LlamaParse Embedding Model Configs API
The Embedding Model Configs API from LlamaParse — 2 operation(s) for embedding model configs.
OpenAPI Specification
openapi: 3.0.3
info:
title: Llama Platform Agent Data Embedding Model Configs API
version: 0.1.0
tags:
- name: Embedding Model Configs
paths:
/api/v1/embedding-model-configs:
get:
tags:
- Embedding Model Configs
summary: List Embedding Model Configs
operationId: list_embedding_model_configs_api_v1_embedding_model_configs_get
security:
- HTTPBearer: []
parameters:
- name: project_id
in: query
required: false
schema:
anyOf:
- type: string
format: uuid
- type: 'null'
title: Project Id
- name: organization_id
in: query
required: false
schema:
anyOf:
- type: string
format: uuid
- type: 'null'
title: Organization Id
- name: session
in: cookie
required: false
schema:
anyOf:
- type: string
- type: 'null'
title: Session
responses:
'200':
description: Successful Response
content:
application/json:
schema:
type: array
items:
$ref: '#/components/schemas/EmbeddingModelConfig'
title: Response List Embedding Model Configs Api V1 Embedding Model Configs Get
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
post:
tags:
- Embedding Model Configs
summary: Create a new Embedding Model Configuration
description: Create a new embedding model configuration within a specified project.
operationId: create_embedding_model_config_api_v1_embedding_model_configs_post
security:
- HTTPBearer: []
parameters:
- name: project_id
in: query
required: false
schema:
anyOf:
- type: string
format: uuid
- type: 'null'
title: Project Id
- name: organization_id
in: query
required: false
schema:
anyOf:
- type: string
format: uuid
- type: 'null'
title: Organization Id
- name: session
in: cookie
required: false
schema:
anyOf:
- type: string
- type: 'null'
title: Session
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/EmbeddingModelConfigCreate'
responses:
'201':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/EmbeddingModelConfig'
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
/api/v1/embedding-model-configs/{embedding_model_config_id}:
put:
tags:
- Embedding Model Configs
summary: Update Embedding Model Config
description: Update an embedding model config by ID.
operationId: update_embedding_model_config_api_v1_embedding_model_configs__embedding_model_config_id__put
security:
- HTTPBearer: []
parameters:
- name: embedding_model_config_id
in: path
required: true
schema:
type: string
format: uuid
title: Embedding Model Config Id
- name: project_id
in: query
required: false
schema:
anyOf:
- type: string
format: uuid
- type: 'null'
title: Project Id
- name: organization_id
in: query
required: false
schema:
anyOf:
- type: string
format: uuid
- type: 'null'
title: Organization Id
- name: session
in: cookie
required: false
schema:
anyOf:
- type: string
- type: 'null'
title: Session
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/EmbeddingModelConfigUpdate'
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/EmbeddingModelConfig'
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
delete:
tags:
- Embedding Model Configs
summary: Delete Embedding Model Config
description: Delete an embedding model config by ID.
operationId: delete_embedding_model_config_api_v1_embedding_model_configs__embedding_model_config_id__delete
security:
- HTTPBearer: []
parameters:
- name: embedding_model_config_id
in: path
required: true
schema:
type: string
format: uuid
title: Embedding Model Config Id
- name: project_id
in: query
required: false
schema:
anyOf:
- type: string
format: uuid
- type: 'null'
title: Project Id
- name: organization_id
in: query
required: false
schema:
anyOf:
- type: string
format: uuid
- type: 'null'
title: Organization Id
- name: session
in: cookie
required: false
schema:
anyOf:
- type: string
- type: 'null'
title: Session
responses:
'204':
description: Successful Response
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
components:
schemas:
OpenAIEmbedding:
properties:
model_name:
type: string
title: Model Name
description: The name of the OpenAI embedding model.
default: text-embedding-ada-002
embed_batch_size:
type: integer
maximum: 2048.0
exclusiveMinimum: 0.0
title: Embed Batch Size
description: The batch size for embedding calls.
default: 10
num_workers:
anyOf:
- type: integer
- type: 'null'
title: Num Workers
description: The number of workers to use for async embedding calls.
additional_kwargs:
additionalProperties: true
type: object
title: Additional Kwargs
description: Additional kwargs for the OpenAI API.
api_key:
anyOf:
- type: string
- type: 'null'
title: Api Key
description: The OpenAI API key.
api_base:
anyOf:
- type: string
- type: 'null'
title: Api Base
description: The base URL for OpenAI API.
default: https://api.openai.com/v1
api_version:
anyOf:
- type: string
- type: 'null'
title: Api Version
description: The version for OpenAI API.
default: ''
max_retries:
type: integer
minimum: 0.0
title: Max Retries
description: Maximum number of retries.
default: 10
timeout:
type: number
minimum: 0.0
title: Timeout
description: Timeout for each request.
default: 60.0
default_headers:
anyOf:
- additionalProperties:
type: string
type: object
- type: 'null'
title: Default Headers
description: The default headers for API requests.
reuse_client:
type: boolean
title: Reuse Client
description: Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability.
default: true
dimensions:
anyOf:
- type: integer
- type: 'null'
title: Dimensions
description: The number of dimensions on the output embedding vectors. Works only with v3 embedding models.
class_name:
type: string
title: Class Name
default: OpenAIEmbedding
type: object
title: OpenAIEmbedding
GeminiEmbedding:
properties:
model_name:
type: string
title: Model Name
description: The modelId of the Gemini model to use.
default: models/embedding-001
embed_batch_size:
type: integer
maximum: 2048.0
exclusiveMinimum: 0.0
title: Embed Batch Size
description: The batch size for embedding calls.
default: 10
num_workers:
anyOf:
- type: integer
- type: 'null'
title: Num Workers
description: The number of workers to use for async embedding calls.
title:
anyOf:
- type: string
- type: 'null'
title: Title
description: Title is only applicable for retrieval_document tasks, and is used to represent a document title. For other tasks, title is invalid.
default: ''
task_type:
anyOf:
- type: string
- type: 'null'
title: Task Type
description: The task for embedding model.
default: retrieval_document
api_key:
anyOf:
- type: string
- type: 'null'
title: Api Key
description: API key to access the model. Defaults to None.
api_base:
anyOf:
- type: string
- type: 'null'
title: Api Base
description: API base to access the model. Defaults to None.
transport:
anyOf:
- type: string
- type: 'null'
title: Transport
description: Transport to access the model. Defaults to None.
output_dimensionality:
anyOf:
- type: integer
- type: 'null'
title: Output Dimensionality
description: Optional reduced dimension for output embeddings. Supported by models/text-embedding-004 and newer (e.g. gemini-embedding-001). Not supported by models/embedding-001.
class_name:
type: string
title: Class Name
default: GeminiEmbedding
type: object
title: GeminiEmbedding
BedrockEmbedding:
properties:
model_name:
type: string
title: Model Name
description: The modelId of the Bedrock model to use.
default: amazon.titan-embed-text-v1
embed_batch_size:
type: integer
maximum: 2048.0
exclusiveMinimum: 0.0
title: Embed Batch Size
description: The batch size for embedding calls.
default: 10
num_workers:
anyOf:
- type: integer
- type: 'null'
title: Num Workers
description: The number of workers to use for async embedding calls.
profile_name:
anyOf:
- type: string
- type: 'null'
title: Profile Name
description: The name of aws profile to use. If not given, then the default profile is used.
aws_access_key_id:
anyOf:
- type: string
- type: 'null'
title: Aws Access Key Id
description: AWS Access Key ID to use
aws_secret_access_key:
anyOf:
- type: string
- type: 'null'
title: Aws Secret Access Key
description: AWS Secret Access Key to use
aws_session_token:
anyOf:
- type: string
- type: 'null'
title: Aws Session Token
description: AWS Session Token to use
region_name:
anyOf:
- type: string
- type: 'null'
title: Region Name
description: AWS region name to use. Uses region configured in AWS CLI if not passed
max_retries:
type: integer
exclusiveMinimum: 0.0
title: Max Retries
description: The maximum number of API retries.
default: 10
timeout:
type: number
title: Timeout
description: The timeout for the Bedrock API request in seconds. It will be used for both connect and read timeouts.
default: 60.0
additional_kwargs:
additionalProperties: true
type: object
title: Additional Kwargs
description: Additional kwargs for the bedrock client.
class_name:
type: string
title: Class Name
default: BedrockEmbedding
type: object
title: BedrockEmbedding
HTTPValidationError:
properties:
detail:
items:
$ref: '#/components/schemas/ValidationError'
type: array
title: Detail
type: object
title: HTTPValidationError
OpenAIEmbeddingConfig:
properties:
type:
type: string
const: OPENAI_EMBEDDING
title: Type
description: Type of the embedding model.
default: OPENAI_EMBEDDING
component:
$ref: '#/components/schemas/OpenAIEmbedding'
description: Configuration for the OpenAI embedding model.
type: object
title: OpenAIEmbeddingConfig
HuggingFaceInferenceAPIEmbedding:
properties:
model_name:
anyOf:
- type: string
- type: 'null'
title: Model Name
description: Hugging Face model name. If None, the task will be used.
embed_batch_size:
type: integer
maximum: 2048.0
exclusiveMinimum: 0.0
title: Embed Batch Size
description: The batch size for embedding calls.
default: 10
num_workers:
anyOf:
- type: integer
- type: 'null'
title: Num Workers
description: The number of workers to use for async embedding calls.
pooling:
anyOf:
- $ref: '#/components/schemas/Pooling'
- type: 'null'
description: Pooling strategy. If None, the model's default pooling is used.
default: cls
query_instruction:
anyOf:
- type: string
- type: 'null'
title: Query Instruction
description: Instruction to prepend during query embedding.
text_instruction:
anyOf:
- type: string
- type: 'null'
title: Text Instruction
description: Instruction to prepend during text embedding.
token:
anyOf:
- type: string
- type: boolean
- type: 'null'
title: Token
description: 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.
timeout:
anyOf:
- type: number
- type: 'null'
title: Timeout
description: 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.
headers:
anyOf:
- additionalProperties:
type: string
type: object
- type: 'null'
title: Headers
description: 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.
cookies:
anyOf:
- additionalProperties:
type: string
type: object
- type: 'null'
title: Cookies
description: Additional cookies to send to the server.
task:
anyOf:
- type: string
- type: 'null'
title: Task
description: Optional task to pick Hugging Face's recommended model, used when model_name is left as default of None.
class_name:
type: string
title: Class Name
default: HuggingFaceInferenceAPIEmbedding
type: object
title: HuggingFaceInferenceAPIEmbedding
EmbeddingModelConfig:
properties:
id:
type: string
format: uuid
title: Id
description: Unique identifier
created_at:
anyOf:
- type: string
format: date-time
- type: 'null'
title: Created At
description: Creation datetime
updated_at:
anyOf:
- type: string
format: date-time
- type: 'null'
title: Updated At
description: Update datetime
name:
type: string
title: Name
description: The name of the embedding model config.
embedding_config:
oneOf:
- $ref: '#/components/schemas/AzureOpenAIEmbeddingConfig'
- $ref: '#/components/schemas/CohereEmbeddingConfig'
- $ref: '#/components/schemas/GeminiEmbeddingConfig'
- $ref: '#/components/schemas/HuggingFaceInferenceAPIEmbeddingConfig'
- $ref: '#/components/schemas/OpenAIEmbeddingConfig'
- $ref: '#/components/schemas/VertexAIEmbeddingConfig'
- $ref: '#/components/schemas/BedrockEmbeddingConfig'
title: Embedding Config
description: The embedding configuration for the embedding model config.
discriminator:
propertyName: type
mapping:
AZURE_EMBEDDING: '#/components/schemas/AzureOpenAIEmbeddingConfig'
BEDROCK_EMBEDDING: '#/components/schemas/BedrockEmbeddingConfig'
COHERE_EMBEDDING: '#/components/schemas/CohereEmbeddingConfig'
GEMINI_EMBEDDING: '#/components/schemas/GeminiEmbeddingConfig'
HUGGINGFACE_API_EMBEDDING: '#/components/schemas/HuggingFaceInferenceAPIEmbeddingConfig'
OPENAI_EMBEDDING: '#/components/schemas/OpenAIEmbeddingConfig'
VERTEXAI_EMBEDDING: '#/components/schemas/VertexAIEmbeddingConfig'
project_id:
type: string
format: uuid
title: Project Id
type: object
required:
- id
- name
- embedding_config
- project_id
title: EmbeddingModelConfig
description: Schema for an embedding model config.
EmbeddingModelConfigCreate:
properties:
name:
type: string
title: Name
description: The name of the embedding model config.
embedding_config:
oneOf:
- $ref: '#/components/schemas/AzureOpenAIEmbeddingConfig'
- $ref: '#/components/schemas/CohereEmbeddingConfig'
- $ref: '#/components/schemas/GeminiEmbeddingConfig'
- $ref: '#/components/schemas/HuggingFaceInferenceAPIEmbeddingConfig'
- $ref: '#/components/schemas/OpenAIEmbeddingConfig'
- $ref: '#/components/schemas/VertexAIEmbeddingConfig'
- $ref: '#/components/schemas/BedrockEmbeddingConfig'
title: Embedding Config
description: The embedding configuration for the embedding model config.
discriminator:
propertyName: type
mapping:
AZURE_EMBEDDING: '#/components/schemas/AzureOpenAIEmbeddingConfig'
BEDROCK_EMBEDDING: '#/components/schemas/BedrockEmbeddingConfig'
COHERE_EMBEDDING: '#/components/schemas/CohereEmbeddingConfig'
GEMINI_EMBEDDING: '#/components/schemas/GeminiEmbeddingConfig'
HUGGINGFACE_API_EMBEDDING: '#/components/schemas/HuggingFaceInferenceAPIEmbeddingConfig'
OPENAI_EMBEDDING: '#/components/schemas/OpenAIEmbeddingConfig'
VERTEXAI_EMBEDDING: '#/components/schemas/VertexAIEmbeddingConfig'
type: object
required:
- name
- embedding_config
title: EmbeddingModelConfigCreate
CohereEmbeddingConfig:
properties:
type:
type: string
const: COHERE_EMBEDDING
title: Type
description: Type of the embedding model.
default: COHERE_EMBEDDING
component:
$ref: '#/components/schemas/CohereEmbedding'
description: Configuration for the Cohere embedding model.
type: object
title: CohereEmbeddingConfig
Pooling:
type: string
enum:
- cls
- mean
- last
title: Pooling
description: Enum of possible pooling choices with pooling behaviors.
VertexAIEmbeddingConfig:
properties:
type:
type: string
const: VERTEXAI_EMBEDDING
title: Type
description: Type of the embedding model.
default: VERTEXAI_EMBEDDING
component:
$ref: '#/components/schemas/VertexTextEmbedding'
description: Configuration for the VertexAI embedding model.
type: object
title: VertexAIEmbeddingConfig
EmbeddingModelConfigUpdate:
properties:
name:
anyOf:
- type: string
- type: 'null'
title: Name
description: The name of the embedding model config.
embedding_config:
anyOf:
- oneOf:
- $ref: '#/components/schemas/AzureOpenAIEmbeddingConfig'
- $ref: '#/components/schemas/CohereEmbeddingConfig'
- $ref: '#/components/schemas/GeminiEmbeddingConfig'
- $ref: '#/components/schemas/HuggingFaceInferenceAPIEmbeddingConfig'
- $ref: '#/components/schemas/OpenAIEmbeddingConfig'
- $ref: '#/components/schemas/VertexAIEmbeddingConfig'
- $ref: '#/components/schemas/BedrockEmbeddingConfig'
discriminator:
propertyName: type
mapping:
AZURE_EMBEDDING: '#/components/schemas/AzureOpenAIEmbeddingConfig'
BEDROCK_EMBEDDING: '#/components/schemas/BedrockEmbeddingConfig'
COHERE_EMBEDDING: '#/components/schemas/CohereEmbeddingConfig'
GEMINI_EMBEDDING: '#/components/schemas/GeminiEmbeddingConfig'
HUGGINGFACE_API_EMBEDDING: '#/components/schemas/HuggingFaceInferenceAPIEmbeddingConfig'
OPENAI_EMBEDDING: '#/components/schemas/OpenAIEmbeddingConfig'
VERTEXAI_EMBEDDING: '#/components/schemas/VertexAIEmbeddingConfig'
- type: 'null'
title: Embedding Config
description: The embedding configuration for the embedding model config.
type: object
title: EmbeddingModelConfigUpdate
HuggingFaceInferenceAPIEmbeddingConfig:
properties:
type:
type: string
const: HUGGINGFACE_API_EMBEDDING
title: Type
description: Type of the embedding model.
default: HUGGINGFACE_API_EMBEDDING
component:
$ref: '#/components/schemas/HuggingFaceInferenceAPIEmbedding'
description: Configuration for the HuggingFace Inference API embedding model.
type: object
title: HuggingFaceInferenceAPIEmbeddingConfig
GeminiEmbeddingConfig:
properties:
type:
type: string
const: GEMINI_EMBEDDING
title: Type
description: Type of the embedding model.
default: GEMINI_EMBEDDING
component:
$ref: '#/components/schemas/GeminiEmbedding'
description: Configuration for the Gemini embedding model.
type: object
title: GeminiEmbeddingConfig
ValidationError:
properties:
loc:
items:
anyOf:
- type: string
- type: integer
type: array
title: Location
msg:
type: string
title: Message
type:
type: string
title: Error Type
input:
title: Input
ctx:
type: object
title: Context
type: object
required:
- loc
- msg
- type
title: ValidationError
VertexTextEmbedding:
properties:
model_name:
type: string
title: Model Name
description: The modelId of the VertexAI model to use.
default: textembedding-gecko@003
embed_batch_size:
type: integer
maximum: 2048.0
exclusiveMinimum: 0.0
title: Embed Batch Size
description: The batch size for embedding calls.
default: 10
num_workers:
anyOf:
- type: integer
- type: 'null'
title: Num Workers
description: The number of workers to use for async embedding calls.
location:
type: string
title: Location
description: The default location to use when making API calls.
project:
type: string
title: Project
description: The default GCP project to use when making Vertex API calls.
embed_mode:
$ref: '#/components/schemas/VertexEmbeddingMode'
description: The embedding mode to use.
default: retrieval
additional_kwargs:
additionalProperties: true
type: object
title: Additional Kwargs
description: Additional kwargs for the Vertex.
client_email:
anyOf:
- type: string
- type: 'null'
title: Client Email
description: The client email for the VertexAI credentials.
token_uri:
anyOf:
- type: string
- type: 'null'
title: Token Uri
description: The token URI for the VertexAI credentials.
private_key_id:
anyOf:
- type: string
- type: 'null'
title: Private Key Id
description: The private key ID for the VertexAI credentials.
private_key:
anyOf:
- type: string
- type: 'null'
title: Private Key
description: The private key for the VertexAI credentials.
class_name:
type: string
title: Class Name
default: VertexTextEmbedding
type: object
required:
- location
- project
- client_email
- token_uri
- private_key_id
- private_key
title: VertexTextEmbedding
CohereEmbedding:
properties:
model_name:
type: string
title: Model Name
description: The modelId of the Cohere model to use.
default: embed-english-v3.0
embed_batch_size:
type: integer
maximum: 2048.0
exclusiveMinimum: 0.0
title: Embed Batch Size
description: The batch size for embedding calls.
default: 10
num_workers:
anyOf:
- type: integer
- type: 'null'
title: Num Workers
description: The number of workers to use for async embedding calls.
api_key:
anyOf:
- type: string
- type: 'null'
title: Api Key
description: The Cohere API key.
truncate:
type: string
title: Truncate
description: Truncation type - START/ END/ NONE
default: END
input_type:
anyOf:
- type: string
- type: 'null'
title: Input Type
description: Model Input type. If not provided, search_document and search_query are used when needed.
embedding_type:
type: string
title: Embedding Type
description: Embedding type. If not provided float embedding_type is used when needed.
default: float
class_name:
type: string
title: Class Name
default: CohereEmbedding
type: object
required:
- api_key
title: CohereEmbedding
AzureOpenAIEmbeddingConfig:
properties:
type:
type: string
const: AZURE_EMBEDDING
title: Type
description: Type of the embedding model.
default: AZURE_EMBEDDING
component:
$ref: '#/components/schemas/AzureOpenAIEmbedding'
description: Configuration for the Azure OpenAI embedding model.
type: object
title: AzureOpenAIEmbeddingConfig
VertexEmbeddingMode:
type: string
enum:
- default
- classification
- clustering
- similarity
- retrieval
title: VertexEmbeddingMode
description: 'Copied from llama_index.embeddings.vertex.base.VertexEmbeddingMode
since importing llama_index.embeddings.vertex.base incurs a lot of memory usage.'
BedrockEmbeddingConfig:
properties:
type:
type: string
const: BEDROCK_EMBEDDING
title: Type
description: Type of the embedding model.
default: BEDROCK_EMBEDDING
component:
$ref: '#/components/schemas/BedrockEmbedding'
description: Configuration for the Bedrock embedding model.
type: object
title: BedrockEmbeddingConfig
AzureOpenAIEmbedding:
properties:
model_name:
type: string
title: Model Name
description: The name of the OpenAI embedding model.
default: text-embedding-ada-002
embed_batch_size:
type: integer
maximum: 2048.0
exclusiveMinimum: 0.0
title: Embed Batch Size
description: The batch size for embedding calls.
default: 10
num_workers:
anyOf:
- type: integer
- type: 'null'
title: Num Workers
description: The number of workers to use for async embedding calls.
additional_kwargs:
additionalProperties: true
type: object
title: Additional Kwargs
description: Additional kwargs for the OpenAI API.
api_key:
anyOf:
- type: string
- type: 'null'
title: Api Key
description: The OpenAI API key.
api_base:
type: string
title: Api Base
description: The base URL for Azure deployment.
default: ''
api_version:
type: string
title: Api Version
description: The version for Azure OpenAI API.
default: ''
max_retries:
type: integer
minimum: 0.0
title: Max Retries
description: Maximum number of retries.
default: 10
timeout:
type: number
minimum: 0.0
title: Timeout
description: Timeout for each request.
default: 60.0
default_headers:
anyOf:
- additionalProperties:
type: string
type: object
- type: 'null'
title: Default Headers
description: The default headers for API requests.
reuse_client:
type: boolean
title: Reuse Client
description: Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability.
default: true
dimensions:
anyOf:
- type: integer
- type: 'null'
title: Dimensions
description: The number of dimensions on the output embedding vectors. Works only with v3 embedding models.
azure_endpoint:
anyOf:
- type: string
- type: 'null'
title: Azure Endpoint
description: The Azure endpoint to use.
azure_deployment:
anyOf:
- type: string
- type: 'null'
title: Azure Deployment
description: The Azure deployment to use.
class_name:
type: string
title: Class Name
default: AzureOpenAIEmbedding
type: object
title: AzureOpenAIEmbeddin
# --- truncated at 32 KB (32 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/llamaparse/refs/heads/main/openapi/llamaparse-embedding-model-configs-api-openapi.yml