Context Precision

Available

rag.context_precision

Measures how much of the retrieved material is actually relevant to the answer, rewarding relevant chunks that are ranked near the top.

Contract

Field	Value
version	1.0.0
metric_type	pointwise
scorer_contract	per_row
direction	higher_is_better
entrypoint	aip_metrics_rag.answered.context_precision
target_kind	None

Required columns

• input_id
• prompt
• expected_output
• sut_response
• retrieved_context

Accepted schemas

[
  {
    "name": "gdi_text_v1",
    "task_types": [
      "multi_turn_rag",
      "single_turn_rag"
    ]
  }
]

Methodology

1. An LLM judge (Ragas LLMContextPrecisionWithReference) receives the question, the reference answer, and each retrieved chunk.
2. The judge decides, per chunk, whether it was useful for producing the reference answer.
3. Ragas computes the rank-weighted mean average precision over the retrieved order.
4. The score is normalised to 0-1 (a NaN verdict is surfaced as an error).

Score semantics

Scores range 0-1. A high score means relevant chunks are concentrated at the top ranks with little noise; a low score means relevant chunks are buried among irrelevant ones. Higher is better.

Worked example

For retrieved chunks ranked [relevant, irrelevant, relevant], the judge marks them [1, 0, 1]; mean average precision ~ 0.83.

Configuration schema

{
  "properties": {
    "concurrency_limit": {
      "default": 10,
      "title": "Concurrency Limit",
      "type": "integer",
      "x-aip-param-role": "operational"
    },
    "inverted": {
      "default": false,
      "title": "Inverted",
      "type": "boolean",
      "x-aip-param-role": "scoring_metadata"
    },
    "lang": {
      "default": "en",
      "enum": [
        "en",
        "de",
        "fr"
      ],
      "title": "Lang",
      "type": "string"
    },
    "max": {
      "default": 1.0,
      "title": "Max",
      "type": "number",
      "x-aip-param-role": "scoring_metadata"
    },
    "metric_name": {
      "default": "context_precision",
      "title": "Metric Name",
      "type": "string",
      "x-aip-param-role": "scoring_metadata"
    },
    "min": {
      "default": 0.0,
      "title": "Min",
      "type": "number",
      "x-aip-param-role": "scoring_metadata"
    },
    "model": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": "gpt-4o",
      "title": "Model"
    },
    "system_type": {
      "const": "rag",
      "default": "rag",
      "title": "System Type",
      "type": "string",
      "x-aip-param-role": "judge_wiring"
    },
    "weight": {
      "default": 1.0,
      "title": "Weight",
      "type": "number",
      "x-aip-param-role": "scoring_metadata"
    }
  },
  "title": "InitializationConfig",
  "type": "object"
}

Execution

{
  "emits_metric_family": false,
  "function_name": null,
  "max_concurrency": 8,
  "processing_kind": "network",
  "stream_batch_size": null,
  "timeout_seconds": 900
}

Complete manifest

accepts:
- name: gdi_text_v1
  task_types:
  - multi_turn_rag
  - single_turn_rag
config_schema:
  properties:
    concurrency_limit:
      default: 10
      title: Concurrency Limit
      type: integer
      x-aip-param-role: operational
    inverted:
      default: false
      title: Inverted
      type: boolean
      x-aip-param-role: scoring_metadata
    lang:
      default: en
      enum:
      - en
      - de
      - fr
      title: Lang
      type: string
    max:
      default: 1.0
      title: Max
      type: number
      x-aip-param-role: scoring_metadata
    metric_name:
      default: context_precision
      title: Metric Name
      type: string
      x-aip-param-role: scoring_metadata
    min:
      default: 0.0
      title: Min
      type: number
      x-aip-param-role: scoring_metadata
    model:
      anyOf:
      - type: string
      - type: 'null'
      default: gpt-4o
      title: Model
    system_type:
      const: rag
      default: rag
      title: System Type
      type: string
      x-aip-param-role: judge_wiring
    weight:
      default: 1.0
      title: Weight
      type: number
      x-aip-param-role: scoring_metadata
  title: InitializationConfig
  type: object
dependencies: []
description: How much of the retrieved material is actually relevant, with little
  noise?
direction: higher_is_better
display_name: Context Precision
entrypoint: aip_metrics_rag.answered.context_precision
execution:
  emits_metric_family: false
  function_name: null
  max_concurrency: 8
  processing_kind: network
  stream_batch_size: null
  timeout_seconds: 900
kind: metric
manifest_version: '1'
max_prompt_slots: 0
metric_metadata:
  methodology:
  - An LLM judge (Ragas LLMContextPrecisionWithReference) receives the question, the
    reference answer, and each retrieved chunk.
  - The judge decides, per chunk, whether it was useful for producing the reference
    answer.
  - Ragas computes the rank-weighted mean average precision over the retrieved order.
  - The score is normalised to 0-1 (a NaN verdict is surfaced as an error).
  score_semantics: Scores range 0-1. A high score means relevant chunks are concentrated
    at the top ranks with little noise; a low score means relevant chunks are buried
    among irrelevant ones. Higher is better.
  summary: Measures how much of the retrieved material is actually relevant to the
    answer, rewarding relevant chunks that are ranked near the top.
  worked_example: For retrieved chunks ranked [relevant, irrelevant, relevant], the
    judge marks them [1, 0, 1]; mean average precision ~ 0.83.
metric_type: pointwise
name: rag.context_precision
partition_types: []
required_columns:
- input_id
- prompt
- expected_output
- sut_response
- retrieved_context
required_kinds: []
scorer_contract: per_row
target_kind: null
unsupported_trace_shapes: []
version: 1.0.0