type: string
description: >-
Human-readable name for the new pipeline.
project_id:
type: string
description: >-
Identifier of the project to create the pipeline in.
sync_interval:
type: integer
description: >-
Optional scheduled sync frequency in seconds.
PipelineFile:
type: object
description: >-
A file associated with a pipeline, including processing status.
properties:
file_id:
type: string
description: >-
Unique identifier of the file.
name:
type: string
description: >-
Original file name.
status:
type: string
enum:
- pending
- processing
- completed
- error
description: >-
Processing status of the file within the pipeline.
metadata:
type: object
additionalProperties: true
description: >-
Custom metadata associated with the file.
PipelineFileInput:
type: object
description: >-
Input for adding a file to a pipeline.
required:
- file_id
properties:
file_id:
type: string
description: >-
Identifier of the file to add to the pipeline.
metadata:
type: object
additionalProperties: true
description: >-
Optional custom metadata to associate with the file.
PipelineJob:
type: object
description: >-
An ingestion job for a pipeline that tracks the processing of
documents.
properties:
id:
type: string
description: >-
Unique identifier of the job.
pipeline_id:
type: string
description: >-
Identifier of the pipeline the job belongs to.
status:
type: string
enum:
- pending
- running
- completed
- failed
description: >-
Current status of the job.
created_at:
type: string
format: date-time
description: >-
Timestamp when the job was created.
completed_at:
type: string
format: date-time
description: >-
Timestamp when the job completed, if applicable.
DataSource:
type: object
description: >-
A data source connected to a pipeline for automatic document ingestion.
properties:
id:
type: string
description: >-
Unique identifier of the data source.
name:
type: string
description: >-
Human-readable name of the data source.
source_type:
type: string
description: >-
Type of the data source.
project_id:
type: string
description: >-
Identifier of the project the data source belongs to.
config:
type: object
additionalProperties: true
description: >-
Configuration specific to the data source type.
created_at:
type: string
format: date-time
description: >-
Timestamp when the data source was created.
DataSourceInput:
type: object
description: >-
Input for creating or connecting a data source.
required:
- name
- source_type
properties:
name:
type: string
description: >-
Human-readable name for the data source.
source_type:
type: string
description: >-
Type of the data source.
project_id:
type: string
description: >-
Identifier of the project to associate the data source with.
config:
type: object
additionalProperties: true
description: >-
Configuration specific to the data source type.
DataSink:
type: object
description: >-
A data sink that receives processed and embedded content from a
pipeline, such as a vector database.
properties:
id:
type: string
description: >-
Unique identifier of the data sink.
name:
type: string
description: >-
Human-readable name of the data sink.
sink_type:
type: string
description: >-
Type of the data sink.
config:
type: object
additionalProperties: true
description: >-
Configuration specific to the data sink type.
RetrievalRequest:
type: object
description: >-
Request body for running a retrieval query against a pipeline.
required:
- query
properties:
query:
type: string
description: >-
The search query to run against the indexed content.
mode:
type: string
enum:
- fast
- accurate
- advanced
description: >-
Retrieval mode that controls the trade-off between speed and
accuracy.
top_k:
type: integer
minimum: 1
description: >-
Maximum number of results to return after re-ranking.
RetrievalResponse:
type: object
description: >-
Response containing retrieval results from a pipeline query.
properties:
results:
type: array
description: >-
List of retrieval results ranked by relevance.
items:
$ref: '#/components/schemas/RetrievalResult'
RetrievalResult:
type: object
description: >-
A single retrieval result containing matched content and metadata.
properties:
text:
type: string
description: >-
The retrieved text content.
score:
type: number
format: float
description: >-
Relevance score for the result.
metadata:
type: object
additionalProperties: true
description: >-
Metadata associated with the retrieved content.