AIGatewayAzureEmbeddingsModelConfig
objectAzure-specific configuration for a model.
The name of the embeddings model.
The URL of the embeddings model.
Allowed values:azure
The Azure deployment ID for the model.
The Azure OpenAI API version to use.
Default:2023-05-15
AIGatewayBedrockEmbeddingsModelConfig
objectAWS Bedrock-specific configuration for a model.
The name of the embeddings model.
The URL of the embeddings model.
Allowed values:bedrock
S3 bucket prefix for batch inference jobs.
Whether to normalize embedding vectors in the response.
Default:false
Latency performance configuration for the model invocation.
S3 URI for storing video generation outputs.
AIGatewayGeminiEmbeddingsModelConfig
objectGoogle Gemini-specific configuration for a model.
The name of the embeddings model.
The URL of the embeddings model.
Allowed values:gemini
The Google Cloud location ID for the model endpoint.
The custom API endpoint for the Gemini model.
AIGatewayHuggingfaceEmbeddingsModelConfig
objectHugging Face-specific configuration for a model.
The name of the embeddings model.
The URL of the embeddings model.
Allowed values:huggingface
Whether to use the Hugging Face inference cache.
Default:false
Whether to wait for the model to load if it is not ready.
Default:false
AIGatewayModelVectorDBConfig
Configuration for the vector database used by the model.
One OfAllowed values:pgvector
the desired dimensionality for the vectors
the distance metric to use for vector searches
Allowed values:cosineeuclidean
the default similarity threshold for accepting semantic search results (float). Higher threshold means more results are considered similar.
the database of the pgvector database
Default:kong-pgvector
the host of the pgvector database
Default:127.0.0.1
the password of the pgvector database
This field is referenceable.
This field is encrypted.
the port of the pgvector database
Default:5432
Show Child Parameters
the timeout of the pgvector database
Default:5000