Automate validation of pipeline configs #132
There are no files selected for viewing
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
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
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -12,3 +12,4 @@ pytest-asyncio | |
| pytest-cov | ||
| pytest-html | ||
| tox>=4.4.2,<5 | ||
| jsonschema | ||
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,45 @@ | ||
| #!/usr/bin/env python | ||
|
|
||
| # Standard | ||
| import glob | ||
| import json | ||
| import sys | ||
|
|
||
| # Third Party | ||
| from jsonschema import validate | ||
| import jsonschema | ||
| import yaml | ||
|
|
||
|
|
||
| def validate_yaml_file(yaml_file, schema): | ||
| with open(yaml_file, "r") as file: | ||
| pipeline = yaml.safe_load(file) | ||
|
|
||
| try: | ||
| validate(instance=pipeline, schema=schema) | ||
| print(f"Validation successful for {yaml_file}.") | ||
| except jsonschema.exceptions.ValidationError as err: | ||
| print(f"Validation failed for {yaml_file}:", err) | ||
| return False | ||
| return True | ||
|
|
||
|
|
||
| def main(): | ||
| schema_path = "src/instructlab/sdg/pipelines/schema/v1.json" | ||
| with open(schema_path, "r") as file: | ||
| schema = json.load(file) | ||
|
|
||
| yaml_files = glob.glob("src/instructlab/sdg/pipelines/**/*.yaml", recursive=True) | ||
|
There was a problem hiding this comment. And loading these from a command-line argument? Then it can be a tool that can be used to validate custom pipeline configs using the installed There was a problem hiding this comment. Yeah, that sounds good. We could even leave this as the default when you don't pass an argument |
||
| all_valid = True | ||
| for yaml_file in yaml_files: | ||
| print("=======================================================") | ||
| print("=== Validating", yaml_file) | ||
| print("=======================================================") | ||
| if not validate_yaml_file(yaml_file, schema): | ||
| all_valid = False | ||
|
|
||
| return 1 if not all_valid else 0 | ||
|
|
||
|
|
||
| if __name__ == "__main__": | ||
| sys.exit(main()) | ||
Empty file.
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,260 @@ | ||
| { | ||
| "type": "object", | ||
| "additionalProperties": false, | ||
| "required": ["version", "blocks"], | ||
| "properties": { | ||
| "version": { | ||
| "type": "string" | ||
| }, | ||
| "blocks": { | ||
| "type": "array", | ||
| "additionalProperties": false, | ||
| "items": { | ||
| "type": "object", | ||
| "additionalProperties": false, | ||
| "required": ["name", "type", "config"], | ||
| "properties": { | ||
| "name": { | ||
| "type": "string" | ||
| }, | ||
| "type": { | ||
| "type": "string" | ||
| }, | ||
| "drop_duplicates": { | ||
| "type": "array", | ||
| "items": { | ||
| "type": "string" | ||
| } | ||
| }, | ||
| "drop_columns": { | ||
| "type": "array", | ||
| "items": { | ||
| "type": "string" | ||
| } | ||
| }, | ||
| "gen_kwargs": { | ||
| "type": "object", | ||
| "properties": { | ||
markmc marked this conversation as resolved.
Show resolved
Hide resolved
|
||
| "model": { | ||
| "type": "string" | ||
| }, | ||
| "max_tokens": { | ||
| "type": "number" | ||
| }, | ||
| "temperature": { | ||
| "type": "number" | ||
| }, | ||
| "n": { | ||
| "type": "number" | ||
| }, | ||
| "extra_body": { | ||
| "type": "object" | ||
| } | ||
| } | ||
| }, | ||
| "config": { | ||
| "anyOf": [ | ||
| { | ||
| "type": "object", | ||
| "description": "ImportBlock", | ||
| "required": ["path"], | ||
| "additionalProperties": false, | ||
| "properties": { | ||
| "path": { | ||
| "type": "string" | ||
| } | ||
| } | ||
| }, | ||
| { | ||
| "type": "object", | ||
| "description": "FilterByValueBlock", | ||
| "required": ["filter_column", "filter_value", "operation"], | ||
| "additionalProperties": false, | ||
| "properties": { | ||
| "convert_dtype": { | ||
| "type": "string", | ||
| "enum": ["float", "int", "bool"] | ||
| }, | ||
| "filter_column": { | ||
| "type": "string" | ||
| }, | ||
| "filter_value": { | ||
| "oneOf": [ | ||
| { | ||
| "type": "string" | ||
| }, | ||
| { | ||
| "type": "number" | ||
| }, | ||
| { | ||
| "type": "array", | ||
| "items": { | ||
| "oneOf": [ | ||
| { | ||
| "type": "string" | ||
| }, | ||
| { | ||
| "type": "number" | ||
| } | ||
| ] | ||
| } | ||
| } | ||
| ] | ||
| }, | ||
| "operation": { | ||
| "type": "string", | ||
| "enum": ["eq", "ne", "gt", "ge", "lt", "le", "contains"] | ||
| } | ||
| } | ||
| }, | ||
| { | ||
| "type": "object", | ||
| "description": "LLMBlock", | ||
markmc marked this conversation as resolved.
Show resolved
Hide resolved
|
||
| "required": ["config_path", "output_cols"], | ||
| "additionalProperties": false, | ||
| "properties": { | ||
| "config_path": { | ||
| "type": "string" | ||
| }, | ||
| "output_cols": { | ||
| "type": "array", | ||
| "items": { | ||
| "type": "string" | ||
| } | ||
| }, | ||
| "parser_kwargs": { | ||
| "type": "object", | ||
| "properties": { | ||
| "parser_name": { | ||
| "type": "string" | ||
| }, | ||
| "parsing_pattern": { | ||
| "type": "string" | ||
| }, | ||
| "parser_cleanup_tags": { | ||
| "type": "array", | ||
| "items": { | ||
| "type": "string" | ||
| } | ||
| } | ||
| } | ||
| }, | ||
| "batch_kwargs": { | ||
| "type": "object", | ||
| "properties": { | ||
| "num_samples": { | ||
| "type": "number" | ||
| } | ||
| } | ||
| } | ||
| } | ||
| }, | ||
| { | ||
| "type": "object", | ||
| "description": "ConditionalLLMBlock", | ||
| "required": ["config_paths", "output_cols", "selector_column_name"], | ||
| "additionalProperties": false, | ||
| "properties": { | ||
| "config_paths": { | ||
| "type": "array", | ||
| "items": { | ||
| "type": "string" | ||
| } | ||
| }, | ||
| "output_cols": { | ||
| "type": "array", | ||
| "items": { | ||
| "type": "string" | ||
| } | ||
| }, | ||
| "selector_column_name": { | ||
| "type": "string" | ||
| }, | ||
| "parser_kwargs": { | ||
| "type": "object", | ||
| "properties": { | ||
| "parser_name": { | ||
| "type": "string" | ||
| }, | ||
| "parsing_pattern": { | ||
| "type": "string" | ||
| }, | ||
| "parser_cleanup_tags": { | ||
| "type": "array", | ||
| "items": { | ||
| "type": "string" | ||
| } | ||
| } | ||
| } | ||
| }, | ||
| "batch_kwargs": { | ||
| "type": "object", | ||
| "properties": { | ||
| "num_samples": { | ||
| "type": "number" | ||
| } | ||
| } | ||
| } | ||
| } | ||
| }, | ||
| { | ||
| "type:": "object", | ||
| "description": "SamplePopulatorBlock", | ||
| "additionalProperties": false, | ||
| "required": ["config_paths", "column_name"], | ||
| "properties": { | ||
| "config_paths": { | ||
| "type": "array", | ||
| "items": { | ||
| "type": "string" | ||
| } | ||
| }, | ||
| "column_name": { | ||
| "type": "string" | ||
| }, | ||
| "post_fix": { | ||
| "type": "string" | ||
| } | ||
| } | ||
| }, | ||
| { | ||
| "type:": "object", | ||
| "description": "SelectorBlock", | ||
| "additionalProperties": false, | ||
| "required": ["choice_map", "choice_col", "output_col"], | ||
| "properties": { | ||
| "choice_map": { | ||
| "type": "object" | ||
| }, | ||
| "choice_col": { | ||
| "type": "string" | ||
| }, | ||
| "output_col": { | ||
| "type": "string" | ||
| } | ||
| } | ||
| }, | ||
| { | ||
| "type:": "object", | ||
| "description": "CombineColumnsBlock", | ||
| "additionalProperties": false, | ||
| "required": ["columns", "output_col"], | ||
| "properties": { | ||
| "output_col": { | ||
| "type": "string" | ||
| }, | ||
| "columns": { | ||
| "type": "array", | ||
| "items": { | ||
| "type": "string" | ||
| } | ||
| } | ||
| } | ||
| } | ||
| ] | ||
| } | ||
| } | ||
| } | ||
| } | ||
| } | ||
| } | ||
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
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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
How about loading this from the
instructlab.sdgpackageThere was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
yes, that would be better