feat(evals): add an output_parser to llm_generate #1736
Merged
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
mikeldking
force-pushed
the
1713-structured-output-parsing
branch
from
5166f3d
to
0007eb3
Compare
mikeldking
force-pushed
the
1713-structured-output-parsing
branch
from
2152048
to
22bf6b7
Compare
axiomofjoy
approved these changes
Nov 13, 2023
| def llm_generate( | ||
| dataframe: pd.DataFrame, | ||
| template: Union[PromptTemplate, str], | ||
| model: BaseEvalModel, | ||
| system_instruction: Optional[str] = None, | ||
| verbose: bool = False, | ||
| ) -> List[str]: | ||
| output_parser: Optional[Callable[[str], Dict[str, Any]]] = None, |
There was a problem hiding this comment.
Suggested change
| output_parser: Optional[Callable[[str], Dict[str, Any]]] = None, | |
| output_parser: Optional[Callable[[str], Any]] = None, |
Seems like the user might want to write all sorts of kinds of parsers.
There was a problem hiding this comment.
@axiomofjoy but we need to know what column to map it to - this at least forces you to declare the column. Or are you thinking of something different?
mikeldking
added a commit
that referenced
this pull request
Nov 14, 2023
* feat(evals): add an output_parser param for structured data extraction * remove brittle test
mikeldking
added a commit
that referenced
this pull request
Nov 14, 2023
* Add explanation template * Spike out explanations * Ruff 🐶 * Use tailored explanation prompt * Add explanation templates for all evals * Wire up prompt template objects * Update models to use new template object * Ruff 🐶 * Resolve type and linter issues * Fix more typing issues * Address first round of feedback * Extract `ClassificationTemplate` ABC * Label extraction belongs to the "template" object * Add logging for unparseable labels * Patch in openai key environment variable for tests * Refactor to address feedback * Evaluators should use PromptTemplates * Pair with Mikyo * Fix for CI * `PROMPT_TEMPLATE_STR` -> `PROMPT_TEMPLATE` * Print prompt if verbose * Add __repr__ to `PromptTemplate` * fix relevance notebook * docs: update evals * Normalize prompt templates in llm_classify * Ruff 🐶 * feat(evals): add an output_parser to llm_generate (#1736) * feat(evals): add an output_parser param for structured data extraction * remove brittle test * docs(evals): document llm_generate with output parser (#1741) --------- Co-authored-by: Mikyo King <mikyo@arize.com>
mikeldking
added a commit
that referenced
this pull request
Nov 15, 2023
* Add explanation template * Spike out explanations * Ruff 🐶 * Use tailored explanation prompt * Add explanation templates for all evals * Wire up prompt template objects * Update models to use new template object * Ruff 🐶 * Resolve type and linter issues * Fix more typing issues * Address first round of feedback * Extract `ClassificationTemplate` ABC * Label extraction belongs to the "template" object * Add logging for unparseable labels * Patch in openai key environment variable for tests * Refactor to address feedback * Evaluators should use PromptTemplates * Pair with Mikyo * Fix for CI * `PROMPT_TEMPLATE_STR` -> `PROMPT_TEMPLATE` * Print prompt if verbose * Add __repr__ to `PromptTemplate` * fix relevance notebook * docs: update evals * Normalize prompt templates in llm_classify * Ruff 🐶 * feat(evals): add an output_parser to llm_generate (#1736) * feat(evals): add an output_parser param for structured data extraction * remove brittle test * docs(evals): document llm_generate with output parser (#1741) --------- Co-authored-by: Mikyo King <mikyo@arize.com>
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.
resolves #1713
In more custom cases, there's a need to parse the output of llm_generate - e.x. trying to extract two labels at once. This also supports providing explanations as part of JSON output if needed. Also GPT-4-Turbo has JSON mode so this helps with that as well.
NB: this is a breaking change but it's under experimental so treating it as a feature.