Custom Metadata tool #163
Open
Custom Metadata tool #163
Conversation
This file contains hidden or 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
…nd merge generic ones into search_assets_tool
firecast
requested changes
Oct 27, 2025
| logger = logging.getLogger(__name__) | ||
|
|
||
|
|
||
| def process_business_metadata( |
There was a problem hiding this comment.
Lets keep it consistent to custom_metadata
| Returns: | ||
| Dictionary containing prompt, metadata details, and id | ||
| """ | ||
| cm_name = cm_def.name or "N/A" |
There was a problem hiding this comment.
Are the default values correct?
| attributes_list_for_prompt: List[str] = [] | ||
| parsed_attributes_for_metadata: List[Dict[str, Any]] = [] | ||
|
|
||
| if cm_def.attribute_defs: |
| if cm_def.attribute_defs: | ||
| for attr_def in cm_def.attribute_defs: | ||
| attr_name = attr_def.display_name or attr_def.name or "Unnamed attribute" | ||
| attr_desc = attr_def.description or "No description" |
There was a problem hiding this comment.
please check default values here as well
| attributes_list_for_prompt.append(f"{attr_name}:{attr_desc}") | ||
|
|
||
| base_description = attr_def.description or "" | ||
| enhanced_description = base_description |
| ) | ||
|
|
||
| # Process explicit custom metadata negative conditions | ||
| if custom_metadata_negative_conditions: |
There was a problem hiding this comment.
why are negative conditions separately processed? Isn't it just a operator difference?
| Returns: | ||
| Dict[str, Any]: Dictionary containing: | ||
| - context: Description of the returned data | ||
| - business_metadata_results: List of business metadata definitions, each containing: |
| - description: Description of the custom metadata set | ||
| - attributes: List of attribute definitions with name, display_name, data_type, | ||
| description, and optional enumEnrichment (with allowed values) | ||
| - id: GUID of the custom metadata definition |
| ), | ||
| "gte": lambda custom_metadata_field_class, | ||
| value: custom_metadata_field_class.gte(value), | ||
| "match": lambda custom_metadata_field_class, |
There was a problem hiding this comment.
how will the LLM know all the allowed values?
| assets = search_assets( | ||
| conditions={ | ||
| "custom_metadata": { | ||
| "Data Quality.quality_score": { |
There was a problem hiding this comment.
shouldn't the LLM use the names rather than displayNames for this?
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.
Changes from Original MCP-8 Implementation
Removed separate
custom_metadata_conditionsparameter - Custom metadata filters are now part of the mainconditionsparameter under a nestedcustom_metadatakey for consistency with standard attributes.Simplified the nested structure - Changed from 4-level nested
custom_metadata_filter+property_filtersformat to simple dot notation:"SetName.AttributeName": value.Removed custom API code - Deleted 69 lines of manual HTTP request handling in
settings.py(includingbuild_api_url(),get_atlan_typedef_api_endpoint(), andmake_request()methods).Switched to PyAtlan native classes - Now uses
CustomMetadataCacheandEnumCachefrom PyAtlan instead of making direct API calls to fetch typedefs.Unified processing logic - Removed the separate
_process_custom_metadata_condition()function (~90 lines). Custom metadata now uses the same_process_condition()function as standard attributes.