carbon_ruby_sdk 0.2.16 → 0.2.18

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 60c08043b97e6964d1c87a7461e6e93a0cff8c7db0fa98be4e0dd2991540a0cf
-  data.tar.gz: a6b5dd7321fb52625d1e8f3c1acbaa1ec6165412980c1cd679b083dfb5dced35
+  metadata.gz: 621a55f88f43768897cf3086257a2c73bb47a8417043d4576e9097069c979a75
+  data.tar.gz: 8a19d96655e5c7230b5dc1d4d34ed2faae53b270e78a973ffae5396041c8ed40
 SHA512:
-  metadata.gz: '07691a370c7f1e6a94e6a9974451e301cd2fe2150c2b5b4618c970a608eef457c42194935ccc8eb718112eb7fee4ab39f746bee654def58d2c50d109e0dd6499'
-  data.tar.gz: 75acc5f7eb04e965000af6070ba92aa82c47ff65f2ee378ff745b38b9357e101c3493c9d645bd14a361f13c3938ff1a3d6ae1104ad1cd8a694c0e6284cf0259a
+  metadata.gz: 610cc7b260e629e544ae15e90b0120276403d5beb06936613b6cc7956272a3761c596ad8d8cb34ad2d91b66b1ba55ebdf25fcf2606139ea3976eae842bb98823
+  data.tar.gz: 8d082ccc3c69fe4b64f47462f3b97cfab0ea508b2cba1cac9db5efc4975461f823d40c39a5ce9e610d09a3ab37a20397770fd6d634c7bb54c32d24587ab2b32a

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    carbon_ruby_sdk (0.2.16)
+    carbon_ruby_sdk (0.2.17)
       faraday (>= 1.0.1, < 3.0)
       faraday-multipart (~> 1.0, >= 1.0.4)
 
@@ -15,9 +15,8 @@ GEM
       irb (>= 1.5.0)
       reline (>= 0.3.1)
     diff-lcs (1.5.1)
-    faraday (2.10.0)
+    faraday (2.9.0)
       faraday-net_http (>= 2.0, < 3.2)
-      logger
     faraday-multipart (1.0.4)
       multipart-post (~> 2)
     faraday-net_http (3.1.0)
@@ -25,13 +24,12 @@ GEM
     io-console (0.7.2)
     irb (1.6.4)
       reline (>= 0.3.0)
-    logger (1.6.0)
-    method_source (1.1.0)
-    multipart-post (2.4.1)
+    method_source (1.0.0)
+    multipart-post (2.4.0)
     net-http (0.4.1)
       uri
-    parallel (1.25.1)
-    parser (3.3.4.0)
+    parallel (1.24.0)
+    parser (3.3.0.5)
       ast (~> 2.4.1)
       racc
     pry (0.14.2)
@@ -40,24 +38,23 @@ GEM
     pry-byebug (3.10.1)
       byebug (~> 11.0)
       pry (>= 0.13, < 0.15)
-    racc (1.8.0)
+    racc (1.7.3)
     rainbow (3.1.1)
     rake (13.0.6)
-    regexp_parser (2.9.2)
-    reline (0.5.9)
+    regexp_parser (2.9.0)
+    reline (0.5.0)
       io-console (~> 0.5)
-    rexml (3.3.2)
-      strscan
+    rexml (3.2.6)
     rspec (3.13.0)
       rspec-core (~> 3.13.0)
       rspec-expectations (~> 3.13.0)
       rspec-mocks (~> 3.13.0)
     rspec-core (3.13.0)
       rspec-support (~> 3.13.0)
-    rspec-expectations (3.13.1)
+    rspec-expectations (3.13.0)
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.13.0)
-    rspec-mocks (3.13.1)
+    rspec-mocks (3.13.0)
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.13.0)
     rspec-support (3.13.1)
@@ -70,15 +67,14 @@ GEM
       rubocop-ast (>= 1.2.0, < 2.0)
       ruby-progressbar (~> 1.7)
       unicode-display_width (>= 1.4.0, < 3.0)
-    rubocop-ast (1.31.3)
-      parser (>= 3.3.1.0)
+    rubocop-ast (1.31.2)
+      parser (>= 3.3.0.4)
     ruby-progressbar (1.13.0)
-    strscan (3.1.0)
     unicode-display_width (2.5.0)
     uri (0.13.0)
 
 PLATFORMS
-  arm64-darwin-21
+  arm64-darwin-22
 
 DEPENDENCIES
   carbon_ruby_sdk!
@@ -90,4 +86,4 @@ DEPENDENCIES
   rubocop (~> 1.12.1)
 
 BUNDLED WITH
-   2.3.7
+   2.4.19

data/README.md

@@ -6,7 +6,7 @@
 
 Connect external data to LLMs, no matter the source.
 
-[![npm](https://img.shields.io/badge/gem-v0.2.16-blue)](https://rubygems.org/gems/carbon_ruby_sdk/versions/0.2.16)
+[![npm](https://img.shields.io/badge/gem-v0.2.18-blue)](https://rubygems.org/gems/carbon_ruby_sdk/versions/0.2.18)
 
 </div>
 
@@ -91,7 +91,7 @@ Connect external data to LLMs, no matter the source.
 Add to Gemfile:
 
 ```ruby
-gem 'carbon_ruby_sdk', '~> 0.2.16'
+gem 'carbon_ruby_sdk', '~> 0.2.18'
 ```
 
 ## Getting Started<a id="getting-started"></a>
@@ -385,6 +385,9 @@ result = carbon.embeddings.get_documents(
   rerank: {
         "model" => "model_example",
     },
+  file_types_at_source: [
+        "string_example"
+    ],
 )
 p result
 ```
@@ -449,6 +452,10 @@ default, this is set to false. If true, the search may return more accurate
 results, but may take longer to complete.
 
 ##### rerank: [`RerankParamsNullable`](./lib/carbon_ruby_sdk/models/rerank_params_nullable.rb)<a id="rerank-rerankparamsnullablelibcarbon_ruby_sdkmodelsrerank_params_nullablerb"></a>
+##### file_types_at_source: Array<[`HelpdeskFileTypes`](./lib/carbon_ruby_sdk/models/helpdesk_file_types.rb)><a id="file_types_at_source-array"></a>
+Filter files based on their type at the source (for example help center tickets
+and articles)
+
 #### 🔄 Return<a id="🔄-return"></a>
 
 [DocumentResponseList](./lib/carbon_ruby_sdk/models/document_response_list.rb)
@@ -1071,6 +1078,7 @@ result = carbon.files.upload(
   max_items_per_chunk: 1,
   parse_pdf_tables_with_ocr: false,
   detect_audio_language: false,
+  transcription_service: "assemblyai",
   media_type: "TEXT",
   split_rows: false,
 )
@@ -1118,6 +1126,10 @@ Whether to use rich table parsing when `use_ocr` is enabled.
 ##### detect_audio_language: `Boolean`<a id="detect_audio_language-boolean"></a>
 Whether to automatically detect the language of the uploaded audio file.
 
+##### transcription_service: [`TranscriptionServiceNullable`](./lib/carbon_ruby_sdk/models/transcription_service_nullable.rb)<a id="transcription_service-transcriptionservicenullablelibcarbon_ruby_sdkmodelstranscription_service_nullablerb"></a>
+The transcription service to use for audio files. If no service is specified,
+'deepgram' will be used.
+
 ##### media_type: [`FileContentTypesNullable`](./lib/carbon_ruby_sdk/models/file_content_types_nullable.rb)<a id="media_type-filecontenttypesnullablelibcarbon_ruby_sdkmodelsfile_content_types_nullablerb"></a>
 The media type of the file. If not provided, it will be inferred from the file
 extension.
@@ -1160,6 +1172,7 @@ result = carbon.files.upload_from_url(
   max_items_per_chunk: 1,
   parse_pdf_tables_with_ocr: false,
   detect_audio_language: false,
+  transcription_service: "assemblyai",
   media_type: "TEXT",
   split_rows: false,
 )
@@ -1183,6 +1196,7 @@ Number of objects per chunk. For csv, tsv, xlsx, and json files only.
 
 ##### parse_pdf_tables_with_ocr: `Boolean`<a id="parse_pdf_tables_with_ocr-boolean"></a>
 ##### detect_audio_language: `Boolean`<a id="detect_audio_language-boolean"></a>
+##### transcription_service: [`TranscriptionServiceNullable`](./lib/carbon_ruby_sdk/models/transcription_service_nullable.rb)<a id="transcription_service-transcriptionservicenullablelibcarbon_ruby_sdkmodelstranscription_service_nullablerb"></a>
 ##### media_type: [`FileContentTypesNullable`](./lib/carbon_ruby_sdk/models/file_content_types_nullable.rb)<a id="media_type-filecontenttypesnullablelibcarbon_ruby_sdkmodelsfile_content_types_nullablerb"></a>
 ##### split_rows: `Boolean`<a id="split_rows-boolean"></a>
 #### 🔄 Return<a id="🔄-return"></a>
@@ -1300,7 +1314,7 @@ result = carbon.integrations.connect_data_source(
         "prepend_filename_to_chunks" => false,
         "sync_files_on_connection" => true,
         "set_page_as_boundary" => false,
-        "request_id" => "e38a7eee-02b7-4f73-be14-ea9bb1f09e85",
+        "request_id" => "f5e8c193-f7e1-4e45-9be5-6aa157dfe3c3",
         "enable_file_picker" => true,
         "sync_source_items" => true,
         "incremental_sync" => false,
@@ -1354,6 +1368,7 @@ result = carbon.integrations.connect_freshdesk(
         "auto_synced_source_types" => ["ARTICLE"],
         "sync_attachments" => false,
         "detect_audio_language" => false,
+        "transcription_service" => "assemblyai",
         "split_rows" => false,
     },
 )
@@ -1520,7 +1535,7 @@ result = carbon.integrations.get_oauth_url(
   set_page_as_boundary: false,
   data_source_id: 1,
   connecting_new_account: false,
-  request_id: "e5fd53f8-ed96-474a-ba66-1fc1948facdf",
+  request_id: "c4055754-ba2d-4f57-a990-6e990abbbd90",
   use_ocr: false,
   parse_pdf_tables_with_ocr: false,
   enable_file_picker: true,
@@ -1530,6 +1545,7 @@ result = carbon.integrations.get_oauth_url(
         "auto_synced_source_types" => ["ARTICLE"],
         "sync_attachments" => false,
         "detect_audio_language" => false,
+        "transcription_service" => "assemblyai",
         "split_rows" => false,
     },
 )
@@ -1581,7 +1597,7 @@ 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:
-BOX, ONEDRIVE, DROPBOX, SHAREPOINT, GOOGLE_DRIVE
+BOX, DROPBOX, GOOGLE_DRIVE, ONEDRIVE, SHAREPOINT
 
 ##### 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
@@ -1887,7 +1903,7 @@ result = carbon.integrations.sync_confluence(
   prepend_filename_to_chunks: false,
   max_items_per_chunk: 1,
   set_page_as_boundary: false,
-  request_id: "77b56048-a895-4377-b0d3-e190d1b7de32",
+  request_id: "991e89b6-1e71-41e1-bdc4-4dd475f21696",
   use_ocr: false,
   parse_pdf_tables_with_ocr: false,
   incremental_sync: false,
@@ -1895,6 +1911,7 @@ result = carbon.integrations.sync_confluence(
         "auto_synced_source_types" => ["ARTICLE"],
         "sync_attachments" => false,
         "detect_audio_language" => false,
+        "transcription_service" => "assemblyai",
         "split_rows" => false,
     },
 )
@@ -1992,7 +2009,7 @@ result = carbon.integrations.sync_files(
   prepend_filename_to_chunks: false,
   max_items_per_chunk: 1,
   set_page_as_boundary: false,
-  request_id: "77b56048-a895-4377-b0d3-e190d1b7de32",
+  request_id: "991e89b6-1e71-41e1-bdc4-4dd475f21696",
   use_ocr: false,
   parse_pdf_tables_with_ocr: false,
   incremental_sync: false,
@@ -2000,6 +2017,7 @@ result = carbon.integrations.sync_files(
         "auto_synced_source_types" => ["ARTICLE"],
         "sync_attachments" => false,
         "detect_audio_language" => false,
+        "transcription_service" => "assemblyai",
         "split_rows" => false,
     },
 )
@@ -2202,6 +2220,7 @@ result = carbon.integrations.sync_gmail(
         "auto_synced_source_types" => ["ARTICLE"],
         "sync_attachments" => false,
         "detect_audio_language" => false,
+        "transcription_service" => "assemblyai",
         "split_rows" => false,
     },
   incremental_sync: false,
@@ -2321,6 +2340,7 @@ result = carbon.integrations.sync_outlook(
         "auto_synced_source_types" => ["ARTICLE"],
         "sync_attachments" => false,
         "detect_audio_language" => false,
+        "transcription_service" => "assemblyai",
         "split_rows" => false,
     },
   incremental_sync: false,
@@ -2464,6 +2484,7 @@ result = carbon.integrations.sync_s3_files(
         "auto_synced_source_types" => ["ARTICLE"],
         "sync_attachments" => false,
         "detect_audio_language" => false,
+        "transcription_service" => "assemblyai",
         "split_rows" => false,
     },
 )

data/lib/carbon_ruby_sdk/api/embeddings_api.rb

@@ -131,9 +131,10 @@ module Carbon
     # @param include_file_level_metadata [Boolean] Flag to control whether or not to include file-level metadata in the response. This metadata will be included in the `content_metadata` field of each document along with chunk/embedding level metadata.
     # @param high_accuracy [Boolean] Flag to control whether or not to perform a high accuracy embedding search. By default, this is set to false. If true, the search may return more accurate results, but may take longer to complete.
     # @param rerank [RerankParamsNullable] 
+    # @param file_types_at_source [Array<HelpdeskFileTypes>] Filter files based on their type at the source (for example help center tickets and articles)
     # @param body [GetEmbeddingDocumentsBody] 
     # @param [Hash] extra additional parameters to pass along through :header_params, :query_params, or parameter name
-    def get_documents(query:, k:, tags: SENTINEL, query_vector: SENTINEL, file_ids: SENTINEL, parent_file_ids: SENTINEL, include_all_children: false, tags_v2: SENTINEL, include_tags: SENTINEL, include_vectors: SENTINEL, include_raw_file: SENTINEL, hybrid_search: SENTINEL, hybrid_search_tuning_parameters: SENTINEL, media_type: SENTINEL, embedding_model: 'OPENAI', include_file_level_metadata: false, high_accuracy: false, rerank: SENTINEL, extra: {})
+    def get_documents(query:, k:, tags: SENTINEL, query_vector: SENTINEL, file_ids: SENTINEL, parent_file_ids: SENTINEL, include_all_children: false, tags_v2: SENTINEL, include_tags: SENTINEL, include_vectors: SENTINEL, include_raw_file: SENTINEL, hybrid_search: SENTINEL, hybrid_search_tuning_parameters: SENTINEL, media_type: SENTINEL, embedding_model: 'OPENAI', include_file_level_metadata: false, high_accuracy: false, rerank: SENTINEL, file_types_at_source: SENTINEL, extra: {})
       _body = {}
       _body[:tags] = tags if tags != SENTINEL
       _body[:query] = query if query != SENTINEL
@@ -153,6 +154,7 @@ module Carbon
       _body[:include_file_level_metadata] = include_file_level_metadata if include_file_level_metadata != SENTINEL
       _body[:high_accuracy] = high_accuracy if high_accuracy != SENTINEL
       _body[:rerank] = rerank if rerank != SENTINEL
+      _body[:file_types_at_source] = file_types_at_source if file_types_at_source != SENTINEL
       get_embedding_documents_body = _body
       api_response = get_documents_with_http_info_impl(get_embedding_documents_body, extra)
       api_response.data
@@ -273,9 +275,10 @@ module Carbon
     # @param include_file_level_metadata [Boolean] Flag to control whether or not to include file-level metadata in the response. This metadata will be included in the `content_metadata` field of each document along with chunk/embedding level metadata.
     # @param high_accuracy [Boolean] Flag to control whether or not to perform a high accuracy embedding search. By default, this is set to false. If true, the search may return more accurate results, but may take longer to complete.
     # @param rerank [RerankParamsNullable] 
+    # @param file_types_at_source [Array<HelpdeskFileTypes>] Filter files based on their type at the source (for example help center tickets and articles)
     # @param body [GetEmbeddingDocumentsBody] 
     # @param [Hash] extra additional parameters to pass along through :header_params, :query_params, or parameter name
-    def get_documents_with_http_info(query:, k:, tags: SENTINEL, query_vector: SENTINEL, file_ids: SENTINEL, parent_file_ids: SENTINEL, include_all_children: false, tags_v2: SENTINEL, include_tags: SENTINEL, include_vectors: SENTINEL, include_raw_file: SENTINEL, hybrid_search: SENTINEL, hybrid_search_tuning_parameters: SENTINEL, media_type: SENTINEL, embedding_model: 'OPENAI', include_file_level_metadata: false, high_accuracy: false, rerank: SENTINEL, extra: {})
+    def get_documents_with_http_info(query:, k:, tags: SENTINEL, query_vector: SENTINEL, file_ids: SENTINEL, parent_file_ids: SENTINEL, include_all_children: false, tags_v2: SENTINEL, include_tags: SENTINEL, include_vectors: SENTINEL, include_raw_file: SENTINEL, hybrid_search: SENTINEL, hybrid_search_tuning_parameters: SENTINEL, media_type: SENTINEL, embedding_model: 'OPENAI', include_file_level_metadata: false, high_accuracy: false, rerank: SENTINEL, file_types_at_source: SENTINEL, extra: {})
       _body = {}
       _body[:tags] = tags if tags != SENTINEL
       _body[:query] = query if query != SENTINEL
@@ -295,6 +298,7 @@ module Carbon
       _body[:include_file_level_metadata] = include_file_level_metadata if include_file_level_metadata != SENTINEL
       _body[:high_accuracy] = high_accuracy if high_accuracy != SENTINEL
       _body[:rerank] = rerank if rerank != SENTINEL
+      _body[:file_types_at_source] = file_types_at_source if file_types_at_source != SENTINEL
       get_embedding_documents_body = _body
       get_documents_with_http_info_impl(get_embedding_documents_body, extra)
     end

data/lib/carbon_ruby_sdk/api/files_api.rb

@@ -1177,11 +1177,12 @@ module Carbon
     # @param max_items_per_chunk [Integer] Number of objects per chunk. For csv, tsv, xlsx, and json files only.
     # @param parse_pdf_tables_with_ocr [Boolean] Whether to use rich table parsing when `use_ocr` is enabled.
     # @param detect_audio_language [Boolean] Whether to automatically detect the language of the uploaded audio file.
+    # @param transcription_service [TranscriptionServiceNullable] The transcription service to use for audio files. If no service is specified, 'deepgram' will be used.
     # @param media_type [FileContentTypesNullable] The media type of the file. If not provided, it will be inferred from the file extension.
     # @param split_rows [Boolean] Whether to split tabular rows into chunks. Currently only valid for CSV, TSV, and XLSX files.
     # @param body [BodyCreateUploadFileUploadfilePost] 
     # @param [Hash] extra additional parameters to pass along through :header_params, :query_params, or parameter name
-    def upload(file:, chunk_size: SENTINEL, chunk_overlap: SENTINEL, skip_embedding_generation: false, set_page_as_boundary: false, embedding_model: 'OPENAI', use_ocr: false, generate_sparse_vectors: false, prepend_filename_to_chunks: false, max_items_per_chunk: SENTINEL, parse_pdf_tables_with_ocr: false, detect_audio_language: false, media_type: SENTINEL, split_rows: false, extra: {})
+    def upload(file:, chunk_size: SENTINEL, chunk_overlap: SENTINEL, skip_embedding_generation: false, set_page_as_boundary: false, embedding_model: 'OPENAI', use_ocr: false, generate_sparse_vectors: false, prepend_filename_to_chunks: false, max_items_per_chunk: SENTINEL, parse_pdf_tables_with_ocr: false, detect_audio_language: false, transcription_service: SENTINEL, media_type: SENTINEL, split_rows: false, extra: {})
       _body = {}
       _body[:file] = file if file != SENTINEL
       body_create_upload_file_uploadfile_post = _body
@@ -1196,6 +1197,7 @@ module Carbon
       extra[:max_items_per_chunk] = max_items_per_chunk if max_items_per_chunk != SENTINEL
       extra[:parse_pdf_tables_with_ocr] = parse_pdf_tables_with_ocr if parse_pdf_tables_with_ocr != SENTINEL
       extra[:detect_audio_language] = detect_audio_language if detect_audio_language != SENTINEL
+      extra[:transcription_service] = transcription_service if transcription_service != SENTINEL
       extra[:media_type] = media_type if media_type != SENTINEL
       extra[:split_rows] = split_rows if split_rows != SENTINEL
       api_response = upload_with_http_info_impl(file, body_create_upload_file_uploadfile_post, extra)
@@ -1242,11 +1244,12 @@ module Carbon
     # @param max_items_per_chunk [Integer] Number of objects per chunk. For csv, tsv, xlsx, and json files only.
     # @param parse_pdf_tables_with_ocr [Boolean] Whether to use rich table parsing when `use_ocr` is enabled.
     # @param detect_audio_language [Boolean] Whether to automatically detect the language of the uploaded audio file.
+    # @param transcription_service [TranscriptionServiceNullable] The transcription service to use for audio files. If no service is specified, 'deepgram' will be used.
     # @param media_type [FileContentTypesNullable] The media type of the file. If not provided, it will be inferred from the file extension.
     # @param split_rows [Boolean] Whether to split tabular rows into chunks. Currently only valid for CSV, TSV, and XLSX files.
     # @param body [BodyCreateUploadFileUploadfilePost] 
     # @param [Hash] extra additional parameters to pass along through :header_params, :query_params, or parameter name
-    def upload_with_http_info(file:, chunk_size: SENTINEL, chunk_overlap: SENTINEL, skip_embedding_generation: false, set_page_as_boundary: false, embedding_model: 'OPENAI', use_ocr: false, generate_sparse_vectors: false, prepend_filename_to_chunks: false, max_items_per_chunk: SENTINEL, parse_pdf_tables_with_ocr: false, detect_audio_language: false, media_type: SENTINEL, split_rows: false, extra: {})
+    def upload_with_http_info(file:, chunk_size: SENTINEL, chunk_overlap: SENTINEL, skip_embedding_generation: false, set_page_as_boundary: false, embedding_model: 'OPENAI', use_ocr: false, generate_sparse_vectors: false, prepend_filename_to_chunks: false, max_items_per_chunk: SENTINEL, parse_pdf_tables_with_ocr: false, detect_audio_language: false, transcription_service: SENTINEL, media_type: SENTINEL, split_rows: false, extra: {})
       _body = {}
       _body[:file] = file if file != SENTINEL
       body_create_upload_file_uploadfile_post = _body
@@ -1261,6 +1264,7 @@ module Carbon
       extra[:max_items_per_chunk] = max_items_per_chunk if max_items_per_chunk != SENTINEL
       extra[:parse_pdf_tables_with_ocr] = parse_pdf_tables_with_ocr if parse_pdf_tables_with_ocr != SENTINEL
       extra[:detect_audio_language] = detect_audio_language if detect_audio_language != SENTINEL
+      extra[:transcription_service] = transcription_service if transcription_service != SENTINEL
       extra[:media_type] = media_type if media_type != SENTINEL
       extra[:split_rows] = split_rows if split_rows != SENTINEL
       upload_with_http_info_impl(file, body_create_upload_file_uploadfile_post, extra)
@@ -1282,6 +1286,7 @@ module Carbon
     # @option opts [Integer] :max_items_per_chunk Number of objects per chunk. For csv, tsv, xlsx, and json files only.
     # @option opts [Boolean] :parse_pdf_tables_with_ocr Whether to use rich table parsing when `use_ocr` is enabled. (default to false)
     # @option opts [Boolean] :detect_audio_language Whether to automatically detect the language of the uploaded audio file. (default to false)
+    # @option opts [TranscriptionServiceNullable] :transcription_service The transcription service to use for audio files. If no service is specified, 'deepgram' will be used.
     # @option opts [FileContentTypesNullable] :media_type The media type of the file. If not provided, it will be inferred from the file extension.
     # @option opts [Boolean] :split_rows Whether to split tabular rows into chunks. Currently only valid for CSV, TSV, and XLSX files. (default to false)
     # @return [UserFile]
@@ -1306,6 +1311,7 @@ module Carbon
     # @option opts [Integer] :max_items_per_chunk Number of objects per chunk. For csv, tsv, xlsx, and json files only.
     # @option opts [Boolean] :parse_pdf_tables_with_ocr Whether to use rich table parsing when `use_ocr` is enabled. (default to false)
     # @option opts [Boolean] :detect_audio_language Whether to automatically detect the language of the uploaded audio file. (default to false)
+    # @option opts [TranscriptionServiceNullable] :transcription_service The transcription service to use for audio files. If no service is specified, 'deepgram' will be used.
     # @option opts [FileContentTypesNullable] :media_type The media type of the file. If not provided, it will be inferred from the file extension.
     # @option opts [Boolean] :split_rows Whether to split tabular rows into chunks. Currently only valid for CSV, TSV, and XLSX files. (default to false)
     # @return [APIResponse] data is UserFile, status code, headers and response
@@ -1337,6 +1343,7 @@ module Carbon
       query_params[:'max_items_per_chunk'] = opts[:'max_items_per_chunk'] if !opts[:'max_items_per_chunk'].nil?
       query_params[:'parse_pdf_tables_with_ocr'] = opts[:'parse_pdf_tables_with_ocr'] if !opts[:'parse_pdf_tables_with_ocr'].nil?
       query_params[:'detect_audio_language'] = opts[:'detect_audio_language'] if !opts[:'detect_audio_language'].nil?
+      query_params[:'transcription_service'] = opts[:'transcription_service'] if !opts[:'transcription_service'].nil?
       query_params[:'media_type'] = opts[:'media_type'] if !opts[:'media_type'].nil?
       query_params[:'split_rows'] = opts[:'split_rows'] if !opts[:'split_rows'].nil?
 
@@ -1396,11 +1403,12 @@ module Carbon
     # @param max_items_per_chunk [Integer] Number of objects per chunk. For csv, tsv, xlsx, and json files only.
     # @param parse_pdf_tables_with_ocr [Boolean] 
     # @param detect_audio_language [Boolean] 
+    # @param transcription_service [TranscriptionServiceNullable] 
     # @param media_type [FileContentTypesNullable] 
     # @param split_rows [Boolean] 
     # @param body [UploadFileFromUrlInput] 
     # @param [Hash] extra additional parameters to pass along through :header_params, :query_params, or parameter name
-    def upload_from_url(url:, file_name: SENTINEL, chunk_size: SENTINEL, chunk_overlap: SENTINEL, skip_embedding_generation: false, set_page_as_boundary: false, embedding_model: 'OPENAI', generate_sparse_vectors: false, use_textract: false, prepend_filename_to_chunks: false, max_items_per_chunk: SENTINEL, parse_pdf_tables_with_ocr: false, detect_audio_language: false, media_type: SENTINEL, split_rows: false, extra: {})
+    def upload_from_url(url:, file_name: SENTINEL, chunk_size: SENTINEL, chunk_overlap: SENTINEL, skip_embedding_generation: false, set_page_as_boundary: false, embedding_model: 'OPENAI', generate_sparse_vectors: false, use_textract: false, prepend_filename_to_chunks: false, max_items_per_chunk: SENTINEL, parse_pdf_tables_with_ocr: false, detect_audio_language: false, transcription_service: SENTINEL, media_type: SENTINEL, split_rows: false, extra: {})
       _body = {}
       _body[:url] = url if url != SENTINEL
       _body[:file_name] = file_name if file_name != SENTINEL
@@ -1415,6 +1423,7 @@ module Carbon
       _body[:max_items_per_chunk] = max_items_per_chunk if max_items_per_chunk != SENTINEL
       _body[:parse_pdf_tables_with_ocr] = parse_pdf_tables_with_ocr if parse_pdf_tables_with_ocr != SENTINEL
       _body[:detect_audio_language] = detect_audio_language if detect_audio_language != SENTINEL
+      _body[:transcription_service] = transcription_service if transcription_service != SENTINEL
       _body[:media_type] = media_type if media_type != SENTINEL
       _body[:split_rows] = split_rows if split_rows != SENTINEL
       upload_file_from_url_input = _body
@@ -1437,11 +1446,12 @@ module Carbon
     # @param max_items_per_chunk [Integer] Number of objects per chunk. For csv, tsv, xlsx, and json files only.
     # @param parse_pdf_tables_with_ocr [Boolean] 
     # @param detect_audio_language [Boolean] 
+    # @param transcription_service [TranscriptionServiceNullable] 
     # @param media_type [FileContentTypesNullable] 
     # @param split_rows [Boolean] 
     # @param body [UploadFileFromUrlInput] 
     # @param [Hash] extra additional parameters to pass along through :header_params, :query_params, or parameter name
-    def upload_from_url_with_http_info(url:, file_name: SENTINEL, chunk_size: SENTINEL, chunk_overlap: SENTINEL, skip_embedding_generation: false, set_page_as_boundary: false, embedding_model: 'OPENAI', generate_sparse_vectors: false, use_textract: false, prepend_filename_to_chunks: false, max_items_per_chunk: SENTINEL, parse_pdf_tables_with_ocr: false, detect_audio_language: false, media_type: SENTINEL, split_rows: false, extra: {})
+    def upload_from_url_with_http_info(url:, file_name: SENTINEL, chunk_size: SENTINEL, chunk_overlap: SENTINEL, skip_embedding_generation: false, set_page_as_boundary: false, embedding_model: 'OPENAI', generate_sparse_vectors: false, use_textract: false, prepend_filename_to_chunks: false, max_items_per_chunk: SENTINEL, parse_pdf_tables_with_ocr: false, detect_audio_language: false, transcription_service: SENTINEL, media_type: SENTINEL, split_rows: false, extra: {})
       _body = {}
       _body[:url] = url if url != SENTINEL
       _body[:file_name] = file_name if file_name != SENTINEL
@@ -1456,6 +1466,7 @@ module Carbon
       _body[:max_items_per_chunk] = max_items_per_chunk if max_items_per_chunk != SENTINEL
       _body[:parse_pdf_tables_with_ocr] = parse_pdf_tables_with_ocr if parse_pdf_tables_with_ocr != SENTINEL
       _body[:detect_audio_language] = detect_audio_language if detect_audio_language != SENTINEL
+      _body[:transcription_service] = transcription_service if transcription_service != SENTINEL
       _body[:media_type] = media_type if media_type != SENTINEL
       _body[:split_rows] = split_rows if split_rows != SENTINEL
       upload_file_from_url_input = _body

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: BOX, ONEDRIVE, DROPBOX, SHAREPOINT, GOOGLE_DRIVE
+    # @param enable_file_picker [Boolean] Enable integration's file picker for sources that support it. Supported sources: BOX, DROPBOX, GOOGLE_DRIVE, ONEDRIVE, SHAREPOINT
     # @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, INTERCOM, GMAIL, OUTLOOK. 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: 'e5fd53f8-ed96-474a-ba66-1fc1948facdf', 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: 'c4055754-ba2d-4f57-a990-6e990abbbd90', 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: BOX, ONEDRIVE, DROPBOX, SHAREPOINT, GOOGLE_DRIVE
+    # @param enable_file_picker [Boolean] Enable integration's file picker for sources that support it. Supported sources: BOX, DROPBOX, GOOGLE_DRIVE, ONEDRIVE, SHAREPOINT
     # @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, INTERCOM, GMAIL, OUTLOOK. 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: 'e5fd53f8-ed96-474a-ba66-1fc1948facdf', 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: 'c4055754-ba2d-4f57-a990-6e990abbbd90', 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
@@ -1646,7 +1646,7 @@ 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: '77b56048-a895-4377-b0d3-e190d1b7de32', 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: '991e89b6-1e71-41e1-bdc4-4dd475f21696', 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
@@ -1696,7 +1696,7 @@ 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: '77b56048-a895-4377-b0d3-e190d1b7de32', 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: '991e89b6-1e71-41e1-bdc4-4dd475f21696', 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
@@ -1904,7 +1904,7 @@ 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: '77b56048-a895-4377-b0d3-e190d1b7de32', 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: '991e89b6-1e71-41e1-bdc4-4dd475f21696', 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
@@ -1952,7 +1952,7 @@ 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: '77b56048-a895-4377-b0d3-e190d1b7de32', 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: '991e89b6-1e71-41e1-bdc4-4dd475f21696', 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/models/file_sync_config.rb

@@ -20,6 +20,8 @@ module Carbon
     # Detect audio language before transcription for audio files
     attr_accessor :detect_audio_language
 
+    attr_accessor :transcription_service
+
     # Whether to split tabular rows into chunks. Currently only valid for CSV, TSV, and XLSX files.
     attr_accessor :split_rows
 
@@ -29,6 +31,7 @@ module Carbon
         :'auto_synced_source_types' => :'auto_synced_source_types',
         :'sync_attachments' => :'sync_attachments',
         :'detect_audio_language' => :'detect_audio_language',
+        :'transcription_service' => :'transcription_service',
         :'split_rows' => :'split_rows'
       }
     end
@@ -44,6 +47,7 @@ module Carbon
         :'auto_synced_source_types' => :'Array<HelpdeskFileTypes>',
         :'sync_attachments' => :'Boolean',
         :'detect_audio_language' => :'Boolean',
+        :'transcription_service' => :'TranscriptionServiceNullable',
         :'split_rows' => :'Boolean'
       }
     end
@@ -51,6 +55,7 @@ module Carbon
     # List of attributes with nullable: true
     def self.openapi_nullable
       Set.new([
+        :'transcription_service',
       ])
     end
 
@@ -87,6 +92,10 @@ module Carbon
         self.detect_audio_language = false
       end
 
+      if attributes.key?(:'transcription_service')
+        self.transcription_service = attributes[:'transcription_service']
+      end
+
       if attributes.key?(:'split_rows')
         self.split_rows = attributes[:'split_rows']
       else
@@ -115,6 +124,7 @@ module Carbon
           auto_synced_source_types == o.auto_synced_source_types &&
           sync_attachments == o.sync_attachments &&
           detect_audio_language == o.detect_audio_language &&
+          transcription_service == o.transcription_service &&
           split_rows == o.split_rows
     end
 
@@ -127,7 +137,7 @@ module Carbon
     # Calculates hash code according to all attributes.
     # @return [Integer] Hash code
     def hash
-      [auto_synced_source_types, sync_attachments, detect_audio_language, split_rows].hash
+      [auto_synced_source_types, sync_attachments, detect_audio_language, transcription_service, split_rows].hash
     end
 
     # Builds the object from hash

data/lib/carbon_ruby_sdk/models/file_sync_config_nullable.rb

@@ -21,6 +21,8 @@ module Carbon
     # Detect audio language before transcription for audio files
     attr_accessor :detect_audio_language
 
+    attr_accessor :transcription_service
+
     # Whether to split tabular rows into chunks. Currently only valid for CSV, TSV, and XLSX files.
     attr_accessor :split_rows
 
@@ -30,6 +32,7 @@ module Carbon
         :'auto_synced_source_types' => :'auto_synced_source_types',
         :'sync_attachments' => :'sync_attachments',
         :'detect_audio_language' => :'detect_audio_language',
+        :'transcription_service' => :'transcription_service',
         :'split_rows' => :'split_rows'
       }
     end
@@ -45,6 +48,7 @@ module Carbon
         :'auto_synced_source_types' => :'Array<HelpdeskFileTypes>',
         :'sync_attachments' => :'Boolean',
         :'detect_audio_language' => :'Boolean',
+        :'transcription_service' => :'TranscriptionServiceNullable',
         :'split_rows' => :'Boolean'
       }
     end
@@ -52,6 +56,7 @@ module Carbon
     # List of attributes with nullable: true
     def self.openapi_nullable
       Set.new([
+        :'transcription_service',
       ])
     end
 
@@ -88,6 +93,10 @@ module Carbon
         self.detect_audio_language = false
       end
 
+      if attributes.key?(:'transcription_service')
+        self.transcription_service = attributes[:'transcription_service']
+      end
+
       if attributes.key?(:'split_rows')
         self.split_rows = attributes[:'split_rows']
       else
@@ -116,6 +125,7 @@ module Carbon
           auto_synced_source_types == o.auto_synced_source_types &&
           sync_attachments == o.sync_attachments &&
           detect_audio_language == o.detect_audio_language &&
+          transcription_service == o.transcription_service &&
           split_rows == o.split_rows
     end
 
@@ -128,7 +138,7 @@ module Carbon
     # Calculates hash code according to all attributes.
     # @return [Integer] Hash code
     def hash
-      [auto_synced_source_types, sync_attachments, detect_audio_language, split_rows].hash
+      [auto_synced_source_types, sync_attachments, detect_audio_language, transcription_service, split_rows].hash
     end
 
     # Builds the object from hash