Skip to main content

​
LogSpanEmbeddingsContent

Content type for embedding generation spans.

​
Overview

LogSpanEmbeddingsContent captures embedding API calls. It is wrapped in a LogSpanContent union via the actual_instance pattern. 
from adaline_api.models.log_span_embeddings_content import LogSpanEmbeddingsContent

​
Fields

​
type
str
required
Must be "Embeddings".
​
input
str
required
The input payload as a JSON string. Must be valid, parseable JSON (the result of json.dumps()).
​
output
str
required
The output payload as a JSON string. Must be valid, parseable JSON (the result of json.dumps()).

​
Construction Pattern

All span content is wrapped in LogSpanContent using the actual_instance parameter: 
from adaline_api.models.log_span_content import LogSpanContent
from adaline_api.models.log_span_embeddings_content import LogSpanEmbeddingsContent

content = LogSpanContent(
    actual_instance=LogSpanEmbeddingsContent(
        type="Embeddings",
        input=json.dumps(request_body),
        output=json.dumps(response_body),
    )
)

​
Example

import json
from adaline_api.models.log_span_content import LogSpanContent
from adaline_api.models.log_span_embeddings_content import LogSpanEmbeddingsContent

embed_input = {"model": "text-embedding-3-large", "input": ["search query"]}
embed_output = {"data": [{"embedding": [0.012, -0.003], "index": 0}], "model": "text-embedding-3-large"}

span.update({
    "status": "success",
    "content": LogSpanContent(
        actual_instance=LogSpanEmbeddingsContent(
            type="Embeddings",
            input=json.dumps(embed_input),
            output=json.dumps(embed_output),
        )
    ),
})