/*
* server
*
* ## Real-time data The only real-time path to get tracing data is to ingest via OpenTelemetry (`POST /api/public/otel/v1/traces`) and retrieve via Observations API v2 (`GET /api/public/v2/observations`) and Metrics API v2 (`GET /api/public/v2/metrics`). Other public API write and read endpoints can delay data by about 10 minutes. Direct OpenTelemetry exporters must send the `x-langfuse-ingestion-version: 4` header; current Python and JS SDKs already do. See the [Public API docs](https://langfuse.com/docs/api-and-data-platform/features/public-api) and [real-time ingestion](https://langfuse.com/integrations/native/opentelemetry.md#real-time-ingestion). ## Authentication Authenticate with the API using [Basic Auth](https://en.wikipedia.org/wiki/Basic_access_authentication), get API keys in the project settings: - username: Langfuse Public Key - password: Langfuse Secret Key ## Exports - OpenAPI spec: https://cloud.langfuse.com/generated/api/openapi.yml - Self-hosted deployments: interactive API reference at `/api/docs` and OpenAPI spec at `/api/openapi.yaml`
*
* The version of the OpenAPI document:
*
* Generated by: https://openapi-generator.tech
*/
use crate::models;
use serde::{Deserialize, Serialize};
/// PromptVariableMappingInput : Connects one prompt variable to data from an observation or experiment. Manual mappings are used for `llm_as_judge` evaluators. `code` evaluators use a fixed runtime mapping managed by Langfuse. How to build a valid mapping list: 1. Create the evaluator or fetch it with `GET /evaluators/{id}`. 2. Read the evaluator `variables` array. 3. Add exactly one mapping object for each variable in that array. 4. Use the variable name exactly as returned, without braces such as `{{` or `}}`. 5. Choose the source field that should populate the variable. `jsonPath` is optional. Use it only when the selected source is a JSON object and you want to extract one nested field before inserting it into the evaluator prompt. Invalid, missing, or duplicate mappings return a validation error. Malformed JSONPath expressions are also rejected.
#[derive(Clone, Default, Debug, PartialEq, Serialize, Deserialize, bon::Builder)]
pub struct PromptVariableMappingInput {
/// Prompt variable name without braces. Example: for the prompt `Judge {{input}} against {{output}}`, use `input` and `output`.
#[serde(rename = "variable")]
pub variable: String,
#[serde(rename = "source")]
pub source: models::PromptVariableMappingSource,
/// Optional JSONPath selector applied to the selected source before it is passed to the evaluator prompt. Requirements: - Must start with `$` - Must be a syntactically valid JSONPath expression - Most useful with `source=metadata`
#[serde(
rename = "jsonPath",
default,
with = "::serde_with::rust::double_option",
skip_serializing_if = "Option::is_none"
)]
pub json_path: Option<Option<String>>,
}
impl PromptVariableMappingInput {
/// Connects one prompt variable to data from an observation or experiment. Manual mappings are used for `llm_as_judge` evaluators. `code` evaluators use a fixed runtime mapping managed by Langfuse. How to build a valid mapping list: 1. Create the evaluator or fetch it with `GET /evaluators/{id}`. 2. Read the evaluator `variables` array. 3. Add exactly one mapping object for each variable in that array. 4. Use the variable name exactly as returned, without braces such as `{{` or `}}`. 5. Choose the source field that should populate the variable. `jsonPath` is optional. Use it only when the selected source is a JSON object and you want to extract one nested field before inserting it into the evaluator prompt. Invalid, missing, or duplicate mappings return a validation error. Malformed JSONPath expressions are also rejected.
pub fn new(
variable: String,
source: models::PromptVariableMappingSource,
) -> PromptVariableMappingInput {
PromptVariableMappingInput {
variable,
source,
json_path: None,
}
}
}