fix: spelling errors in prompt templates (#5571)

* fix: minor spelling error

* fix more

* fix formatting

* fix more

packages/phoenix-evals/src/phoenix/evals/default_templates.py

@@ -535,7 +535,7 @@
 -----------
 Your response should be an explanation and then a single word LABEL: either "correct" or
 "incorrect".
-You must assume that the db exists and that columns are appropiately named.
+You must assume that the db exists and that columns are appropriately named.
 You must take into account the response as additional information to determine the correctness.
 
 - "correct" indicates that the sql query correctly solves the instruction.
@@ -660,9 +660,9 @@
   [END DATA]
 
   Examine the conversation and determine whether or not the user got frustrated from the experience.
-  Frustration can range from midly frustrated to extremely frustrated. If the user seemed frustrated
-  at the beginning of the conversation but seemed satisfied at the end, they should not be deemed
-  as frustrated. Focus on how the user left the conversation.
+  Frustration can range from mildly frustrated to extremely frustrated. If the user seemed
+  frustrated at the beginning of the conversation but seemed satisfied at the end, they should not
+  be deemed as frustrated. Focus on how the user left the conversation.
 
   Your response must be a single word, either "frustrated" or "ok", and should not
   contain any text or characters aside from that word. "frustrated" means the user was left
@@ -681,21 +681,21 @@
   [END DATA]
 
   Examine the conversation and determine whether or not the user got frustrated from the experience.
-  Frustration can range from midly frustrated to extremely frustrated. If the user seemed frustrated
-  at the beginning of the conversation but seemed satisfied at the end, they should not be deemed
-  as frustrated. Focus on how the user left the conversation.
+  Frustration can range from mildly frustrated to extremely frustrated. If the user seemed
+  frustrated at the beginning of the conversation but seemed satisfied at the end, they should not
+  be deemed as frustrated. Focus on how the user left the conversation.
 
   You are going to respond with an EXPLANATION and LABEL.
   Please read the text carefully, then write out in a step by step manner an
-  EXPLANATION as to why you think the user is frusterated.
+  EXPLANATION as to why you think the user is frustrated.
   Your LABEL response must be a single word, either "frustrated" or "ok", and should not
   contain any text or characters aside from that word. "frustrated" means the user was left
   frustrated as a result of the conversation. "ok" means that the user did not get frustrated
   from the conversation.
 
 Example response:
 ************
-EXPLANATION: An explanation of your reasoning for why the user is frusterated
+EXPLANATION: An explanation of your reasoning for why the user is frustrated
 LABEL: "frustrated" or "ok"
 ************
 """

src/phoenix/experiments/evaluators/llm_evaluators.py

@@ -232,7 +232,7 @@ class RelevanceEvaluator(LLMEvaluator):
         "query. First, explain step-by-step why you think the text is or is not relevant. "
         "Then provide a single word label; 'true' if the text is relevant or 'false' if the text "
         "is not relevant. "
-        "Here is an example template for your reponse:\n\n"
+        "Here is an example template for your response:\n\n"
         "CRITERIA: the response is 'relevant' to the query\n"
         "QUERY: *text that contains a query*\n"
         "RESPONSE: *a response that may or may not be relevant to the query*\n"
@@ -367,7 +367,7 @@ class LLMRelationalEvaluator(LLMEvaluator):
         "First, explain step-by-step why you think the response '{relation}' the reference. "
         "Then provide a single word label; 'true' if the response '{relation}' the reference or "
         "'false' if the text is not '{relation}' to the reference. "
-        "Here is an example template for your reponse:\n\n"
+        "Here is an example template for your response:\n\n"
         "CRITERIA: the response '{relation}' the reference\n"
         "REFERENCE: *text that contains a reference*\n"
         "RESPONSE: *a response that may or may not be '{relation}' to the reference*\n"