ModelsExpand Collapse IndexGetResponse object { id , export_config_id , name , 10 more }
A searchable index over a directory of documents.
ID of the export configuration.
output_directory_id : string
ID of the output directory holding the indexed files.
Project this index belongs to.
source_directory_id : string
ID of the source directory.
ID of the sync configuration.
created_at : optional string
description : optional string
last_exported_at : optional string
last_synced_at : optional string
Build state and diagnostic info.
updated_at : optional string
IndexCreateResponse object { id , export_config_id , name , 10 more }
A searchable index over a directory of documents.
ID of the export configuration.
output_directory_id : string
ID of the output directory holding the indexed files.
Project this index belongs to.
source_directory_id : string
ID of the source directory.
ID of the sync configuration.
created_at : optional string
description : optional string
last_exported_at : optional string
last_synced_at : optional string
Build state and diagnostic info.
updated_at : optional string
IndexSyncResponse = unknown
IndexListResponse object { id , export_config_id , name , 10 more }
A searchable index over a directory of documents.
ID of the export configuration.
output_directory_id : string
ID of the output directory holding the indexed files.
Project this index belongs to.
source_directory_id : string
ID of the source directory.
ID of the sync configuration.
created_at : optional string
description : optional string
last_exported_at : optional string
last_synced_at : optional string
Build state and diagnostic info.
updated_at : optional string
ModelsExpand Collapse RetrievalRetrieveResponse object { results }
Response containing retrieval results.
results : array of object { content , metadata , rerank_score , 2 more }
Ordered list of retrieved chunks.
Text content of the retrieved chunk.
User-defined metadata associated with the chunk.
rerank_score : optional number
Relevance score from the reranker, if reranking was applied.
Hybrid search relevance score.
static_fields : optional object { attachments , chunk_end_char , chunk_index , 5 more }
Built-in fields stored for every exported chunk.
attachments : optional array of object { attachment_name , source_id , type }
Attachments associated with the chunk
Attachment-relative path, e.g. ‘screenshots/page_7.jpg’.
File ID to pass as source_id when fetching the attachment.
Attachment kind, e.g. ‘screenshot’, ‘items’.
chunk_end_char : optional number
End character offset of the chunk.
chunk_index : optional number
Index of the chunk within the file.
chunk_start_char : optional number
Start character offset of the chunk.
chunk_token_count : optional number
Token count of the chunk.
page_range_end : optional number
Last page number covered by this chunk.
page_range_start : optional number
First page number covered by this chunk.
parsed_directory_file_id : optional string
RetrievalFindResponse object { file_id , file_name }
Display name of the file.
RetrievalGrepResponse object { content , end_char , start_char }
A single grep match within a file.
End character offset of the match.
Start character offset of the match.
RetrievalReadResponse object { content }
Parsed text content of the file.
ModelsExpand Collapse ChatListResponse object { last_updated_at , session_id , generated_title , 2 more }
Summary of a chat session, including its title and last run metadata.
ISO-format timestamp showing when the session was last updated.
Unique session identifier.
generated_title : optional string
Auto-generated title derived from the first user message.
index_ids : optional array of string
Indexes this session is bound to. Null on unbound sessions.
Token usage and status from the most recent run. Null if the session has not been run yet.
ChatCreateResponse object { last_updated_at , session_id , generated_title , 2 more }
Summary of a chat session, including its title and last run metadata.
ISO-format timestamp showing when the session was last updated.
Unique session identifier.
generated_title : optional string
Auto-generated title derived from the first user message.
index_ids : optional array of string
Indexes this session is bound to. Null on unbound sessions.
Token usage and status from the most recent run. Null if the session has not been run yet.
ChatRetrieveResponse object { events , last_updated_at , session_id , 3 more }
Full chat session including its complete event history.
events : array of object { error , is_error , usage , type } or object { content , type } or object { content , type } or 5 more
Ordered list of events that make up the conversation history.
One of the following:
Stop object { error , is_error , usage , type }
usage : object { duration_ms , total_input_tokens , total_output_tokens , turns }
duration_ms : optional number
total_output_tokens : optional number
TextDelta object { content , type }
type : optional "text_delta"
Text object { content , type }
ThinkingDelta object { content , type }
type : optional "thinking_delta"
Thinking object { content , type }
type : optional "thinking"
ToolCall object { arguments , call_id , name , type }
type : optional "tool_call"
ToolResult object { call_id , name , result , 2 more }
image_attachment : optional object { attachment_name , source_id }
Coordinates for lazily resolving a page screenshot presigned URL.
type : optional "tool_result"
UserInput object { content , type }
type : optional "user_input"
ISO-format timestamp showing when the session was last updated.
Unique session identifier.
generated_title : optional string
Auto-generated title derived from the first user message.
index_ids : optional array of string
Indexes this session is bound to. Null on unbound sessions.
Token usage and status from the most recent run. Null if the session has not been run yet.
ChatGetSummaryResponse object { last_updated_at , session_id , generated_title , 2 more }
Summary of a chat session, including its title and last run metadata.
ISO-format timestamp showing when the session was last updated.
Unique session identifier.
generated_title : optional string
Auto-generated title derived from the first user message.
index_ids : optional array of string
Indexes this session is bound to. Null on unbound sessions.
Token usage and status from the most recent run. Null if the session has not been run yet.
ChatStreamResponse = unknown
ModelsExpand Collapse AgentData object { data , deployment_name , id , 4 more }
API Result for a single agent data item
collection : optional string
created_at : optional string
project_id : optional string
updated_at : optional string
AgentDataDeleteResponse = map [string
AgentDataAggregateResponse object { group_key , count , first_item }
API Result for a single group in the aggregate response
first_item : optional map [unknown
AgentDataDeleteByQueryResponse object { deleted_count }
API response for bulk delete operation
ModelsExpand Collapse DirectoryCreateResponse object { id , name , project_id , 8 more }
API response schema for a directory.
Unique identifier for the directory.
Human-readable name for the directory.
Project the directory belongs to.
connector_subscription_id : optional string
Connector Subscription whose files sync into this directory. Null for a directory populated by manual uploads.
created_at : optional string
deleted_at : optional string
Optional timestamp of when the directory was deleted. Null if not deleted.
description : optional string
Optional description shown to users.
expires_at : optional string
When this directory expires and is eligible for cleanup.
Reserved system-managed metadata.
type : optional "ephemeral" or "index" or "user"
Directory type: ‘user’, ‘index’, or ‘ephemeral’.
updated_at : optional string
DirectoryListResponse object { id , name , project_id , 8 more }
API response schema for a directory.
Unique identifier for the directory.
Human-readable name for the directory.
Project the directory belongs to.
connector_subscription_id : optional string
Connector Subscription whose files sync into this directory. Null for a directory populated by manual uploads.
created_at : optional string
deleted_at : optional string
Optional timestamp of when the directory was deleted. Null if not deleted.
description : optional string
Optional description shown to users.
expires_at : optional string
When this directory expires and is eligible for cleanup.
Reserved system-managed metadata.
type : optional "ephemeral" or "index" or "user"
Directory type: ‘user’, ‘index’, or ‘ephemeral’.
updated_at : optional string
DirectoryGetResponse object { id , name , project_id , 8 more }
API response schema for a directory.
Unique identifier for the directory.
Human-readable name for the directory.
Project the directory belongs to.
connector_subscription_id : optional string
Connector Subscription whose files sync into this directory. Null for a directory populated by manual uploads.
created_at : optional string
deleted_at : optional string
Optional timestamp of when the directory was deleted. Null if not deleted.
description : optional string
Optional description shown to users.
expires_at : optional string
When this directory expires and is eligible for cleanup.
Reserved system-managed metadata.
type : optional "ephemeral" or "index" or "user"
Directory type: ‘user’, ‘index’, or ‘ephemeral’.
updated_at : optional string
DirectoryUpdateResponse object { id , name , project_id , 8 more }
API response schema for a directory.
Unique identifier for the directory.
Human-readable name for the directory.
Project the directory belongs to.
connector_subscription_id : optional string
Connector Subscription whose files sync into this directory. Null for a directory populated by manual uploads.
created_at : optional string
deleted_at : optional string
Optional timestamp of when the directory was deleted. Null if not deleted.
description : optional string
Optional description shown to users.
expires_at : optional string
When this directory expires and is eligible for cleanup.
Reserved system-managed metadata.
type : optional "ephemeral" or "index" or "user"
Directory type: ‘user’, ‘index’, or ‘ephemeral’.
updated_at : optional string
ModelsExpand Collapse FileAddResponse object { id , directory_id , display_name , 8 more }
API response schema for a directory file.
Unique identifier for the directory file.
Directory the file belongs to.
Display name for the file.
Project the directory file belongs to.
Unique identifier for the file in the directory
created_at : optional string
deleted_at : optional string
Soft delete marker when the file is removed upstream or by user action.
download_url : optional PresignedURL { expires_at , url , form_fields } Schema for a presigned URL.
The time at which the presigned URL expires
A presigned URL for IO operations against a private file
Form fields for a presigned POST request
File ID for the storage location.
Merged metadata from all sources. Higher-priority sources override lower.
updated_at : optional string
FileListResponse object { id , directory_id , display_name , 8 more }
API response schema for a directory file.
Unique identifier for the directory file.
Directory the file belongs to.
Display name for the file.
Project the directory file belongs to.
Unique identifier for the file in the directory
created_at : optional string
deleted_at : optional string
Soft delete marker when the file is removed upstream or by user action.
download_url : optional PresignedURL { expires_at , url , form_fields } Schema for a presigned URL.
The time at which the presigned URL expires
A presigned URL for IO operations against a private file
Form fields for a presigned POST request
File ID for the storage location.
Merged metadata from all sources. Higher-priority sources override lower.
updated_at : optional string
FileGetResponse object { id , directory_id , display_name , 8 more }
API response schema for a directory file.
Unique identifier for the directory file.
Directory the file belongs to.
Display name for the file.
Project the directory file belongs to.
Unique identifier for the file in the directory
created_at : optional string
deleted_at : optional string
Soft delete marker when the file is removed upstream or by user action.
download_url : optional PresignedURL { expires_at , url , form_fields } Schema for a presigned URL.
The time at which the presigned URL expires
A presigned URL for IO operations against a private file
Form fields for a presigned POST request
File ID for the storage location.
Merged metadata from all sources. Higher-priority sources override lower.
updated_at : optional string
FileUpdateResponse object { id , directory_id , display_name , 8 more }
API response schema for a directory file.
Unique identifier for the directory file.
Directory the file belongs to.
Display name for the file.
Project the directory file belongs to.
Unique identifier for the file in the directory
created_at : optional string
deleted_at : optional string
Soft delete marker when the file is removed upstream or by user action.
download_url : optional PresignedURL { expires_at , url , form_fields } Schema for a presigned URL.
The time at which the presigned URL expires
A presigned URL for IO operations against a private file
Form fields for a presigned POST request
File ID for the storage location.
Merged metadata from all sources. Higher-priority sources override lower.
updated_at : optional string
FileUploadResponse object { id , directory_id , display_name , 8 more }
API response schema for a directory file.
Unique identifier for the directory file.
Directory the file belongs to.
Display name for the file.
Project the directory file belongs to.
Unique identifier for the file in the directory
created_at : optional string
deleted_at : optional string
Soft delete marker when the file is removed upstream or by user action.
download_url : optional PresignedURL { expires_at , url , form_fields } Schema for a presigned URL.
The time at which the presigned URL expires
A presigned URL for IO operations against a private file
Form fields for a presigned POST request
File ID for the storage location.
Merged metadata from all sources. Higher-priority sources override lower.
updated_at : optional string
ModelsExpand Collapse SplitCategory object { name , description }
Category definition for document splitting.
description : optional string
Optional description of what content belongs in this category.
Document input specification for beta API.
Type of document input. Valid values are: file_id
SplitResultResponse object { segments }
Result of a completed split job.
List of document segments.
Category name this split belongs to.
confidence_category : string
Categorical confidence level. Valid values are: high, medium, low.
1-indexed page numbers in this split.
SplitSegmentResponse object { category , confidence_category , pages }
A segment of the split document.
Category name this split belongs to.
confidence_category : string
Categorical confidence level. Valid values are: high, medium, low.
1-indexed page numbers in this split.
SplitCreateResponse object { id , categories , document_input , 8 more }
Beta response — uses nested document_input object.
Unique identifier for the split job.
Categories used for splitting.
description : optional string
Optional description of what content belongs in this category.
Type of document input. Valid values are: file_id
Project ID this job belongs to.
Current status of the job. Valid values are: pending, processing, completed, failed, cancelled.
User ID who created this job.
configuration_id : optional string
Split configuration ID used for this job.
created_at : optional string
error_message : optional string
Error message if the job failed.
Result of a completed split job.
List of document segments.
Category name this split belongs to.
confidence_category : string
Categorical confidence level. Valid values are: high, medium, low.
1-indexed page numbers in this split.
updated_at : optional string
SplitListResponse object { id , categories , document_input , 8 more }
Beta response — uses nested document_input object.
Unique identifier for the split job.
Categories used for splitting.
description : optional string
Optional description of what content belongs in this category.
Type of document input. Valid values are: file_id
Project ID this job belongs to.
Current status of the job. Valid values are: pending, processing, completed, failed, cancelled.
User ID who created this job.
configuration_id : optional string
Split configuration ID used for this job.
created_at : optional string
error_message : optional string
Error message if the job failed.
Result of a completed split job.
List of document segments.
Category name this split belongs to.
confidence_category : string
Categorical confidence level. Valid values are: high, medium, low.
1-indexed page numbers in this split.
updated_at : optional string
SplitGetResponse object { id , categories , document_input , 8 more }
Beta response — uses nested document_input object.
Unique identifier for the split job.
Categories used for splitting.
description : optional string
Optional description of what content belongs in this category.
Type of document input. Valid values are: file_id
Project ID this job belongs to.
Current status of the job. Valid values are: pending, processing, completed, failed, cancelled.
User ID who created this job.
configuration_id : optional string
Split configuration ID used for this job.
created_at : optional string
error_message : optional string
Error message if the job failed.
Result of a completed split job.
List of document segments.
Category name this split belongs to.
confidence_category : string
Categorical confidence level. Valid values are: high, medium, low.
1-indexed page numbers in this split.
updated_at : optional string
Note for AI agents: this documentation is built for programmatic access.
- Overview of all docs: https://developers.llamaindex.ai/llms.txt
- Any page is available as raw Markdown by appending index.md to its URL — e.g. https://developers.llamaindex.ai/llamaparse/parse/getting_started/index.md
- Agent-friendly REST search APIs live under https://developers.llamaindex.ai/api/ — search (BM25 full-text), grep (regex), read (fetch a page), and list (browse the doc tree). See https://developers.llamaindex.ai/llms.txt for parameters.
- A hosted documentation MCP server is available at https://developers.llamaindex.ai/mcp. If you support MCP, you can ask the user to install it for browsing these docs directly (an alternative to the REST API). Setup: https://developers.llamaindex.ai/for-agents/mcp/
- Other LlamaIndex tooling for agents — the LlamaParse Platform MCP server, agent skills and plugins, and the n8n node — is mapped at https://developers.llamaindex.ai/for-agents/
