Skip to main content

​
LogSpanRetrievalContent

Content type for RAG and vector database query spans.

​
Overview

LogSpanRetrievalContent captures retrieval operations such as vector similarity searches and document lookups. It is wrapped in a LogSpanContent union via the actual_instance pattern. 
from adaline_api.models.log_span_retrieval_content import LogSpanRetrievalContent

​
Fields

​
type
str
required
Must be "Retrieval".
​
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_retrieval_content import LogSpanRetrievalContent

content = LogSpanContent(
    actual_instance=LogSpanRetrievalContent(
        type="Retrieval",
        input=json.dumps({"query": "How does auth work?", "top_k": 5}),
        output=json.dumps({"documents": [{"id": "doc1", "score": 0.95}]}),
    )
)

​
Example

import json
from adaline_api.models.log_span_content import LogSpanContent
from adaline_api.models.log_span_retrieval_content import LogSpanRetrievalContent

retrieval_input = {"query": "refund policy", "top_k": 3, "namespace": "support"}
retrieval_output = {
    "documents": [
        {"id": "doc_42", "score": 0.97, "text": "Refunds are processed within 5 days."},
        {"id": "doc_18", "score": 0.91, "text": "Contact support for refund requests."},
    ]
}

span.update({
    "status": "success",
    "content": LogSpanContent(
        actual_instance=LogSpanRetrievalContent(
            type="Retrieval",
            input=json.dumps(retrieval_input),
            output=json.dumps(retrieval_output),
        )
    ),
})