carbon_ruby_sdk 0.2.2 → 0.2.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 48a58cba1f17ea688e80ef5572f4944be16851ffe4ab0bed12010fe0f8b12f3e
-  data.tar.gz: 637e68cdedc5092c2c3de53c87f99b732cb2ba2eea49f6e0296220cd741dc217
+  metadata.gz: af28a3b256d49d38a6aca558d12a49a6e3f2888587dedeef54311ad7d0bd0ac9
+  data.tar.gz: a685b15e3ad3ab32463c4bd03c92432c21bc3c7cf3b8f29bcf340cde6e468377
 SHA512:
-  metadata.gz: a3ca1057eaaa76eac67308c1f22a46828e1abc53732e8ab309d4d9fe53f87a59cd9712e9d541d2ef7f3b05854dbef675ab80fbf38ea7cd2b54b1cb2cab41f002
-  data.tar.gz: 4354aafdeb4fdd30b24c74b266b0c839eadcba4776590a412b77f54bff85465e49f734e538bc634f3d176d20c1157932a9dc7470acb3cbebc3572619bdceb0e2
+  metadata.gz: 023c5d51386e0e76ecd6954f25c69a8562302f89de2a1a15cd72fbfc0e3491c6129ad496da1ad9dbfd80a0030c30ba501cb2e8552cbdd92c07513a20f0257211
+  data.tar.gz: 465fbc642ce7bf817b5c5d647d34c1c963e254a21facef003efc0a60a5074dad6c1b642a1093e3f0e9228505bde79b9f5c55e263827987395734718b019c7a06

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    carbon_ruby_sdk (0.2.1)
+    carbon_ruby_sdk (0.2.2)
       faraday (>= 1.0.1, < 3.0)
       faraday-multipart (~> 1.0, >= 1.0.4)
 

data/README.md

@@ -6,7 +6,7 @@
 
 Connect external data to LLMs, no matter the source.
 
-[![npm](https://img.shields.io/badge/gem-v0.2.2-blue)](https://rubygems.org/gems/carbon_ruby_sdk/versions/0.2.2)
+[![npm](https://img.shields.io/badge/gem-v0.2.3-blue)](https://rubygems.org/gems/carbon_ruby_sdk/versions/0.2.3)
 
 </div>
 
@@ -86,7 +86,7 @@ Connect external data to LLMs, no matter the source.
 Add to Gemfile:
 
 ```ruby
-gem 'carbon_ruby_sdk', '~> 0.2.2'
+gem 'carbon_ruby_sdk', '~> 0.2.3'
 ```
 
 ## Getting Started<a id="getting-started"></a>
@@ -1240,7 +1240,7 @@ result = carbon.integrations.connect_data_source(
         "prepend_filename_to_chunks" => false,
         "sync_files_on_connection" => true,
         "set_page_as_boundary" => false,
-        "request_id" => "368135ce-5cca-4fb5-a19d-42b9a409af35",
+        "request_id" => "652297b9-0f55-46d8-869d-13a36e89e5da",
         "enable_file_picker" => true,
         "sync_source_items" => true,
         "incremental_sync" => false,
@@ -1459,7 +1459,7 @@ result = carbon.integrations.get_oauth_url(
   set_page_as_boundary: false,
   data_source_id: 1,
   connecting_new_account: false,
-  request_id: "2e662fad-1193-4482-a2d7-ec7b821a9d2b",
+  request_id: "71f214fa-2155-41cb-9336-9b3070e86897",
   use_ocr: false,
   parse_pdf_tables_with_ocr: false,
   enable_file_picker: true,
@@ -1519,7 +1519,7 @@ Enable OCR for files that support it. Supported formats: pdf
 ##### parse_pdf_tables_with_ocr: `Boolean`<a id="parse_pdf_tables_with_ocr-boolean"></a>
 ##### enable_file_picker: `Boolean`<a id="enable_file_picker-boolean"></a>
 Enable integration's file picker for sources that support it. Supported sources:
-SHAREPOINT, BOX, ONEDRIVE, GOOGLE_DRIVE, DROPBOX
+DROPBOX, GOOGLE_DRIVE, SHAREPOINT, ONEDRIVE, BOX
 
 ##### sync_source_items: `Boolean`<a id="sync_source_items-boolean"></a>
 Enabling this flag will fetch all available content from the source to be listed
@@ -1781,7 +1781,7 @@ result = carbon.integrations.sync_confluence(
   prepend_filename_to_chunks: false,
   max_items_per_chunk: 1,
   set_page_as_boundary: false,
-  request_id: "dd2130b5-0f9f-4f3a-b450-f3fa458763ae",
+  request_id: "6136b467-242e-49df-9478-d3e0cfdde299",
   use_ocr: false,
   parse_pdf_tables_with_ocr: false,
   incremental_sync: false,
@@ -1884,7 +1884,7 @@ result = carbon.integrations.sync_files(
   prepend_filename_to_chunks: false,
   max_items_per_chunk: 1,
   set_page_as_boundary: false,
-  request_id: "dd2130b5-0f9f-4f3a-b450-f3fa458763ae",
+  request_id: "6136b467-242e-49df-9478-d3e0cfdde299",
   use_ocr: false,
   parse_pdf_tables_with_ocr: false,
   incremental_sync: false,
@@ -2741,6 +2741,8 @@ result = carbon.utilities.scrape_sitemap(
   css_classes_to_skip: [],
   css_selectors_to_skip: [],
   embedding_model: "OPENAI",
+  url_paths_to_include: [],
+  url_paths_to_exclude: [],
 )
 p result
 ```
@@ -2760,6 +2762,16 @@ p result
 ##### css_classes_to_skip: Array<`String`><a id="css_classes_to_skip-array"></a>
 ##### css_selectors_to_skip: Array<`String`><a id="css_selectors_to_skip-array"></a>
 ##### embedding_model: [`EmbeddingGenerators`](./lib/carbon_ruby_sdk/models/embedding_generators.rb)<a id="embedding_model-embeddinggeneratorslibcarbon_ruby_sdkmodelsembedding_generatorsrb"></a>
+##### url_paths_to_include: Array<`String`><a id="url_paths_to_include-array"></a>
+URL subpaths or directories that you want to include. For example if you want to
+only include URLs that start with /questions in stackoverflow.com, you will add
+/questions/ in this input
+
+##### url_paths_to_exclude: Array<`String`><a id="url_paths_to_exclude-array"></a>
+URL subpaths or directories that you want to exclude. For example if you want to
+exclude URLs that start with /questions in stackoverflow.com, you will add
+/questions/ in this input
+
 #### 🌐 Endpoint<a id="🌐-endpoint"></a>
 
 `/scrape_sitemap` `POST`
@@ -2799,6 +2811,7 @@ result = carbon.utilities.scrape_web(
             "css_classes_to_skip" => [],
             "css_selectors_to_skip" => [],
             "embedding_model" => "OPENAI",
+            "url_paths_to_include" => [],
         }
     ],
 )

data/lib/carbon_ruby_sdk/api/integrations_api.rb

@@ -653,13 +653,13 @@ module Carbon
     # @param request_id [String] This request id will be added to all files that get synced using the generated OAuth URL
     # @param use_ocr [Boolean] Enable OCR for files that support it. Supported formats: pdf
     # @param parse_pdf_tables_with_ocr [Boolean] 
-    # @param enable_file_picker [Boolean] Enable integration's file picker for sources that support it. Supported sources: SHAREPOINT, BOX, ONEDRIVE, GOOGLE_DRIVE, DROPBOX
+    # @param enable_file_picker [Boolean] Enable integration's file picker for sources that support it. Supported sources: DROPBOX, GOOGLE_DRIVE, SHAREPOINT, ONEDRIVE, BOX
     # @param sync_source_items [Boolean] Enabling this flag will fetch all available content from the source to be listed via list items endpoint
     # @param incremental_sync [Boolean] Only sync files if they have not already been synced or if the embedding properties have changed. This flag is currently supported by ONEDRIVE, GOOGLE_DRIVE, BOX, DROPBOX. It will be ignored for other data sources.
     # @param file_sync_config [FileSyncConfigNullable] 
     # @param body [OAuthURLRequest] 
     # @param [Hash] extra additional parameters to pass along through :header_params, :query_params, or parameter name
-    def get_oauth_url(service:, tags: SENTINEL, scope: SENTINEL, chunk_size: 1500, chunk_overlap: 20, skip_embedding_generation: false, embedding_model: 'OPENAI', zendesk_subdomain: SENTINEL, microsoft_tenant: SENTINEL, sharepoint_site_name: SENTINEL, confluence_subdomain: SENTINEL, generate_sparse_vectors: false, prepend_filename_to_chunks: false, max_items_per_chunk: SENTINEL, salesforce_domain: SENTINEL, sync_files_on_connection: true, set_page_as_boundary: false, data_source_id: SENTINEL, connecting_new_account: false, request_id: '2e662fad-1193-4482-a2d7-ec7b821a9d2b', use_ocr: false, parse_pdf_tables_with_ocr: false, enable_file_picker: true, sync_source_items: true, incremental_sync: false, file_sync_config: SENTINEL, extra: {})
+    def get_oauth_url(service:, tags: SENTINEL, scope: SENTINEL, chunk_size: 1500, chunk_overlap: 20, skip_embedding_generation: false, embedding_model: 'OPENAI', zendesk_subdomain: SENTINEL, microsoft_tenant: SENTINEL, sharepoint_site_name: SENTINEL, confluence_subdomain: SENTINEL, generate_sparse_vectors: false, prepend_filename_to_chunks: false, max_items_per_chunk: SENTINEL, salesforce_domain: SENTINEL, sync_files_on_connection: true, set_page_as_boundary: false, data_source_id: SENTINEL, connecting_new_account: false, request_id: '71f214fa-2155-41cb-9336-9b3070e86897', use_ocr: false, parse_pdf_tables_with_ocr: false, enable_file_picker: true, sync_source_items: true, incremental_sync: false, file_sync_config: SENTINEL, extra: {})
       _body = {}
       _body[:tags] = tags if tags != SENTINEL
       _body[:scope] = scope if scope != SENTINEL
@@ -721,13 +721,13 @@ module Carbon
     # @param request_id [String] This request id will be added to all files that get synced using the generated OAuth URL
     # @param use_ocr [Boolean] Enable OCR for files that support it. Supported formats: pdf
     # @param parse_pdf_tables_with_ocr [Boolean] 
-    # @param enable_file_picker [Boolean] Enable integration's file picker for sources that support it. Supported sources: SHAREPOINT, BOX, ONEDRIVE, GOOGLE_DRIVE, DROPBOX
+    # @param enable_file_picker [Boolean] Enable integration's file picker for sources that support it. Supported sources: DROPBOX, GOOGLE_DRIVE, SHAREPOINT, ONEDRIVE, BOX
     # @param sync_source_items [Boolean] Enabling this flag will fetch all available content from the source to be listed via list items endpoint
     # @param incremental_sync [Boolean] Only sync files if they have not already been synced or if the embedding properties have changed. This flag is currently supported by ONEDRIVE, GOOGLE_DRIVE, BOX, DROPBOX. It will be ignored for other data sources.
     # @param file_sync_config [FileSyncConfigNullable] 
     # @param body [OAuthURLRequest] 
     # @param [Hash] extra additional parameters to pass along through :header_params, :query_params, or parameter name
-    def get_oauth_url_with_http_info(service:, tags: SENTINEL, scope: SENTINEL, chunk_size: 1500, chunk_overlap: 20, skip_embedding_generation: false, embedding_model: 'OPENAI', zendesk_subdomain: SENTINEL, microsoft_tenant: SENTINEL, sharepoint_site_name: SENTINEL, confluence_subdomain: SENTINEL, generate_sparse_vectors: false, prepend_filename_to_chunks: false, max_items_per_chunk: SENTINEL, salesforce_domain: SENTINEL, sync_files_on_connection: true, set_page_as_boundary: false, data_source_id: SENTINEL, connecting_new_account: false, request_id: '2e662fad-1193-4482-a2d7-ec7b821a9d2b', use_ocr: false, parse_pdf_tables_with_ocr: false, enable_file_picker: true, sync_source_items: true, incremental_sync: false, file_sync_config: SENTINEL, extra: {})
+    def get_oauth_url_with_http_info(service:, tags: SENTINEL, scope: SENTINEL, chunk_size: 1500, chunk_overlap: 20, skip_embedding_generation: false, embedding_model: 'OPENAI', zendesk_subdomain: SENTINEL, microsoft_tenant: SENTINEL, sharepoint_site_name: SENTINEL, confluence_subdomain: SENTINEL, generate_sparse_vectors: false, prepend_filename_to_chunks: false, max_items_per_chunk: SENTINEL, salesforce_domain: SENTINEL, sync_files_on_connection: true, set_page_as_boundary: false, data_source_id: SENTINEL, connecting_new_account: false, request_id: '71f214fa-2155-41cb-9336-9b3070e86897', use_ocr: false, parse_pdf_tables_with_ocr: false, enable_file_picker: true, sync_source_items: true, incremental_sync: false, file_sync_config: SENTINEL, extra: {})
       _body = {}
       _body[:tags] = tags if tags != SENTINEL
       _body[:scope] = scope if scope != SENTINEL
@@ -1523,7 +1523,7 @@ module Carbon
     # @param file_sync_config [FileSyncConfigNullable] 
     # @param body [SyncFilesRequest] 
     # @param [Hash] extra additional parameters to pass along through :header_params, :query_params, or parameter name
-    def sync_confluence(data_source_id:, ids:, tags: SENTINEL, chunk_size: 1500, chunk_overlap: 20, skip_embedding_generation: false, embedding_model: 'OPENAI', generate_sparse_vectors: false, prepend_filename_to_chunks: false, max_items_per_chunk: SENTINEL, set_page_as_boundary: false, request_id: 'dd2130b5-0f9f-4f3a-b450-f3fa458763ae', use_ocr: false, parse_pdf_tables_with_ocr: false, incremental_sync: false, file_sync_config: SENTINEL, extra: {})
+    def sync_confluence(data_source_id:, ids:, tags: SENTINEL, chunk_size: 1500, chunk_overlap: 20, skip_embedding_generation: false, embedding_model: 'OPENAI', generate_sparse_vectors: false, prepend_filename_to_chunks: false, max_items_per_chunk: SENTINEL, set_page_as_boundary: false, request_id: '6136b467-242e-49df-9478-d3e0cfdde299', use_ocr: false, parse_pdf_tables_with_ocr: false, incremental_sync: false, file_sync_config: SENTINEL, extra: {})
       _body = {}
       _body[:tags] = tags if tags != SENTINEL
       _body[:data_source_id] = data_source_id if data_source_id != SENTINEL
@@ -1571,7 +1571,7 @@ module Carbon
     # @param file_sync_config [FileSyncConfigNullable] 
     # @param body [SyncFilesRequest] 
     # @param [Hash] extra additional parameters to pass along through :header_params, :query_params, or parameter name
-    def sync_confluence_with_http_info(data_source_id:, ids:, tags: SENTINEL, chunk_size: 1500, chunk_overlap: 20, skip_embedding_generation: false, embedding_model: 'OPENAI', generate_sparse_vectors: false, prepend_filename_to_chunks: false, max_items_per_chunk: SENTINEL, set_page_as_boundary: false, request_id: 'dd2130b5-0f9f-4f3a-b450-f3fa458763ae', use_ocr: false, parse_pdf_tables_with_ocr: false, incremental_sync: false, file_sync_config: SENTINEL, extra: {})
+    def sync_confluence_with_http_info(data_source_id:, ids:, tags: SENTINEL, chunk_size: 1500, chunk_overlap: 20, skip_embedding_generation: false, embedding_model: 'OPENAI', generate_sparse_vectors: false, prepend_filename_to_chunks: false, max_items_per_chunk: SENTINEL, set_page_as_boundary: false, request_id: '6136b467-242e-49df-9478-d3e0cfdde299', use_ocr: false, parse_pdf_tables_with_ocr: false, incremental_sync: false, file_sync_config: SENTINEL, extra: {})
       _body = {}
       _body[:tags] = tags if tags != SENTINEL
       _body[:data_source_id] = data_source_id if data_source_id != SENTINEL
@@ -1779,7 +1779,7 @@ module Carbon
     # @param file_sync_config [FileSyncConfigNullable] 
     # @param body [SyncFilesRequest] 
     # @param [Hash] extra additional parameters to pass along through :header_params, :query_params, or parameter name
-    def sync_files(data_source_id:, ids:, tags: SENTINEL, chunk_size: 1500, chunk_overlap: 20, skip_embedding_generation: false, embedding_model: 'OPENAI', generate_sparse_vectors: false, prepend_filename_to_chunks: false, max_items_per_chunk: SENTINEL, set_page_as_boundary: false, request_id: 'dd2130b5-0f9f-4f3a-b450-f3fa458763ae', use_ocr: false, parse_pdf_tables_with_ocr: false, incremental_sync: false, file_sync_config: SENTINEL, extra: {})
+    def sync_files(data_source_id:, ids:, tags: SENTINEL, chunk_size: 1500, chunk_overlap: 20, skip_embedding_generation: false, embedding_model: 'OPENAI', generate_sparse_vectors: false, prepend_filename_to_chunks: false, max_items_per_chunk: SENTINEL, set_page_as_boundary: false, request_id: '6136b467-242e-49df-9478-d3e0cfdde299', use_ocr: false, parse_pdf_tables_with_ocr: false, incremental_sync: false, file_sync_config: SENTINEL, extra: {})
       _body = {}
       _body[:tags] = tags if tags != SENTINEL
       _body[:data_source_id] = data_source_id if data_source_id != SENTINEL
@@ -1827,7 +1827,7 @@ module Carbon
     # @param file_sync_config [FileSyncConfigNullable] 
     # @param body [SyncFilesRequest] 
     # @param [Hash] extra additional parameters to pass along through :header_params, :query_params, or parameter name
-    def sync_files_with_http_info(data_source_id:, ids:, tags: SENTINEL, chunk_size: 1500, chunk_overlap: 20, skip_embedding_generation: false, embedding_model: 'OPENAI', generate_sparse_vectors: false, prepend_filename_to_chunks: false, max_items_per_chunk: SENTINEL, set_page_as_boundary: false, request_id: 'dd2130b5-0f9f-4f3a-b450-f3fa458763ae', use_ocr: false, parse_pdf_tables_with_ocr: false, incremental_sync: false, file_sync_config: SENTINEL, extra: {})
+    def sync_files_with_http_info(data_source_id:, ids:, tags: SENTINEL, chunk_size: 1500, chunk_overlap: 20, skip_embedding_generation: false, embedding_model: 'OPENAI', generate_sparse_vectors: false, prepend_filename_to_chunks: false, max_items_per_chunk: SENTINEL, set_page_as_boundary: false, request_id: '6136b467-242e-49df-9478-d3e0cfdde299', use_ocr: false, parse_pdf_tables_with_ocr: false, incremental_sync: false, file_sync_config: SENTINEL, extra: {})
       _body = {}
       _body[:tags] = tags if tags != SENTINEL
       _body[:data_source_id] = data_source_id if data_source_id != SENTINEL

data/lib/carbon_ruby_sdk/api/utilities_api.rb

@@ -342,9 +342,11 @@ module Carbon
     # @param css_classes_to_skip [Array<String>] 
     # @param css_selectors_to_skip [Array<String>] 
     # @param embedding_model [EmbeddingGenerators] 
+    # @param url_paths_to_include [Array<String>] URL subpaths or directories that you want to include. For example if you want to only include URLs that start with /questions in stackoverflow.com, you will add /questions/ in this input
+    # @param url_paths_to_exclude [Array<String>] URL subpaths or directories that you want to exclude. For example if you want to exclude URLs that start with /questions in stackoverflow.com, you will add /questions/ in this input
     # @param body [SitemapScrapeRequest] 
     # @param [Hash] extra additional parameters to pass along through :header_params, :query_params, or parameter name
-    def scrape_sitemap(url:, tags: SENTINEL, max_pages_to_scrape: SENTINEL, chunk_size: 1500, chunk_overlap: 20, skip_embedding_generation: false, enable_auto_sync: false, generate_sparse_vectors: false, prepend_filename_to_chunks: false, html_tags_to_skip: SENTINEL, css_classes_to_skip: SENTINEL, css_selectors_to_skip: SENTINEL, embedding_model: 'OPENAI', extra: {})
+    def scrape_sitemap(url:, tags: SENTINEL, max_pages_to_scrape: SENTINEL, chunk_size: 1500, chunk_overlap: 20, skip_embedding_generation: false, enable_auto_sync: false, generate_sparse_vectors: false, prepend_filename_to_chunks: false, html_tags_to_skip: SENTINEL, css_classes_to_skip: SENTINEL, css_selectors_to_skip: SENTINEL, embedding_model: 'OPENAI', url_paths_to_include: SENTINEL, url_paths_to_exclude: SENTINEL, extra: {})
       _body = {}
       _body[:tags] = tags if tags != SENTINEL
       _body[:url] = url if url != SENTINEL
@@ -359,6 +361,8 @@ module Carbon
       _body[:css_classes_to_skip] = css_classes_to_skip if css_classes_to_skip != SENTINEL
       _body[:css_selectors_to_skip] = css_selectors_to_skip if css_selectors_to_skip != SENTINEL
       _body[:embedding_model] = embedding_model if embedding_model != SENTINEL
+      _body[:url_paths_to_include] = url_paths_to_include if url_paths_to_include != SENTINEL
+      _body[:url_paths_to_exclude] = url_paths_to_exclude if url_paths_to_exclude != SENTINEL
       sitemap_scrape_request = _body
       api_response = scrape_sitemap_with_http_info_impl(sitemap_scrape_request, extra)
       api_response.data
@@ -387,9 +391,11 @@ module Carbon
     # @param css_classes_to_skip [Array<String>] 
     # @param css_selectors_to_skip [Array<String>] 
     # @param embedding_model [EmbeddingGenerators] 
+    # @param url_paths_to_include [Array<String>] URL subpaths or directories that you want to include. For example if you want to only include URLs that start with /questions in stackoverflow.com, you will add /questions/ in this input
+    # @param url_paths_to_exclude [Array<String>] URL subpaths or directories that you want to exclude. For example if you want to exclude URLs that start with /questions in stackoverflow.com, you will add /questions/ in this input
     # @param body [SitemapScrapeRequest] 
     # @param [Hash] extra additional parameters to pass along through :header_params, :query_params, or parameter name
-    def scrape_sitemap_with_http_info(url:, tags: SENTINEL, max_pages_to_scrape: SENTINEL, chunk_size: 1500, chunk_overlap: 20, skip_embedding_generation: false, enable_auto_sync: false, generate_sparse_vectors: false, prepend_filename_to_chunks: false, html_tags_to_skip: SENTINEL, css_classes_to_skip: SENTINEL, css_selectors_to_skip: SENTINEL, embedding_model: 'OPENAI', extra: {})
+    def scrape_sitemap_with_http_info(url:, tags: SENTINEL, max_pages_to_scrape: SENTINEL, chunk_size: 1500, chunk_overlap: 20, skip_embedding_generation: false, enable_auto_sync: false, generate_sparse_vectors: false, prepend_filename_to_chunks: false, html_tags_to_skip: SENTINEL, css_classes_to_skip: SENTINEL, css_selectors_to_skip: SENTINEL, embedding_model: 'OPENAI', url_paths_to_include: SENTINEL, url_paths_to_exclude: SENTINEL, extra: {})
       _body = {}
       _body[:tags] = tags if tags != SENTINEL
       _body[:url] = url if url != SENTINEL
@@ -404,6 +410,8 @@ module Carbon
       _body[:css_classes_to_skip] = css_classes_to_skip if css_classes_to_skip != SENTINEL
       _body[:css_selectors_to_skip] = css_selectors_to_skip if css_selectors_to_skip != SENTINEL
       _body[:embedding_model] = embedding_model if embedding_model != SENTINEL
+      _body[:url_paths_to_include] = url_paths_to_include if url_paths_to_include != SENTINEL
+      _body[:url_paths_to_exclude] = url_paths_to_exclude if url_paths_to_exclude != SENTINEL
       sitemap_scrape_request = _body
       scrape_sitemap_with_http_info_impl(sitemap_scrape_request, extra)
     end

data/lib/carbon_ruby_sdk/models/o_auth_url_request.rb

@@ -61,7 +61,7 @@ module Carbon
 
     attr_accessor :parse_pdf_tables_with_ocr
 
-    # Enable integration's file picker for sources that support it. Supported sources: SHAREPOINT, BOX, ONEDRIVE, GOOGLE_DRIVE, DROPBOX
+    # Enable integration's file picker for sources that support it. Supported sources: DROPBOX, GOOGLE_DRIVE, SHAREPOINT, ONEDRIVE, BOX
     attr_accessor :enable_file_picker
 
     # Enabling this flag will fetch all available content from the source to be listed via list items endpoint
@@ -279,7 +279,7 @@ module Carbon
       if attributes.key?(:'request_id')
         self.request_id = attributes[:'request_id']
       else
-        self.request_id = '2e662fad-1193-4482-a2d7-ec7b821a9d2b'
+        self.request_id = '71f214fa-2155-41cb-9336-9b3070e86897'
       end
 
       if attributes.key?(:'use_ocr')

data/lib/carbon_ruby_sdk/models/sitemap_scrape_request.rb

@@ -37,6 +37,12 @@ module Carbon
 
     attr_accessor :embedding_model
 
+    # URL subpaths or directories that you want to include. For example if you want to only include         URLs that start with /questions in stackoverflow.com, you will add /questions/ in this input
+    attr_accessor :url_paths_to_include
+
+    # URL subpaths or directories that you want to exclude. For example if you want to exclude         URLs that start with /questions in stackoverflow.com, you will add /questions/ in this input
+    attr_accessor :url_paths_to_exclude
+
     # Attribute mapping from ruby-style variable name to JSON key.
     def self.attribute_map
       {
@@ -52,7 +58,9 @@ module Carbon
         :'html_tags_to_skip' => :'html_tags_to_skip',
         :'css_classes_to_skip' => :'css_classes_to_skip',
         :'css_selectors_to_skip' => :'css_selectors_to_skip',
-        :'embedding_model' => :'embedding_model'
+        :'embedding_model' => :'embedding_model',
+        :'url_paths_to_include' => :'url_paths_to_include',
+        :'url_paths_to_exclude' => :'url_paths_to_exclude'
       }
     end
 
@@ -76,7 +84,9 @@ module Carbon
         :'html_tags_to_skip' => :'Array<String>',
         :'css_classes_to_skip' => :'Array<String>',
         :'css_selectors_to_skip' => :'Array<String>',
-        :'embedding_model' => :'EmbeddingGenerators'
+        :'embedding_model' => :'EmbeddingGenerators',
+        :'url_paths_to_include' => :'Array<String>',
+        :'url_paths_to_exclude' => :'Array<String>'
       }
     end
 
@@ -94,6 +104,8 @@ module Carbon
         :'html_tags_to_skip',
         :'css_classes_to_skip',
         :'css_selectors_to_skip',
+        :'url_paths_to_include',
+        :'url_paths_to_exclude'
       ])
     end
 
@@ -185,6 +197,18 @@ module Carbon
       else
         self.embedding_model = 'OPENAI'
       end
+
+      if attributes.key?(:'url_paths_to_include')
+        if (value = attributes[:'url_paths_to_include']).is_a?(Array)
+          self.url_paths_to_include = value
+        end
+      end
+
+      if attributes.key?(:'url_paths_to_exclude')
+        if (value = attributes[:'url_paths_to_exclude']).is_a?(Array)
+          self.url_paths_to_exclude = value
+        end
+      end
     end
 
     # Show invalid properties with the reasons. Usually used together with valid?
@@ -199,6 +223,14 @@ module Carbon
         invalid_properties.push('invalid value for "max_pages_to_scrape", must be greater than or equal to 1.')
       end
 
+      if !@url_paths_to_include.nil? && @url_paths_to_include.length > 10
+        invalid_properties.push('invalid value for "url_paths_to_include", number of items must be less than or equal to 10.')
+      end
+
+      if !@url_paths_to_exclude.nil? && @url_paths_to_exclude.length > 10
+        invalid_properties.push('invalid value for "url_paths_to_exclude", number of items must be less than or equal to 10.')
+      end
+
       invalid_properties
     end
 
@@ -207,6 +239,8 @@ module Carbon
     def valid?
       return false if @url.nil?
       return false if !@max_pages_to_scrape.nil? && @max_pages_to_scrape < 1
+      return false if !@url_paths_to_include.nil? && @url_paths_to_include.length > 10
+      return false if !@url_paths_to_exclude.nil? && @url_paths_to_exclude.length > 10
       true
     end
 
@@ -220,6 +254,26 @@ module Carbon
       @max_pages_to_scrape = max_pages_to_scrape
     end
 
+    # Custom attribute writer method with validation
+    # @param [Object] url_paths_to_include Value to be assigned
+    def url_paths_to_include=(url_paths_to_include)
+      if !url_paths_to_include.nil? && url_paths_to_include.length > 10
+        fail ArgumentError, 'invalid value for "url_paths_to_include", number of items must be less than or equal to 10.'
+      end
+
+      @url_paths_to_include = url_paths_to_include
+    end
+
+    # Custom attribute writer method with validation
+    # @param [Object] url_paths_to_exclude Value to be assigned
+    def url_paths_to_exclude=(url_paths_to_exclude)
+      if !url_paths_to_exclude.nil? && url_paths_to_exclude.length > 10
+        fail ArgumentError, 'invalid value for "url_paths_to_exclude", number of items must be less than or equal to 10.'
+      end
+
+      @url_paths_to_exclude = url_paths_to_exclude
+    end
+
     # Checks equality by comparing each attribute.
     # @param [Object] Object to be compared
     def ==(o)
@@ -237,7 +291,9 @@ module Carbon
           html_tags_to_skip == o.html_tags_to_skip &&
           css_classes_to_skip == o.css_classes_to_skip &&
           css_selectors_to_skip == o.css_selectors_to_skip &&
-          embedding_model == o.embedding_model
+          embedding_model == o.embedding_model &&
+          url_paths_to_include == o.url_paths_to_include &&
+          url_paths_to_exclude == o.url_paths_to_exclude
     end
 
     # @see the `==` method
@@ -249,7 +305,7 @@ module Carbon
     # Calculates hash code according to all attributes.
     # @return [Integer] Hash code
     def hash
-      [tags, url, max_pages_to_scrape, chunk_size, chunk_overlap, skip_embedding_generation, enable_auto_sync, generate_sparse_vectors, prepend_filename_to_chunks, html_tags_to_skip, css_classes_to_skip, css_selectors_to_skip, embedding_model].hash
+      [tags, url, max_pages_to_scrape, chunk_size, chunk_overlap, skip_embedding_generation, enable_auto_sync, generate_sparse_vectors, prepend_filename_to_chunks, html_tags_to_skip, css_classes_to_skip, css_selectors_to_skip, embedding_model, url_paths_to_include, url_paths_to_exclude].hash
     end
 
     # Builds the object from hash

data/lib/carbon_ruby_sdk/models/sync_files_request.rb

@@ -187,7 +187,7 @@ module Carbon
       if attributes.key?(:'request_id')
         self.request_id = attributes[:'request_id']
       else
-        self.request_id = 'dd2130b5-0f9f-4f3a-b450-f3fa458763ae'
+        self.request_id = '6136b467-242e-49df-9478-d3e0cfdde299'
       end
 
       if attributes.key?(:'use_ocr')

data/lib/carbon_ruby_sdk/models/sync_options.rb

@@ -182,7 +182,7 @@ module Carbon
       if attributes.key?(:'request_id')
         self.request_id = attributes[:'request_id']
       else
-        self.request_id = '368135ce-5cca-4fb5-a19d-42b9a409af35'
+        self.request_id = '652297b9-0f55-46d8-869d-13a36e89e5da'
       end
 
       if attributes.key?(:'enable_file_picker')

data/lib/carbon_ruby_sdk/models/webscrape_request.rb

@@ -39,6 +39,9 @@ module Carbon
 
     attr_accessor :embedding_model
 
+    # URL subpaths or directories that you want to include. For example if you want to only include         URLs that start with /questions in stackoverflow.com, you will add /questions/ in this input
+    attr_accessor :url_paths_to_include
+
     # Attribute mapping from ruby-style variable name to JSON key.
     def self.attribute_map
       {
@@ -55,7 +58,8 @@ module Carbon
         :'html_tags_to_skip' => :'html_tags_to_skip',
         :'css_classes_to_skip' => :'css_classes_to_skip',
         :'css_selectors_to_skip' => :'css_selectors_to_skip',
-        :'embedding_model' => :'embedding_model'
+        :'embedding_model' => :'embedding_model',
+        :'url_paths_to_include' => :'url_paths_to_include'
       }
     end
 
@@ -80,7 +84,8 @@ module Carbon
         :'html_tags_to_skip' => :'Array<String>',
         :'css_classes_to_skip' => :'Array<String>',
         :'css_selectors_to_skip' => :'Array<String>',
-        :'embedding_model' => :'EmbeddingGenerators'
+        :'embedding_model' => :'EmbeddingGenerators',
+        :'url_paths_to_include' => :'Array<String>'
       }
     end
 
@@ -99,6 +104,7 @@ module Carbon
         :'html_tags_to_skip',
         :'css_classes_to_skip',
         :'css_selectors_to_skip',
+        :'url_paths_to_include'
       ])
     end
 
@@ -198,6 +204,12 @@ module Carbon
       else
         self.embedding_model = 'OPENAI'
       end
+
+      if attributes.key?(:'url_paths_to_include')
+        if (value = attributes[:'url_paths_to_include']).is_a?(Array)
+          self.url_paths_to_include = value
+        end
+      end
     end
 
     # Show invalid properties with the reasons. Usually used together with valid?
@@ -216,6 +228,10 @@ module Carbon
         invalid_properties.push('invalid value for "max_pages_to_scrape", must be greater than or equal to 1.')
       end
 
+      if !@url_paths_to_include.nil? && @url_paths_to_include.length > 10
+        invalid_properties.push('invalid value for "url_paths_to_include", number of items must be less than or equal to 10.')
+      end
+
       invalid_properties
     end
 
@@ -225,6 +241,7 @@ module Carbon
       return false if @url.nil?
       return false if !@recursion_depth.nil? && @recursion_depth < 0
       return false if !@max_pages_to_scrape.nil? && @max_pages_to_scrape < 1
+      return false if !@url_paths_to_include.nil? && @url_paths_to_include.length > 10
       true
     end
 
@@ -248,6 +265,16 @@ module Carbon
       @max_pages_to_scrape = max_pages_to_scrape
     end
 
+    # Custom attribute writer method with validation
+    # @param [Object] url_paths_to_include Value to be assigned
+    def url_paths_to_include=(url_paths_to_include)
+      if !url_paths_to_include.nil? && url_paths_to_include.length > 10
+        fail ArgumentError, 'invalid value for "url_paths_to_include", number of items must be less than or equal to 10.'
+      end
+
+      @url_paths_to_include = url_paths_to_include
+    end
+
     # Checks equality by comparing each attribute.
     # @param [Object] Object to be compared
     def ==(o)
@@ -266,7 +293,8 @@ module Carbon
           html_tags_to_skip == o.html_tags_to_skip &&
           css_classes_to_skip == o.css_classes_to_skip &&
           css_selectors_to_skip == o.css_selectors_to_skip &&
-          embedding_model == o.embedding_model
+          embedding_model == o.embedding_model &&
+          url_paths_to_include == o.url_paths_to_include
     end
 
     # @see the `==` method
@@ -278,7 +306,7 @@ module Carbon
     # Calculates hash code according to all attributes.
     # @return [Integer] Hash code
     def hash
-      [tags, url, recursion_depth, max_pages_to_scrape, chunk_size, chunk_overlap, skip_embedding_generation, enable_auto_sync, generate_sparse_vectors, prepend_filename_to_chunks, html_tags_to_skip, css_classes_to_skip, css_selectors_to_skip, embedding_model].hash
+      [tags, url, recursion_depth, max_pages_to_scrape, chunk_size, chunk_overlap, skip_embedding_generation, enable_auto_sync, generate_sparse_vectors, prepend_filename_to_chunks, html_tags_to_skip, css_classes_to_skip, css_selectors_to_skip, embedding_model, url_paths_to_include].hash
     end
 
     # Builds the object from hash

data/lib/carbon_ruby_sdk/version.rb

@@ -7,5 +7,5 @@ The version of the OpenAPI document: 1.0.0
 =end
 
 module Carbon
-  VERSION = '0.2.2'
+  VERSION = '0.2.3'
 end

data/spec/models/sitemap_scrape_request_spec.rb

@@ -97,4 +97,16 @@ describe Carbon::SitemapScrapeRequest do
     end
   end
 
+  describe 'test attribute "url_paths_to_include"' do
+    it 'should work' do
+      # assertion here. ref: https://www.relishapp.com/rspec/rspec-expectations/docs/built-in-matchers
+    end
+  end
+
+  describe 'test attribute "url_paths_to_exclude"' do
+    it 'should work' do
+      # assertion here. ref: https://www.relishapp.com/rspec/rspec-expectations/docs/built-in-matchers
+    end
+  end
+
 end

data/spec/models/webscrape_request_spec.rb

@@ -103,4 +103,10 @@ describe Carbon::WebscrapeRequest do
     end
   end
 
+  describe 'test attribute "url_paths_to_include"' do
+    it 'should work' do
+      # assertion here. ref: https://www.relishapp.com/rspec/rspec-expectations/docs/built-in-matchers
+    end
+  end
+
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: carbon_ruby_sdk
 version: !ruby/object:Gem::Version
-  version: 0.2.2
+  version: 0.2.3
 platform: ruby
 authors:
 - Konfig
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-06-01 00:00:00.000000000 Z
+date: 2024-06-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: faraday