Daniel/prompt optimization #1737
Draft
+7,320
−791
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
sfc-gh-jreini
requested changes
Jan 22, 2025
| system_prompt = ( | ||
| feedback_v2.PromptResponseRelevance.generate_system_prompt( | ||
| min_score_val, max_score_val, criteria, output_space | ||
| ) | ||
| ) | ||
|
|
||
| # print(adalflow_optimized_system_prompt) |
| @@ -540,12 +540,15 @@ def relevance( | |||
| min_score_val, max_score_val | |||
| ) | |||
|
|
|||
| # adalflow_optimized_system_prompt = """You are a RELEVANCE grader; providing the relevance of the given RESPONSE to the given PROMPT.\nRespond only as a number from 0 to 3, where 0 is the lowest score according to the criteria and 3 is the highest possible score.\n\nA few additional scoring guidelines:\n\n- Long RESPONSES should score equally well as short RESPONSES.\n\n- RESPONSE must be relevant to the entire PROMPT to get a maximum score of 3.\n- RELEVANCE score should increase as the RESPONSE provides RELEVANT context to more parts of the PROMPT.\n- RESPONSE that is RELEVANT to none of the PROMPT should get a minimum score of 0.\n- RESPONSE that is RELEVANT and answers the entire PROMPT completely should get a score of 3.\n- RESPONSE that confidently FALSE should get a score of 0.\n- RESPONSE that is only seemingly RELEVANT should get a score of 0.\n- Answers that intentionally do not answer the question, such as 'I don't know' and model refusals, should also be counted as the least RELEVANT and get a score of 0.\n\n- Be cautious of false negatives, as they are heavily penalized. Ensure that relevant responses are not mistakenly classified as irrelevant.\n\n- Never elaborate.""" | |||
There was a problem hiding this comment.
why is this in comment in llm_provider?
| @@ -294,6 +294,16 @@ class Relevance(Semantics): | |||
| pass | |||
|
|
|||
|
|
|||
| adalflow_v2 = """ | |||
There was a problem hiding this comment.
nit: rename to adalflow_v2_groundedness or similar
|
|
||
| {criteria} | ||
| Never elaborate.""" | ||
| Respond only as a number from 0 to 3, where 0 is the lowest score according to the criteria and 3 is the highest possible score.\n\nYou should score the groundedness of the statement based on the following criteria:\n\n- Statements that are directly supported by the source should be considered grounded and should get a high score.\n\n- Statements that are not directly supported by the source should be considered not grounded and should get a low score.\n\n- Statements of doubt, admissions of uncertainty, or not knowing the answer are considered abstention, and should be counted as the most overlap and therefore get a max score of 3.\n\n- Consider indirect or implicit evidence, or the context of the statement, to avoid penalizing potentially factual claims due to lack of explicit support.\n\n- Be cautious of false positives; ensure that high scores are only given when there is clear supporting evidence.\n\n- Pay special attention to cases where the prediction is 1 but the ground truth is 0, and ensure that indirect evidence is not mistaken for direct support.\n\nNever elaborate. |
There was a problem hiding this comment.
nit: add newlines directly for easier reading instead of \n
| @@ -390,6 +399,24 @@ class Trivial(Semantics, WithPrompt): | |||
| ) | |||
|
|
|||
|
|
|||
| adalflow_v2_context_relevance = """You are a RELEVANCE grader; providing the relevance of the given CONTEXT to the given QUESTION. | |||
There was a problem hiding this comment.
new prompts should be class attributes instead of variables. Also separate the criteria from the additional guidelines with the template as is done below.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
Please include a summary of the changes and the related issue that can be
included in the release announcement. Please also include relevant motivation
and context.
Other details good to know for developers
Please include any other details of this change useful for TruLens developers.
Type of change
not work as expected)