Llama API | Inference › Embeddings

Inference

inference

Methods

Chat Completion -> { completion_message, logprobs } | { event }

post/alpha/inference/chat-completion

Completion ->

CompletionResponse

| { delta, logprobs, stop_reason }

post/alpha/inference/completion

Embeddings ->

EmbeddingsResponse

post/alpha/inference/embeddings

Parameters

X-LlamaStack-Client-Version: string

Optional

X-LlamaStack-Provider-Data: string

Optional

Response fields

EmbeddingsResponse

Request example

curl http://any-hosted-llama-stack.com/alpha/inference/embeddings \
    -H 'Content-Type: application/json' \
    -d '{
      "contents": [
        "string"
      ],
      "model_id": "model_id"
    }'

200Example

{
  "embeddings": [
    [
      0
    ]
  ]
}

Domain types

CompletionResponse = { content, stop_reason, logprobs }

EmbeddingsResponse = { embeddings }

TokenLogProbs = { logprobs_by_token }