Update Embedding Model Config

PUT 
https://api.cloud.llamaindex.ai/api/v1/embedding-model-configs/:embedding_model_config_id

Update an embedding model config by ID.

Request

Path Parameters

embedding_model_config_id uuidrequired

Cookie Parameters

session any

application/json

Bodyrequired

name object
The name of the embedding model config.
anyOf
MOD1
string
MOD2
embedding_config object
The embedding configuration for the embedding model config.
anyOf
MOD1
type
Possible values: [AZURE_EMBEDDING, BEDROCK_EMBEDDING, COHERE_EMBEDDING, GEMINI_EMBEDDING, HUGGINGFACE_API_EMBEDDING, OPENAI_EMBEDDING, VERTEXAI_EMBEDDING]
AZURE_EMBEDDING
component object
Configuration for the Azure OpenAI embedding model.
model_nameModel Name (string)
The name of the OpenAI embedding model.
Default value: text-embedding-ada-002
embed_batch_sizeEmbed Batch Size (integer)
The batch size for embedding calls.
Possible values: > 0 and <= 2048
Default value: 10
num_workers object
The number of workers to use for async embedding calls.
anyOf
MOD1
integer
MOD2
additional_kwargsobject
Additional kwargs for the OpenAI API.
api_key object
The OpenAI API key.
anyOf
MOD1
string
MOD2
api_baseApi Base (string)
The base URL for Azure deployment.
Default value:
api_versionApi Version (string)
The version for Azure OpenAI API.
Default value:
max_retriesMax Retries (integer)
Maximum number of retries.
Default value: 10
timeoutTimeout (number)
Timeout for each request.
Default value: 60
default_headers object
The default headers for API requests.
anyOf
MOD1
object
MOD2
reuse_clientReuse Client (boolean)
Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability.
Default value: true
dimensions object
The number of dimensions on the output embedding vectors. Works only with v3 embedding models.
anyOf
MOD1
integer
MOD2
azure_endpoint object
The Azure endpoint to use.
anyOf
MOD1
string
MOD2
azure_deployment object
The Azure deployment to use.
anyOf
MOD1
string
MOD2
class_nameClass Name (string)
Default value: AzureOpenAIEmbedding
BEDROCK_EMBEDDING
component object
Configuration for the Bedrock embedding model.
model_nameModel Name (string)
The modelId of the Bedrock model to use.
Default value: amazon.titan-embed-text-v1
embed_batch_sizeEmbed Batch Size (integer)
The batch size for embedding calls.
Possible values: > 0 and <= 2048
Default value: 10
num_workers object
The number of workers to use for async embedding calls.
anyOf
MOD1
integer
MOD2
profile_name object
The name of aws profile to use. If not given, then the default profile is used.
anyOf
MOD1
string
MOD2
aws_access_key_id object
AWS Access Key ID to use
anyOf
MOD1
string
MOD2
aws_secret_access_key object
AWS Secret Access Key to use
anyOf
MOD1
string
MOD2
aws_session_token object
AWS Session Token to use
anyOf
MOD1
string
MOD2
region_name object
AWS region name to use. Uses region configured in AWS CLI if not passed
anyOf
MOD1
string
MOD2
max_retriesMax Retries (integer)
The maximum number of API retries.
Possible values: > 0
Default value: 10
timeoutTimeout (number)
The timeout for the Bedrock API request in seconds. It will be used for both connect and read timeouts.
Default value: 60
additional_kwargsobject
Additional kwargs for the bedrock client.
class_nameClass Name (string)
Default value: BedrockEmbedding
COHERE_EMBEDDING
component object
Configuration for the Cohere embedding model.
model_nameModel Name (string)
The modelId of the Cohere model to use.
Default value: embed-english-v3.0
embed_batch_sizeEmbed Batch Size (integer)
The batch size for embedding calls.
Possible values: > 0 and <= 2048
Default value: 10
num_workers object
The number of workers to use for async embedding calls.
anyOf
MOD1
integer
MOD2
api_key objectrequired
The Cohere API key.
anyOf
MOD1
string
MOD2
truncateTruncate (string)
Truncation type - START/ END/ NONE
Default value: END
input_type object
Model Input type. If not provided, search_document and search_query are used when needed.
anyOf
MOD1
string
MOD2
embedding_typeEmbedding Type (string)
Embedding type. If not provided float embedding_type is used when needed.
Default value: float
class_nameClass Name (string)
Default value: CohereEmbedding
GEMINI_EMBEDDING
component object
Configuration for the Gemini embedding model.
model_nameModel Name (string)
The modelId of the Gemini model to use.
Default value: models/embedding-001
embed_batch_sizeEmbed Batch Size (integer)
The batch size for embedding calls.
Possible values: > 0 and <= 2048
Default value: 10
num_workers object
The number of workers to use for async embedding calls.
anyOf
MOD1
integer
MOD2
title object
Title is only applicable for retrieval_document tasks, and is used to represent a document title. For other tasks, title is invalid.
anyOf
MOD1
string
MOD2
task_type object
The task for embedding model.
anyOf
MOD1
string
MOD2
api_key object
API key to access the model. Defaults to None.
anyOf
MOD1
string
MOD2
api_base object
API base to access the model. Defaults to None.
anyOf
MOD1
string
MOD2
transport object
Transport to access the model. Defaults to None.
anyOf
MOD1
string
MOD2
class_nameClass Name (string)
Default value: GeminiEmbedding
HUGGINGFACE_API_EMBEDDING
component object
Configuration for the HuggingFace Inference API embedding model.
model_name object
Hugging Face model name. If None, the task will be used.
anyOf
MOD1
string
MOD2
embed_batch_sizeEmbed Batch Size (integer)
The batch size for embedding calls.
Possible values: > 0 and <= 2048
Default value: 10
num_workers object
The number of workers to use for async embedding calls.
anyOf
MOD1
integer
MOD2
pooling object
Pooling strategy. If None, the model's default pooling is used.
anyOf
Pooling
string
Enum of possible pooling choices with pooling behaviors.
Possible values: [cls, mean, last]
MOD2
query_instruction object
Instruction to prepend during query embedding.
anyOf
MOD1
string
MOD2
text_instruction object
Instruction to prepend during text embedding.
anyOf
MOD1
string
MOD2
token object
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.
anyOf
MOD1
string
MOD2
boolean
MOD3
timeout object
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.
anyOf
MOD1
number
MOD2
headers object
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.
anyOf
MOD1
object
MOD2
cookies object
Additional cookies to send to the server.
anyOf
MOD1
object
MOD2
task object
Optional task to pick Hugging Face's recommended model, used when model_name is left as default of None.
anyOf
MOD1
string
MOD2
class_nameClass Name (string)
Default value: HuggingFaceInferenceAPIEmbedding
OPENAI_EMBEDDING
component object
Configuration for the OpenAI embedding model.
model_nameModel Name (string)
The name of the OpenAI embedding model.
Default value: text-embedding-ada-002
embed_batch_sizeEmbed Batch Size (integer)
The batch size for embedding calls.
Possible values: > 0 and <= 2048
Default value: 10
num_workers object
The number of workers to use for async embedding calls.
anyOf
MOD1
integer
MOD2
additional_kwargsobject
Additional kwargs for the OpenAI API.
api_key object
The OpenAI API key.
anyOf
MOD1
string
MOD2
api_base object
The base URL for OpenAI API.
anyOf
MOD1
string
MOD2
api_version object
The version for OpenAI API.
anyOf
MOD1
string
MOD2
max_retriesMax Retries (integer)
Maximum number of retries.
Default value: 10
timeoutTimeout (number)
Timeout for each request.
Default value: 60
default_headers object
The default headers for API requests.
anyOf
MOD1
object
MOD2
reuse_clientReuse Client (boolean)
Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability.
Default value: true
dimensions object
The number of dimensions on the output embedding vectors. Works only with v3 embedding models.
anyOf
MOD1
integer
MOD2
class_nameClass Name (string)
Default value: OpenAIEmbedding
VERTEXAI_EMBEDDING
component object
Configuration for the VertexAI embedding model.
model_nameModel Name (string)
The modelId of the VertexAI model to use.
Default value: textembedding-gecko@003
embed_batch_sizeEmbed Batch Size (integer)
The batch size for embedding calls.
Possible values: > 0 and <= 2048
Default value: 10
num_workers object
The number of workers to use for async embedding calls.
anyOf
MOD1
integer
MOD2
locationLocation (string)required
The default location to use when making API calls.
projectProject (string)required
The default GCP project to use when making Vertex API calls.
embed_modeVertexEmbeddingMode (string)
The embedding mode to use.
Possible values: [default, classification, clustering, similarity, retrieval]
Default value: retrieval
additional_kwargsobject
Additional kwargs for the Vertex.
client_email objectrequired
The client email for the VertexAI credentials.
anyOf
MOD1
string
MOD2
token_uri objectrequired
The token URI for the VertexAI credentials.
anyOf
MOD1
string
MOD2
private_key_id objectrequired
The private key ID for the VertexAI credentials.
anyOf
MOD1
string
MOD2
private_key objectrequired
The private key for the VertexAI credentials.
anyOf
MOD1
string
MOD2
class_nameClass Name (string)
Default value: VertexTextEmbedding
MOD2

Responses

200

Successful Response

application/json

Schema

Schema

iduuidrequired
Unique identifier
created_at object
Creation datetime
anyOf
MOD1
string
MOD2
updated_at object
Update datetime
anyOf
MOD1
string
MOD2
nameName (string)required
The name of the embedding model config.
embedding_config objectrequired
The embedding configuration for the embedding model config.
type
The embedding configuration for the embedding model config.
Possible values: [AZURE_EMBEDDING, BEDROCK_EMBEDDING, COHERE_EMBEDDING, GEMINI_EMBEDDING, HUGGINGFACE_API_EMBEDDING, OPENAI_EMBEDDING, VERTEXAI_EMBEDDING]
AZURE_EMBEDDING
component object
Configuration for the Azure OpenAI embedding model.
model_nameModel Name (string)
The name of the OpenAI embedding model.
Default value: text-embedding-ada-002
embed_batch_sizeEmbed Batch Size (integer)
The batch size for embedding calls.
Possible values: > 0 and <= 2048
Default value: 10
num_workers object
The number of workers to use for async embedding calls.
anyOf
MOD1
integer
MOD2
additional_kwargsobject
Additional kwargs for the OpenAI API.
api_key object
The OpenAI API key.
anyOf
MOD1
string
MOD2
api_baseApi Base (string)
The base URL for Azure deployment.
Default value:
api_versionApi Version (string)
The version for Azure OpenAI API.
Default value:
max_retriesMax Retries (integer)
Maximum number of retries.
Default value: 10
timeoutTimeout (number)
Timeout for each request.
Default value: 60
default_headers object
The default headers for API requests.
anyOf
MOD1
object
MOD2
reuse_clientReuse Client (boolean)
Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability.
Default value: true
dimensions object
The number of dimensions on the output embedding vectors. Works only with v3 embedding models.
anyOf
MOD1
integer
MOD2
azure_endpoint object
The Azure endpoint to use.
anyOf
MOD1
string
MOD2
azure_deployment object
The Azure deployment to use.
anyOf
MOD1
string
MOD2
class_nameClass Name (string)
Default value: AzureOpenAIEmbedding
BEDROCK_EMBEDDING
component object
Configuration for the Bedrock embedding model.
model_nameModel Name (string)
The modelId of the Bedrock model to use.
Default value: amazon.titan-embed-text-v1
embed_batch_sizeEmbed Batch Size (integer)
The batch size for embedding calls.
Possible values: > 0 and <= 2048
Default value: 10
num_workers object
The number of workers to use for async embedding calls.
anyOf
MOD1
integer
MOD2
profile_name object
The name of aws profile to use. If not given, then the default profile is used.
anyOf
MOD1
string
MOD2
aws_access_key_id object
AWS Access Key ID to use
anyOf
MOD1
string
MOD2
aws_secret_access_key object
AWS Secret Access Key to use
anyOf
MOD1
string
MOD2
aws_session_token object
AWS Session Token to use
anyOf
MOD1
string
MOD2
region_name object
AWS region name to use. Uses region configured in AWS CLI if not passed
anyOf
MOD1
string
MOD2
max_retriesMax Retries (integer)
The maximum number of API retries.
Possible values: > 0
Default value: 10
timeoutTimeout (number)
The timeout for the Bedrock API request in seconds. It will be used for both connect and read timeouts.
Default value: 60
additional_kwargsobject
Additional kwargs for the bedrock client.
class_nameClass Name (string)
Default value: BedrockEmbedding
COHERE_EMBEDDING
component object
Configuration for the Cohere embedding model.
model_nameModel Name (string)
The modelId of the Cohere model to use.
Default value: embed-english-v3.0
embed_batch_sizeEmbed Batch Size (integer)
The batch size for embedding calls.
Possible values: > 0 and <= 2048
Default value: 10
num_workers object
The number of workers to use for async embedding calls.
anyOf
MOD1
integer
MOD2
api_key objectrequired
The Cohere API key.
anyOf
MOD1
string
MOD2
truncateTruncate (string)
Truncation type - START/ END/ NONE
Default value: END
input_type object
Model Input type. If not provided, search_document and search_query are used when needed.
anyOf
MOD1
string
MOD2
embedding_typeEmbedding Type (string)
Embedding type. If not provided float embedding_type is used when needed.
Default value: float
class_nameClass Name (string)
Default value: CohereEmbedding
GEMINI_EMBEDDING
component object
Configuration for the Gemini embedding model.
model_nameModel Name (string)
The modelId of the Gemini model to use.
Default value: models/embedding-001
embed_batch_sizeEmbed Batch Size (integer)
The batch size for embedding calls.
Possible values: > 0 and <= 2048
Default value: 10
num_workers object
The number of workers to use for async embedding calls.
anyOf
MOD1
integer
MOD2
title object
Title is only applicable for retrieval_document tasks, and is used to represent a document title. For other tasks, title is invalid.
anyOf
MOD1
string
MOD2
task_type object
The task for embedding model.
anyOf
MOD1
string
MOD2
api_key object
API key to access the model. Defaults to None.
anyOf
MOD1
string
MOD2
api_base object
API base to access the model. Defaults to None.
anyOf
MOD1
string
MOD2
transport object
Transport to access the model. Defaults to None.
anyOf
MOD1
string
MOD2
class_nameClass Name (string)
Default value: GeminiEmbedding
HUGGINGFACE_API_EMBEDDING
component object
Configuration for the HuggingFace Inference API embedding model.
model_name object
Hugging Face model name. If None, the task will be used.
anyOf
MOD1
string
MOD2
embed_batch_sizeEmbed Batch Size (integer)
The batch size for embedding calls.
Possible values: > 0 and <= 2048
Default value: 10
num_workers object
The number of workers to use for async embedding calls.
anyOf
MOD1
integer
MOD2
pooling object
Pooling strategy. If None, the model's default pooling is used.
anyOf
Pooling
string
Enum of possible pooling choices with pooling behaviors.
Possible values: [cls, mean, last]
MOD2
query_instruction object
Instruction to prepend during query embedding.
anyOf
MOD1
string
MOD2
text_instruction object
Instruction to prepend during text embedding.
anyOf
MOD1
string
MOD2
token object
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.
anyOf
MOD1
string
MOD2
boolean
MOD3
timeout object
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.
anyOf
MOD1
number
MOD2
headers object
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.
anyOf
MOD1
object
MOD2
cookies object
Additional cookies to send to the server.
anyOf
MOD1
object
MOD2
task object
Optional task to pick Hugging Face's recommended model, used when model_name is left as default of None.
anyOf
MOD1
string
MOD2
class_nameClass Name (string)
Default value: HuggingFaceInferenceAPIEmbedding
OPENAI_EMBEDDING
component object
Configuration for the OpenAI embedding model.
model_nameModel Name (string)
The name of the OpenAI embedding model.
Default value: text-embedding-ada-002
embed_batch_sizeEmbed Batch Size (integer)
The batch size for embedding calls.
Possible values: > 0 and <= 2048
Default value: 10
num_workers object
The number of workers to use for async embedding calls.
anyOf
MOD1
integer
MOD2
additional_kwargsobject
Additional kwargs for the OpenAI API.
api_key object
The OpenAI API key.
anyOf
MOD1
string
MOD2
api_base object
The base URL for OpenAI API.
anyOf
MOD1
string
MOD2
api_version object
The version for OpenAI API.
anyOf
MOD1
string
MOD2
max_retriesMax Retries (integer)
Maximum number of retries.
Default value: 10
timeoutTimeout (number)
Timeout for each request.
Default value: 60
default_headers object
The default headers for API requests.
anyOf
MOD1
object
MOD2
reuse_clientReuse Client (boolean)
Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability.
Default value: true
dimensions object
The number of dimensions on the output embedding vectors. Works only with v3 embedding models.
anyOf
MOD1
integer
MOD2
class_nameClass Name (string)
Default value: OpenAIEmbedding
VERTEXAI_EMBEDDING
component object
Configuration for the VertexAI embedding model.
model_nameModel Name (string)
The modelId of the VertexAI model to use.
Default value: textembedding-gecko@003
embed_batch_sizeEmbed Batch Size (integer)
The batch size for embedding calls.
Possible values: > 0 and <= 2048
Default value: 10
num_workers object
The number of workers to use for async embedding calls.
anyOf
MOD1
integer
MOD2
locationLocation (string)required
The default location to use when making API calls.
projectProject (string)required
The default GCP project to use when making Vertex API calls.
embed_modeVertexEmbeddingMode (string)
The embedding mode to use.
Possible values: [default, classification, clustering, similarity, retrieval]
Default value: retrieval
additional_kwargsobject
Additional kwargs for the Vertex.
client_email objectrequired
The client email for the VertexAI credentials.
anyOf
MOD1
string
MOD2
token_uri objectrequired
The token URI for the VertexAI credentials.
anyOf
MOD1
string
MOD2
private_key_id objectrequired
The private key ID for the VertexAI credentials.
anyOf
MOD1
string
MOD2
private_key objectrequired
The private key for the VertexAI credentials.
anyOf
MOD1
string
MOD2
class_nameClass Name (string)
Default value: VertexTextEmbedding
project_iduuidrequired

Example (auto)

{
  "id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
  "created_at": "2024-07-29T15:51:28.071Z",
  "updated_at": "2024-07-29T15:51:28.071Z",
  "name": "string",
  "embedding_config": {
    "type": "AZURE_EMBEDDING",
    "component": {
      "model_name": "text-embedding-ada-002",
      "embed_batch_size": 10,
      "num_workers": 0,
      "additional_kwargs": {},
      "api_key": "string",
      "api_base": "string",
      "api_version": "string",
      "max_retries": 10,
      "timeout": 60,
      "default_headers": {},
      "reuse_client": true,
      "dimensions": 0,
      "azure_endpoint": "string",
      "azure_deployment": "string",
      "class_name": "AzureOpenAIEmbedding"
    }
  },
  "project_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6"
}

422

Validation Error

application/json

Schema

Schema

detail object[]
Array [
loc object[]required
Array [
anyOf
MOD1
string
MOD2
integer
]
msgMessage (string)required
typeError Type (string)required
]

Example (auto)

{
  "detail": [
    {
      "loc": [
        "string",
        0
      ],
      "msg": "string",
      "type": "string"
    }
  ]
}

Authorization: http

name: HTTPBearertype: httpscheme: bearer

name: HTTPBearertype: httpscheme: bearer

• csharp
• curl
• dart
• go
• http
• java
• javascript
• kotlin
• c
• nodejs
• objective-c
• ocaml
• php
• powershell
• python
• r
• ruby
• rust
• shell
• swift

• HTTPCLIENT
• RESTSHARP

var client = new HttpClient();
var request = new HttpRequestMessage(HttpMethod.Put, "https://api.cloud.llamaindex.ai/api/v1/embedding-model-configs/:embedding_model_config_id");
request.Headers.Add("Accept", "application/json");
request.Headers.Add("Authorization", "Bearer <token>");
request.Headers.Add("Authorization", "Bearer <token>");
var content = new StringContent("{\n  \"name\": \"string\",\n  \"embedding_config\": {\n    \"type\": \"AZURE_EMBEDDING\",\n    \"component\": {\n      \"model_name\": \"text-embedding-ada-002\",\n      \"embed_batch_size\": 10,\n      \"num_workers\": 0,\n      \"additional_kwargs\": {},\n      \"api_key\": \"string\",\n      \"api_base\": \"string\",\n      \"api_version\": \"string\",\n      \"max_retries\": 10,\n      \"timeout\": 60,\n      \"default_headers\": {},\n      \"reuse_client\": true,\n      \"dimensions\": 0,\n      \"azure_endpoint\": \"string\",\n      \"azure_deployment\": \"string\",\n      \"class_name\": \"AzureOpenAIEmbedding\"\n    }\n  }\n}", null, "application/json");
request.Content = content;
var response = await client.SendAsync(request);
response.EnsureSuccessStatusCode();
Console.WriteLine(await response.Content.ReadAsStringAsync());

Request Collapse all

Base URL

https://api.cloud.llamaindex.ai

Auth

Bearer Token

Bearer Token

Parameters

embedding_model_config_id — pathrequired

session — cookie

Body required

{
  "name": "string",
  "embedding_config": {
    "type": "AZURE_EMBEDDING",
    "component": {
      "model_name": "text-embedding-ada-002",
      "embed_batch_size": 10,
      "num_workers": 0,
      "additional_kwargs": {},
      "api_key": "string",
      "api_base": "string",
      "api_version": "string",
      "max_retries": 10,
      "timeout": 60,
      "default_headers": {},
      "reuse_client": true,
      "dimensions": 0,
      "azure_endpoint": "string",
      "azure_deployment": "string",
      "class_name": "AzureOpenAIEmbedding"
    }
  }
}

ResponseClear

Click the Send API Request button above and see the response here!