From c93243cc0429c9740294fd6f2304c0ac8b8d2245 Mon Sep 17 00:00:00 2001 From: Abhishek Ranjan Date: Mon, 19 May 2025 22:48:24 +0530 Subject: [PATCH] fix: minor typo in context_precision.md for `Context Precision without reference` definition, i.e LLMContextPrecisionWithoutReference metric can be used when you have both retrieved contexts and also reference contexts associated with a user_input. Here, it should be reference `answer` instead of reference `contexts` as per my understanding Similarly, for `Context Precision with reference definition` i.e LLMContextPrecisionWithReference metric is can be used when you have both retrieved contexts and also reference answer associated with a user_input. here, reference answer should be replaced with reference context --- .../concepts/metrics/available_metrics/context_precision.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/docs/concepts/metrics/available_metrics/context_precision.md b/docs/concepts/metrics/available_metrics/context_precision.md index 449dadcea..0cccddd95 100644 --- a/docs/concepts/metrics/available_metrics/context_precision.md +++ b/docs/concepts/metrics/available_metrics/context_precision.md @@ -17,7 +17,7 @@ The following metrics uses LLM to identify if a retrieved context is relevant or ### Context Precision without reference -`LLMContextPrecisionWithoutReference` metric can be used when you have both retrieved contexts and also reference contexts associated with a `user_input`. To estimate if a retrieved contexts is relevant or not this method uses the LLM to compare each of the retrieved context or chunk present in `retrieved_contexts` with `response`. +`LLMContextPrecisionWithoutReference` metric can be used when you have both retrieved contexts and also reference answer associated with a `user_input`. To estimate if a retrieved contexts is relevant or not this method uses the LLM to compare each of the retrieved context or chunk present in `retrieved_contexts` with `response`. #### Example @@ -43,7 +43,7 @@ Output ### Context Precision with reference -`LLMContextPrecisionWithReference` metric is can be used when you have both retrieved contexts and also reference answer associated with a `user_input`. To estimate if a retrieved contexts is relevant or not this method uses the LLM to compare each of the retrieved context or chunk present in `retrieved_contexts` with `reference`. +`LLMContextPrecisionWithReference` metric is can be used when you have both retrieved contexts and also reference context associated with a `user_input`. To estimate if a retrieved contexts is relevant or not this method uses the LLM to compare each of the retrieved context or chunk present in `retrieved_contexts` with `reference`. #### Example @@ -92,4 +92,4 @@ await context_precision.single_turn_ascore(sample) Output ``` 0.9999999999 -``` \ No newline at end of file +```