Update the Judge LLM settings in the examples to avoid retries (#204)

Closes #202 

## By Submitting this PR I confirm:
- I am familiar with the [Contributing Guidelines](https://github.com/NVIDIA/AIQToolkit/blob/develop/docs/source/advanced/contributing.md).
- We require that all contributors "sign-off" on their commits. This certifies that the contribution is your original work, or you have rights to submit it under the same license, or a compatible license.
  - Any contribution which contains commits that are not Signed-Off will not be accepted.
- When the PR is ready for review, new or existing tests cover these changes.
- When the PR is ready for review, the documentation is up to date with these changes.

Authors:
  - Anuradha Karuppiah (https://github.com/AnuradhaKaruppiah)

Approvers:
  - Eric Evans II (https://github.com/ericevans-nv)

URL: #204

Author: AnuradhaKaruppiah

docs/source/guides/evaluate.md

@@ -112,11 +112,19 @@ These metrics use a judge LLM for evaluating the generated output and retrieved
 llms:
   nim_rag_eval_llm:
     _type: nim
-    model_name: meta/llama-3.3-70b-instruct
-    temperature: 0.0000001
-    top_p: 0.0001
-    max_tokens: 2
+    model_name: meta/llama-3.1-70b-instruct
+    max_tokens: 8
 ```
+For these metrics, it is recommended to use 8 tokens for the judge LLM.
+
+Evaluation is dependent on the judge LLM's ability to accurately evaluate the generated output and retrieved context. This is the leadership board for the judge LLM:
+```
+    1)- mistralai/mixtral-8x22b-instruct-v0.1
+    2)- mistralai/mixtral-8x7b-instruct-v0.1
+    3)- meta/llama-3.1-70b-instruct
+    4)- meta/llama-3.3-70b-instruct
+```
+For a complete list of up-to-date judge LLMs, refer to the [RAGAS NV metrics leadership board](https://github.com/explodinggradients/ragas/blob/main/src/ragas/metrics/_nv_metrics.py)
 
 ### Trajectory Evaluator
 This evaluator uses the intermediate steps generated by the workflow to evaluate the workflow trajectory. The evaluator configuration includes the evaluator type and any additional parameters required by the evaluator.

examples/documentation_guides/workflows/text_file_ingest/src/text_file_ingest/configs/config.yml

@@ -35,9 +35,7 @@ llms:
   nim_rag_eval_llm:
     _type: nim
     model_name: meta/llama-3.1-70b-instruct
-    temperature: 0.0000001
-    top_p: 0.0001
-    max_tokens: 2
+    max_tokens: 8
   nim_rag_eval_large_llm:
     _type: nim
     model_name: meta/llama-3.1-70b-instruct

examples/email_phishing_analyzer/configs/config-llama-3.1-8b-instruct.yml

@@ -51,9 +51,7 @@ llms:
   nim_rag_eval_llm:
     _type: nim
     model_name: meta/llama-3.1-70b-instruct
-    temperature: 0.0000001
-    top_p: 0.0001
-    max_tokens: 2
+    max_tokens: 8
   nim_trajectory_eval_llm:
     _type: nim
     model_name: meta/llama-3.1-70b-instruct

examples/email_phishing_analyzer/configs/config-llama-3.3-70b-instruct.yml

@@ -51,9 +51,7 @@ llms:
   nim_rag_eval_llm:
     _type: nim
     model_name: meta/llama-3.1-70b-instruct
-    temperature: 0.0000001
-    top_p: 0.0001
-    max_tokens: 2
+    max_tokens: 8
   nim_trajectory_eval_llm:
     _type: nim
     model_name: meta/llama-3.1-70b-instruct

examples/email_phishing_analyzer/configs/config-mixtral-8x22b-instruct-v0.1.yml

@@ -51,9 +51,7 @@ llms:
   nim_rag_eval_llm:
     _type: nim
     model_name: meta/llama-3.1-70b-instruct
-    temperature: 0.0000001
-    top_p: 0.0001
-    max_tokens: 2
+    max_tokens: 8
   nim_trajectory_eval_llm:
     _type: nim
     model_name: meta/llama-3.1-70b-instruct

examples/email_phishing_analyzer/configs/config-phi-3-medium-4k-instruct.yml

@@ -50,9 +50,7 @@ llms:
   nim_rag_eval_llm:
     _type: nim
     model_name: meta/llama-3.1-70b-instruct
-    temperature: 0.0000001
-    top_p: 0.0001
-    max_tokens: 2
+    max_tokens: 8
   nim_trajectory_eval_llm:
     _type: nim
     model_name: meta/llama-3.1-70b-instruct

examples/email_phishing_analyzer/configs/config-phi-3-mini-4k-instruct.yml

@@ -51,9 +51,7 @@ llms:
   nim_rag_eval_llm:
     _type: nim
     model_name: meta/llama-3.1-70b-instruct
-    temperature: 0.0000001
-    top_p: 0.0001
-    max_tokens: 2
+    max_tokens: 8
   nim_trajectory_eval_llm:
     _type: nim
     model_name: meta/llama-3.1-70b-instruct

examples/email_phishing_analyzer/configs/config-reasoning.yml

@@ -60,9 +60,7 @@ llms:
   nim_rag_eval_llm:
     _type: nim
     model_name: meta/llama-3.1-70b-instruct
-    temperature: 0.0000001
-    top_p: 0.0001
-    max_tokens: 2
+    max_tokens: 8
   r1_model:
     _type: nim
     model_name: deepseek-ai/deepseek-r1

examples/email_phishing_analyzer/configs/config.yml

@@ -51,9 +51,7 @@ llms:
   nim_rag_eval_llm:
     _type: nim
     model_name: meta/llama-3.1-70b-instruct
-    temperature: 0.0000001
-    top_p: 0.0001
-    max_tokens: 2
+    max_tokens: 8
   nim_trajectory_eval_llm:
     _type: nim
     model_name: meta/llama-3.1-70b-instruct

examples/simple/src/aiq_simple/configs/eval_config.yml

@@ -34,9 +34,7 @@ llms:
   nim_rag_eval_llm:
     _type: nim
     model_name: meta/llama-3.1-70b-instruct
-    temperature: 0.0000001
-    top_p: 0.0001
-    max_tokens: 6
+    max_tokens: 8
   nim_trajectory_eval_llm:
     _type: nim
     model_name: meta/llama-3.1-70b-instruct

examples/simple/src/aiq_simple/configs/eval_upload_config.yml

@@ -38,10 +38,8 @@ llms:
     temperature: 0.0
   nim_rag_eval_llm:
     _type: nim
-    model_name: meta/llama-3.3-70b-instruct
-    temperature: 0.0000001
-    top_p: 0.0001
-    max_tokens: 2
+    model_name: meta/llama-3.1-70b-instruct
+    max_tokens: 8
   nim_trajectory_eval_llm:
     _type: nim
     model_name: meta/llama-3.1-70b-instruct