carbon_ruby_sdk 0.2.33 → 0.2.35

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 77d46a687aaa46c1584184d14fd6543a88d8dd1712307d0b029797d57b20b8d2
-  data.tar.gz: a3984f2b2cc3a0f0c169c3d2fcf28f07c10a4377335a83ea86f9dcc0068f8334
+  metadata.gz: b8d6fb0f54090c63643bf089a081d545764e9b889db47e92849544392a941e39
+  data.tar.gz: 923f95de1ae3793c444c1b02e1f0cbd09f7c657d1bddde13567146fdeb515d42
 SHA512:
-  metadata.gz: 70b48fcec1456a51a1b8bc3ac5d426ad4b5f641437f6432ad8cc29dcb9f53882f6b225689899684171c15c27d6a6037c6f5cfc504d66c0c7a5bb99c22c0d9a75
-  data.tar.gz: d29777938d2828f6c8d74bf1005448b07c7c87c10da5b9dde987f33a8a758dda62fd4d3433a0e1b2b7d075c981fefaee1e26aad5d2b0eacc144f61769cdbac8f
+  metadata.gz: '05565949db79a7439f2ff6acaf8c42e51ebf4b64ff54d835b4d508181b2b201a472185f4db8922fe801a53b17e650bd48765936c258c78b1a95b657bf3373494'
+  data.tar.gz: d252a3df6a15280c315dffdadfa2cf0ed2f22a54e2f8e8fe5e43a04f85981c6c25f614ecde43893a9f1329e20d3e3e0a9b30ed563250581f085948395496fb30

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    carbon_ruby_sdk (0.2.33)
+    carbon_ruby_sdk (0.2.35)
       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-v0.2.33-blue)](https://rubygems.org/gems/carbon_ruby_sdk/versions/0.2.33)
+[![npm](https://img.shields.io/badge/gem-v0.2.35-blue)](https://rubygems.org/gems/carbon_ruby_sdk/versions/0.2.35)
 
 </div>
 
@@ -56,6 +56,8 @@ Connect external data to LLMs, no matter the source.
   * [`carbon.integrations.list_labels`](#carbonintegrationslist_labels)
   * [`carbon.integrations.list_outlook_categories`](#carbonintegrationslist_outlook_categories)
   * [`carbon.integrations.list_repos`](#carbonintegrationslist_repos)
+  * [`carbon.integrations.sync_azure_blob_files`](#carbonintegrationssync_azure_blob_files)
+  * [`carbon.integrations.sync_azure_blob_storage`](#carbonintegrationssync_azure_blob_storage)
   * [`carbon.integrations.sync_confluence`](#carbonintegrationssync_confluence)
   * [`carbon.integrations.sync_data_source_items`](#carbonintegrationssync_data_source_items)
   * [`carbon.integrations.sync_files`](#carbonintegrationssync_files)
@@ -94,7 +96,7 @@ Connect external data to LLMs, no matter the source.
 Add to Gemfile:
 
 ```ruby
-gem 'carbon_ruby_sdk', '~> 0.2.33'
+gem 'carbon_ruby_sdk', '~> 0.2.35'
 ```
 
 ## Getting Started<a id="getting-started"></a>
@@ -1080,6 +1082,7 @@ result = carbon.files.resync(
   chunk_size: 1,
   chunk_overlap: 1,
   force_embedding_generation: false,
+  skip_file_processing: false,
 )
 p result
 ```
@@ -1090,6 +1093,7 @@ p result
 ##### chunk_size: `Integer`<a id="chunk_size-integer"></a>
 ##### chunk_overlap: `Integer`<a id="chunk_overlap-integer"></a>
 ##### force_embedding_generation: `Boolean`<a id="force_embedding_generation-boolean"></a>
+##### skip_file_processing: `Boolean`<a id="skip_file_processing-boolean"></a>
 #### 🔄 Return<a id="🔄-return"></a>
 
 [UserFile](./lib/carbon_ruby_sdk/models/user_file.rb)
@@ -1479,6 +1483,7 @@ result = carbon.integrations.connect_freshdesk(
         "include_speaker_labels" => false,
         "split_rows" => false,
         "generate_chunks_only" => false,
+        "skip_file_processing" => false,
     },
 )
 p result
@@ -1538,6 +1543,16 @@ result = carbon.integrations.connect_gitbook(
   sync_files_on_connection: true,
   request_id: "string_example",
   sync_source_items: true,
+  file_sync_config: {
+        "auto_synced_source_types" => ["ARTICLE"],
+        "sync_attachments" => false,
+        "detect_audio_language" => false,
+        "transcription_service" => "assemblyai",
+        "include_speaker_labels" => false,
+        "split_rows" => false,
+        "generate_chunks_only" => false,
+        "skip_file_processing" => false,
+    },
 )
 p result
 ```
@@ -1559,6 +1574,7 @@ p result
 Enabling this flag will fetch all available content from the source to be listed
 via list items endpoint
 
+##### file_sync_config: [`FileSyncConfigNullable`](./lib/carbon_ruby_sdk/models/file_sync_config_nullable.rb)<a id="file_sync_config-filesyncconfignullablelibcarbon_ruby_sdkmodelsfile_sync_config_nullablerb"></a>
 #### 🔄 Return<a id="🔄-return"></a>
 
 [GenericSuccessResponse](./lib/carbon_ruby_sdk/models/generic_success_response.rb)
@@ -1601,6 +1617,7 @@ result = carbon.integrations.connect_guru(
         "include_speaker_labels" => false,
         "split_rows" => false,
         "generate_chunks_only" => false,
+        "skip_file_processing" => false,
     },
 )
 p result
@@ -1732,6 +1749,7 @@ result = carbon.integrations.get_oauth_url(
         "include_speaker_labels" => false,
         "split_rows" => false,
         "generate_chunks_only" => false,
+        "skip_file_processing" => false,
     },
   automatically_open_file_picker: true,
   gong_account_email: "string_example",
@@ -2080,6 +2098,129 @@ p result
 ---
 
 
+### `carbon.integrations.sync_azure_blob_files`<a id="carbonintegrationssync_azure_blob_files"></a>
+
+After optionally loading the items via /integrations/items/sync and integrations/items/list, use the container name 
+and file name as the ID in this endpoint to sync them into Carbon. Additional parameters below can associate 
+data with the selected items or modify the sync behavior
+
+#### 🛠️ Usage<a id="🛠️-usage"></a>
+
+```ruby
+result = carbon.integrations.sync_azure_blob_files(
+  ids: [
+        {
+        }
+    ],
+  tags: {},
+  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: 1,
+  set_page_as_boundary: false,
+  data_source_id: 1,
+  request_id: "string_example",
+  use_ocr: false,
+  parse_pdf_tables_with_ocr: false,
+  file_sync_config: {
+        "auto_synced_source_types" => ["ARTICLE"],
+        "sync_attachments" => false,
+        "detect_audio_language" => false,
+        "transcription_service" => "assemblyai",
+        "include_speaker_labels" => false,
+        "split_rows" => false,
+        "generate_chunks_only" => false,
+        "skip_file_processing" => false,
+    },
+)
+p result
+```
+
+#### ⚙️ Parameters<a id="⚙️-parameters"></a>
+
+##### ids: Array<[`AzureBlobGetFileInput`](./lib/carbon_ruby_sdk/models/azure_blob_get_file_input.rb)><a id="ids-array"></a>
+##### tags: `Object`<a id="tags-object"></a>
+##### chunk_size: `Integer`<a id="chunk_size-integer"></a>
+##### chunk_overlap: `Integer`<a id="chunk_overlap-integer"></a>
+##### skip_embedding_generation: `Boolean`<a id="skip_embedding_generation-boolean"></a>
+##### embedding_model: [`EmbeddingGenerators`](./lib/carbon_ruby_sdk/models/embedding_generators.rb)<a id="embedding_model-embeddinggeneratorslibcarbon_ruby_sdkmodelsembedding_generatorsrb"></a>
+##### generate_sparse_vectors: `Boolean`<a id="generate_sparse_vectors-boolean"></a>
+##### prepend_filename_to_chunks: `Boolean`<a id="prepend_filename_to_chunks-boolean"></a>
+##### max_items_per_chunk: `Integer`<a id="max_items_per_chunk-integer"></a>
+Number of objects per chunk. For csv, tsv, xlsx, and json files only.
+
+##### set_page_as_boundary: `Boolean`<a id="set_page_as_boundary-boolean"></a>
+##### data_source_id: `Integer`<a id="data_source_id-integer"></a>
+##### request_id: `String`<a id="request_id-string"></a>
+##### use_ocr: `Boolean`<a id="use_ocr-boolean"></a>
+##### parse_pdf_tables_with_ocr: `Boolean`<a id="parse_pdf_tables_with_ocr-boolean"></a>
+##### file_sync_config: [`FileSyncConfigNullable`](./lib/carbon_ruby_sdk/models/file_sync_config_nullable.rb)<a id="file_sync_config-filesyncconfignullablelibcarbon_ruby_sdkmodelsfile_sync_config_nullablerb"></a>
+#### 🔄 Return<a id="🔄-return"></a>
+
+[GenericSuccessResponse](./lib/carbon_ruby_sdk/models/generic_success_response.rb)
+
+#### 🌐 Endpoint<a id="🌐-endpoint"></a>
+
+`/integrations/azure_blob_storage/files` `POST`
+
+[🔙 **Back to Table of Contents**](#table-of-contents)
+
+---
+
+
+### `carbon.integrations.sync_azure_blob_storage`<a id="carbonintegrationssync_azure_blob_storage"></a>
+
+This endpoint can be used to connect Azure Blob Storage.
+
+For Azure Blob Storage, follow these steps:
+<ol>
+  <li>Create a new Azure Storage account and grant the following permissions:
+    <ul>
+      <li>List containers.</li>
+      <li>Read from specific containers and blobs to sync with Carbon. Ensure any future containers or blobs carry the same permissions.</li>
+    </ul>
+  </li>
+  <li>Generate a shared access signature (SAS) token or an access key for the storage account.</li>
+</ol>
+
+Once created, provide us with the following details to generate the connection URL:
+<ol>
+  <li>Storage Account KeyName.</li>
+  <li>Storage Account Name.</li>
+</ol>
+
+#### 🛠️ Usage<a id="🛠️-usage"></a>
+
+```ruby
+result = carbon.integrations.sync_azure_blob_storage(
+  account_name: "string_example",
+  account_key: "string_example",
+  sync_source_items: true,
+)
+p result
+```
+
+#### ⚙️ Parameters<a id="⚙️-parameters"></a>
+
+##### account_name: `String`<a id="account_name-string"></a>
+##### account_key: `String`<a id="account_key-string"></a>
+##### sync_source_items: `Boolean`<a id="sync_source_items-boolean"></a>
+#### 🔄 Return<a id="🔄-return"></a>
+
+[OrganizationUserDataSourceAPI](./lib/carbon_ruby_sdk/models/organization_user_data_source_api.rb)
+
+#### 🌐 Endpoint<a id="🌐-endpoint"></a>
+
+`/integrations/azure_blob_storage` `POST`
+
+[🔙 **Back to Table of Contents**](#table-of-contents)
+
+---
+
+
 ### `carbon.integrations.sync_confluence`<a id="carbonintegrationssync_confluence"></a>
 ![Deprecated](https://img.shields.io/badge/deprecated-yellow)
 
@@ -2119,6 +2260,7 @@ result = carbon.integrations.sync_confluence(
         "include_speaker_labels" => false,
         "split_rows" => false,
         "generate_chunks_only" => false,
+        "skip_file_processing" => false,
     },
 )
 p result
@@ -2227,6 +2369,7 @@ result = carbon.integrations.sync_files(
         "include_speaker_labels" => false,
         "split_rows" => false,
         "generate_chunks_only" => false,
+        "skip_file_processing" => false,
     },
 )
 p result
@@ -2329,6 +2472,16 @@ result = carbon.integrations.sync_gitbook(
   generate_sparse_vectors: false,
   prepend_filename_to_chunks: false,
   request_id: "string_example",
+  file_sync_config: {
+        "auto_synced_source_types" => ["ARTICLE"],
+        "sync_attachments" => false,
+        "detect_audio_language" => false,
+        "transcription_service" => "assemblyai",
+        "include_speaker_labels" => false,
+        "split_rows" => false,
+        "generate_chunks_only" => false,
+        "skip_file_processing" => false,
+    },
 )
 p result
 ```
@@ -2345,6 +2498,7 @@ p result
 ##### generate_sparse_vectors: `Boolean`<a id="generate_sparse_vectors-boolean"></a>
 ##### prepend_filename_to_chunks: `Boolean`<a id="prepend_filename_to_chunks-boolean"></a>
 ##### request_id: `String`<a id="request_id-string"></a>
+##### file_sync_config: [`FileSyncConfigNullable`](./lib/carbon_ruby_sdk/models/file_sync_config_nullable.rb)<a id="file_sync_config-filesyncconfignullablelibcarbon_ruby_sdkmodelsfile_sync_config_nullablerb"></a>
 #### 🌐 Endpoint<a id="🌐-endpoint"></a>
 
 `/integrations/gitbook/sync` `POST`
@@ -2434,6 +2588,7 @@ result = carbon.integrations.sync_gmail(
         "include_speaker_labels" => false,
         "split_rows" => false,
         "generate_chunks_only" => false,
+        "skip_file_processing" => false,
     },
   incremental_sync: false,
 )
@@ -2556,6 +2711,7 @@ result = carbon.integrations.sync_outlook(
         "include_speaker_labels" => false,
         "split_rows" => false,
         "generate_chunks_only" => false,
+        "skip_file_processing" => false,
     },
   incremental_sync: false,
 )
@@ -2702,6 +2858,7 @@ result = carbon.integrations.sync_s3_files(
         "include_speaker_labels" => false,
         "split_rows" => false,
         "generate_chunks_only" => false,
+        "skip_file_processing" => false,
     },
 )
 p result

data/lib/carbon_ruby_sdk/api/files_api.rb

@@ -1231,14 +1231,16 @@ module Carbon
     # @param chunk_size [Integer] 
     # @param chunk_overlap [Integer] 
     # @param force_embedding_generation [Boolean] 
+    # @param skip_file_processing [Boolean] 
     # @param body [ResyncFileQueryInput] 
     # @param [Hash] extra additional parameters to pass along through :header_params, :query_params, or parameter name
-    def resync(file_id:, chunk_size: SENTINEL, chunk_overlap: SENTINEL, force_embedding_generation: false, extra: {})
+    def resync(file_id:, chunk_size: SENTINEL, chunk_overlap: SENTINEL, force_embedding_generation: false, skip_file_processing: false, extra: {})
       _body = {}
       _body[:file_id] = file_id if file_id != SENTINEL
       _body[:chunk_size] = chunk_size if chunk_size != SENTINEL
       _body[:chunk_overlap] = chunk_overlap if chunk_overlap != SENTINEL
       _body[:force_embedding_generation] = force_embedding_generation if force_embedding_generation != SENTINEL
+      _body[:skip_file_processing] = skip_file_processing if skip_file_processing != SENTINEL
       resync_file_query_input = _body
       api_response = resync_with_http_info_impl(resync_file_query_input, extra)
       api_response.data
@@ -1250,14 +1252,16 @@ module Carbon
     # @param chunk_size [Integer] 
     # @param chunk_overlap [Integer] 
     # @param force_embedding_generation [Boolean] 
+    # @param skip_file_processing [Boolean] 
     # @param body [ResyncFileQueryInput] 
     # @param [Hash] extra additional parameters to pass along through :header_params, :query_params, or parameter name
-    def resync_with_http_info(file_id:, chunk_size: SENTINEL, chunk_overlap: SENTINEL, force_embedding_generation: false, extra: {})
+    def resync_with_http_info(file_id:, chunk_size: SENTINEL, chunk_overlap: SENTINEL, force_embedding_generation: false, skip_file_processing: false, extra: {})
       _body = {}
       _body[:file_id] = file_id if file_id != SENTINEL
       _body[:chunk_size] = chunk_size if chunk_size != SENTINEL
       _body[:chunk_overlap] = chunk_overlap if chunk_overlap != SENTINEL
       _body[:force_embedding_generation] = force_embedding_generation if force_embedding_generation != SENTINEL
+      _body[:skip_file_processing] = skip_file_processing if skip_file_processing != SENTINEL
       resync_file_query_input = _body
       resync_with_http_info_impl(resync_file_query_input, extra)
     end