carbon_ruby_sdk 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/Gemfile +11 -0
- data/Gemfile.lock +89 -0
- data/README.md +2325 -0
- data/Rakefile +10 -0
- data/carbon_ruby_sdk.gemspec +39 -0
- data/header.png +0 -0
- data/lib/carbon_ruby_sdk/api/auth_api.rb +177 -0
- data/lib/carbon_ruby_sdk/api/data_sources_api.rb +217 -0
- data/lib/carbon_ruby_sdk/api/embeddings_api.rb +565 -0
- data/lib/carbon_ruby_sdk/api/files_api.rb +1526 -0
- data/lib/carbon_ruby_sdk/api/health_api.rb +92 -0
- data/lib/carbon_ruby_sdk/api/integrations_api.rb +2201 -0
- data/lib/carbon_ruby_sdk/api/organizations_api.rb +92 -0
- data/lib/carbon_ruby_sdk/api/users_api.rb +209 -0
- data/lib/carbon_ruby_sdk/api/utilities_api.rb +710 -0
- data/lib/carbon_ruby_sdk/api/webhooks_api.rb +296 -0
- data/lib/carbon_ruby_sdk/api_client.rb +436 -0
- data/lib/carbon_ruby_sdk/api_client_custom.rb +14 -0
- data/lib/carbon_ruby_sdk/api_error.rb +53 -0
- data/lib/carbon_ruby_sdk/configuration.rb +354 -0
- data/lib/carbon_ruby_sdk/models/add_webhook_props.rb +220 -0
- data/lib/carbon_ruby_sdk/models/body_create_upload_file_uploadfile_post.rb +220 -0
- data/lib/carbon_ruby_sdk/models/chunk_properties.rb +248 -0
- data/lib/carbon_ruby_sdk/models/chunk_properties_nullable.rb +248 -0
- data/lib/carbon_ruby_sdk/models/chunks_and_embeddings.rb +246 -0
- data/lib/carbon_ruby_sdk/models/chunks_and_embeddings_upload_input.rb +247 -0
- data/lib/carbon_ruby_sdk/models/data_source_last_sync_actions.rb +38 -0
- data/lib/carbon_ruby_sdk/models/data_source_sync_statuses.rb +38 -0
- data/lib/carbon_ruby_sdk/models/data_source_type.rb +76 -0
- data/lib/carbon_ruby_sdk/models/data_source_type_nullable.rb +76 -0
- data/lib/carbon_ruby_sdk/models/delete_files_query_input.rb +252 -0
- data/lib/carbon_ruby_sdk/models/directory_item.rb +266 -0
- data/lib/carbon_ruby_sdk/models/document_response.rb +328 -0
- data/lib/carbon_ruby_sdk/models/document_response_list.rb +222 -0
- data/lib/carbon_ruby_sdk/models/embedding_and_chunk.rb +256 -0
- data/lib/carbon_ruby_sdk/models/embedding_generators.rb +43 -0
- data/lib/carbon_ruby_sdk/models/embedding_generators_nullable.rb +43 -0
- data/lib/carbon_ruby_sdk/models/embedding_properties.rb +226 -0
- data/lib/carbon_ruby_sdk/models/embeddings_and_chunks_filters.rb +232 -0
- data/lib/carbon_ruby_sdk/models/embeddings_and_chunks_order_by_columns.rb +37 -0
- data/lib/carbon_ruby_sdk/models/embeddings_and_chunks_query_input.rb +262 -0
- data/lib/carbon_ruby_sdk/models/embeddings_and_chunks_response.rb +236 -0
- data/lib/carbon_ruby_sdk/models/external_file_sync_statuses.rb +43 -0
- data/lib/carbon_ruby_sdk/models/external_source_item.rb +420 -0
- data/lib/carbon_ruby_sdk/models/fetch_urls_response.rb +236 -0
- data/lib/carbon_ruby_sdk/models/file_content_types.rb +36 -0
- data/lib/carbon_ruby_sdk/models/file_content_types_nullable.rb +36 -0
- data/lib/carbon_ruby_sdk/models/file_formats.rb +76 -0
- data/lib/carbon_ruby_sdk/models/file_formats_nullable.rb +76 -0
- data/lib/carbon_ruby_sdk/models/file_statistics.rb +256 -0
- data/lib/carbon_ruby_sdk/models/file_statistics_nullable.rb +256 -0
- data/lib/carbon_ruby_sdk/models/fresh_desk_connect_request.rb +316 -0
- data/lib/carbon_ruby_sdk/models/generic_success_response.rb +220 -0
- data/lib/carbon_ruby_sdk/models/get_embedding_documents_body.rb +416 -0
- data/lib/carbon_ruby_sdk/models/gitbook_connect_request.rb +234 -0
- data/lib/carbon_ruby_sdk/models/gitbook_sync_request.rb +336 -0
- data/lib/carbon_ruby_sdk/models/gmail_sync_input.rb +301 -0
- data/lib/carbon_ruby_sdk/models/http_validation_error.rb +217 -0
- data/lib/carbon_ruby_sdk/models/hybrid_search_tuning_params.rb +234 -0
- data/lib/carbon_ruby_sdk/models/hybrid_search_tuning_params_nullable.rb +235 -0
- data/lib/carbon_ruby_sdk/models/list_data_source_items_request.rb +239 -0
- data/lib/carbon_ruby_sdk/models/list_data_source_items_response.rb +236 -0
- data/lib/carbon_ruby_sdk/models/list_request.rb +230 -0
- data/lib/carbon_ruby_sdk/models/list_response.rb +222 -0
- data/lib/carbon_ruby_sdk/models/location_property_inner.rb +226 -0
- data/lib/carbon_ruby_sdk/models/modify_user_configuration_input.rb +234 -0
- data/lib/carbon_ruby_sdk/models/o_auth_url_request.rb +362 -0
- data/lib/carbon_ruby_sdk/models/order_dir.rb +36 -0
- data/lib/carbon_ruby_sdk/models/organization_response.rb +362 -0
- data/lib/carbon_ruby_sdk/models/organization_user_data_source_api.rb +380 -0
- data/lib/carbon_ruby_sdk/models/organization_user_data_source_filters.rb +238 -0
- data/lib/carbon_ruby_sdk/models/organization_user_data_source_order_by_columns.rb +36 -0
- data/lib/carbon_ruby_sdk/models/organization_user_data_source_query_input.rb +246 -0
- data/lib/carbon_ruby_sdk/models/organization_user_data_source_response.rb +236 -0
- data/lib/carbon_ruby_sdk/models/organization_user_file_tag_create.rb +236 -0
- data/lib/carbon_ruby_sdk/models/organization_user_file_tags_remove.rb +236 -0
- data/lib/carbon_ruby_sdk/models/organization_user_files_to_sync_filters.rb +330 -0
- data/lib/carbon_ruby_sdk/models/organization_user_files_to_sync_order_by_types.rb +39 -0
- data/lib/carbon_ruby_sdk/models/organization_user_files_to_sync_query_input.rb +276 -0
- data/lib/carbon_ruby_sdk/models/outlook_sync_input.rb +313 -0
- data/lib/carbon_ruby_sdk/models/pagination.rb +228 -0
- data/lib/carbon_ruby_sdk/models/presigned_url_response.rb +220 -0
- data/lib/carbon_ruby_sdk/models/rank_property.rb +226 -0
- data/lib/carbon_ruby_sdk/models/raw_text_input.rb +295 -0
- data/lib/carbon_ruby_sdk/models/raw_transcript_property_inner_value.rb +226 -0
- data/lib/carbon_ruby_sdk/models/resync_file_query_input.rb +240 -0
- data/lib/carbon_ruby_sdk/models/revoke_access_token_input.rb +220 -0
- data/lib/carbon_ruby_sdk/models/rss_feed_input.rb +301 -0
- data/lib/carbon_ruby_sdk/models/s3_auth_request.rb +234 -0
- data/lib/carbon_ruby_sdk/models/s3_file_sync_input.rb +313 -0
- data/lib/carbon_ruby_sdk/models/s3_get_file_input.rb +226 -0
- data/lib/carbon_ruby_sdk/models/single_chunks_and_embeddings_upload_input.rb +256 -0
- data/lib/carbon_ruby_sdk/models/sitemap_scrape_request.rb +361 -0
- data/lib/carbon_ruby_sdk/models/source_property.rb +226 -0
- data/lib/carbon_ruby_sdk/models/sync_directory_request.rb +220 -0
- data/lib/carbon_ruby_sdk/models/sync_files_request.rb +328 -0
- data/lib/carbon_ruby_sdk/models/tags.rb +232 -0
- data/lib/carbon_ruby_sdk/models/tags1.rb +230 -0
- data/lib/carbon_ruby_sdk/models/text_embedding_generators.rb +42 -0
- data/lib/carbon_ruby_sdk/models/token_response.rb +234 -0
- data/lib/carbon_ruby_sdk/models/upload_file_from_url_input.rb +326 -0
- data/lib/carbon_ruby_sdk/models/user_file.rb +524 -0
- data/lib/carbon_ruby_sdk/models/user_files_v2.rb +236 -0
- data/lib/carbon_ruby_sdk/models/user_request_content.rb +220 -0
- data/lib/carbon_ruby_sdk/models/user_response.rb +354 -0
- data/lib/carbon_ruby_sdk/models/validation_error.rb +250 -0
- data/lib/carbon_ruby_sdk/models/webhook.rb +290 -0
- data/lib/carbon_ruby_sdk/models/webhook_filters.rb +218 -0
- data/lib/carbon_ruby_sdk/models/webhook_no_key.rb +276 -0
- data/lib/carbon_ruby_sdk/models/webhook_order_by_columns.rb +36 -0
- data/lib/carbon_ruby_sdk/models/webhook_query_input.rb +246 -0
- data/lib/carbon_ruby_sdk/models/webhook_query_response.rb +236 -0
- data/lib/carbon_ruby_sdk/models/webscrape_request.rb +375 -0
- data/lib/carbon_ruby_sdk/models/white_labeling_response.rb +234 -0
- data/lib/carbon_ruby_sdk/models/youtube_transcript_response.rb +252 -0
- data/lib/carbon_ruby_sdk/version.rb +11 -0
- data/lib/carbon_ruby_sdk.rb +207 -0
- data/spec/api/auth_api_spec.rb +50 -0
- data/spec/api/data_sources_api_spec.rb +51 -0
- data/spec/api/embeddings_api_spec.rb +63 -0
- data/spec/api/files_api_spec.rb +178 -0
- data/spec/api/health_api_spec.rb +39 -0
- data/spec/api/integrations_api_spec.rb +226 -0
- data/spec/api/organizations_api_spec.rb +39 -0
- data/spec/api/users_api_spec.rb +51 -0
- data/spec/api/utilities_api_spec.rb +102 -0
- data/spec/api/webhooks_api_spec.rb +62 -0
- data/spec/api_client_spec.rb +191 -0
- data/spec/configuration_spec.rb +38 -0
- data/spec/getting_started_spec.rb +196 -0
- data/spec/models/add_webhook_props_spec.rb +28 -0
- data/spec/models/body_create_upload_file_uploadfile_post_spec.rb +28 -0
- data/spec/models/chunk_properties_nullable_spec.rb +40 -0
- data/spec/models/chunk_properties_spec.rb +40 -0
- data/spec/models/chunks_and_embeddings_spec.rb +40 -0
- data/spec/models/chunks_and_embeddings_upload_input_spec.rb +40 -0
- data/spec/models/data_source_last_sync_actions_spec.rb +22 -0
- data/spec/models/data_source_sync_statuses_spec.rb +22 -0
- data/spec/models/data_source_type_nullable_spec.rb +22 -0
- data/spec/models/data_source_type_spec.rb +22 -0
- data/spec/models/delete_files_query_input_spec.rb +46 -0
- data/spec/models/directory_item_spec.rb +46 -0
- data/spec/models/document_response_list_spec.rb +28 -0
- data/spec/models/document_response_spec.rb +88 -0
- data/spec/models/embedding_and_chunk_spec.rb +46 -0
- data/spec/models/embedding_generators_nullable_spec.rb +22 -0
- data/spec/models/embedding_generators_spec.rb +22 -0
- data/spec/models/embedding_properties_spec.rb +34 -0
- data/spec/models/embeddings_and_chunks_filters_spec.rb +34 -0
- data/spec/models/embeddings_and_chunks_order_by_columns_spec.rb +22 -0
- data/spec/models/embeddings_and_chunks_query_input_spec.rb +52 -0
- data/spec/models/embeddings_and_chunks_response_spec.rb +34 -0
- data/spec/models/external_file_sync_statuses_spec.rb +22 -0
- data/spec/models/external_source_item_spec.rb +124 -0
- data/spec/models/fetch_urls_response_spec.rb +34 -0
- data/spec/models/file_content_types_nullable_spec.rb +22 -0
- data/spec/models/file_content_types_spec.rb +22 -0
- data/spec/models/file_formats_nullable_spec.rb +22 -0
- data/spec/models/file_formats_spec.rb +22 -0
- data/spec/models/file_statistics_nullable_spec.rb +52 -0
- data/spec/models/file_statistics_spec.rb +52 -0
- data/spec/models/fresh_desk_connect_request_spec.rb +76 -0
- data/spec/models/generic_success_response_spec.rb +28 -0
- data/spec/models/get_embedding_documents_body_spec.rb +106 -0
- data/spec/models/gitbook_connect_request_spec.rb +34 -0
- data/spec/models/gitbook_sync_request_spec.rb +76 -0
- data/spec/models/gmail_sync_input_spec.rb +70 -0
- data/spec/models/http_validation_error_spec.rb +28 -0
- data/spec/models/hybrid_search_tuning_params_nullable_spec.rb +34 -0
- data/spec/models/hybrid_search_tuning_params_spec.rb +34 -0
- data/spec/models/list_data_source_items_request_spec.rb +40 -0
- data/spec/models/list_data_source_items_response_spec.rb +34 -0
- data/spec/models/list_request_spec.rb +34 -0
- data/spec/models/list_response_spec.rb +28 -0
- data/spec/models/location_property_inner_spec.rb +22 -0
- data/spec/models/modify_user_configuration_input_spec.rb +34 -0
- data/spec/models/o_auth_url_request_spec.rb +106 -0
- data/spec/models/order_dir_spec.rb +22 -0
- data/spec/models/organization_response_spec.rb +94 -0
- data/spec/models/organization_user_data_source_api_spec.rb +100 -0
- data/spec/models/organization_user_data_source_filters_spec.rb +40 -0
- data/spec/models/organization_user_data_source_order_by_columns_spec.rb +22 -0
- data/spec/models/organization_user_data_source_query_input_spec.rb +46 -0
- data/spec/models/organization_user_data_source_response_spec.rb +34 -0
- data/spec/models/organization_user_file_tag_create_spec.rb +34 -0
- data/spec/models/organization_user_file_tags_remove_spec.rb +34 -0
- data/spec/models/organization_user_files_to_sync_filters_spec.rb +88 -0
- data/spec/models/organization_user_files_to_sync_order_by_types_spec.rb +22 -0
- data/spec/models/organization_user_files_to_sync_query_input_spec.rb +64 -0
- data/spec/models/outlook_sync_input_spec.rb +76 -0
- data/spec/models/pagination_spec.rb +34 -0
- data/spec/models/presigned_url_response_spec.rb +28 -0
- data/spec/models/rank_property_spec.rb +22 -0
- data/spec/models/raw_text_input_spec.rb +70 -0
- data/spec/models/raw_transcript_property_inner_value_spec.rb +22 -0
- data/spec/models/resync_file_query_input_spec.rb +40 -0
- data/spec/models/revoke_access_token_input_spec.rb +28 -0
- data/spec/models/rss_feed_input_spec.rb +70 -0
- data/spec/models/s3_auth_request_spec.rb +34 -0
- data/spec/models/s3_file_sync_input_spec.rb +76 -0
- data/spec/models/s3_get_file_input_spec.rb +34 -0
- data/spec/models/single_chunks_and_embeddings_upload_input_spec.rb +46 -0
- data/spec/models/sitemap_scrape_request_spec.rb +100 -0
- data/spec/models/source_property_spec.rb +22 -0
- data/spec/models/sync_directory_request_spec.rb +28 -0
- data/spec/models/sync_files_request_spec.rb +82 -0
- data/spec/models/tags1_spec.rb +22 -0
- data/spec/models/tags_spec.rb +22 -0
- data/spec/models/text_embedding_generators_spec.rb +22 -0
- data/spec/models/token_response_spec.rb +34 -0
- data/spec/models/upload_file_from_url_input_spec.rb +88 -0
- data/spec/models/user_file_spec.rb +190 -0
- data/spec/models/user_files_v2_spec.rb +34 -0
- data/spec/models/user_request_content_spec.rb +28 -0
- data/spec/models/user_response_spec.rb +88 -0
- data/spec/models/validation_error_spec.rb +40 -0
- data/spec/models/webhook_filters_spec.rb +28 -0
- data/spec/models/webhook_no_key_spec.rb +52 -0
- data/spec/models/webhook_order_by_columns_spec.rb +22 -0
- data/spec/models/webhook_query_input_spec.rb +46 -0
- data/spec/models/webhook_query_response_spec.rb +34 -0
- data/spec/models/webhook_spec.rb +58 -0
- data/spec/models/webscrape_request_spec.rb +106 -0
- data/spec/models/white_labeling_response_spec.rb +34 -0
- data/spec/models/youtube_transcript_response_spec.rb +46 -0
- data/spec/spec_helper.rb +107 -0
- metadata +440 -0
@@ -0,0 +1,710 @@
|
|
1
|
+
=begin
|
2
|
+
#Carbon
|
3
|
+
|
4
|
+
#Connect external data to LLMs, no matter the source.
|
5
|
+
|
6
|
+
The version of the OpenAPI document: 1.0.0
|
7
|
+
=end
|
8
|
+
|
9
|
+
require 'cgi'
|
10
|
+
|
11
|
+
module Carbon
|
12
|
+
class UtilitiesApi
|
13
|
+
attr_accessor :api_client
|
14
|
+
|
15
|
+
def initialize(api_client = ApiClient.default)
|
16
|
+
@api_client = api_client
|
17
|
+
end
|
18
|
+
|
19
|
+
# Fetch Urls
|
20
|
+
#
|
21
|
+
# Extracts all URLs from a webpage.
|
22
|
+
#
|
23
|
+
# Args:
|
24
|
+
# url (str): URL of the webpage
|
25
|
+
#
|
26
|
+
# Returns:
|
27
|
+
# FetchURLsResponse: A response object with a list of URLs extracted from the webpage and the webpage content.
|
28
|
+
#
|
29
|
+
# @param url [String]
|
30
|
+
# @param [Hash] extra additional parameters to pass along through :header_params, :query_params, or parameter name
|
31
|
+
def fetch_urls(url:, extra: {})
|
32
|
+
api_response = fetch_urls_with_http_info_impl(url, extra)
|
33
|
+
api_response.data
|
34
|
+
end
|
35
|
+
|
36
|
+
# Fetch Urls
|
37
|
+
#
|
38
|
+
# Extracts all URLs from a webpage.
|
39
|
+
#
|
40
|
+
# Args:
|
41
|
+
# url (str): URL of the webpage
|
42
|
+
#
|
43
|
+
# Returns:
|
44
|
+
# FetchURLsResponse: A response object with a list of URLs extracted from the webpage and the webpage content.
|
45
|
+
#
|
46
|
+
# @param url [String]
|
47
|
+
# @param [Hash] extra additional parameters to pass along through :header_params, :query_params, or parameter name
|
48
|
+
def fetch_urls_with_http_info(url:, extra: {})
|
49
|
+
fetch_urls_with_http_info_impl(url, extra)
|
50
|
+
end
|
51
|
+
|
52
|
+
# Fetch Urls
|
53
|
+
# Extracts all URLs from a webpage. Args: url (str): URL of the webpage Returns: FetchURLsResponse: A response object with a list of URLs extracted from the webpage and the webpage content.
|
54
|
+
# @param url [String]
|
55
|
+
# @param [Hash] opts the optional parameters
|
56
|
+
# @return [FetchURLsResponse]
|
57
|
+
private def fetch_urls_impl(url, opts = {})
|
58
|
+
data, _status_code, _headers = fetch_urls_with_http_info(url, opts)
|
59
|
+
data
|
60
|
+
end
|
61
|
+
|
62
|
+
# Fetch Urls
|
63
|
+
# Extracts all URLs from a webpage. Args: url (str): URL of the webpage Returns: FetchURLsResponse: A response object with a list of URLs extracted from the webpage and the webpage content.
|
64
|
+
# @param url [String]
|
65
|
+
# @param [Hash] opts the optional parameters
|
66
|
+
# @return [APIResponse] data is FetchURLsResponse, status code, headers and response
|
67
|
+
private def fetch_urls_with_http_info_impl(url, opts = {})
|
68
|
+
if @api_client.config.debugging
|
69
|
+
@api_client.config.logger.debug 'Calling API: UtilitiesApi.fetch_urls ...'
|
70
|
+
end
|
71
|
+
# verify the required parameter 'url' is set
|
72
|
+
if @api_client.config.client_side_validation && url.nil?
|
73
|
+
fail ArgumentError, "Missing the required parameter 'url' when calling UtilitiesApi.fetch_urls"
|
74
|
+
end
|
75
|
+
# resource path
|
76
|
+
local_var_path = '/fetch_urls'
|
77
|
+
|
78
|
+
# query parameters
|
79
|
+
query_params = opts[:query_params] || {}
|
80
|
+
query_params[:'url'] = url
|
81
|
+
|
82
|
+
# header parameters
|
83
|
+
header_params = opts[:header_params] || {}
|
84
|
+
# HTTP header 'Accept' (if needed)
|
85
|
+
header_params['Accept'] = @api_client.select_header_accept(['application/json'])
|
86
|
+
|
87
|
+
# form parameters
|
88
|
+
form_params = opts[:form_params] || {}
|
89
|
+
|
90
|
+
# http body (model)
|
91
|
+
post_body = opts[:debug_body]
|
92
|
+
|
93
|
+
# return_type
|
94
|
+
return_type = opts[:debug_return_type] || 'FetchURLsResponse'
|
95
|
+
|
96
|
+
# auth_names
|
97
|
+
auth_names = opts[:debug_auth_names] || ['accessToken', 'apiKey', 'customerId']
|
98
|
+
|
99
|
+
new_options = opts.merge(
|
100
|
+
:operation => :"UtilitiesApi.fetch_urls",
|
101
|
+
:header_params => header_params,
|
102
|
+
:query_params => query_params,
|
103
|
+
:form_params => form_params,
|
104
|
+
:body => post_body,
|
105
|
+
:auth_names => auth_names,
|
106
|
+
:return_type => return_type
|
107
|
+
)
|
108
|
+
|
109
|
+
data, status_code, headers, response = @api_client.call_api(:GET, local_var_path, new_options)
|
110
|
+
if @api_client.config.debugging
|
111
|
+
@api_client.config.logger.debug "API called: UtilitiesApi#fetch_urls\nData: #{data.inspect}\nStatus code: #{status_code}\nHeaders: #{headers}"
|
112
|
+
end
|
113
|
+
APIResponse::new(data, status_code, headers, response)
|
114
|
+
end
|
115
|
+
|
116
|
+
|
117
|
+
# Fetch Youtube Transcripts
|
118
|
+
#
|
119
|
+
# Fetches english transcripts from YouTube videos.
|
120
|
+
#
|
121
|
+
# Args:
|
122
|
+
# id (str): The ID of the YouTube video.
|
123
|
+
# raw (bool): Whether to return the raw transcript or not. Defaults to False.
|
124
|
+
#
|
125
|
+
# Returns:
|
126
|
+
# dict: A dictionary with the transcript of the YouTube video.
|
127
|
+
#
|
128
|
+
# @param id [String]
|
129
|
+
# @param raw [Boolean]
|
130
|
+
# @param [Hash] extra additional parameters to pass along through :header_params, :query_params, or parameter name
|
131
|
+
def fetch_youtube_transcripts(id:, raw: false, extra: {})
|
132
|
+
extra[:raw] = raw if raw != SENTINEL
|
133
|
+
api_response = fetch_youtube_transcripts_with_http_info_impl(id, extra)
|
134
|
+
api_response.data
|
135
|
+
end
|
136
|
+
|
137
|
+
# Fetch Youtube Transcripts
|
138
|
+
#
|
139
|
+
# Fetches english transcripts from YouTube videos.
|
140
|
+
#
|
141
|
+
# Args:
|
142
|
+
# id (str): The ID of the YouTube video.
|
143
|
+
# raw (bool): Whether to return the raw transcript or not. Defaults to False.
|
144
|
+
#
|
145
|
+
# Returns:
|
146
|
+
# dict: A dictionary with the transcript of the YouTube video.
|
147
|
+
#
|
148
|
+
# @param id [String]
|
149
|
+
# @param raw [Boolean]
|
150
|
+
# @param [Hash] extra additional parameters to pass along through :header_params, :query_params, or parameter name
|
151
|
+
def fetch_youtube_transcripts_with_http_info(id:, raw: false, extra: {})
|
152
|
+
extra[:raw] = raw if raw != SENTINEL
|
153
|
+
fetch_youtube_transcripts_with_http_info_impl(id, extra)
|
154
|
+
end
|
155
|
+
|
156
|
+
# Fetch Youtube Transcripts
|
157
|
+
# Fetches english transcripts from YouTube videos. Args: id (str): The ID of the YouTube video. raw (bool): Whether to return the raw transcript or not. Defaults to False. Returns: dict: A dictionary with the transcript of the YouTube video.
|
158
|
+
# @param id [String]
|
159
|
+
# @param [Hash] opts the optional parameters
|
160
|
+
# @option opts [Boolean] :raw (default to false)
|
161
|
+
# @return [YoutubeTranscriptResponse]
|
162
|
+
private def fetch_youtube_transcripts_impl(id, opts = {})
|
163
|
+
data, _status_code, _headers = fetch_youtube_transcripts_with_http_info(id, opts)
|
164
|
+
data
|
165
|
+
end
|
166
|
+
|
167
|
+
# Fetch Youtube Transcripts
|
168
|
+
# Fetches english transcripts from YouTube videos. Args: id (str): The ID of the YouTube video. raw (bool): Whether to return the raw transcript or not. Defaults to False. Returns: dict: A dictionary with the transcript of the YouTube video.
|
169
|
+
# @param id [String]
|
170
|
+
# @param [Hash] opts the optional parameters
|
171
|
+
# @option opts [Boolean] :raw (default to false)
|
172
|
+
# @return [APIResponse] data is YoutubeTranscriptResponse, status code, headers and response
|
173
|
+
private def fetch_youtube_transcripts_with_http_info_impl(id, opts = {})
|
174
|
+
if @api_client.config.debugging
|
175
|
+
@api_client.config.logger.debug 'Calling API: UtilitiesApi.fetch_youtube_transcripts ...'
|
176
|
+
end
|
177
|
+
# verify the required parameter 'id' is set
|
178
|
+
if @api_client.config.client_side_validation && id.nil?
|
179
|
+
fail ArgumentError, "Missing the required parameter 'id' when calling UtilitiesApi.fetch_youtube_transcripts"
|
180
|
+
end
|
181
|
+
# resource path
|
182
|
+
local_var_path = '/fetch_youtube_transcript'
|
183
|
+
|
184
|
+
# query parameters
|
185
|
+
query_params = opts[:query_params] || {}
|
186
|
+
query_params[:'id'] = id
|
187
|
+
query_params[:'raw'] = opts[:'raw'] if !opts[:'raw'].nil?
|
188
|
+
|
189
|
+
# header parameters
|
190
|
+
header_params = opts[:header_params] || {}
|
191
|
+
# HTTP header 'Accept' (if needed)
|
192
|
+
header_params['Accept'] = @api_client.select_header_accept(['application/json'])
|
193
|
+
|
194
|
+
# form parameters
|
195
|
+
form_params = opts[:form_params] || {}
|
196
|
+
|
197
|
+
# http body (model)
|
198
|
+
post_body = opts[:debug_body]
|
199
|
+
|
200
|
+
# return_type
|
201
|
+
return_type = opts[:debug_return_type] || 'YoutubeTranscriptResponse'
|
202
|
+
|
203
|
+
# auth_names
|
204
|
+
auth_names = opts[:debug_auth_names] || ['accessToken', 'apiKey', 'customerId']
|
205
|
+
|
206
|
+
new_options = opts.merge(
|
207
|
+
:operation => :"UtilitiesApi.fetch_youtube_transcripts",
|
208
|
+
:header_params => header_params,
|
209
|
+
:query_params => query_params,
|
210
|
+
:form_params => form_params,
|
211
|
+
:body => post_body,
|
212
|
+
:auth_names => auth_names,
|
213
|
+
:return_type => return_type
|
214
|
+
)
|
215
|
+
|
216
|
+
data, status_code, headers, response = @api_client.call_api(:GET, local_var_path, new_options)
|
217
|
+
if @api_client.config.debugging
|
218
|
+
@api_client.config.logger.debug "API called: UtilitiesApi#fetch_youtube_transcripts\nData: #{data.inspect}\nStatus code: #{status_code}\nHeaders: #{headers}"
|
219
|
+
end
|
220
|
+
APIResponse::new(data, status_code, headers, response)
|
221
|
+
end
|
222
|
+
|
223
|
+
|
224
|
+
# Sitemap
|
225
|
+
#
|
226
|
+
# Retrieves all URLs from a sitemap, which can subsequently be utilized with our `web_scrape` endpoint.
|
227
|
+
#
|
228
|
+
# <!--Args:
|
229
|
+
# url (str): URL of the sitemap
|
230
|
+
#
|
231
|
+
# Returns:
|
232
|
+
# dict: A dictionary with a list of URLs extracted from the sitemap.-->
|
233
|
+
#
|
234
|
+
# @param url [String]
|
235
|
+
# @param [Hash] extra additional parameters to pass along through :header_params, :query_params, or parameter name
|
236
|
+
def process_sitemap(url:, extra: {})
|
237
|
+
api_response = process_sitemap_with_http_info_impl(url, extra)
|
238
|
+
api_response.data
|
239
|
+
end
|
240
|
+
|
241
|
+
# Sitemap
|
242
|
+
#
|
243
|
+
# Retrieves all URLs from a sitemap, which can subsequently be utilized with our `web_scrape` endpoint.
|
244
|
+
#
|
245
|
+
# <!--Args:
|
246
|
+
# url (str): URL of the sitemap
|
247
|
+
#
|
248
|
+
# Returns:
|
249
|
+
# dict: A dictionary with a list of URLs extracted from the sitemap.-->
|
250
|
+
#
|
251
|
+
# @param url [String]
|
252
|
+
# @param [Hash] extra additional parameters to pass along through :header_params, :query_params, or parameter name
|
253
|
+
def process_sitemap_with_http_info(url:, extra: {})
|
254
|
+
process_sitemap_with_http_info_impl(url, extra)
|
255
|
+
end
|
256
|
+
|
257
|
+
# Sitemap
|
258
|
+
# Retrieves all URLs from a sitemap, which can subsequently be utilized with our `web_scrape` endpoint. <!--Args: url (str): URL of the sitemap Returns: dict: A dictionary with a list of URLs extracted from the sitemap.-->
|
259
|
+
# @param url [String]
|
260
|
+
# @param [Hash] opts the optional parameters
|
261
|
+
# @return [Object]
|
262
|
+
private def process_sitemap_impl(url, opts = {})
|
263
|
+
data, _status_code, _headers = process_sitemap_with_http_info(url, opts)
|
264
|
+
data
|
265
|
+
end
|
266
|
+
|
267
|
+
# Sitemap
|
268
|
+
# Retrieves all URLs from a sitemap, which can subsequently be utilized with our `web_scrape` endpoint. <!--Args: url (str): URL of the sitemap Returns: dict: A dictionary with a list of URLs extracted from the sitemap.-->
|
269
|
+
# @param url [String]
|
270
|
+
# @param [Hash] opts the optional parameters
|
271
|
+
# @return [APIResponse] data is Object, status code, headers and response
|
272
|
+
private def process_sitemap_with_http_info_impl(url, opts = {})
|
273
|
+
if @api_client.config.debugging
|
274
|
+
@api_client.config.logger.debug 'Calling API: UtilitiesApi.process_sitemap ...'
|
275
|
+
end
|
276
|
+
# verify the required parameter 'url' is set
|
277
|
+
if @api_client.config.client_side_validation && url.nil?
|
278
|
+
fail ArgumentError, "Missing the required parameter 'url' when calling UtilitiesApi.process_sitemap"
|
279
|
+
end
|
280
|
+
# resource path
|
281
|
+
local_var_path = '/process_sitemap'
|
282
|
+
|
283
|
+
# query parameters
|
284
|
+
query_params = opts[:query_params] || {}
|
285
|
+
query_params[:'url'] = url
|
286
|
+
|
287
|
+
# header parameters
|
288
|
+
header_params = opts[:header_params] || {}
|
289
|
+
# HTTP header 'Accept' (if needed)
|
290
|
+
header_params['Accept'] = @api_client.select_header_accept(['application/json'])
|
291
|
+
|
292
|
+
# form parameters
|
293
|
+
form_params = opts[:form_params] || {}
|
294
|
+
|
295
|
+
# http body (model)
|
296
|
+
post_body = opts[:debug_body]
|
297
|
+
|
298
|
+
# return_type
|
299
|
+
return_type = opts[:debug_return_type] || 'Object'
|
300
|
+
|
301
|
+
# auth_names
|
302
|
+
auth_names = opts[:debug_auth_names] || ['accessToken', 'apiKey', 'customerId']
|
303
|
+
|
304
|
+
new_options = opts.merge(
|
305
|
+
:operation => :"UtilitiesApi.process_sitemap",
|
306
|
+
:header_params => header_params,
|
307
|
+
:query_params => query_params,
|
308
|
+
:form_params => form_params,
|
309
|
+
:body => post_body,
|
310
|
+
:auth_names => auth_names,
|
311
|
+
:return_type => return_type
|
312
|
+
)
|
313
|
+
|
314
|
+
data, status_code, headers, response = @api_client.call_api(:GET, local_var_path, new_options)
|
315
|
+
if @api_client.config.debugging
|
316
|
+
@api_client.config.logger.debug "API called: UtilitiesApi#process_sitemap\nData: #{data.inspect}\nStatus code: #{status_code}\nHeaders: #{headers}"
|
317
|
+
end
|
318
|
+
APIResponse::new(data, status_code, headers, response)
|
319
|
+
end
|
320
|
+
|
321
|
+
|
322
|
+
# Scrape Sitemap
|
323
|
+
#
|
324
|
+
# Extracts all URLs from a sitemap and performs a web scrape on each of them.
|
325
|
+
#
|
326
|
+
# Args:
|
327
|
+
# sitemap_url (str): URL of the sitemap
|
328
|
+
#
|
329
|
+
# Returns:
|
330
|
+
# dict: A response object with the status of the scraping job message.-->
|
331
|
+
#
|
332
|
+
# @param url [String]
|
333
|
+
# @param tags [Hash<String, Tags1>]
|
334
|
+
# @param max_pages_to_scrape [Integer]
|
335
|
+
# @param chunk_size [Integer]
|
336
|
+
# @param chunk_overlap [Integer]
|
337
|
+
# @param skip_embedding_generation [Boolean]
|
338
|
+
# @param enable_auto_sync [Boolean]
|
339
|
+
# @param generate_sparse_vectors [Boolean]
|
340
|
+
# @param prepend_filename_to_chunks [Boolean]
|
341
|
+
# @param html_tags_to_skip [Array<String>]
|
342
|
+
# @param css_classes_to_skip [Array<String>]
|
343
|
+
# @param css_selectors_to_skip [Array<String>]
|
344
|
+
# @param embedding_model [EmbeddingGenerators]
|
345
|
+
# @param body [SitemapScrapeRequest]
|
346
|
+
# @param [Hash] extra additional parameters to pass along through :header_params, :query_params, or parameter name
|
347
|
+
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: {})
|
348
|
+
_body = {}
|
349
|
+
_body[:tags] = tags if tags != SENTINEL
|
350
|
+
_body[:url] = url if url != SENTINEL
|
351
|
+
_body[:max_pages_to_scrape] = max_pages_to_scrape if max_pages_to_scrape != SENTINEL
|
352
|
+
_body[:chunk_size] = chunk_size if chunk_size != SENTINEL
|
353
|
+
_body[:chunk_overlap] = chunk_overlap if chunk_overlap != SENTINEL
|
354
|
+
_body[:skip_embedding_generation] = skip_embedding_generation if skip_embedding_generation != SENTINEL
|
355
|
+
_body[:enable_auto_sync] = enable_auto_sync if enable_auto_sync != SENTINEL
|
356
|
+
_body[:generate_sparse_vectors] = generate_sparse_vectors if generate_sparse_vectors != SENTINEL
|
357
|
+
_body[:prepend_filename_to_chunks] = prepend_filename_to_chunks if prepend_filename_to_chunks != SENTINEL
|
358
|
+
_body[:html_tags_to_skip] = html_tags_to_skip if html_tags_to_skip != SENTINEL
|
359
|
+
_body[:css_classes_to_skip] = css_classes_to_skip if css_classes_to_skip != SENTINEL
|
360
|
+
_body[:css_selectors_to_skip] = css_selectors_to_skip if css_selectors_to_skip != SENTINEL
|
361
|
+
_body[:embedding_model] = embedding_model if embedding_model != SENTINEL
|
362
|
+
sitemap_scrape_request = _body
|
363
|
+
api_response = scrape_sitemap_with_http_info_impl(sitemap_scrape_request, extra)
|
364
|
+
api_response.data
|
365
|
+
end
|
366
|
+
|
367
|
+
# Scrape Sitemap
|
368
|
+
#
|
369
|
+
# Extracts all URLs from a sitemap and performs a web scrape on each of them.
|
370
|
+
#
|
371
|
+
# Args:
|
372
|
+
# sitemap_url (str): URL of the sitemap
|
373
|
+
#
|
374
|
+
# Returns:
|
375
|
+
# dict: A response object with the status of the scraping job message.-->
|
376
|
+
#
|
377
|
+
# @param url [String]
|
378
|
+
# @param tags [Hash<String, Tags1>]
|
379
|
+
# @param max_pages_to_scrape [Integer]
|
380
|
+
# @param chunk_size [Integer]
|
381
|
+
# @param chunk_overlap [Integer]
|
382
|
+
# @param skip_embedding_generation [Boolean]
|
383
|
+
# @param enable_auto_sync [Boolean]
|
384
|
+
# @param generate_sparse_vectors [Boolean]
|
385
|
+
# @param prepend_filename_to_chunks [Boolean]
|
386
|
+
# @param html_tags_to_skip [Array<String>]
|
387
|
+
# @param css_classes_to_skip [Array<String>]
|
388
|
+
# @param css_selectors_to_skip [Array<String>]
|
389
|
+
# @param embedding_model [EmbeddingGenerators]
|
390
|
+
# @param body [SitemapScrapeRequest]
|
391
|
+
# @param [Hash] extra additional parameters to pass along through :header_params, :query_params, or parameter name
|
392
|
+
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: {})
|
393
|
+
_body = {}
|
394
|
+
_body[:tags] = tags if tags != SENTINEL
|
395
|
+
_body[:url] = url if url != SENTINEL
|
396
|
+
_body[:max_pages_to_scrape] = max_pages_to_scrape if max_pages_to_scrape != SENTINEL
|
397
|
+
_body[:chunk_size] = chunk_size if chunk_size != SENTINEL
|
398
|
+
_body[:chunk_overlap] = chunk_overlap if chunk_overlap != SENTINEL
|
399
|
+
_body[:skip_embedding_generation] = skip_embedding_generation if skip_embedding_generation != SENTINEL
|
400
|
+
_body[:enable_auto_sync] = enable_auto_sync if enable_auto_sync != SENTINEL
|
401
|
+
_body[:generate_sparse_vectors] = generate_sparse_vectors if generate_sparse_vectors != SENTINEL
|
402
|
+
_body[:prepend_filename_to_chunks] = prepend_filename_to_chunks if prepend_filename_to_chunks != SENTINEL
|
403
|
+
_body[:html_tags_to_skip] = html_tags_to_skip if html_tags_to_skip != SENTINEL
|
404
|
+
_body[:css_classes_to_skip] = css_classes_to_skip if css_classes_to_skip != SENTINEL
|
405
|
+
_body[:css_selectors_to_skip] = css_selectors_to_skip if css_selectors_to_skip != SENTINEL
|
406
|
+
_body[:embedding_model] = embedding_model if embedding_model != SENTINEL
|
407
|
+
sitemap_scrape_request = _body
|
408
|
+
scrape_sitemap_with_http_info_impl(sitemap_scrape_request, extra)
|
409
|
+
end
|
410
|
+
|
411
|
+
# Scrape Sitemap
|
412
|
+
# Extracts all URLs from a sitemap and performs a web scrape on each of them. Args: sitemap_url (str): URL of the sitemap Returns: dict: A response object with the status of the scraping job message.-->
|
413
|
+
# @param sitemap_scrape_request [SitemapScrapeRequest]
|
414
|
+
# @param [Hash] opts the optional parameters
|
415
|
+
# @return [Object]
|
416
|
+
private def scrape_sitemap_impl(sitemap_scrape_request, opts = {})
|
417
|
+
data, _status_code, _headers = scrape_sitemap_with_http_info(sitemap_scrape_request, opts)
|
418
|
+
data
|
419
|
+
end
|
420
|
+
|
421
|
+
# Scrape Sitemap
|
422
|
+
# Extracts all URLs from a sitemap and performs a web scrape on each of them. Args: sitemap_url (str): URL of the sitemap Returns: dict: A response object with the status of the scraping job message.-->
|
423
|
+
# @param sitemap_scrape_request [SitemapScrapeRequest]
|
424
|
+
# @param [Hash] opts the optional parameters
|
425
|
+
# @return [APIResponse] data is Object, status code, headers and response
|
426
|
+
private def scrape_sitemap_with_http_info_impl(sitemap_scrape_request, opts = {})
|
427
|
+
if @api_client.config.debugging
|
428
|
+
@api_client.config.logger.debug 'Calling API: UtilitiesApi.scrape_sitemap ...'
|
429
|
+
end
|
430
|
+
# verify the required parameter 'sitemap_scrape_request' is set
|
431
|
+
if @api_client.config.client_side_validation && sitemap_scrape_request.nil?
|
432
|
+
fail ArgumentError, "Missing the required parameter 'sitemap_scrape_request' when calling UtilitiesApi.scrape_sitemap"
|
433
|
+
end
|
434
|
+
# resource path
|
435
|
+
local_var_path = '/scrape_sitemap'
|
436
|
+
|
437
|
+
# query parameters
|
438
|
+
query_params = opts[:query_params] || {}
|
439
|
+
|
440
|
+
# header parameters
|
441
|
+
header_params = opts[:header_params] || {}
|
442
|
+
# HTTP header 'Accept' (if needed)
|
443
|
+
header_params['Accept'] = @api_client.select_header_accept(['application/json'])
|
444
|
+
# HTTP header 'Content-Type'
|
445
|
+
content_type = @api_client.select_header_content_type(['application/json'])
|
446
|
+
if !content_type.nil?
|
447
|
+
header_params['Content-Type'] = content_type
|
448
|
+
end
|
449
|
+
|
450
|
+
# form parameters
|
451
|
+
form_params = opts[:form_params] || {}
|
452
|
+
|
453
|
+
# http body (model)
|
454
|
+
post_body = opts[:debug_body] || @api_client.object_to_http_body(sitemap_scrape_request)
|
455
|
+
|
456
|
+
# return_type
|
457
|
+
return_type = opts[:debug_return_type] || 'Object'
|
458
|
+
|
459
|
+
# auth_names
|
460
|
+
auth_names = opts[:debug_auth_names] || ['accessToken', 'apiKey', 'customerId']
|
461
|
+
|
462
|
+
new_options = opts.merge(
|
463
|
+
:operation => :"UtilitiesApi.scrape_sitemap",
|
464
|
+
:header_params => header_params,
|
465
|
+
:query_params => query_params,
|
466
|
+
:form_params => form_params,
|
467
|
+
:body => post_body,
|
468
|
+
:auth_names => auth_names,
|
469
|
+
:return_type => return_type
|
470
|
+
)
|
471
|
+
|
472
|
+
data, status_code, headers, response = @api_client.call_api(:POST, local_var_path, new_options)
|
473
|
+
if @api_client.config.debugging
|
474
|
+
@api_client.config.logger.debug "API called: UtilitiesApi#scrape_sitemap\nData: #{data.inspect}\nStatus code: #{status_code}\nHeaders: #{headers}"
|
475
|
+
end
|
476
|
+
APIResponse::new(data, status_code, headers, response)
|
477
|
+
end
|
478
|
+
|
479
|
+
|
480
|
+
# Web Scrape
|
481
|
+
#
|
482
|
+
# Conduct a web scrape on a given webpage URL. Our web scraper is fully compatible with JavaScript and supports recursion depth, enabling you to efficiently extract all content from the target website.
|
483
|
+
#
|
484
|
+
# <!--Args:
|
485
|
+
# scraping_requests (List[WebscrapeRequest]): A list of WebscrapeRequest objects.
|
486
|
+
#
|
487
|
+
#
|
488
|
+
# Returns:
|
489
|
+
# dict: A response object with the status of the scraping job message.-->
|
490
|
+
#
|
491
|
+
# @param body [Array<WebscrapeRequest>]
|
492
|
+
# @param [Hash] extra additional parameters to pass along through :header_params, :query_params, or parameter name
|
493
|
+
def scrape_web(body:, extra: {})
|
494
|
+
webscrape_request = body
|
495
|
+
api_response = scrape_web_with_http_info_impl(webscrape_request, extra)
|
496
|
+
api_response.data
|
497
|
+
end
|
498
|
+
|
499
|
+
# Web Scrape
|
500
|
+
#
|
501
|
+
# Conduct a web scrape on a given webpage URL. Our web scraper is fully compatible with JavaScript and supports recursion depth, enabling you to efficiently extract all content from the target website.
|
502
|
+
#
|
503
|
+
# <!--Args:
|
504
|
+
# scraping_requests (List[WebscrapeRequest]): A list of WebscrapeRequest objects.
|
505
|
+
#
|
506
|
+
#
|
507
|
+
# Returns:
|
508
|
+
# dict: A response object with the status of the scraping job message.-->
|
509
|
+
#
|
510
|
+
# @param body [Array<WebscrapeRequest>]
|
511
|
+
# @param [Hash] extra additional parameters to pass along through :header_params, :query_params, or parameter name
|
512
|
+
def scrape_web_with_http_info(body:, extra: {})
|
513
|
+
webscrape_request = body
|
514
|
+
scrape_web_with_http_info_impl(webscrape_request, extra)
|
515
|
+
end
|
516
|
+
|
517
|
+
# Web Scrape
|
518
|
+
# Conduct a web scrape on a given webpage URL. Our web scraper is fully compatible with JavaScript and supports recursion depth, enabling you to efficiently extract all content from the target website. <!--Args: scraping_requests (List[WebscrapeRequest]): A list of WebscrapeRequest objects. Returns: dict: A response object with the status of the scraping job message.-->
|
519
|
+
# @param webscrape_request [Array<WebscrapeRequest>]
|
520
|
+
# @param [Hash] opts the optional parameters
|
521
|
+
# @return [Object]
|
522
|
+
private def scrape_web_impl(webscrape_request, opts = {})
|
523
|
+
data, _status_code, _headers = scrape_web_with_http_info(webscrape_request, opts)
|
524
|
+
data
|
525
|
+
end
|
526
|
+
|
527
|
+
# Web Scrape
|
528
|
+
# Conduct a web scrape on a given webpage URL. Our web scraper is fully compatible with JavaScript and supports recursion depth, enabling you to efficiently extract all content from the target website. <!--Args: scraping_requests (List[WebscrapeRequest]): A list of WebscrapeRequest objects. Returns: dict: A response object with the status of the scraping job message.-->
|
529
|
+
# @param webscrape_request [Array<WebscrapeRequest>]
|
530
|
+
# @param [Hash] opts the optional parameters
|
531
|
+
# @return [APIResponse] data is Object, status code, headers and response
|
532
|
+
private def scrape_web_with_http_info_impl(webscrape_request, opts = {})
|
533
|
+
if @api_client.config.debugging
|
534
|
+
@api_client.config.logger.debug 'Calling API: UtilitiesApi.scrape_web ...'
|
535
|
+
end
|
536
|
+
# verify the required parameter 'webscrape_request' is set
|
537
|
+
if @api_client.config.client_side_validation && webscrape_request.nil?
|
538
|
+
fail ArgumentError, "Missing the required parameter 'webscrape_request' when calling UtilitiesApi.scrape_web"
|
539
|
+
end
|
540
|
+
# resource path
|
541
|
+
local_var_path = '/web_scrape'
|
542
|
+
|
543
|
+
# query parameters
|
544
|
+
query_params = opts[:query_params] || {}
|
545
|
+
|
546
|
+
# header parameters
|
547
|
+
header_params = opts[:header_params] || {}
|
548
|
+
# HTTP header 'Accept' (if needed)
|
549
|
+
header_params['Accept'] = @api_client.select_header_accept(['application/json'])
|
550
|
+
# HTTP header 'Content-Type'
|
551
|
+
content_type = @api_client.select_header_content_type(['application/json'])
|
552
|
+
if !content_type.nil?
|
553
|
+
header_params['Content-Type'] = content_type
|
554
|
+
end
|
555
|
+
|
556
|
+
# form parameters
|
557
|
+
form_params = opts[:form_params] || {}
|
558
|
+
|
559
|
+
# http body (model)
|
560
|
+
post_body = opts[:debug_body] || @api_client.object_to_http_body(webscrape_request)
|
561
|
+
|
562
|
+
# return_type
|
563
|
+
return_type = opts[:debug_return_type] || 'Object'
|
564
|
+
|
565
|
+
# auth_names
|
566
|
+
auth_names = opts[:debug_auth_names] || ['accessToken', 'apiKey', 'customerId']
|
567
|
+
|
568
|
+
new_options = opts.merge(
|
569
|
+
:operation => :"UtilitiesApi.scrape_web",
|
570
|
+
:header_params => header_params,
|
571
|
+
:query_params => query_params,
|
572
|
+
:form_params => form_params,
|
573
|
+
:body => post_body,
|
574
|
+
:auth_names => auth_names,
|
575
|
+
:return_type => return_type
|
576
|
+
)
|
577
|
+
|
578
|
+
data, status_code, headers, response = @api_client.call_api(:POST, local_var_path, new_options)
|
579
|
+
if @api_client.config.debugging
|
580
|
+
@api_client.config.logger.debug "API called: UtilitiesApi#scrape_web\nData: #{data.inspect}\nStatus code: #{status_code}\nHeaders: #{headers}"
|
581
|
+
end
|
582
|
+
APIResponse::new(data, status_code, headers, response)
|
583
|
+
end
|
584
|
+
|
585
|
+
|
586
|
+
# Search Urls
|
587
|
+
#
|
588
|
+
# Perform a web search and obtain a list of relevant URLs.
|
589
|
+
#
|
590
|
+
# As an illustration, when you perform a search for “content related to MRNA,” you will receive a list of links such as the following:
|
591
|
+
#
|
592
|
+
# - https://tomrenz.substack.com/p/mrna-and-why-it-matters
|
593
|
+
#
|
594
|
+
# - https://www.statnews.com/2020/11/10/the-story-of-mrna-how-a-once-dismissed-idea-became-a-leading-technology-in-the-covid-vaccine-race/
|
595
|
+
#
|
596
|
+
# - https://www.statnews.com/2022/11/16/covid-19-vaccines-were-a-success-but-mrna-still-has-a-delivery-problem/
|
597
|
+
#
|
598
|
+
# - https://joomi.substack.com/p/were-still-being-misled-about-how
|
599
|
+
#
|
600
|
+
# Subsequently, you can submit these links to the web_scrape endpoint in order to retrieve the content of the respective web pages.
|
601
|
+
#
|
602
|
+
# Args:
|
603
|
+
# query (str): Query to search for
|
604
|
+
#
|
605
|
+
# Returns:
|
606
|
+
# FetchURLsResponse: A response object with a list of URLs for a given search query.
|
607
|
+
#
|
608
|
+
# @param query [String]
|
609
|
+
# @param [Hash] extra additional parameters to pass along through :header_params, :query_params, or parameter name
|
610
|
+
def search_urls(query:, extra: {})
|
611
|
+
api_response = search_urls_with_http_info_impl(query, extra)
|
612
|
+
api_response.data
|
613
|
+
end
|
614
|
+
|
615
|
+
# Search Urls
|
616
|
+
#
|
617
|
+
# Perform a web search and obtain a list of relevant URLs.
|
618
|
+
#
|
619
|
+
# As an illustration, when you perform a search for “content related to MRNA,” you will receive a list of links such as the following:
|
620
|
+
#
|
621
|
+
# - https://tomrenz.substack.com/p/mrna-and-why-it-matters
|
622
|
+
#
|
623
|
+
# - https://www.statnews.com/2020/11/10/the-story-of-mrna-how-a-once-dismissed-idea-became-a-leading-technology-in-the-covid-vaccine-race/
|
624
|
+
#
|
625
|
+
# - https://www.statnews.com/2022/11/16/covid-19-vaccines-were-a-success-but-mrna-still-has-a-delivery-problem/
|
626
|
+
#
|
627
|
+
# - https://joomi.substack.com/p/were-still-being-misled-about-how
|
628
|
+
#
|
629
|
+
# Subsequently, you can submit these links to the web_scrape endpoint in order to retrieve the content of the respective web pages.
|
630
|
+
#
|
631
|
+
# Args:
|
632
|
+
# query (str): Query to search for
|
633
|
+
#
|
634
|
+
# Returns:
|
635
|
+
# FetchURLsResponse: A response object with a list of URLs for a given search query.
|
636
|
+
#
|
637
|
+
# @param query [String]
|
638
|
+
# @param [Hash] extra additional parameters to pass along through :header_params, :query_params, or parameter name
|
639
|
+
def search_urls_with_http_info(query:, extra: {})
|
640
|
+
search_urls_with_http_info_impl(query, extra)
|
641
|
+
end
|
642
|
+
|
643
|
+
# Search Urls
|
644
|
+
# Perform a web search and obtain a list of relevant URLs. As an illustration, when you perform a search for “content related to MRNA,” you will receive a list of links such as the following: - https://tomrenz.substack.com/p/mrna-and-why-it-matters - https://www.statnews.com/2020/11/10/the-story-of-mrna-how-a-once-dismissed-idea-became-a-leading-technology-in-the-covid-vaccine-race/ - https://www.statnews.com/2022/11/16/covid-19-vaccines-were-a-success-but-mrna-still-has-a-delivery-problem/ - https://joomi.substack.com/p/were-still-being-misled-about-how Subsequently, you can submit these links to the web_scrape endpoint in order to retrieve the content of the respective web pages. Args: query (str): Query to search for Returns: FetchURLsResponse: A response object with a list of URLs for a given search query.
|
645
|
+
# @param query [String]
|
646
|
+
# @param [Hash] opts the optional parameters
|
647
|
+
# @return [FetchURLsResponse]
|
648
|
+
private def search_urls_impl(query, opts = {})
|
649
|
+
data, _status_code, _headers = search_urls_with_http_info(query, opts)
|
650
|
+
data
|
651
|
+
end
|
652
|
+
|
653
|
+
# Search Urls
|
654
|
+
# Perform a web search and obtain a list of relevant URLs. As an illustration, when you perform a search for “content related to MRNA,” you will receive a list of links such as the following: - https://tomrenz.substack.com/p/mrna-and-why-it-matters - https://www.statnews.com/2020/11/10/the-story-of-mrna-how-a-once-dismissed-idea-became-a-leading-technology-in-the-covid-vaccine-race/ - https://www.statnews.com/2022/11/16/covid-19-vaccines-were-a-success-but-mrna-still-has-a-delivery-problem/ - https://joomi.substack.com/p/were-still-being-misled-about-how Subsequently, you can submit these links to the web_scrape endpoint in order to retrieve the content of the respective web pages. Args: query (str): Query to search for Returns: FetchURLsResponse: A response object with a list of URLs for a given search query.
|
655
|
+
# @param query [String]
|
656
|
+
# @param [Hash] opts the optional parameters
|
657
|
+
# @return [APIResponse] data is FetchURLsResponse, status code, headers and response
|
658
|
+
private def search_urls_with_http_info_impl(query, opts = {})
|
659
|
+
if @api_client.config.debugging
|
660
|
+
@api_client.config.logger.debug 'Calling API: UtilitiesApi.search_urls ...'
|
661
|
+
end
|
662
|
+
# verify the required parameter 'query' is set
|
663
|
+
if @api_client.config.client_side_validation && query.nil?
|
664
|
+
fail ArgumentError, "Missing the required parameter 'query' when calling UtilitiesApi.search_urls"
|
665
|
+
end
|
666
|
+
# resource path
|
667
|
+
local_var_path = '/search_urls'
|
668
|
+
|
669
|
+
# query parameters
|
670
|
+
query_params = opts[:query_params] || {}
|
671
|
+
query_params[:'query'] = query
|
672
|
+
|
673
|
+
# header parameters
|
674
|
+
header_params = opts[:header_params] || {}
|
675
|
+
# HTTP header 'Accept' (if needed)
|
676
|
+
header_params['Accept'] = @api_client.select_header_accept(['application/json'])
|
677
|
+
|
678
|
+
# form parameters
|
679
|
+
form_params = opts[:form_params] || {}
|
680
|
+
|
681
|
+
# http body (model)
|
682
|
+
post_body = opts[:debug_body]
|
683
|
+
|
684
|
+
# return_type
|
685
|
+
return_type = opts[:debug_return_type] || 'FetchURLsResponse'
|
686
|
+
|
687
|
+
# auth_names
|
688
|
+
auth_names = opts[:debug_auth_names] || ['accessToken', 'apiKey', 'customerId']
|
689
|
+
|
690
|
+
new_options = opts.merge(
|
691
|
+
:operation => :"UtilitiesApi.search_urls",
|
692
|
+
:header_params => header_params,
|
693
|
+
:query_params => query_params,
|
694
|
+
:form_params => form_params,
|
695
|
+
:body => post_body,
|
696
|
+
:auth_names => auth_names,
|
697
|
+
:return_type => return_type
|
698
|
+
)
|
699
|
+
|
700
|
+
data, status_code, headers, response = @api_client.call_api(:GET, local_var_path, new_options)
|
701
|
+
if @api_client.config.debugging
|
702
|
+
@api_client.config.logger.debug "API called: UtilitiesApi#search_urls\nData: #{data.inspect}\nStatus code: #{status_code}\nHeaders: #{headers}"
|
703
|
+
end
|
704
|
+
APIResponse::new(data, status_code, headers, response)
|
705
|
+
end
|
706
|
+
end
|
707
|
+
|
708
|
+
# top-level client access to avoid having the user to insantiate their own API instances
|
709
|
+
Utilities = UtilitiesApi::new
|
710
|
+
end
|