GET

/v1/schemas/ollama/embeddings/api/embed

Accept:

kind inputactivity embeddingshash 68dbc8ba…extracted Nov 10, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `d8e08be41dd858c933c32bef5ee8d0c5faf7d7462069a49b368731cfbceaab03` { "fetchedAt": 1794288644, "extractorVersion": "2", "verifiedAt": null }

Request body

6 properties · 2 required · 1 $defs

property	type	description	constraints
model*	string	Model name
input*	string \| string[]	Text or array of texts to generate embeddings for
truncate	boolean	If true, truncate inputs that exceed the context window. If false, returns an error.	default: true
dimensions	integer	Number of dimensions to generate embeddings for
keep_alive	string	Model keep-alive duration
options	ModelOptions	Runtime options that control text generation

Types

1 $defs

ModelOptionsobject

Runtime options that control text generation

seed	integer	Random seed used for reproducible outputs
temperature	number	Controls randomness in generation (higher = more random)	format: float
top_k	integer	Limits next token selection to the K most likely
top_p	number	Cumulative probability threshold for nucleus sampling	format: float
min_p	number	Minimum probability threshold for token selection	format: float
stop	string \| string[]	Stop sequences that will halt generation
num_ctx	integer	Context length size (number of tokens)
num_predict	integer	Maximum number of tokens to generate

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"ollama","endpointId":"api/embed","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}