-
Notifications
You must be signed in to change notification settings - Fork 281
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Entity recognizer skill doesn't extracts output. #183
Comments
Hi @surendransuri , Please check the |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
I have tried using EntityRecognizer skill to extract the entities combined with SplitText, EmbeddingSkill.
On the output I am not getting extracted entities, it is showing null values for people, skills, locations etc.
PFB code:
fields = [
SearchField(name="parent_id", type=SearchFieldDataType.String, sortable=True, filterable=True, facetable=True),
SearchField(name="chunk_id", type=SearchFieldDataType.String, key=True, sortable=True, filterable=True, facetable=True, analyzer_name="keyword"),
SearchField(name="chunk", type=SearchFieldDataType.String, sortable=False, filterable=False, facetable=False),
SearchField(name="vector", type=SearchFieldDataType.Collection(SearchFieldDataType.Single), vector_search_dimensions=1536, vector_search_profile_name="myHnswProfile"),
SearchField(name="title", type=SearchFieldDataType.String),
SearchField(name="url", type=SearchFieldDataType.String),
SearchField(name="last_modified", type=SearchFieldDataType.DateTimeOffset),
SearchField(name="people", type=SearchFieldDataType.String),
SearchField(name="skills", type=SearchFieldDataType.String)
]
entity_skill=EntityRecognitionSkill(
description="Skill Used to detect entities from the document",
context= "/document/content/",
categories=["Person",
"Email",
"Location",
"Organization",
"PhoneNumber",
"Address",
"Skill"
],
inputs=[
InputFieldMappingEntry(name="text", source="/document/content"),
InputFieldMappingEntry(name="languageCode", source="/document/language")
],
outputs=[
OutputFieldMappingEntry(name="persons", target_name="people"),
OutputFieldMappingEntry(name="skills", target_name="skills"),
],
)
index_projections = SearchIndexerIndexProjections(
selectors=[
SearchIndexerIndexProjectionSelector(
target_index_name=index_name,
parent_key_field_name="parent_id",
source_context="/document/pages/",
mappings=[
InputFieldMappingEntry(name="chunk", source="/document/pages/"),
InputFieldMappingEntry(name="vector", source="/document/pages/*/vector"),
InputFieldMappingEntry(name="title", source="/document/metadata_storage_name"),
InputFieldMappingEntry(name="people", source="/document/content/people"),
InputFieldMappingEntry(name="skills", source="/document/content/skills")
],
),
],
parameters=SearchIndexerIndexProjectionsParameters(
projection_mode=IndexProjectionMode.SKIP_INDEXING_PARENT_DOCUMENTS
)
indexer = SearchIndexer(
name=indexer_name,
description="Indexer to index documents and generate embeddings",
skillset_name=skillset_name,
target_index_name=index_name,
data_source_name=data_source.name,
# Map the metadata_storage_name field to the title field in the index to display the PDF title in the search results
field_mappings=[FieldMapping(source_field_name="metadata_storage_name", target_field_name="title"),
FieldMapping(source_field_name="metadata_storage_path", target_field_name="url"),
FieldMapping(source_field_name="metadata_storage_last_modified", target_field_name="last_modified")
] ,
output_field_mappings=[FieldMapping(source_field_name="/document/content/people", target_field_name="people"),
FieldMapping(source_field_name="/document/content/skills", target_field_name="skills")]
)
The text was updated successfully, but these errors were encountered: