Package ai.pipestream.data.v1

Interface SearchMetadataOrBuilder

All Superinterfaces:
com.google.protobuf.MessageLiteOrBuilder, com.google.protobuf.MessageOrBuilder
All Known Implementing Classes:
SearchMetadata, SearchMetadata.Builder
@Generated public interface SearchMetadataOrBuilder extends com.google.protobuf.MessageOrBuilder

  • Method Details

    • hasTitle

      boolean hasTitle()
       Document title or heading.
      optional string title = 1;
      Returns:
      Whether the title field is set.

    • getTitle

      String getTitle()
       Document title or heading.
      optional string title = 1;
      Returns:
      The title.

    • getTitleBytes

      com.google.protobuf.ByteString getTitleBytes()
       Document title or heading.
      optional string title = 1;
      Returns:
      The bytes for title.

    • hasBody

      boolean hasBody()
       Full text content of the document.
      optional string body = 2;
      Returns:
      Whether the body field is set.

    • getBody

      String getBody()
       Full text content of the document.
      optional string body = 2;
      Returns:
      The body.

    • getBodyBytes

      com.google.protobuf.ByteString getBodyBytes()
       Full text content of the document.
      optional string body = 2;
      Returns:
      The bytes for body.

    • hasKeywords

      boolean hasKeywords()
       Extracted keywords for search and categorization.
      optional .ai.pipestream.data.v1.Keywords keywords = 3;
      Returns:
      Whether the keywords field is set.

    • getKeywords

      Keywords getKeywords()
       Extracted keywords for search and categorization.
      optional .ai.pipestream.data.v1.Keywords keywords = 3;
      Returns:
      The keywords.

    • getKeywordsOrBuilder

      KeywordsOrBuilder getKeywordsOrBuilder()
       Extracted keywords for search and categorization.
      optional .ai.pipestream.data.v1.Keywords keywords = 3;

    • hasDocumentType

      boolean hasDocumentType()
       Document type classification (e.g., "PDF", "HTML", "DOCX").
      optional string document_type = 4;
      Returns:
      Whether the documentType field is set.

    • getDocumentType

      String getDocumentType()
       Document type classification (e.g., "PDF", "HTML", "DOCX").
      optional string document_type = 4;
      Returns:
      The documentType.

    • getDocumentTypeBytes

      com.google.protobuf.ByteString getDocumentTypeBytes()
       Document type classification (e.g., "PDF", "HTML", "DOCX").
      optional string document_type = 4;
      Returns:
      The bytes for documentType.

    • hasSourceUri

      boolean hasSourceUri()
       Original source URI where the document was obtained.
      optional string source_uri = 5;
      Returns:
      Whether the sourceUri field is set.

    • getSourceUri

      String getSourceUri()
       Original source URI where the document was obtained.
      optional string source_uri = 5;
      Returns:
      The sourceUri.

    • getSourceUriBytes

      com.google.protobuf.ByteString getSourceUriBytes()
       Original source URI where the document was obtained.
      optional string source_uri = 5;
      Returns:
      The bytes for sourceUri.

    • hasSourceMimeType

      boolean hasSourceMimeType()
       MIME type of the source document.
      optional string source_mime_type = 6;
      Returns:
      Whether the sourceMimeType field is set.

    • getSourceMimeType

      String getSourceMimeType()
       MIME type of the source document.
      optional string source_mime_type = 6;
      Returns:
      The sourceMimeType.

    • getSourceMimeTypeBytes

      com.google.protobuf.ByteString getSourceMimeTypeBytes()
       MIME type of the source document.
      optional string source_mime_type = 6;
      Returns:
      The bytes for sourceMimeType.

    • hasCreationDate

      boolean hasCreationDate()
       Timestamp when the document was originally created.
      optional .google.protobuf.Timestamp creation_date = 7;
      Returns:
      Whether the creationDate field is set.

    • getCreationDate

      com.google.protobuf.Timestamp getCreationDate()
       Timestamp when the document was originally created.
      optional .google.protobuf.Timestamp creation_date = 7;
      Returns:
      The creationDate.

    • getCreationDateOrBuilder

      com.google.protobuf.TimestampOrBuilder getCreationDateOrBuilder()
       Timestamp when the document was originally created.
      optional .google.protobuf.Timestamp creation_date = 7;

    • hasLastModifiedDate

      boolean hasLastModifiedDate()
       Timestamp when the document was last modified at source.
      optional .google.protobuf.Timestamp last_modified_date = 8;
      Returns:
      Whether the lastModifiedDate field is set.

    • getLastModifiedDate

      com.google.protobuf.Timestamp getLastModifiedDate()
       Timestamp when the document was last modified at source.
      optional .google.protobuf.Timestamp last_modified_date = 8;
      Returns:
      The lastModifiedDate.

    • getLastModifiedDateOrBuilder

      com.google.protobuf.TimestampOrBuilder getLastModifiedDateOrBuilder()
       Timestamp when the document was last modified at source.
      optional .google.protobuf.Timestamp last_modified_date = 8;

    • hasProcessedDate

      boolean hasProcessedDate()
       Timestamp when the document was processed by the pipeline.
      optional .google.protobuf.Timestamp processed_date = 9;
      Returns:
      Whether the processedDate field is set.

    • getProcessedDate

      com.google.protobuf.Timestamp getProcessedDate()
       Timestamp when the document was processed by the pipeline.
      optional .google.protobuf.Timestamp processed_date = 9;
      Returns:
      The processedDate.

    • getProcessedDateOrBuilder

      com.google.protobuf.TimestampOrBuilder getProcessedDateOrBuilder()
       Timestamp when the document was processed by the pipeline.
      optional .google.protobuf.Timestamp processed_date = 9;

    • hasLanguage

      boolean hasLanguage()
       Language code of the document content (e.g., "en", "es", "fr").
      optional string language = 10;
      Returns:
      Whether the language field is set.

    • getLanguage

      String getLanguage()
       Language code of the document content (e.g., "en", "es", "fr").
      optional string language = 10;
      Returns:
      The language.

    • getLanguageBytes

      com.google.protobuf.ByteString getLanguageBytes()
       Language code of the document content (e.g., "en", "es", "fr").
      optional string language = 10;
      Returns:
      The bytes for language.

    • hasAuthor

      boolean hasAuthor()
       Document author or creator.
      optional string author = 11;
      Returns:
      Whether the author field is set.

    • getAuthor

      String getAuthor()
       Document author or creator.
      optional string author = 11;
      Returns:
      The author.

    • getAuthorBytes

      com.google.protobuf.ByteString getAuthorBytes()
       Document author or creator.
      optional string author = 11;
      Returns:
      The bytes for author.

    • hasCategory

      boolean hasCategory()
       Category or classification label for the document.
      optional string category = 12;
      Returns:
      Whether the category field is set.

    • getCategory

      String getCategory()
       Category or classification label for the document.
      optional string category = 12;
      Returns:
      The category.

    • getCategoryBytes

      com.google.protobuf.ByteString getCategoryBytes()
       Category or classification label for the document.
      optional string category = 12;
      Returns:
      The bytes for category.

    • hasTags

      boolean hasTags()
       Key-value tags for flexible categorization.
      optional .ai.pipestream.data.v1.Tags tags = 13;
      Returns:
      Whether the tags field is set.

    • getTags

      Tags getTags()
       Key-value tags for flexible categorization.
      optional .ai.pipestream.data.v1.Tags tags = 13;
      Returns:
      The tags.

    • getTagsOrBuilder

      TagsOrBuilder getTagsOrBuilder()
       Key-value tags for flexible categorization.
      optional .ai.pipestream.data.v1.Tags tags = 13;

    • hasContentLength

      boolean hasContentLength()
       Length of the document content in bytes or characters.
      optional int32 content_length = 14;
      Returns:
      Whether the contentLength field is set.

    • getContentLength

      int getContentLength()
       Length of the document content in bytes or characters.
      optional int32 content_length = 14;
      Returns:
      The contentLength.

    • hasRelevanceScore

      boolean hasRelevanceScore()
       Relevance score for search ranking purposes.
      optional double relevance_score = 15;
      Returns:
      Whether the relevanceScore field is set.

    • getRelevanceScore

      double getRelevanceScore()
       Relevance score for search ranking purposes.
      optional double relevance_score = 15;
      Returns:
      The relevanceScore.

    • hasCustomFields

      boolean hasCustomFields()
       Additional custom fields not covered by standard schema.
      optional .google.protobuf.Struct custom_fields = 16;
      Returns:
      Whether the customFields field is set.

    • getCustomFields

      com.google.protobuf.Struct getCustomFields()
       Additional custom fields not covered by standard schema.
      optional .google.protobuf.Struct custom_fields = 16;
      Returns:
      The customFields.

    • getCustomFieldsOrBuilder

      com.google.protobuf.StructOrBuilder getCustomFieldsOrBuilder()
       Additional custom fields not covered by standard schema.
      optional .google.protobuf.Struct custom_fields = 16;

    • getMetadataCount

      int getMetadataCount()
       Generic key-value metadata for extensibility.
      map<string, string> metadata = 17;

    • containsMetadata

      boolean containsMetadata(String key)
       Generic key-value metadata for extensibility.
      map<string, string> metadata = 17;

    • getMetadata

      @Deprecated Map<String,String> getMetadata()
      Deprecated.
      Use getMetadataMap() instead.

    • getMetadataMap

      Map<String,String> getMetadataMap()
       Generic key-value metadata for extensibility.
      map<string, string> metadata = 17;

    • getMetadataOrDefault

      String getMetadataOrDefault(String key, String defaultValue)
       Generic key-value metadata for extensibility.
      map<string, string> metadata = 17;

    • getMetadataOrThrow

      String getMetadataOrThrow(String key)
       Generic key-value metadata for extensibility.
      map<string, string> metadata = 17;

    • getSemanticResultsList

      List<SemanticProcessingResult> getSemanticResultsList()
       Results from semantic chunking and embedding processes.

 Supports multiple processing configurations applied to the same document.
      repeated .ai.pipestream.data.v1.SemanticProcessingResult semantic_results = 18;

    • getSemanticResults

      SemanticProcessingResult getSemanticResults(int index)
       Results from semantic chunking and embedding processes.

 Supports multiple processing configurations applied to the same document.
      repeated .ai.pipestream.data.v1.SemanticProcessingResult semantic_results = 18;

    • getSemanticResultsCount

      int getSemanticResultsCount()
       Results from semantic chunking and embedding processes.

 Supports multiple processing configurations applied to the same document.
      repeated .ai.pipestream.data.v1.SemanticProcessingResult semantic_results = 18;

    • getSemanticResultsOrBuilderList

      List<? extends SemanticProcessingResultOrBuilder> getSemanticResultsOrBuilderList()
       Results from semantic chunking and embedding processes.

 Supports multiple processing configurations applied to the same document.
      repeated .ai.pipestream.data.v1.SemanticProcessingResult semantic_results = 18;

    • getSemanticResultsOrBuilder

      SemanticProcessingResultOrBuilder getSemanticResultsOrBuilder(int index)
       Results from semantic chunking and embedding processes.

 Supports multiple processing configurations applied to the same document.
      repeated .ai.pipestream.data.v1.SemanticProcessingResult semantic_results = 18;

    • hasDoi

      boolean hasDoi()
       Digital Object Identifier for academic papers and publications.
      optional string doi = 19;
      Returns:
      Whether the doi field is set.

    • getDoi

      String getDoi()
       Digital Object Identifier for academic papers and publications.
      optional string doi = 19;
      Returns:
      The doi.

    • getDoiBytes

      com.google.protobuf.ByteString getDoiBytes()
       Digital Object Identifier for academic papers and publications.
      optional string doi = 19;
      Returns:
      The bytes for doi.

    • hasDocOutline

      boolean hasDocOutline()
       Neutral document outline for navigation and chunking.

 Supports EPUB TOC, HTML headings, Markdown headings, LaTeX sections, PDF outlines, etc.
      optional .ai.pipestream.data.v1.DocOutline doc_outline = 20;
      Returns:
      Whether the docOutline field is set.

    • getDocOutline

      DocOutline getDocOutline()
       Neutral document outline for navigation and chunking.

 Supports EPUB TOC, HTML headings, Markdown headings, LaTeX sections, PDF outlines, etc.
      optional .ai.pipestream.data.v1.DocOutline doc_outline = 20;
      Returns:
      The docOutline.

    • getDocOutlineOrBuilder

      DocOutlineOrBuilder getDocOutlineOrBuilder()
       Neutral document outline for navigation and chunking.

 Supports EPUB TOC, HTML headings, Markdown headings, LaTeX sections, PDF outlines, etc.
      optional .ai.pipestream.data.v1.DocOutline doc_outline = 20;

    • getDiscoveredLinksList

      List<LinkReference> getDiscoveredLinksList()
       Links discovered within the document.

 Useful for analyzing document relationships and external references.
      repeated .ai.pipestream.data.v1.LinkReference discovered_links = 21;

    • getDiscoveredLinks

      LinkReference getDiscoveredLinks(int index)
       Links discovered within the document.

 Useful for analyzing document relationships and external references.
      repeated .ai.pipestream.data.v1.LinkReference discovered_links = 21;

    • getDiscoveredLinksCount

      int getDiscoveredLinksCount()
       Links discovered within the document.

 Useful for analyzing document relationships and external references.
      repeated .ai.pipestream.data.v1.LinkReference discovered_links = 21;

    • getDiscoveredLinksOrBuilderList

      List<? extends LinkReferenceOrBuilder> getDiscoveredLinksOrBuilderList()
       Links discovered within the document.

 Useful for analyzing document relationships and external references.
      repeated .ai.pipestream.data.v1.LinkReference discovered_links = 21;

    • getDiscoveredLinksOrBuilder

      LinkReferenceOrBuilder getDiscoveredLinksOrBuilder(int index)
       Links discovered within the document.

 Useful for analyzing document relationships and external references.
      repeated .ai.pipestream.data.v1.LinkReference discovered_links = 21;

    • hasSourcePath

      boolean hasSourcePath()
       Path portion of source_uri for categorization.

 Example: "/docs/legal/NY/file.pdf" from "https://example.com/docs/legal/NY/file.pdf"
      optional string source_path = 22;
      Returns:
      Whether the sourcePath field is set.

    • getSourcePath

      String getSourcePath()
       Path portion of source_uri for categorization.

 Example: "/docs/legal/NY/file.pdf" from "https://example.com/docs/legal/NY/file.pdf"
      optional string source_path = 22;
      Returns:
      The sourcePath.

    • getSourcePathBytes

      com.google.protobuf.ByteString getSourcePathBytes()
       Path portion of source_uri for categorization.

 Example: "/docs/legal/NY/file.pdf" from "https://example.com/docs/legal/NY/file.pdf"
      optional string source_path = 22;
      Returns:
      The bytes for sourcePath.

    • getSourcePathSegmentsList

      List<String> getSourcePathSegmentsList()
       Split path segments from source_path.

 Example: ["docs", "legal", "NY", "file.pdf"]
      repeated string source_path_segments = 23;
      Returns:
      A list containing the sourcePathSegments.

    • getSourcePathSegmentsCount

      int getSourcePathSegmentsCount()
       Split path segments from source_path.

 Example: ["docs", "legal", "NY", "file.pdf"]
      repeated string source_path_segments = 23;
      Returns:
      The count of sourcePathSegments.

    • getSourcePathSegments

      String getSourcePathSegments(int index)
       Split path segments from source_path.

 Example: ["docs", "legal", "NY", "file.pdf"]
      repeated string source_path_segments = 23;
      Parameters:
      index - The index of the element to return.
      Returns:
      The sourcePathSegments at the given index.

    • getSourcePathSegmentsBytes

      com.google.protobuf.ByteString getSourcePathSegmentsBytes(int index)
       Split path segments from source_path.

 Example: ["docs", "legal", "NY", "file.pdf"]
      repeated string source_path_segments = 23;
      Parameters:
      index - The index of the value to return.
      Returns:
      The bytes of the sourcePathSegments at the given index.

    • hasSourceSlug

      boolean hasSourceSlug()
       Last segment of source_path.

 Example: "file.pdf" from "/docs/legal/NY/file.pdf"
      optional string source_slug = 24;
      Returns:
      Whether the sourceSlug field is set.

    • getSourceSlug

      String getSourceSlug()
       Last segment of source_path.

 Example: "file.pdf" from "/docs/legal/NY/file.pdf"
      optional string source_slug = 24;
      Returns:
      The sourceSlug.

    • getSourceSlugBytes

      com.google.protobuf.ByteString getSourceSlugBytes()
       Last segment of source_path.

 Example: "file.pdf" from "/docs/legal/NY/file.pdf"
      optional string source_slug = 24;
      Returns:
      The bytes for sourceSlug.