SambaNova Systems Embeddings API
The Embeddings API from SambaNova Systems — 1 operation(s) for embeddings.
OpenAPI Specification
openapi: 3.1.0
info:
title: Sambanova Agents Service Audio Embeddings API
description: Service for Sambanova agents
version: 0.0.1
termsOfService: https://sambanova.ai/cloud-end-user-license-agreement
contact:
email: info@sambanova.ai
name: SambaNova information
license:
name: Apache 2.0
url: https://www.apache.org/licenses/LICENSE-2.0.html
servers:
- url: https://chat.sambanova.ai/api
security:
- api_key: []
tags:
- name: Embeddings
paths:
/embeddings:
post:
operationId: createEmbedding
tags:
- Embeddings
summary: Create embeddings
security:
- api_key: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/EmbeddingsRequest'
description: Texts to embed and parameters
required: true
responses:
'200':
description: Successful response
content:
application/json:
schema:
$ref: '#/components/schemas/EmbeddingsResponse'
'400':
description: Bad Request - Missing or invalid parameters
content:
text/plain:
schema:
type: string
example: 'Invalid request body: - missing property ''model''"'
application/json:
schema:
oneOf:
- $ref: '#/components/schemas/GeneralError'
- $ref: '#/components/schemas/SimpleError'
examples:
missing_model:
summary: No model parameter provided
value:
error:
message: you must provide a model parameter
type: invalid_request_error
param: null
code: null
request_id: a4fa849e
invalid_json:
summary: Malformed JSON body
value:
error:
code: null
message: 'We could not parse the JSON body of your request. (HINT: This likely means you aren''t using your HTTP library correctly. A JSON payload is expected, but what was sent was not valid JSON.)'
param: null
type: invalid_request_error
request_id: 3f7db127
simple:
summary: Simple error (unhandled cases)
value:
error: Model name is required
'401':
description: Unauthorized access
content:
application/json:
schema:
$ref: '#/components/schemas/GeneralError'
examples:
invalid_api_key:
summary: Invalid API key provided
value:
error:
message: 'Incorrect API key provided: *****. You can find your API key at https://cloud.sambanova.ai/apis.'
type: invalid_request_error
param: null
code: invalid_api_key
request_id: d79vcq57os633dverhi0
missing_api_key:
summary: No API key provided
value:
error:
message: 'You didn''t provide an API key. You need to provide your API key in an Authorization header using Bearer auth (i.e. Authorization: Bearer YOUR_KEY).'
type: invalid_request_error
param: null
code: null
request_id: d7a0dct7os633dvesi60
'404':
description: Not found - model does not exist or wrong endpoint called
content:
application/json:
schema:
oneOf:
- $ref: '#/components/schemas/GeneralError'
- $ref: '#/components/schemas/SimpleError'
examples:
model_not_found:
summary: Model does not exist or is not accessible
value:
error:
code: model_not_found
message: The model `abc` does not exist or you do not have access to it.
param: model
type: invalid_request_error
request_id: 887a8227
simple:
summary: Simple error (unhandled cases e.g. wrong endpoint)
value:
error: Not found
'408':
description: Request timeout
content:
application/json:
schema:
$ref: '#/components/schemas/SimpleError'
'410':
description: Gone - model is no longer available (deprecated or removed)
content:
application/json:
schema:
$ref: '#/components/schemas/SimpleError'
'429':
description: Too Many Requests
content:
application/json:
schema:
$ref: '#/components/schemas/GeneralError'
'500':
description: Internal Server Error. Unexpected issue on server side.
content:
text/plain:
schema:
type: string
'503':
description: Service Temporarily Unavailable
content:
text/plain:
schema:
type: string
example: Service Temporarily Unavailable
x-codeSamples:
- lang: JavaScript
source: "import SambaNova from 'sambanova';\n\nconst client = new SambaNova({\n apiKey: process.env['SAMBANOVA_API_KEY'], // This is the default and can be omitted\n});\n\nconst embeddingsResponse = await client.embeddings.create({\n input: ['text to embed number 1', 'text to embed number 2'],\n model: 'E5-Mistral-7B-Instruct',\n});\n\nconsole.log(embeddingsResponse.data);"
- lang: Python
source: "import os\nfrom sambanova import SambaNova\n\nclient = SambaNova(\n api_key=os.environ.get(\"SAMBANOVA_API_KEY\"), # This is the default and can be omitted\n)\nembeddings_response = client.embeddings.create(\n input=[\"text to embed number 1\", \"text to embed number 2\"],\n model=\"E5-Mistral-7B-Instruct\",\n)\nprint(embeddings_response.data)"
components:
schemas:
SimpleError:
title: SimpleError
type: object
description: other kind of simple schema errors
properties:
error:
title: error
type: string
description: error detail.
nullable: true
required:
- error
Usage:
title: Usage
type: object
description: Usage metrics for the completion, embeddings,transcription or translation request
additionalProperties: true
properties:
acceptance_rate:
title: Acceptance Rate
type: number
description: acceptance rate
completion_tokens:
title: Completion Tokens
type: integer
description: number of tokens generated in completion
completion_tokens_after_first_per_sec:
title: Completion Tokens After First Per Sec
type: number
description: completion tokens per second after first token generation
completion_tokens_after_first_per_sec_first_ten:
title: Completion Tokens After First Per Sec First Ten
type: number
description: completion tokens per second after first token generation first ten
completion_tokens_after_first_per_sec_graph:
title: Completion Tokens After First Per Sec Graph
type: number
description: completion tokens per second after first token generation
completion_tokens_per_sec:
title: Completion Tokens Per Sec
type: number
description: completion tokens per second
end_time:
title: End Time
type: number
description: The Unix timestamp (in seconds) of when the generation finished.
is_last_response:
title: Is Last Response
type: boolean
description: whether or not is last response, always true for non streaming response
const: true
prompt_tokens_details:
title: Prompt tokens details
type: object
description: Extra tokens details
additionalProperties: true
properties:
cached_tokens:
title: Cached tokens
description: amount of cached tokens
type: integer
prompt_tokens:
title: Prompt Tokens
type: integer
description: number of tokens used in the prompt sent
start_time:
title: Start Time
type: number
description: The Unix timestamp (in seconds) of when the generation started.
time_to_first_token:
title: Time To First Token
type: number
description: also TTF, time (in seconds) taken to generate the first token
time_to_first_token_graph:
title: Time To First Token Graph
type: number
description: Time (in seconds) to first token, adjusted for graph rendering. May differ slightly from time_to_first_token.
stop_reason:
title: Stop Reason
type: string
description: The reason generation stopped (e.g. "stop", "length"). Mirrors the choice-level finish_reason but reported at the usage level.
nullable: true
completion_tokens_details:
title: Completion Tokens Details
type: object
description: Breakdown of completion token consumption.
additionalProperties: true
properties:
reasoning_tokens:
title: Reasoning Tokens
type: integer
description: Number of tokens consumed by the model's internal reasoning process. Only present on reasoning-capable models.
nullable: true
total_latency:
title: Total Latency
type: number
description: total time (in seconds) taken to generate the full generation
total_tokens:
title: Total Tokens
type: integer
description: prompt tokens + completion tokens
total_tokens_per_sec:
title: Total Tokens Per Sec
type: number
description: tokens per second including prompt and completion
nullable: true
examples:
- completion_tokens: 260
completion_tokens_after_first_per_sec: 422.79282728043336
completion_tokens_after_first_per_sec_first_ten: 423.6108998455803
completion_tokens_after_first_per_sec_graph: 423.6108998455803
completion_tokens_per_sec: 314.53312043711406
completion_tokens_details:
reasoning_tokens: 55
end_time: 1776189309.02061
is_last_response: true
prompt_tokens: 90
prompt_tokens_details:
cached_tokens: 0
start_time: 1776189308.193988
stop_reason: stop
time_to_first_token: 0.21402883529663086
time_to_first_token_graph: 0.2102978229522705
total_latency: 0.8266220092773438
total_tokens: 350
total_tokens_per_sec: 423.40996981919204
- prompt_tokens: 43
total_tokens: 393
EmbeddingsRequest:
title: Embeddings Request
type: object
description: embeddings request object
additionalProperties: true
properties:
model:
title: Model
description: The model ID to use See available [models](https://docs.sambanova.ai/docs/en/models/sambacloud-models)
anyOf:
- type: string
- enum:
- E5-Mistral-7B-Instruct
input:
title: input
description: Input text to embed. to embed multiple inputs in a single request, pass an array of strings. The input must not exceed the max input tokens for the model
oneOf:
- type: string
description: The string that will be turned into an embedding.
- type: array
description: The array of strings that will be turned into an embeddings.
minItems: 1
items:
type: string
required:
- model
- input
example:
input:
- text to embed number 1
- text to embed number 2
model: E5-Mistral-7B-Instruct
EmbeddingsResponse:
title: Embeddings Response
type: object
description: Embeddings response returned by the model
properties:
object:
title: object
type: string
description: The object type, which is always "list".
enum:
- list
model:
type: string
description: The name of the model used to generate the embedding.
usage:
$ref: '#/components/schemas/Usage'
data:
type: array
description: The list of embeddings generated by the model.
items:
$ref: '#/components/schemas/Embedding'
required:
- object
- model
- usage
- data
example:
data:
- index: 0
object: embedding
embedding:
- 0.024864232167601585
- -0.01452154759317636
- 0.008880083449184895
- index: 1
object: embedding
embedding:
- 0.010919672437012196
- 0.0016351072117686272
- 0.008019134402275085
model: E5-Mistral-7B-Instruct
object: list
usage:
prompt_tokens: 716
total_tokens: 716
Embedding:
type: object
title: Embedding
description: Represents an embedding vector returned by embeddings endpoint.
properties:
index:
type: integer
title: index
description: The index of the embedding in the list of embeddings.
object:
type: string
title: object
description: Object type, always embedding.
enum:
- embedding
embedding:
type: array
items:
type: number
title: embedding
description: List of floats containing the embedding vector.
nullable: true
required:
- index
- object
- embedding
GeneralError:
title: GeneralError
type: object
description: other kind of errors
properties:
error:
type: object
properties:
code:
title: code
type: string
description: error code
nullable: true
message:
title: message
type: string
description: error message
param:
title: param
type: string
description: error params
nullable: true
type:
title: type
type: string
description: error type
error_model_output:
title: Error Model Output
type: string
description: Raw model output that could not be parsed. Present on `server_error` responses when the model produced output that failed internal parsing (e.g. a malformed tool call JSON).
nullable: true
request_id:
title: request_id
type: string
description: unique request identifier for debugging
nullable: true
required:
- error
securitySchemes:
api_key:
type: http
description: SambaNova API Key
scheme: bearer
bearerFormat: apiKey
externalDocs:
description: Find out more in the official SambaNova docs
url: https://docs.sambanova.ai/cloud/api-reference/overview