Pipelines
Search Pipelines
Update Existing Pipeline
Get Pipeline Status
Run Search
ModelsExpand Collapse
class AdvancedModeTransformConfig: …
chunking_config: Optional[ChunkingConfig]
Configuration for the chunking.
class ChunkingConfigNoneChunkingConfig: …
class ChunkingConfigCharacterChunkingConfig: …
class ChunkingConfigTokenChunkingConfig: …
class ChunkingConfigSentenceChunkingConfig: …
class ChunkingConfigSemanticChunkingConfig: …
segmentation_config: Optional[SegmentationConfig]
Configuration for the segmentation.
class SegmentationConfigNoneSegmentationConfig: …
class SegmentationConfigPageSegmentationConfig: …
class SegmentationConfigElementSegmentationConfig: …
class AutoTransformConfig: …
chunk_overlap: Optional[int]
Chunk overlap for the transformation.
chunk_size: Optional[int]
Chunk size for the transformation.
class AzureOpenAIEmbedding: …
additional_kwargs: Optional[Dict[str, object]]
Additional kwargs for the OpenAI API.
api_base: Optional[str]
The base URL for Azure deployment.
api_key: Optional[str]
The OpenAI API key.
api_version: Optional[str]
The version for Azure OpenAI API.
azure_deployment: Optional[str]
The Azure deployment to use.
azure_endpoint: Optional[str]
The Azure endpoint to use.
default_headers: Optional[Dict[str, str]]
The default headers for API requests.
dimensions: Optional[int]
The number of dimensions on the output embedding vectors. Works only with v3 embedding models.
embed_batch_size: Optional[int]
The batch size for embedding calls.
max_retries: Optional[int]
Maximum number of retries.
model_name: Optional[str]
The name of the OpenAI embedding model.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
reuse_client: Optional[bool]
Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability.
timeout: Optional[float]
Timeout for each request.
class AzureOpenAIEmbeddingConfig: …
component: Optional[AzureOpenAIEmbedding]
Configuration for the Azure OpenAI embedding model.
additional_kwargs: Optional[Dict[str, object]]
Additional kwargs for the OpenAI API.
api_base: Optional[str]
The base URL for Azure deployment.
api_key: Optional[str]
The OpenAI API key.
api_version: Optional[str]
The version for Azure OpenAI API.
azure_deployment: Optional[str]
The Azure deployment to use.
azure_endpoint: Optional[str]
The Azure endpoint to use.
default_headers: Optional[Dict[str, str]]
The default headers for API requests.
dimensions: Optional[int]
The number of dimensions on the output embedding vectors. Works only with v3 embedding models.
embed_batch_size: Optional[int]
The batch size for embedding calls.
max_retries: Optional[int]
Maximum number of retries.
model_name: Optional[str]
The name of the OpenAI embedding model.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
reuse_client: Optional[bool]
Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability.
timeout: Optional[float]
Timeout for each request.
type: Optional[Literal["AZURE_EMBEDDING"]]
Type of the embedding model.
class BedrockEmbedding: …
additional_kwargs: Optional[Dict[str, object]]
Additional kwargs for the bedrock client.
aws_access_key_id: Optional[str]
AWS Access Key ID to use
aws_secret_access_key: Optional[str]
AWS Secret Access Key to use
aws_session_token: Optional[str]
AWS Session Token to use
embed_batch_size: Optional[int]
The batch size for embedding calls.
max_retries: Optional[int]
The maximum number of API retries.
model_name: Optional[str]
The modelId of the Bedrock model to use.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
profile_name: Optional[str]
The name of aws profile to use. If not given, then the default profile is used.
region_name: Optional[str]
AWS region name to use. Uses region configured in AWS CLI if not passed
timeout: Optional[float]
The timeout for the Bedrock API request in seconds. It will be used for both connect and read timeouts.
class BedrockEmbeddingConfig: …
component: Optional[BedrockEmbedding]
Configuration for the Bedrock embedding model.
additional_kwargs: Optional[Dict[str, object]]
Additional kwargs for the bedrock client.
aws_access_key_id: Optional[str]
AWS Access Key ID to use
aws_secret_access_key: Optional[str]
AWS Secret Access Key to use
aws_session_token: Optional[str]
AWS Session Token to use
embed_batch_size: Optional[int]
The batch size for embedding calls.
max_retries: Optional[int]
The maximum number of API retries.
model_name: Optional[str]
The modelId of the Bedrock model to use.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
profile_name: Optional[str]
The name of aws profile to use. If not given, then the default profile is used.
region_name: Optional[str]
AWS region name to use. Uses region configured in AWS CLI if not passed
timeout: Optional[float]
The timeout for the Bedrock API request in seconds. It will be used for both connect and read timeouts.
type: Optional[Literal["BEDROCK_EMBEDDING"]]
Type of the embedding model.
class CohereEmbedding: …
api_key: Optional[str]
The Cohere API key.
embed_batch_size: Optional[int]
The batch size for embedding calls.
embedding_type: Optional[str]
Embedding type. If not provided float embedding_type is used when needed.
input_type: Optional[str]
Model Input type. If not provided, search_document and search_query are used when needed.
model_name: Optional[str]
The modelId of the Cohere model to use.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
truncate: Optional[str]
Truncation type - START/ END/ NONE
class CohereEmbeddingConfig: …
component: Optional[CohereEmbedding]
Configuration for the Cohere embedding model.
api_key: Optional[str]
The Cohere API key.
embed_batch_size: Optional[int]
The batch size for embedding calls.
embedding_type: Optional[str]
Embedding type. If not provided float embedding_type is used when needed.
input_type: Optional[str]
Model Input type. If not provided, search_document and search_query are used when needed.
model_name: Optional[str]
The modelId of the Cohere model to use.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
truncate: Optional[str]
Truncation type - START/ END/ NONE
type: Optional[Literal["COHERE_EMBEDDING"]]
Type of the embedding model.
class DataSinkCreate: …
Schema for creating a data sink.
component: Component
Component that implements the data sink
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
api_key: str
The API key for authenticating with Pinecone
class CloudPostgresVectorStore: …
hnsw_settings: Optional[PgVectorHnswSettings]
HNSW settings for PGVector.
distance_method: Optional[Literal["l2", "ip", "cosine", 3 more]]
The distance method to use.
ef_construction: Optional[int]
The number of edges to use during the construction phase.
ef_search: Optional[int]
The number of edges to use during the search phase.
m: Optional[int]
The number of bi-directional links created for each new element.
vector_type: Optional[Literal["vector", "half_vec", "bit", "sparse_vec"]]
The type of vector to use.
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
class CloudAzureAISearchVectorStore: …
Cloud Azure AI Search Vector Store.
class CloudMongoDBAtlasVectorSearch: …
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 CloudMilvusVectorStore: …
Cloud Milvus Vector Store.
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'
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'
name: str
The name of the data sink.
sink_type: Literal["PINECONE", "POSTGRES", "QDRANT", 4 more]
class GeminiEmbedding: …
api_base: Optional[str]
API base to access the model. Defaults to None.
api_key: Optional[str]
API key to access the model. Defaults to None.
embed_batch_size: Optional[int]
The batch size for embedding calls.
model_name: Optional[str]
The modelId of the Gemini model to use.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
task_type: Optional[str]
The task for embedding model.
title: Optional[str]
Title is only applicable for retrieval_document tasks, and is used to represent a document title. For other tasks, title is invalid.
transport: Optional[str]
Transport to access the model. Defaults to None.
class GeminiEmbeddingConfig: …
component: Optional[GeminiEmbedding]
Configuration for the Gemini embedding model.
api_base: Optional[str]
API base to access the model. Defaults to None.
api_key: Optional[str]
API key to access the model. Defaults to None.
embed_batch_size: Optional[int]
The batch size for embedding calls.
model_name: Optional[str]
The modelId of the Gemini model to use.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
task_type: Optional[str]
The task for embedding model.
title: Optional[str]
Title is only applicable for retrieval_document tasks, and is used to represent a document title. For other tasks, title is invalid.
transport: Optional[str]
Transport to access the model. Defaults to None.
type: Optional[Literal["GEMINI_EMBEDDING"]]
Type of the embedding model.
class HuggingFaceInferenceAPIEmbedding: …
token: Optional[Union[str, bool, null]]
Hugging Face token. Will default to the locally saved token. Pass token=False if you don’t want to send your token to the server.
cookies: Optional[Dict[str, str]]
Additional cookies to send to the server.
embed_batch_size: Optional[int]
The batch size for embedding calls.
headers: Optional[Dict[str, str]]
Additional headers to send to the server. By default only the authorization and user-agent headers are sent. Values in this dictionary will override the default values.
model_name: Optional[str]
Hugging Face model name. If None, the task will be used.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
pooling: Optional[Literal["cls", "mean", "last"]]
Enum of possible pooling choices with pooling behaviors.
query_instruction: Optional[str]
Instruction to prepend during query embedding.
task: Optional[str]
Optional task to pick Hugging Face's recommended model, used when model_name is left as default of None.
text_instruction: Optional[str]
Instruction to prepend during text embedding.
timeout: Optional[float]
The maximum number of seconds to wait for a response from the server. Loading a new model in Inference API can take up to several minutes. Defaults to None, meaning it will loop until the server is available.
class HuggingFaceInferenceAPIEmbeddingConfig: …
component: Optional[HuggingFaceInferenceAPIEmbedding]
Configuration for the HuggingFace Inference API embedding model.
token: Optional[Union[str, bool, null]]
Hugging Face token. Will default to the locally saved token. Pass token=False if you don’t want to send your token to the server.
cookies: Optional[Dict[str, str]]
Additional cookies to send to the server.
embed_batch_size: Optional[int]
The batch size for embedding calls.
headers: Optional[Dict[str, str]]
Additional headers to send to the server. By default only the authorization and user-agent headers are sent. Values in this dictionary will override the default values.
model_name: Optional[str]
Hugging Face model name. If None, the task will be used.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
pooling: Optional[Literal["cls", "mean", "last"]]
Enum of possible pooling choices with pooling behaviors.
query_instruction: Optional[str]
Instruction to prepend during query embedding.
task: Optional[str]
Optional task to pick Hugging Face's recommended model, used when model_name is left as default of None.
text_instruction: Optional[str]
Instruction to prepend during text embedding.
timeout: Optional[float]
The maximum number of seconds to wait for a response from the server. Loading a new model in Inference API can take up to several minutes. Defaults to None, meaning it will loop until the server is available.
type: Optional[Literal["HUGGINGFACE_API_EMBEDDING"]]
Type of the embedding model.
class LlamaParseParameters: …
Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline.
images_to_save: Optional[List[Literal["screenshot", "embedded", "layout"]]]
parse_mode: Optional[ParsingMode]
Enum for representing the mode of parsing to be used.
priority: Optional[Literal["low", "medium", "high", "critical"]]
The priority for the request. This field may be ignored or overwritten depending on the organization tier.
replace_failed_page_mode: Optional[FailPageMode]
Enum for representing the different available page error handling modes.
The outbound webhook configurations
webhook_events: Optional[List[Literal["extract.pending", "extract.success", "extract.error", 13 more]]]
List of event names to subscribe to
webhook_headers: Optional[Dict[str, str]]
Custom HTTP headers to include with webhook requests.
webhook_output_format: Optional[str]
The output format to use for the webhook. Defaults to string if none supplied. Currently supported values: string, json
webhook_url: Optional[str]
The URL to send webhook notifications to.
class LlmParameters: …
model_name: Optional[Literal["GPT_4O", "GPT_4O_MINI", "GPT_4_1", 11 more]]
The name of the model to use for LLM completions.
system_prompt: Optional[str]
The system prompt to use for the completion.
temperature: Optional[float]
The temperature value for the model.
use_chain_of_thought_reasoning: Optional[bool]
Whether to use chain of thought reasoning.
use_citation: Optional[bool]
Whether to show citations in the response.
class ManagedIngestionStatusResponse: …
status: Literal["NOT_STARTED", "IN_PROGRESS", "SUCCESS", 3 more]
Status of the ingestion.
deployment_date: Optional[datetime]
Date of the deployment.
effective_at: Optional[datetime]
When the status is effective
error: Optional[List[Error]]
List of errors that occurred during ingestion.
job_id: str
ID of the job that failed.
message: str
List of errors that occurred during ingestion.
step: Literal["MANAGED_INGESTION", "DATA_SOURCE", "FILE_UPDATER", 4 more]
Name of the job that failed.
job_id: Optional[str]
ID of the latest job.
Literal["system", "developer", "user", 5 more]
Message role.
class MetadataFilters: …
Metadata filters for vector stores.
filters: List[Filter]
class FilterMetadataFilter: …
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 converted to string before.
See: https://docs.pydantic.dev/latest/usage/types/#strict-types
value: Union[float, str, List[str], 3 more]
operator: Optional[Literal["==", ">", "<", 11 more]]
Vector store filter operator.
class MetadataFilters: …
Metadata filters for vector stores.
filters: List[Filter]
class FilterMetadataFilter: …
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 converted to string before.
See: https://docs.pydantic.dev/latest/usage/types/#strict-types
value: Union[float, str, List[str], 3 more]
operator: Optional[Literal["==", ">", "<", 11 more]]
Vector store filter operator.
condition: Optional[Literal["and", "or", "not"]]
Vector store filter conditions to combine different filters.
condition: Optional[Literal["and", "or", "not"]]
Vector store filter conditions to combine different filters.
class OpenAIEmbedding: …
additional_kwargs: Optional[Dict[str, object]]
Additional kwargs for the OpenAI API.
api_base: Optional[str]
The base URL for OpenAI API.
api_key: Optional[str]
The OpenAI API key.
api_version: Optional[str]
The version for OpenAI API.
default_headers: Optional[Dict[str, str]]
The default headers for API requests.
dimensions: Optional[int]
The number of dimensions on the output embedding vectors. Works only with v3 embedding models.
embed_batch_size: Optional[int]
The batch size for embedding calls.
max_retries: Optional[int]
Maximum number of retries.
model_name: Optional[str]
The name of the OpenAI embedding model.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
reuse_client: Optional[bool]
Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability.
timeout: Optional[float]
Timeout for each request.
class OpenAIEmbeddingConfig: …
component: Optional[OpenAIEmbedding]
Configuration for the OpenAI embedding model.
additional_kwargs: Optional[Dict[str, object]]
Additional kwargs for the OpenAI API.
api_base: Optional[str]
The base URL for OpenAI API.
api_key: Optional[str]
The OpenAI API key.
api_version: Optional[str]
The version for OpenAI API.
default_headers: Optional[Dict[str, str]]
The default headers for API requests.
dimensions: Optional[int]
The number of dimensions on the output embedding vectors. Works only with v3 embedding models.
embed_batch_size: Optional[int]
The batch size for embedding calls.
max_retries: Optional[int]
Maximum number of retries.
model_name: Optional[str]
The name of the OpenAI embedding model.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
reuse_client: Optional[bool]
Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability.
timeout: Optional[float]
Timeout for each request.
type: Optional[Literal["OPENAI_EMBEDDING"]]
Type of the embedding model.
class PageFigureNodeWithScore: …
Page figure metadata with score
node: Node
confidence: float
The confidence of the figure
figure_name: str
The name of the figure
figure_size: int
The size of the figure in bytes
file_id: str
The ID of the file that the figure was taken from
page_index: int
The index of the page for which the figure is taken (0-indexed)
is_likely_noise: Optional[bool]
Whether the figure is likely to be noise
metadata: Optional[Dict[str, object]]
Metadata for the figure
score: float
The score of the figure node
class PageScreenshotNodeWithScore: …
Page screenshot metadata with score
node: Node
file_id: str
The ID of the file that the page screenshot was taken from
image_size: int
The size of the image in bytes
page_index: int
The index of the page for which the screenshot is taken (0-indexed)
metadata: Optional[Dict[str, object]]
Metadata for the screenshot
score: float
The score of the screenshot node
class Pipeline: …
Schema for a pipeline.
id: str
Unique identifier
embedding_config: EmbeddingConfig
class EmbeddingConfigManagedOpenAIEmbeddingConfig: …
component: Optional[EmbeddingConfigManagedOpenAIEmbeddingConfigComponent]
Configuration for the Managed OpenAI embedding model.
embed_batch_size: Optional[int]
The batch size for embedding calls.
model_name: Optional[Literal["openai-text-embedding-3-small"]]
The name of the OpenAI embedding model.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
type: Optional[Literal["MANAGED_OPENAI_EMBEDDING"]]
Type of the embedding model.
class AzureOpenAIEmbeddingConfig: …
component: Optional[AzureOpenAIEmbedding]
Configuration for the Azure OpenAI embedding model.
additional_kwargs: Optional[Dict[str, object]]
Additional kwargs for the OpenAI API.
api_base: Optional[str]
The base URL for Azure deployment.
api_key: Optional[str]
The OpenAI API key.
api_version: Optional[str]
The version for Azure OpenAI API.
azure_deployment: Optional[str]
The Azure deployment to use.
azure_endpoint: Optional[str]
The Azure endpoint to use.
default_headers: Optional[Dict[str, str]]
The default headers for API requests.
dimensions: Optional[int]
The number of dimensions on the output embedding vectors. Works only with v3 embedding models.
embed_batch_size: Optional[int]
The batch size for embedding calls.
max_retries: Optional[int]
Maximum number of retries.
model_name: Optional[str]
The name of the OpenAI embedding model.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
reuse_client: Optional[bool]
Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability.
timeout: Optional[float]
Timeout for each request.
type: Optional[Literal["AZURE_EMBEDDING"]]
Type of the embedding model.
class CohereEmbeddingConfig: …
component: Optional[CohereEmbedding]
Configuration for the Cohere embedding model.
api_key: Optional[str]
The Cohere API key.
embed_batch_size: Optional[int]
The batch size for embedding calls.
embedding_type: Optional[str]
Embedding type. If not provided float embedding_type is used when needed.
input_type: Optional[str]
Model Input type. If not provided, search_document and search_query are used when needed.
model_name: Optional[str]
The modelId of the Cohere model to use.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
truncate: Optional[str]
Truncation type - START/ END/ NONE
type: Optional[Literal["COHERE_EMBEDDING"]]
Type of the embedding model.
class GeminiEmbeddingConfig: …
component: Optional[GeminiEmbedding]
Configuration for the Gemini embedding model.
api_base: Optional[str]
API base to access the model. Defaults to None.
api_key: Optional[str]
API key to access the model. Defaults to None.
embed_batch_size: Optional[int]
The batch size for embedding calls.
model_name: Optional[str]
The modelId of the Gemini model to use.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
task_type: Optional[str]
The task for embedding model.
title: Optional[str]
Title is only applicable for retrieval_document tasks, and is used to represent a document title. For other tasks, title is invalid.
transport: Optional[str]
Transport to access the model. Defaults to None.
type: Optional[Literal["GEMINI_EMBEDDING"]]
Type of the embedding model.
class HuggingFaceInferenceAPIEmbeddingConfig: …
component: Optional[HuggingFaceInferenceAPIEmbedding]
Configuration for the HuggingFace Inference API embedding model.
token: Optional[Union[str, bool, null]]
Hugging Face token. Will default to the locally saved token. Pass token=False if you don’t want to send your token to the server.
cookies: Optional[Dict[str, str]]
Additional cookies to send to the server.
embed_batch_size: Optional[int]
The batch size for embedding calls.
headers: Optional[Dict[str, str]]
Additional headers to send to the server. By default only the authorization and user-agent headers are sent. Values in this dictionary will override the default values.
model_name: Optional[str]
Hugging Face model name. If None, the task will be used.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
pooling: Optional[Literal["cls", "mean", "last"]]
Enum of possible pooling choices with pooling behaviors.
query_instruction: Optional[str]
Instruction to prepend during query embedding.
task: Optional[str]
Optional task to pick Hugging Face's recommended model, used when model_name is left as default of None.
text_instruction: Optional[str]
Instruction to prepend during text embedding.
timeout: Optional[float]
The maximum number of seconds to wait for a response from the server. Loading a new model in Inference API can take up to several minutes. Defaults to None, meaning it will loop until the server is available.
type: Optional[Literal["HUGGINGFACE_API_EMBEDDING"]]
Type of the embedding model.
class OpenAIEmbeddingConfig: …
component: Optional[OpenAIEmbedding]
Configuration for the OpenAI embedding model.
additional_kwargs: Optional[Dict[str, object]]
Additional kwargs for the OpenAI API.
api_base: Optional[str]
The base URL for OpenAI API.
api_key: Optional[str]
The OpenAI API key.
api_version: Optional[str]
The version for OpenAI API.
default_headers: Optional[Dict[str, str]]
The default headers for API requests.
dimensions: Optional[int]
The number of dimensions on the output embedding vectors. Works only with v3 embedding models.
embed_batch_size: Optional[int]
The batch size for embedding calls.
max_retries: Optional[int]
Maximum number of retries.
model_name: Optional[str]
The name of the OpenAI embedding model.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
reuse_client: Optional[bool]
Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability.
timeout: Optional[float]
Timeout for each request.
type: Optional[Literal["OPENAI_EMBEDDING"]]
Type of the embedding model.
class VertexAIEmbeddingConfig: …
component: Optional[VertexTextEmbedding]
Configuration for the VertexAI embedding model.
client_email: Optional[str]
The client email for the VertexAI credentials.
location: str
The default location to use when making API calls.
private_key: Optional[str]
The private key for the VertexAI credentials.
private_key_id: Optional[str]
The private key ID for the VertexAI credentials.
project: str
The default GCP project to use when making Vertex API calls.
token_uri: Optional[str]
The token URI for the VertexAI credentials.
additional_kwargs: Optional[Dict[str, object]]
Additional kwargs for the Vertex.
embed_batch_size: Optional[int]
The batch size for embedding calls.
embed_mode: Optional[Literal["default", "classification", "clustering", 2 more]]
The embedding mode to use.
model_name: Optional[str]
The modelId of the VertexAI model to use.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
type: Optional[Literal["VERTEXAI_EMBEDDING"]]
Type of the embedding model.
class BedrockEmbeddingConfig: …
component: Optional[BedrockEmbedding]
Configuration for the Bedrock embedding model.
additional_kwargs: Optional[Dict[str, object]]
Additional kwargs for the bedrock client.
aws_access_key_id: Optional[str]
AWS Access Key ID to use
aws_secret_access_key: Optional[str]
AWS Secret Access Key to use
aws_session_token: Optional[str]
AWS Session Token to use
embed_batch_size: Optional[int]
The batch size for embedding calls.
max_retries: Optional[int]
The maximum number of API retries.
model_name: Optional[str]
The modelId of the Bedrock model to use.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
profile_name: Optional[str]
The name of aws profile to use. If not given, then the default profile is used.
region_name: Optional[str]
AWS region name to use. Uses region configured in AWS CLI if not passed
timeout: Optional[float]
The timeout for the Bedrock API request in seconds. It will be used for both connect and read timeouts.
type: Optional[Literal["BEDROCK_EMBEDDING"]]
Type of the embedding model.
config_hash: Optional[ConfigHash]
Hashes for the configuration of a pipeline.
embedding_config_hash: Optional[str]
Hash of the embedding config.
parsing_config_hash: Optional[str]
Hash of the llama parse parameters.
transform_config_hash: Optional[str]
Hash of the transform config.
created_at: Optional[datetime]
Creation datetime
data_sink: Optional[DataSink]
Schema for a data sink.
id: str
Unique identifier
component: Component
Component that implements the data sink
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
api_key: str
The API key for authenticating with Pinecone
class CloudPostgresVectorStore: …
hnsw_settings: Optional[PgVectorHnswSettings]
HNSW settings for PGVector.
distance_method: Optional[Literal["l2", "ip", "cosine", 3 more]]
The distance method to use.
ef_construction: Optional[int]
The number of edges to use during the construction phase.
ef_search: Optional[int]
The number of edges to use during the search phase.
m: Optional[int]
The number of bi-directional links created for each new element.
vector_type: Optional[Literal["vector", "half_vec", "bit", "sparse_vec"]]
The type of vector to use.
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
class CloudAzureAISearchVectorStore: …
Cloud Azure AI Search Vector Store.
class CloudMongoDBAtlasVectorSearch: …
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 CloudMilvusVectorStore: …
Cloud Milvus Vector Store.
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'
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'
name: str
The name of the data sink.
sink_type: Literal["PINECONE", "POSTGRES", "QDRANT", 4 more]
created_at: Optional[datetime]
Creation datetime
updated_at: Optional[datetime]
Update datetime
embedding_model_config: Optional[EmbeddingModelConfig]
Schema for an embedding model config.
id: str
Unique identifier
embedding_config: EmbeddingModelConfigEmbeddingConfig
The embedding configuration for the embedding model config.
class AzureOpenAIEmbeddingConfig: …
component: Optional[AzureOpenAIEmbedding]
Configuration for the Azure OpenAI embedding model.
additional_kwargs: Optional[Dict[str, object]]
Additional kwargs for the OpenAI API.
api_base: Optional[str]
The base URL for Azure deployment.
api_key: Optional[str]
The OpenAI API key.
api_version: Optional[str]
The version for Azure OpenAI API.
azure_deployment: Optional[str]
The Azure deployment to use.
azure_endpoint: Optional[str]
The Azure endpoint to use.
default_headers: Optional[Dict[str, str]]
The default headers for API requests.
dimensions: Optional[int]
The number of dimensions on the output embedding vectors. Works only with v3 embedding models.
embed_batch_size: Optional[int]
The batch size for embedding calls.
max_retries: Optional[int]
Maximum number of retries.
model_name: Optional[str]
The name of the OpenAI embedding model.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
reuse_client: Optional[bool]
Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability.
timeout: Optional[float]
Timeout for each request.
type: Optional[Literal["AZURE_EMBEDDING"]]
Type of the embedding model.
class CohereEmbeddingConfig: …
component: Optional[CohereEmbedding]
Configuration for the Cohere embedding model.
api_key: Optional[str]
The Cohere API key.
embed_batch_size: Optional[int]
The batch size for embedding calls.
embedding_type: Optional[str]
Embedding type. If not provided float embedding_type is used when needed.
input_type: Optional[str]
Model Input type. If not provided, search_document and search_query are used when needed.
model_name: Optional[str]
The modelId of the Cohere model to use.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
truncate: Optional[str]
Truncation type - START/ END/ NONE
type: Optional[Literal["COHERE_EMBEDDING"]]
Type of the embedding model.
class GeminiEmbeddingConfig: …
component: Optional[GeminiEmbedding]
Configuration for the Gemini embedding model.
api_base: Optional[str]
API base to access the model. Defaults to None.
api_key: Optional[str]
API key to access the model. Defaults to None.
embed_batch_size: Optional[int]
The batch size for embedding calls.
model_name: Optional[str]
The modelId of the Gemini model to use.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
task_type: Optional[str]
The task for embedding model.
title: Optional[str]
Title is only applicable for retrieval_document tasks, and is used to represent a document title. For other tasks, title is invalid.
transport: Optional[str]
Transport to access the model. Defaults to None.
type: Optional[Literal["GEMINI_EMBEDDING"]]
Type of the embedding model.
class HuggingFaceInferenceAPIEmbeddingConfig: …
component: Optional[HuggingFaceInferenceAPIEmbedding]
Configuration for the HuggingFace Inference API embedding model.
token: Optional[Union[str, bool, null]]
Hugging Face token. Will default to the locally saved token. Pass token=False if you don’t want to send your token to the server.
cookies: Optional[Dict[str, str]]
Additional cookies to send to the server.
embed_batch_size: Optional[int]
The batch size for embedding calls.
headers: Optional[Dict[str, str]]
Additional headers to send to the server. By default only the authorization and user-agent headers are sent. Values in this dictionary will override the default values.
model_name: Optional[str]
Hugging Face model name. If None, the task will be used.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
pooling: Optional[Literal["cls", "mean", "last"]]
Enum of possible pooling choices with pooling behaviors.
query_instruction: Optional[str]
Instruction to prepend during query embedding.
task: Optional[str]
Optional task to pick Hugging Face's recommended model, used when model_name is left as default of None.
text_instruction: Optional[str]
Instruction to prepend during text embedding.
timeout: Optional[float]
The maximum number of seconds to wait for a response from the server. Loading a new model in Inference API can take up to several minutes. Defaults to None, meaning it will loop until the server is available.
type: Optional[Literal["HUGGINGFACE_API_EMBEDDING"]]
Type of the embedding model.
class OpenAIEmbeddingConfig: …
component: Optional[OpenAIEmbedding]
Configuration for the OpenAI embedding model.
additional_kwargs: Optional[Dict[str, object]]
Additional kwargs for the OpenAI API.
api_base: Optional[str]
The base URL for OpenAI API.
api_key: Optional[str]
The OpenAI API key.
api_version: Optional[str]
The version for OpenAI API.
default_headers: Optional[Dict[str, str]]
The default headers for API requests.
dimensions: Optional[int]
The number of dimensions on the output embedding vectors. Works only with v3 embedding models.
embed_batch_size: Optional[int]
The batch size for embedding calls.
max_retries: Optional[int]
Maximum number of retries.
model_name: Optional[str]
The name of the OpenAI embedding model.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
reuse_client: Optional[bool]
Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability.
timeout: Optional[float]
Timeout for each request.
type: Optional[Literal["OPENAI_EMBEDDING"]]
Type of the embedding model.
class VertexAIEmbeddingConfig: …
component: Optional[VertexTextEmbedding]
Configuration for the VertexAI embedding model.
client_email: Optional[str]
The client email for the VertexAI credentials.
location: str
The default location to use when making API calls.
private_key: Optional[str]
The private key for the VertexAI credentials.
private_key_id: Optional[str]
The private key ID for the VertexAI credentials.
project: str
The default GCP project to use when making Vertex API calls.
token_uri: Optional[str]
The token URI for the VertexAI credentials.
additional_kwargs: Optional[Dict[str, object]]
Additional kwargs for the Vertex.
embed_batch_size: Optional[int]
The batch size for embedding calls.
embed_mode: Optional[Literal["default", "classification", "clustering", 2 more]]
The embedding mode to use.
model_name: Optional[str]
The modelId of the VertexAI model to use.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
type: Optional[Literal["VERTEXAI_EMBEDDING"]]
Type of the embedding model.
class BedrockEmbeddingConfig: …
component: Optional[BedrockEmbedding]
Configuration for the Bedrock embedding model.
additional_kwargs: Optional[Dict[str, object]]
Additional kwargs for the bedrock client.
aws_access_key_id: Optional[str]
AWS Access Key ID to use
aws_secret_access_key: Optional[str]
AWS Secret Access Key to use
aws_session_token: Optional[str]
AWS Session Token to use
embed_batch_size: Optional[int]
The batch size for embedding calls.
max_retries: Optional[int]
The maximum number of API retries.
model_name: Optional[str]
The modelId of the Bedrock model to use.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
profile_name: Optional[str]
The name of aws profile to use. If not given, then the default profile is used.
region_name: Optional[str]
AWS region name to use. Uses region configured in AWS CLI if not passed
timeout: Optional[float]
The timeout for the Bedrock API request in seconds. It will be used for both connect and read timeouts.
type: Optional[Literal["BEDROCK_EMBEDDING"]]
Type of the embedding model.
name: str
The name of the embedding model config.
created_at: Optional[datetime]
Creation datetime
updated_at: Optional[datetime]
Update datetime
embedding_model_config_id: Optional[str]
The ID of the EmbeddingModelConfig this pipeline is using.
llama_parse_parameters: Optional[LlamaParseParameters]
Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline.
images_to_save: Optional[List[Literal["screenshot", "embedded", "layout"]]]
parse_mode: Optional[ParsingMode]
Enum for representing the mode of parsing to be used.
priority: Optional[Literal["low", "medium", "high", "critical"]]
The priority for the request. This field may be ignored or overwritten depending on the organization tier.
replace_failed_page_mode: Optional[FailPageMode]
Enum for representing the different available page error handling modes.
The outbound webhook configurations
webhook_events: Optional[List[Literal["extract.pending", "extract.success", "extract.error", 13 more]]]
List of event names to subscribe to
webhook_headers: Optional[Dict[str, str]]
Custom HTTP headers to include with webhook requests.
webhook_output_format: Optional[str]
The output format to use for the webhook. Defaults to string if none supplied. Currently supported values: string, json
webhook_url: Optional[str]
The URL to send webhook notifications to.
managed_pipeline_id: Optional[str]
The ID of the ManagedPipeline this playground pipeline is linked to.
metadata_config: Optional[PipelineMetadataConfig]
Metadata configuration for the pipeline.
excluded_embed_metadata_keys: Optional[List[str]]
List of metadata keys to exclude from embeddings
excluded_llm_metadata_keys: Optional[List[str]]
List of metadata keys to exclude from LLM during retrieval
pipeline_type: Optional[PipelineType]
Type of pipeline. Either PLAYGROUND or MANAGED.
preset_retrieval_parameters: Optional[PresetRetrievalParams]
Preset retrieval parameters for the pipeline.
alpha: Optional[float]
Alpha value for hybrid retrieval to determine the weights between dense and sparse retrieval. 0 is sparse retrieval and 1 is dense retrieval.
dense_similarity_cutoff: Optional[float]
Minimum similarity score wrt query for retrieval
dense_similarity_top_k: Optional[int]
Number of nodes for dense retrieval.
enable_reranking: Optional[bool]
Enable reranking for retrieval
files_top_k: Optional[int]
Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content).
rerank_top_n: Optional[int]
Number of reranked nodes for returning.
retrieval_mode: Optional[RetrievalMode]
The retrieval mode for the query.
Deprecatedretrieve_image_nodes: Optional[bool]
Whether to retrieve image nodes.
retrieve_page_figure_nodes: Optional[bool]
Whether to retrieve page figure nodes.
retrieve_page_screenshot_nodes: Optional[bool]
Whether to retrieve page screenshot nodes.
search_filters: Optional[MetadataFilters]
Metadata filters for vector stores.
filters: List[Filter]
class FilterMetadataFilter: …
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 converted to string before.
See: https://docs.pydantic.dev/latest/usage/types/#strict-types
value: Union[float, str, List[str], 3 more]
operator: Optional[Literal["==", ">", "<", 11 more]]
Vector store filter operator.
class MetadataFilters: …
Metadata filters for vector stores.
filters: List[Filter]
class FilterMetadataFilter: …
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 converted to string before.
See: https://docs.pydantic.dev/latest/usage/types/#strict-types
value: Union[float, str, List[str], 3 more]
operator: Optional[Literal["==", ">", "<", 11 more]]
Vector store filter operator.
condition: Optional[Literal["and", "or", "not"]]
Vector store filter conditions to combine different filters.
condition: Optional[Literal["and", "or", "not"]]
Vector store filter conditions to combine different filters.
search_filters_inference_schema: Optional[Dict[str, Union[Dict[str, object], List[object], str, 3 more]]]
JSON Schema that will be used to infer search_filters. Omit or leave as null to skip inference.
sparse_similarity_top_k: Optional[int]
Number of nodes for sparse retrieval.
sparse_model_config: Optional[SparseModelConfig]
Configuration for sparse embedding models used in hybrid search.
This allows users to choose between Splade and BM25 models for sparse retrieval in managed data sinks.
model_type: Optional[Literal["splade", "bm25", "auto"]]
The sparse model type to use. 'bm25' uses Qdrant's FastEmbed BM25 model (default for new pipelines), 'splade' uses HuggingFace Splade model, 'auto' selects based on deployment mode (BYOC uses term frequency, Cloud uses Splade).
status: Optional[Literal["CREATED", "DELETING"]]
Status of the pipeline.
transform_config: Optional[TransformConfig]
Configuration for the transformation.
class AutoTransformConfig: …
chunk_overlap: Optional[int]
Chunk overlap for the transformation.
chunk_size: Optional[int]
Chunk size for the transformation.
class AdvancedModeTransformConfig: …
chunking_config: Optional[ChunkingConfig]
Configuration for the chunking.
class ChunkingConfigNoneChunkingConfig: …
class ChunkingConfigCharacterChunkingConfig: …
class ChunkingConfigTokenChunkingConfig: …
class ChunkingConfigSentenceChunkingConfig: …
class ChunkingConfigSemanticChunkingConfig: …
segmentation_config: Optional[SegmentationConfig]
Configuration for the segmentation.
class SegmentationConfigNoneSegmentationConfig: …
class SegmentationConfigPageSegmentationConfig: …
class SegmentationConfigElementSegmentationConfig: …
updated_at: Optional[datetime]
Update datetime
class PipelineCreate: …
Schema for creating a pipeline.
data_sink: Optional[DataSinkCreate]
Schema for creating a data sink.
component: Component
Component that implements the data sink
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
api_key: str
The API key for authenticating with Pinecone
class CloudPostgresVectorStore: …
hnsw_settings: Optional[PgVectorHnswSettings]
HNSW settings for PGVector.
distance_method: Optional[Literal["l2", "ip", "cosine", 3 more]]
The distance method to use.
ef_construction: Optional[int]
The number of edges to use during the construction phase.
ef_search: Optional[int]
The number of edges to use during the search phase.
m: Optional[int]
The number of bi-directional links created for each new element.
vector_type: Optional[Literal["vector", "half_vec", "bit", "sparse_vec"]]
The type of vector to use.
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
class CloudAzureAISearchVectorStore: …
Cloud Azure AI Search Vector Store.
class CloudMongoDBAtlasVectorSearch: …
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 CloudMilvusVectorStore: …
Cloud Milvus Vector Store.
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'
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'
name: str
The name of the data sink.
sink_type: Literal["PINECONE", "POSTGRES", "QDRANT", 4 more]
data_sink_id: Optional[str]
Data sink ID. When provided instead of data_sink, the data sink will be looked up by ID.
embedding_config: Optional[EmbeddingConfig]
class AzureOpenAIEmbeddingConfig: …
component: Optional[AzureOpenAIEmbedding]
Configuration for the Azure OpenAI embedding model.
additional_kwargs: Optional[Dict[str, object]]
Additional kwargs for the OpenAI API.
api_base: Optional[str]
The base URL for Azure deployment.
api_key: Optional[str]
The OpenAI API key.
api_version: Optional[str]
The version for Azure OpenAI API.
azure_deployment: Optional[str]
The Azure deployment to use.
azure_endpoint: Optional[str]
The Azure endpoint to use.
default_headers: Optional[Dict[str, str]]
The default headers for API requests.
dimensions: Optional[int]
The number of dimensions on the output embedding vectors. Works only with v3 embedding models.
embed_batch_size: Optional[int]
The batch size for embedding calls.
max_retries: Optional[int]
Maximum number of retries.
model_name: Optional[str]
The name of the OpenAI embedding model.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
reuse_client: Optional[bool]
Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability.
timeout: Optional[float]
Timeout for each request.
type: Optional[Literal["AZURE_EMBEDDING"]]
Type of the embedding model.
class CohereEmbeddingConfig: …
component: Optional[CohereEmbedding]
Configuration for the Cohere embedding model.
api_key: Optional[str]
The Cohere API key.
embed_batch_size: Optional[int]
The batch size for embedding calls.
embedding_type: Optional[str]
Embedding type. If not provided float embedding_type is used when needed.
input_type: Optional[str]
Model Input type. If not provided, search_document and search_query are used when needed.
model_name: Optional[str]
The modelId of the Cohere model to use.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
truncate: Optional[str]
Truncation type - START/ END/ NONE
type: Optional[Literal["COHERE_EMBEDDING"]]
Type of the embedding model.
class GeminiEmbeddingConfig: …
component: Optional[GeminiEmbedding]
Configuration for the Gemini embedding model.
api_base: Optional[str]
API base to access the model. Defaults to None.
api_key: Optional[str]
API key to access the model. Defaults to None.
embed_batch_size: Optional[int]
The batch size for embedding calls.
model_name: Optional[str]
The modelId of the Gemini model to use.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
task_type: Optional[str]
The task for embedding model.
title: Optional[str]
Title is only applicable for retrieval_document tasks, and is used to represent a document title. For other tasks, title is invalid.
transport: Optional[str]
Transport to access the model. Defaults to None.
type: Optional[Literal["GEMINI_EMBEDDING"]]
Type of the embedding model.
class HuggingFaceInferenceAPIEmbeddingConfig: …
component: Optional[HuggingFaceInferenceAPIEmbedding]
Configuration for the HuggingFace Inference API embedding model.
token: Optional[Union[str, bool, null]]
Hugging Face token. Will default to the locally saved token. Pass token=False if you don’t want to send your token to the server.
cookies: Optional[Dict[str, str]]
Additional cookies to send to the server.
embed_batch_size: Optional[int]
The batch size for embedding calls.
headers: Optional[Dict[str, str]]
Additional headers to send to the server. By default only the authorization and user-agent headers are sent. Values in this dictionary will override the default values.
model_name: Optional[str]
Hugging Face model name. If None, the task will be used.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
pooling: Optional[Literal["cls", "mean", "last"]]
Enum of possible pooling choices with pooling behaviors.
query_instruction: Optional[str]
Instruction to prepend during query embedding.
task: Optional[str]
Optional task to pick Hugging Face's recommended model, used when model_name is left as default of None.
text_instruction: Optional[str]
Instruction to prepend during text embedding.
timeout: Optional[float]
The maximum number of seconds to wait for a response from the server. Loading a new model in Inference API can take up to several minutes. Defaults to None, meaning it will loop until the server is available.
type: Optional[Literal["HUGGINGFACE_API_EMBEDDING"]]
Type of the embedding model.
class OpenAIEmbeddingConfig: …
component: Optional[OpenAIEmbedding]
Configuration for the OpenAI embedding model.
additional_kwargs: Optional[Dict[str, object]]
Additional kwargs for the OpenAI API.
api_base: Optional[str]
The base URL for OpenAI API.
api_key: Optional[str]
The OpenAI API key.
api_version: Optional[str]
The version for OpenAI API.
default_headers: Optional[Dict[str, str]]
The default headers for API requests.
dimensions: Optional[int]
The number of dimensions on the output embedding vectors. Works only with v3 embedding models.
embed_batch_size: Optional[int]
The batch size for embedding calls.
max_retries: Optional[int]
Maximum number of retries.
model_name: Optional[str]
The name of the OpenAI embedding model.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
reuse_client: Optional[bool]
Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability.
timeout: Optional[float]
Timeout for each request.
type: Optional[Literal["OPENAI_EMBEDDING"]]
Type of the embedding model.
class VertexAIEmbeddingConfig: …
component: Optional[VertexTextEmbedding]
Configuration for the VertexAI embedding model.
client_email: Optional[str]
The client email for the VertexAI credentials.
location: str
The default location to use when making API calls.
private_key: Optional[str]
The private key for the VertexAI credentials.
private_key_id: Optional[str]
The private key ID for the VertexAI credentials.
project: str
The default GCP project to use when making Vertex API calls.
token_uri: Optional[str]
The token URI for the VertexAI credentials.
additional_kwargs: Optional[Dict[str, object]]
Additional kwargs for the Vertex.
embed_batch_size: Optional[int]
The batch size for embedding calls.
embed_mode: Optional[Literal["default", "classification", "clustering", 2 more]]
The embedding mode to use.
model_name: Optional[str]
The modelId of the VertexAI model to use.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
type: Optional[Literal["VERTEXAI_EMBEDDING"]]
Type of the embedding model.
class BedrockEmbeddingConfig: …
component: Optional[BedrockEmbedding]
Configuration for the Bedrock embedding model.
additional_kwargs: Optional[Dict[str, object]]
Additional kwargs for the bedrock client.
aws_access_key_id: Optional[str]
AWS Access Key ID to use
aws_secret_access_key: Optional[str]
AWS Secret Access Key to use
aws_session_token: Optional[str]
AWS Session Token to use
embed_batch_size: Optional[int]
The batch size for embedding calls.
max_retries: Optional[int]
The maximum number of API retries.
model_name: Optional[str]
The modelId of the Bedrock model to use.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
profile_name: Optional[str]
The name of aws profile to use. If not given, then the default profile is used.
region_name: Optional[str]
AWS region name to use. Uses region configured in AWS CLI if not passed
timeout: Optional[float]
The timeout for the Bedrock API request in seconds. It will be used for both connect and read timeouts.
type: Optional[Literal["BEDROCK_EMBEDDING"]]
Type of the embedding model.
embedding_model_config_id: Optional[str]
Embedding model config ID. When provided instead of embedding_config, the embedding model config will be looked up by ID.
llama_parse_parameters: Optional[LlamaParseParameters]
Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline.
images_to_save: Optional[List[Literal["screenshot", "embedded", "layout"]]]
parse_mode: Optional[ParsingMode]
Enum for representing the mode of parsing to be used.
priority: Optional[Literal["low", "medium", "high", "critical"]]
The priority for the request. This field may be ignored or overwritten depending on the organization tier.
replace_failed_page_mode: Optional[FailPageMode]
Enum for representing the different available page error handling modes.
The outbound webhook configurations
webhook_events: Optional[List[Literal["extract.pending", "extract.success", "extract.error", 13 more]]]
List of event names to subscribe to
webhook_headers: Optional[Dict[str, str]]
Custom HTTP headers to include with webhook requests.
webhook_output_format: Optional[str]
The output format to use for the webhook. Defaults to string if none supplied. Currently supported values: string, json
webhook_url: Optional[str]
The URL to send webhook notifications to.
managed_pipeline_id: Optional[str]
The ID of the ManagedPipeline this playground pipeline is linked to.
metadata_config: Optional[PipelineMetadataConfig]
Metadata configuration for the pipeline.
excluded_embed_metadata_keys: Optional[List[str]]
List of metadata keys to exclude from embeddings
excluded_llm_metadata_keys: Optional[List[str]]
List of metadata keys to exclude from LLM during retrieval
pipeline_type: Optional[PipelineType]
Type of pipeline. Either PLAYGROUND or MANAGED.
preset_retrieval_parameters: Optional[PresetRetrievalParams]
Preset retrieval parameters for the pipeline.
alpha: Optional[float]
Alpha value for hybrid retrieval to determine the weights between dense and sparse retrieval. 0 is sparse retrieval and 1 is dense retrieval.
dense_similarity_cutoff: Optional[float]
Minimum similarity score wrt query for retrieval
dense_similarity_top_k: Optional[int]
Number of nodes for dense retrieval.
enable_reranking: Optional[bool]
Enable reranking for retrieval
files_top_k: Optional[int]
Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content).
rerank_top_n: Optional[int]
Number of reranked nodes for returning.
retrieval_mode: Optional[RetrievalMode]
The retrieval mode for the query.
Deprecatedretrieve_image_nodes: Optional[bool]
Whether to retrieve image nodes.
retrieve_page_figure_nodes: Optional[bool]
Whether to retrieve page figure nodes.
retrieve_page_screenshot_nodes: Optional[bool]
Whether to retrieve page screenshot nodes.
search_filters: Optional[MetadataFilters]
Metadata filters for vector stores.
filters: List[Filter]
class FilterMetadataFilter: …
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 converted to string before.
See: https://docs.pydantic.dev/latest/usage/types/#strict-types
value: Union[float, str, List[str], 3 more]
operator: Optional[Literal["==", ">", "<", 11 more]]
Vector store filter operator.
class MetadataFilters: …
Metadata filters for vector stores.
filters: List[Filter]
class FilterMetadataFilter: …
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 converted to string before.
See: https://docs.pydantic.dev/latest/usage/types/#strict-types
value: Union[float, str, List[str], 3 more]
operator: Optional[Literal["==", ">", "<", 11 more]]
Vector store filter operator.
condition: Optional[Literal["and", "or", "not"]]
Vector store filter conditions to combine different filters.
condition: Optional[Literal["and", "or", "not"]]
Vector store filter conditions to combine different filters.
search_filters_inference_schema: Optional[Dict[str, Union[Dict[str, object], List[object], str, 3 more]]]
JSON Schema that will be used to infer search_filters. Omit or leave as null to skip inference.
sparse_similarity_top_k: Optional[int]
Number of nodes for sparse retrieval.
sparse_model_config: Optional[SparseModelConfig]
Configuration for sparse embedding models used in hybrid search.
This allows users to choose between Splade and BM25 models for sparse retrieval in managed data sinks.
model_type: Optional[Literal["splade", "bm25", "auto"]]
The sparse model type to use. 'bm25' uses Qdrant's FastEmbed BM25 model (default for new pipelines), 'splade' uses HuggingFace Splade model, 'auto' selects based on deployment mode (BYOC uses term frequency, Cloud uses Splade).
status: Optional[str]
Status of the pipeline deployment.
transform_config: Optional[TransformConfig]
Configuration for the transformation.
class AutoTransformConfig: …
chunk_overlap: Optional[int]
Chunk overlap for the transformation.
chunk_size: Optional[int]
Chunk size for the transformation.
class AdvancedModeTransformConfig: …
chunking_config: Optional[ChunkingConfig]
Configuration for the chunking.
class ChunkingConfigNoneChunkingConfig: …
class ChunkingConfigCharacterChunkingConfig: …
class ChunkingConfigTokenChunkingConfig: …
class ChunkingConfigSentenceChunkingConfig: …
class ChunkingConfigSemanticChunkingConfig: …
segmentation_config: Optional[SegmentationConfig]
Configuration for the segmentation.
class SegmentationConfigNoneSegmentationConfig: …
class SegmentationConfigPageSegmentationConfig: …
class SegmentationConfigElementSegmentationConfig: …
class PipelineMetadataConfig: …
excluded_embed_metadata_keys: Optional[List[str]]
List of metadata keys to exclude from embeddings
excluded_llm_metadata_keys: Optional[List[str]]
List of metadata keys to exclude from LLM during retrieval
Literal["PLAYGROUND", "MANAGED"]
Enum for representing the type of a pipeline
class PresetRetrievalParams: …
Schema for the search params for an retrieval execution that can be preset for a pipeline.
alpha: Optional[float]
Alpha value for hybrid retrieval to determine the weights between dense and sparse retrieval. 0 is sparse retrieval and 1 is dense retrieval.
dense_similarity_cutoff: Optional[float]
Minimum similarity score wrt query for retrieval
dense_similarity_top_k: Optional[int]
Number of nodes for dense retrieval.
enable_reranking: Optional[bool]
Enable reranking for retrieval
files_top_k: Optional[int]
Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content).
rerank_top_n: Optional[int]
Number of reranked nodes for returning.
retrieval_mode: Optional[RetrievalMode]
The retrieval mode for the query.
Deprecatedretrieve_image_nodes: Optional[bool]
Whether to retrieve image nodes.
retrieve_page_figure_nodes: Optional[bool]
Whether to retrieve page figure nodes.
retrieve_page_screenshot_nodes: Optional[bool]
Whether to retrieve page screenshot nodes.
search_filters: Optional[MetadataFilters]
Metadata filters for vector stores.
filters: List[Filter]
class FilterMetadataFilter: …
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 converted to string before.
See: https://docs.pydantic.dev/latest/usage/types/#strict-types
value: Union[float, str, List[str], 3 more]
operator: Optional[Literal["==", ">", "<", 11 more]]
Vector store filter operator.
class MetadataFilters: …
Metadata filters for vector stores.
filters: List[Filter]
class FilterMetadataFilter: …
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 converted to string before.
See: https://docs.pydantic.dev/latest/usage/types/#strict-types
value: Union[float, str, List[str], 3 more]
operator: Optional[Literal["==", ">", "<", 11 more]]
Vector store filter operator.
condition: Optional[Literal["and", "or", "not"]]
Vector store filter conditions to combine different filters.
condition: Optional[Literal["and", "or", "not"]]
Vector store filter conditions to combine different filters.
search_filters_inference_schema: Optional[Dict[str, Union[Dict[str, object], List[object], str, 3 more]]]
JSON Schema that will be used to infer search_filters. Omit or leave as null to skip inference.
sparse_similarity_top_k: Optional[int]
Number of nodes for sparse retrieval.
Literal["chunks", "files_via_metadata", "files_via_content", "auto_routed"]
class SparseModelConfig: …
Configuration for sparse embedding models used in hybrid search.
This allows users to choose between Splade and BM25 models for sparse retrieval in managed data sinks.
model_type: Optional[Literal["splade", "bm25", "auto"]]
The sparse model type to use. 'bm25' uses Qdrant's FastEmbed BM25 model (default for new pipelines), 'splade' uses HuggingFace Splade model, 'auto' selects based on deployment mode (BYOC uses term frequency, Cloud uses Splade).
class VertexAIEmbeddingConfig: …
component: Optional[VertexTextEmbedding]
Configuration for the VertexAI embedding model.
client_email: Optional[str]
The client email for the VertexAI credentials.
location: str
The default location to use when making API calls.
private_key: Optional[str]
The private key for the VertexAI credentials.
private_key_id: Optional[str]
The private key ID for the VertexAI credentials.
project: str
The default GCP project to use when making Vertex API calls.
token_uri: Optional[str]
The token URI for the VertexAI credentials.
additional_kwargs: Optional[Dict[str, object]]
Additional kwargs for the Vertex.
embed_batch_size: Optional[int]
The batch size for embedding calls.
embed_mode: Optional[Literal["default", "classification", "clustering", 2 more]]
The embedding mode to use.
model_name: Optional[str]
The modelId of the VertexAI model to use.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
type: Optional[Literal["VERTEXAI_EMBEDDING"]]
Type of the embedding model.
class VertexTextEmbedding: …
client_email: Optional[str]
The client email for the VertexAI credentials.
location: str
The default location to use when making API calls.
private_key: Optional[str]
The private key for the VertexAI credentials.
private_key_id: Optional[str]
The private key ID for the VertexAI credentials.
project: str
The default GCP project to use when making Vertex API calls.
token_uri: Optional[str]
The token URI for the VertexAI credentials.
additional_kwargs: Optional[Dict[str, object]]
Additional kwargs for the Vertex.
embed_batch_size: Optional[int]
The batch size for embedding calls.
embed_mode: Optional[Literal["default", "classification", "clustering", 2 more]]
The embedding mode to use.
model_name: Optional[str]
The modelId of the VertexAI model to use.
num_workers: Optional[int]
The number of workers to use for async embedding calls.
PipelinesSync
Sync Pipeline
Cancel Pipeline Sync
PipelinesData Sources
List Pipeline Data Sources
Add Data Sources To Pipeline
Update Pipeline Data Source
Get Pipeline Data Source Status
Sync Pipeline Data Source
ModelsExpand Collapse
class PipelineDataSource: …
Schema for a data source in a pipeline.
id: str
Unique identifier
component: Component
Component that implements the data source
class CloudS3DataSource: …
bucket: str
The name of the S3 bucket to read from.
aws_access_id: Optional[str]
The AWS access ID to use for authentication.
aws_access_secret: Optional[str]
The AWS access secret to use for authentication.
prefix: Optional[str]
The prefix of the S3 objects to read from.
regex_pattern: Optional[str]
The regex pattern to filter S3 objects. Must be a valid regex pattern.
s3_endpoint_url: Optional[str]
The S3 endpoint URL to use for authentication.
class CloudAzStorageBlobDataSource: …
account_url: str
The Azure Storage Blob account URL to use for authentication.
container_name: str
The name of the Azure Storage Blob container to read from.
account_key: Optional[str]
The Azure Storage Blob account key to use for authentication.
account_name: Optional[str]
The Azure Storage Blob account name to use for authentication.
blob: Optional[str]
The blob name to read from.
client_id: Optional[str]
The Azure AD client ID to use for authentication.
client_secret: Optional[str]
The Azure AD client secret to use for authentication.
prefix: Optional[str]
The prefix of the Azure Storage Blob objects to read from.
tenant_id: Optional[str]
The Azure AD tenant ID to use for authentication.
class CloudOneDriveDataSource: …
client_id: str
The client ID to use for authentication.
client_secret: str
The client secret to use for authentication.
tenant_id: str
The tenant ID to use for authentication.
user_principal_name: str
The user principal name to use for authentication.
folder_id: Optional[str]
The ID of the OneDrive folder to read from.
folder_path: Optional[str]
The path of the OneDrive folder to read from.
required_exts: Optional[List[str]]
The list of required file extensions.
class CloudSharepointDataSource: …
client_id: str
The client ID to use for authentication.
client_secret: str
The client secret to use for authentication.
tenant_id: str
The tenant ID to use for authentication.
drive_name: Optional[str]
The name of the Sharepoint drive to read from.
exclude_path_patterns: Optional[List[str]]
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$', '^~']
folder_id: Optional[str]
The ID of the Sharepoint folder to read from.
folder_path: Optional[str]
The path of the Sharepoint folder to read from.
get_permissions: Optional[bool]
Whether to get permissions for the sharepoint site.
include_path_patterns: Optional[List[str]]
List of regex patterns for file paths to include. Full paths (including filename) must match at least one pattern to be included. Example: ['/reports/', '/docs/..pdf$', '^Report..pdf$']
required_exts: Optional[List[str]]
The list of required file extensions.
site_id: Optional[str]
The ID of the SharePoint site to download from.
site_name: Optional[str]
The name of the SharePoint site to download from.
class CloudSlackDataSource: …
slack_token: str
Slack Bot Token.
channel_ids: Optional[str]
Slack Channel.
channel_patterns: Optional[str]
Slack Channel name pattern.
earliest_date: Optional[str]
Earliest date.
earliest_date_timestamp: Optional[float]
Earliest date timestamp.
latest_date: Optional[str]
Latest date.
latest_date_timestamp: Optional[float]
Latest date timestamp.
class CloudNotionPageDataSource: …
integration_token: str
The integration token to use for authentication.
database_ids: Optional[str]
The Notion Database Id to read content from.
page_ids: Optional[str]
The Page ID's of the Notion to read from.
class CloudConfluenceDataSource: …
authentication_mechanism: str
Type of Authentication for connecting to Confluence APIs.
server_url: str
The server URL of the Confluence instance.
api_token: Optional[str]
The API token to use for authentication.
cql: Optional[str]
The CQL query to use for fetching pages.
failure_handling: Optional[FailureHandlingConfig]
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
skip_list_failures: Optional[bool]
Whether to skip failed batches/lists and continue processing
index_restricted_pages: Optional[bool]
Whether to index restricted pages.
keep_markdown_format: Optional[bool]
Whether to keep the markdown format.
label: Optional[str]
The label to use for fetching pages.
page_ids: Optional[str]
The page IDs of the Confluence to read from.
space_key: Optional[str]
The space key to read from.
user_name: Optional[str]
The username to use for authentication.
class CloudJiraDataSource: …
Cloud Jira Data Source integrating JiraReader.
authentication_mechanism: str
Type of Authentication for connecting to Jira APIs.
query: str
JQL (Jira Query Language) query to search.
api_token: Optional[str]
The API/ Access Token used for Basic, PAT and OAuth2 authentication.
cloud_id: Optional[str]
The cloud ID, used in case of OAuth2.
email: Optional[str]
The email address to use for authentication.
server_url: Optional[str]
The server url for Jira Cloud.
class CloudJiraDataSourceV2: …
Cloud Jira Data Source integrating JiraReaderV2.
authentication_mechanism: str
Type of Authentication for connecting to Jira APIs.
query: str
JQL (Jira Query Language) query to search.
server_url: str
The server url for Jira Cloud.
api_token: Optional[str]
The API Access Token used for Basic, PAT and OAuth2 authentication.
api_version: Optional[Literal["2", "3"]]
Jira REST API version to use (2 or 3). 3 supports Atlassian Document Format (ADF).
cloud_id: Optional[str]
The cloud ID, used in case of OAuth2.
email: Optional[str]
The email address to use for authentication.
expand: Optional[str]
Fields to expand in the response.
fields: Optional[List[str]]
List of fields to retrieve from Jira. If None, retrieves all fields.
get_permissions: Optional[bool]
Whether to fetch project role permissions and issue-level security
requests_per_minute: Optional[int]
Rate limit for Jira API requests per minute.
class CloudBoxDataSource: …
authentication_mechanism: Literal["developer_token", "ccg"]
The type of authentication to use (Developer Token or CCG)
client_id: Optional[str]
Box API key used for identifying the application the user is authenticating with
client_secret: Optional[str]
Box API secret used for making auth requests.
developer_token: Optional[str]
Developer token for authentication if authentication_mechanism is 'developer_token'.
enterprise_id: Optional[str]
Box Enterprise ID, if provided authenticates as service.
folder_id: Optional[str]
The ID of the Box folder to read from.
user_id: Optional[str]
Box User ID, if provided authenticates as user.
data_source_id: str
The ID of the data source.
last_synced_at: datetime
The last time the data source was automatically synced.
name: str
The name of the data source.
pipeline_id: str
The ID of the pipeline.
source_type: Literal["S3", "AZURE_STORAGE_BLOB", "GOOGLE_DRIVE", 8 more]
created_at: Optional[datetime]
Creation datetime
custom_metadata: Optional[Dict[str, Union[Dict[str, object], List[object], str, 3 more]]]
Custom metadata that will be present on all data loaded from the data source
status: Optional[Literal["NOT_STARTED", "IN_PROGRESS", "SUCCESS", 2 more]]
The status of the data source in the pipeline.
status_updated_at: Optional[datetime]
The last time the status was updated.
sync_interval: Optional[float]
The interval at which the data source should be synced.
sync_schedule_set_by: Optional[str]
The id of the user who set the sync schedule.
updated_at: Optional[datetime]
Update datetime
version_metadata: Optional[DataSourceReaderVersionMetadata]
Version metadata for the data source
reader_version: Optional[Literal["1.0", "2.0", "2.1"]]
The version of the reader to use for this data source.
PipelinesImages
List File Page Screenshots
Get File Page Screenshot
Get File Page Figure
List File Pages Figures
PipelinesFiles
Get Pipeline File Status Counts
Get Pipeline File Status
Add Files To Pipeline Api
Update Pipeline File
Delete Pipeline File
List Pipeline Files2
ModelsExpand Collapse
class PipelineFile: …
Schema for a file that is associated with a pipeline.
id: str
Unique identifier
pipeline_id: str
The ID of the pipeline that the file is associated with
config_hash: Optional[Dict[str, Union[Dict[str, object], List[object], str, 3 more]]]
Hashes for the configuration of the pipeline.
created_at: Optional[datetime]
Creation datetime
custom_metadata: Optional[Dict[str, Union[Dict[str, object], List[object], str, 3 more]]]
Custom metadata for the file
data_source_id: Optional[str]
The ID of the data source that the file belongs to
external_file_id: Optional[str]
The ID of the file in the external system
file_id: Optional[str]
The ID of the file
file_size: Optional[int]
Size of the file in bytes
file_type: Optional[str]
File type (e.g. pdf, docx, etc.)
indexed_page_count: Optional[int]
The number of pages that have been indexed for this file
last_modified_at: Optional[datetime]
The last modified time of the file
name: Optional[str]
Name of the file
permission_info: Optional[Dict[str, Union[Dict[str, object], List[object], str, 3 more]]]
Permission information for the file
project_id: Optional[str]
The ID of the project that the file belongs to
resource_info: Optional[Dict[str, Union[Dict[str, object], List[object], str, 3 more]]]
Resource information for the file
status: Optional[Literal["NOT_STARTED", "IN_PROGRESS", "SUCCESS", 2 more]]
Status of the pipeline file
status_updated_at: Optional[datetime]
The last time the status was updated
updated_at: Optional[datetime]
Update datetime
PipelinesMetadata
Import Pipeline Metadata
Delete Pipeline Files Metadata
PipelinesDocuments
Create Batch Pipeline Documents
Paginated List Pipeline Documents
Get Pipeline Document
Delete Pipeline Document
Get Pipeline Document Status
Sync Pipeline Document
List Pipeline Document Chunks
Upsert Batch Pipeline Documents
ModelsExpand Collapse
class CloudDocument: …
Cloud document stored in S3.
page_positions: Optional[List[int]]
indices in the CloudDocument.text where a new page begins. e.g. Second page starts at index specified by page_positions[1].
class CloudDocumentCreate: …
Create a new cloud document.
page_positions: Optional[List[int]]
indices in the CloudDocument.text where a new page begins. e.g. Second page starts at index specified by page_positions[1].
class TextNode: …
Provided for backward compatibility.
Note: we keep the field with the typo "seperator" to maintain backward compatibility for serialized objects.
embedding: Optional[List[float]]
Embedding of the node.
end_char_idx: Optional[int]
End char index of the node.
excluded_embed_metadata_keys: Optional[List[str]]
Metadata keys that are excluded from text for the embed model.
excluded_llm_metadata_keys: Optional[List[str]]
Metadata keys that are excluded from text for the LLM.
extra_info: Optional[Dict[str, object]]
A flat dictionary of metadata fields
id: Optional[str]
Unique ID of the node.
metadata_seperator: Optional[str]
Separator between metadata fields when converting to string.
metadata_template: Optional[str]
Template for how metadata is formatted, with {key} and {value} placeholders.
mimetype: Optional[str]
MIME type of the node content.
relationships: Optional[Dict[str, Relationships]]
A mapping of relationships to other node information.
class RelationshipsRelatedNodeInfo: …
node_type: Optional[Union[Literal["1", "2", "3", 2 more], str, null]]
Literal["1", "2", "3", 2 more]
List[RelationshipsUnionMember1]
node_type: Optional[Union[Literal["1", "2", "3", 2 more], str, null]]
Literal["1", "2", "3", 2 more]
start_char_idx: Optional[int]
Start char index of the node.
text: Optional[str]
Text content of the node.
text_template: Optional[str]
Template for how text is formatted, with {content} and {metadata_str} placeholders.