context.dev 1.10.0 → 1.12.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/CHANGELOG.md +16 -0
- data/README.md +3 -3
- data/lib/context_dev/models/web_web_crawl_md_params.rb +10 -1
- data/lib/context_dev/models/web_web_scrape_html_params.rb +9 -1
- data/lib/context_dev/models/web_web_scrape_md_params.rb +9 -1
- data/lib/context_dev/resources/web.rb +15 -4
- data/lib/context_dev/version.rb +1 -1
- data/rbi/context_dev/models/web_web_crawl_md_params.rbi +13 -0
- data/rbi/context_dev/models/web_web_scrape_html_params.rbi +11 -0
- data/rbi/context_dev/models/web_web_scrape_md_params.rbi +11 -0
- data/rbi/context_dev/resources/web.rbi +10 -0
- data/sig/context_dev/models/web_web_crawl_md_params.rbs +7 -0
- data/sig/context_dev/models/web_web_scrape_html_params.rbs +12 -1
- data/sig/context_dev/models/web_web_scrape_md_params.rbs +7 -0
- data/sig/context_dev/resources/web.rbs +3 -0
- metadata +1 -1
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: eca40d9a8e0ee6b1b327d64f6f6c87c3a8afe437e8e6a2043697d9331e6d5da1
|
|
4
|
+
data.tar.gz: 58e54fecfb39594e74ec0a0cbfd719afbefd1faf6cc389b8e5e8d30ff77e60bc
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: e22c565c16b51903bccd960e241b810c80a841c0b2033746f5ed135e4d5ad7a85ea4ed1925e28bd2012ffb31c8c1504b78b24bb40480e0578a3f515feda8484b
|
|
7
|
+
data.tar.gz: 933ef990401d164b31596333372e7093e89eed80659f8ea1be7483467db03757d2daa03dac8061ce7b7961059472ef1298d50f6b407ae0f217677e0297dad9f4
|
data/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,21 @@
|
|
|
1
1
|
# Changelog
|
|
2
2
|
|
|
3
|
+
## 1.12.0 (2026-05-01)
|
|
4
|
+
|
|
5
|
+
Full Changelog: [v1.11.0...v1.12.0](https://github.com/context-dot-dev/context-ruby-sdk/compare/v1.11.0...v1.12.0)
|
|
6
|
+
|
|
7
|
+
### Features
|
|
8
|
+
|
|
9
|
+
* **api:** api update ([59a9399](https://github.com/context-dot-dev/context-ruby-sdk/commit/59a93997a90f6afac755abf6686c139b92d8463e))
|
|
10
|
+
|
|
11
|
+
## 1.11.0 (2026-05-01)
|
|
12
|
+
|
|
13
|
+
Full Changelog: [v1.10.0...v1.11.0](https://github.com/context-dot-dev/context-ruby-sdk/compare/v1.10.0...v1.11.0)
|
|
14
|
+
|
|
15
|
+
### Features
|
|
16
|
+
|
|
17
|
+
* **api:** manual updates ([490fde0](https://github.com/context-dot-dev/context-ruby-sdk/commit/490fde06ead702db0640f9d1161c3d8ecedd31a9))
|
|
18
|
+
|
|
3
19
|
## 1.10.0 (2026-05-01)
|
|
4
20
|
|
|
5
21
|
Full Changelog: [v1.9.0...v1.10.0](https://github.com/context-dot-dev/context-ruby-sdk/compare/v1.9.0...v1.10.0)
|
data/README.md
CHANGED
|
@@ -8,8 +8,8 @@ It is generated with [Stainless](https://www.stainless.com/).
|
|
|
8
8
|
|
|
9
9
|
Use the Context Dev MCP Server to enable AI assistants to interact with this API, allowing them to explore endpoints, make test requests, and use documentation to help integrate this SDK into your application.
|
|
10
10
|
|
|
11
|
-
[](https://cursor.com/en-US/install-mcp?name=context
|
|
12
|
-
[](https://vscode.stainless.com/mcp/%7B%22name%22%3A%22context
|
|
11
|
+
[](https://cursor.com/en-US/install-mcp?name=context-dev-mcp&config=eyJuYW1lIjoiY29udGV4dC1kZXYtbWNwIiwidHJhbnNwb3J0IjoiaHR0cCIsInVybCI6Imh0dHBzOi8vY29udGV4dC1kZXYuc3RsbWNwLmNvbSIsImhlYWRlcnMiOnsieC1jb250ZXh0LWRldi1hcGkta2V5IjoiTXkgQVBJIEtleSJ9fQ)
|
|
12
|
+
[](https://vscode.stainless.com/mcp/%7B%22name%22%3A%22context-dev-mcp%22%2C%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fcontext-dev.stlmcp.com%22%2C%22headers%22%3A%7B%22x-context-dev-api-key%22%3A%22My%20API%20Key%22%7D%7D)
|
|
13
13
|
|
|
14
14
|
> Note: You may need to set environment variables in your MCP client.
|
|
15
15
|
|
|
@@ -26,7 +26,7 @@ To use this gem, install via Bundler by adding the following to your application
|
|
|
26
26
|
<!-- x-release-please-start-version -->
|
|
27
27
|
|
|
28
28
|
```ruby
|
|
29
|
-
gem "context.dev", "~> 1.
|
|
29
|
+
gem "context.dev", "~> 1.12.0"
|
|
30
30
|
```
|
|
31
31
|
|
|
32
32
|
<!-- x-release-please-end -->
|
|
@@ -21,6 +21,13 @@ module ContextDev
|
|
|
21
21
|
# @return [Boolean, nil]
|
|
22
22
|
optional :follow_subdomains, ContextDev::Internal::Type::Boolean, api_name: :followSubdomains
|
|
23
23
|
|
|
24
|
+
# @!attribute include_frames
|
|
25
|
+
# When true, the contents of iframes are rendered to Markdown for each crawled
|
|
26
|
+
# page.
|
|
27
|
+
#
|
|
28
|
+
# @return [Boolean, nil]
|
|
29
|
+
optional :include_frames, ContextDev::Internal::Type::Boolean, api_name: :includeFrames
|
|
30
|
+
|
|
24
31
|
# @!attribute include_images
|
|
25
32
|
# Include image references in the Markdown output
|
|
26
33
|
#
|
|
@@ -80,7 +87,7 @@ module ContextDev
|
|
|
80
87
|
# @return [Boolean, nil]
|
|
81
88
|
optional :use_main_content_only, ContextDev::Internal::Type::Boolean, api_name: :useMainContentOnly
|
|
82
89
|
|
|
83
|
-
# @!method initialize(url:, follow_subdomains: nil, include_images: nil, include_links: nil, max_age_ms: nil, max_depth: nil, max_pages: nil, parse_pdf: nil, shorten_base64_images: nil, url_regex: nil, use_main_content_only: nil, request_options: {})
|
|
90
|
+
# @!method initialize(url:, follow_subdomains: nil, include_frames: nil, include_images: nil, include_links: nil, max_age_ms: nil, max_depth: nil, max_pages: nil, parse_pdf: nil, shorten_base64_images: nil, url_regex: nil, use_main_content_only: nil, request_options: {})
|
|
84
91
|
# Some parameter documentations has been truncated, see
|
|
85
92
|
# {ContextDev::Models::WebWebCrawlMdParams} for more details.
|
|
86
93
|
#
|
|
@@ -88,6 +95,8 @@ module ContextDev
|
|
|
88
95
|
#
|
|
89
96
|
# @param follow_subdomains [Boolean] When true, follow links on subdomains of the starting URL's domain (e.g. docs.ex
|
|
90
97
|
#
|
|
98
|
+
# @param include_frames [Boolean] When true, the contents of iframes are rendered to Markdown for each crawled pag
|
|
99
|
+
#
|
|
91
100
|
# @param include_images [Boolean] Include image references in the Markdown output
|
|
92
101
|
#
|
|
93
102
|
# @param include_links [Boolean] Preserve hyperlinks in the Markdown output
|
|
@@ -13,6 +13,12 @@ module ContextDev
|
|
|
13
13
|
# @return [String]
|
|
14
14
|
required :url, String
|
|
15
15
|
|
|
16
|
+
# @!attribute include_frames
|
|
17
|
+
# When true, iframes are rendered inline into the returned HTML.
|
|
18
|
+
#
|
|
19
|
+
# @return [Boolean, nil]
|
|
20
|
+
optional :include_frames, ContextDev::Internal::Type::Boolean
|
|
21
|
+
|
|
16
22
|
# @!attribute max_age_ms
|
|
17
23
|
# Return a cached result if a prior scrape for the same parameters exists and is
|
|
18
24
|
# younger than this many milliseconds. Defaults to 1 day (86400000 ms) when
|
|
@@ -29,12 +35,14 @@ module ContextDev
|
|
|
29
35
|
# @return [Boolean, nil]
|
|
30
36
|
optional :parse_pdf, ContextDev::Internal::Type::Boolean
|
|
31
37
|
|
|
32
|
-
# @!method initialize(url:, max_age_ms: nil, parse_pdf: nil, request_options: {})
|
|
38
|
+
# @!method initialize(url:, include_frames: nil, max_age_ms: nil, parse_pdf: nil, request_options: {})
|
|
33
39
|
# Some parameter documentations has been truncated, see
|
|
34
40
|
# {ContextDev::Models::WebWebScrapeHTMLParams} for more details.
|
|
35
41
|
#
|
|
36
42
|
# @param url [String] Full URL to scrape (must include http:// or https:// protocol)
|
|
37
43
|
#
|
|
44
|
+
# @param include_frames [Boolean] When true, iframes are rendered inline into the returned HTML.
|
|
45
|
+
#
|
|
38
46
|
# @param max_age_ms [Integer] Return a cached result if a prior scrape for the same parameters exists and is y
|
|
39
47
|
#
|
|
40
48
|
# @param parse_pdf [Boolean] When true (default), PDF URLs are fetched and their text layer is extracted and
|
|
@@ -14,6 +14,12 @@ module ContextDev
|
|
|
14
14
|
# @return [String]
|
|
15
15
|
required :url, String
|
|
16
16
|
|
|
17
|
+
# @!attribute include_frames
|
|
18
|
+
# When true, the contents of iframes are rendered to Markdown.
|
|
19
|
+
#
|
|
20
|
+
# @return [Boolean, nil]
|
|
21
|
+
optional :include_frames, ContextDev::Internal::Type::Boolean
|
|
22
|
+
|
|
17
23
|
# @!attribute include_images
|
|
18
24
|
# Include image references in Markdown output
|
|
19
25
|
#
|
|
@@ -55,12 +61,14 @@ module ContextDev
|
|
|
55
61
|
# @return [Boolean, nil]
|
|
56
62
|
optional :use_main_content_only, ContextDev::Internal::Type::Boolean
|
|
57
63
|
|
|
58
|
-
# @!method initialize(url:, include_images: nil, include_links: nil, max_age_ms: nil, parse_pdf: nil, shorten_base64_images: nil, use_main_content_only: nil, request_options: {})
|
|
64
|
+
# @!method initialize(url:, include_frames: nil, include_images: nil, include_links: nil, max_age_ms: nil, parse_pdf: nil, shorten_base64_images: nil, use_main_content_only: nil, request_options: {})
|
|
59
65
|
# Some parameter documentations has been truncated, see
|
|
60
66
|
# {ContextDev::Models::WebWebScrapeMdParams} for more details.
|
|
61
67
|
#
|
|
62
68
|
# @param url [String] Full URL to scrape into LLM usable Markdown (must include http:// or https:// pr
|
|
63
69
|
#
|
|
70
|
+
# @param include_frames [Boolean] When true, the contents of iframes are rendered to Markdown.
|
|
71
|
+
#
|
|
64
72
|
# @param include_images [Boolean] Include image references in Markdown output
|
|
65
73
|
#
|
|
66
74
|
# @param include_links [Boolean] Preserve hyperlinks in Markdown output
|
|
@@ -105,12 +105,14 @@ module ContextDev
|
|
|
105
105
|
# Performs a crawl starting from a given URL, extracts page content as Markdown,
|
|
106
106
|
# and returns results for all crawled pages.
|
|
107
107
|
#
|
|
108
|
-
# @overload web_crawl_md(url:, follow_subdomains: nil, include_images: nil, include_links: nil, max_age_ms: nil, max_depth: nil, max_pages: nil, parse_pdf: nil, shorten_base64_images: nil, url_regex: nil, use_main_content_only: nil, request_options: {})
|
|
108
|
+
# @overload web_crawl_md(url:, follow_subdomains: nil, include_frames: nil, include_images: nil, include_links: nil, max_age_ms: nil, max_depth: nil, max_pages: nil, parse_pdf: nil, shorten_base64_images: nil, url_regex: nil, use_main_content_only: nil, request_options: {})
|
|
109
109
|
#
|
|
110
110
|
# @param url [String] The starting URL for the crawl (must include http:// or https:// protocol)
|
|
111
111
|
#
|
|
112
112
|
# @param follow_subdomains [Boolean] When true, follow links on subdomains of the starting URL's domain (e.g. docs.ex
|
|
113
113
|
#
|
|
114
|
+
# @param include_frames [Boolean] When true, the contents of iframes are rendered to Markdown for each crawled pag
|
|
115
|
+
#
|
|
114
116
|
# @param include_images [Boolean] Include image references in the Markdown output
|
|
115
117
|
#
|
|
116
118
|
# @param include_links [Boolean] Preserve hyperlinks in the Markdown output
|
|
@@ -150,10 +152,12 @@ module ContextDev
|
|
|
150
152
|
#
|
|
151
153
|
# Scrapes the given URL and returns the raw HTML content of the page.
|
|
152
154
|
#
|
|
153
|
-
# @overload web_scrape_html(url:, max_age_ms: nil, parse_pdf: nil, request_options: {})
|
|
155
|
+
# @overload web_scrape_html(url:, include_frames: nil, max_age_ms: nil, parse_pdf: nil, request_options: {})
|
|
154
156
|
#
|
|
155
157
|
# @param url [String] Full URL to scrape (must include http:// or https:// protocol)
|
|
156
158
|
#
|
|
159
|
+
# @param include_frames [Boolean] When true, iframes are rendered inline into the returned HTML.
|
|
160
|
+
#
|
|
157
161
|
# @param max_age_ms [Integer] Return a cached result if a prior scrape for the same parameters exists and is y
|
|
158
162
|
#
|
|
159
163
|
# @param parse_pdf [Boolean] When true (default), PDF URLs are fetched and their text layer is extracted and
|
|
@@ -169,7 +173,11 @@ module ContextDev
|
|
|
169
173
|
@client.request(
|
|
170
174
|
method: :get,
|
|
171
175
|
path: "web/scrape/html",
|
|
172
|
-
query: query.transform_keys(
|
|
176
|
+
query: query.transform_keys(
|
|
177
|
+
include_frames: "includeFrames",
|
|
178
|
+
max_age_ms: "maxAgeMs",
|
|
179
|
+
parse_pdf: "parsePDF"
|
|
180
|
+
),
|
|
173
181
|
model: ContextDev::Models::WebWebScrapeHTMLResponse,
|
|
174
182
|
options: options
|
|
175
183
|
)
|
|
@@ -205,10 +213,12 @@ module ContextDev
|
|
|
205
213
|
#
|
|
206
214
|
# Scrapes the given URL into LLM usable Markdown.
|
|
207
215
|
#
|
|
208
|
-
# @overload web_scrape_md(url:, include_images: nil, include_links: nil, max_age_ms: nil, parse_pdf: nil, shorten_base64_images: nil, use_main_content_only: nil, request_options: {})
|
|
216
|
+
# @overload web_scrape_md(url:, include_frames: nil, include_images: nil, include_links: nil, max_age_ms: nil, parse_pdf: nil, shorten_base64_images: nil, use_main_content_only: nil, request_options: {})
|
|
209
217
|
#
|
|
210
218
|
# @param url [String] Full URL to scrape into LLM usable Markdown (must include http:// or https:// pr
|
|
211
219
|
#
|
|
220
|
+
# @param include_frames [Boolean] When true, the contents of iframes are rendered to Markdown.
|
|
221
|
+
#
|
|
212
222
|
# @param include_images [Boolean] Include image references in Markdown output
|
|
213
223
|
#
|
|
214
224
|
# @param include_links [Boolean] Preserve hyperlinks in Markdown output
|
|
@@ -233,6 +243,7 @@ module ContextDev
|
|
|
233
243
|
method: :get,
|
|
234
244
|
path: "web/scrape/markdown",
|
|
235
245
|
query: query.transform_keys(
|
|
246
|
+
include_frames: "includeFrames",
|
|
236
247
|
include_images: "includeImages",
|
|
237
248
|
include_links: "includeLinks",
|
|
238
249
|
max_age_ms: "maxAgeMs",
|
data/lib/context_dev/version.rb
CHANGED
|
@@ -24,6 +24,14 @@ module ContextDev
|
|
|
24
24
|
sig { params(follow_subdomains: T::Boolean).void }
|
|
25
25
|
attr_writer :follow_subdomains
|
|
26
26
|
|
|
27
|
+
# When true, the contents of iframes are rendered to Markdown for each crawled
|
|
28
|
+
# page.
|
|
29
|
+
sig { returns(T.nilable(T::Boolean)) }
|
|
30
|
+
attr_reader :include_frames
|
|
31
|
+
|
|
32
|
+
sig { params(include_frames: T::Boolean).void }
|
|
33
|
+
attr_writer :include_frames
|
|
34
|
+
|
|
27
35
|
# Include image references in the Markdown output
|
|
28
36
|
sig { returns(T.nilable(T::Boolean)) }
|
|
29
37
|
attr_reader :include_images
|
|
@@ -96,6 +104,7 @@ module ContextDev
|
|
|
96
104
|
params(
|
|
97
105
|
url: String,
|
|
98
106
|
follow_subdomains: T::Boolean,
|
|
107
|
+
include_frames: T::Boolean,
|
|
99
108
|
include_images: T::Boolean,
|
|
100
109
|
include_links: T::Boolean,
|
|
101
110
|
max_age_ms: Integer,
|
|
@@ -115,6 +124,9 @@ module ContextDev
|
|
|
115
124
|
# docs.example.com when starting from example.com). www and apex are always
|
|
116
125
|
# treated as equivalent.
|
|
117
126
|
follow_subdomains: nil,
|
|
127
|
+
# When true, the contents of iframes are rendered to Markdown for each crawled
|
|
128
|
+
# page.
|
|
129
|
+
include_frames: nil,
|
|
118
130
|
# Include image references in the Markdown output
|
|
119
131
|
include_images: nil,
|
|
120
132
|
# Preserve hyperlinks in the Markdown output
|
|
@@ -147,6 +159,7 @@ module ContextDev
|
|
|
147
159
|
{
|
|
148
160
|
url: String,
|
|
149
161
|
follow_subdomains: T::Boolean,
|
|
162
|
+
include_frames: T::Boolean,
|
|
150
163
|
include_images: T::Boolean,
|
|
151
164
|
include_links: T::Boolean,
|
|
152
165
|
max_age_ms: Integer,
|
|
@@ -18,6 +18,13 @@ module ContextDev
|
|
|
18
18
|
sig { returns(String) }
|
|
19
19
|
attr_accessor :url
|
|
20
20
|
|
|
21
|
+
# When true, iframes are rendered inline into the returned HTML.
|
|
22
|
+
sig { returns(T.nilable(T::Boolean)) }
|
|
23
|
+
attr_reader :include_frames
|
|
24
|
+
|
|
25
|
+
sig { params(include_frames: T::Boolean).void }
|
|
26
|
+
attr_writer :include_frames
|
|
27
|
+
|
|
21
28
|
# Return a cached result if a prior scrape for the same parameters exists and is
|
|
22
29
|
# younger than this many milliseconds. Defaults to 1 day (86400000 ms) when
|
|
23
30
|
# omitted. Max is 30 days (2592000000 ms). Set to 0 to always scrape fresh.
|
|
@@ -39,6 +46,7 @@ module ContextDev
|
|
|
39
46
|
sig do
|
|
40
47
|
params(
|
|
41
48
|
url: String,
|
|
49
|
+
include_frames: T::Boolean,
|
|
42
50
|
max_age_ms: Integer,
|
|
43
51
|
parse_pdf: T::Boolean,
|
|
44
52
|
request_options: ContextDev::RequestOptions::OrHash
|
|
@@ -47,6 +55,8 @@ module ContextDev
|
|
|
47
55
|
def self.new(
|
|
48
56
|
# Full URL to scrape (must include http:// or https:// protocol)
|
|
49
57
|
url:,
|
|
58
|
+
# When true, iframes are rendered inline into the returned HTML.
|
|
59
|
+
include_frames: nil,
|
|
50
60
|
# Return a cached result if a prior scrape for the same parameters exists and is
|
|
51
61
|
# younger than this many milliseconds. Defaults to 1 day (86400000 ms) when
|
|
52
62
|
# omitted. Max is 30 days (2592000000 ms). Set to 0 to always scrape fresh.
|
|
@@ -63,6 +73,7 @@ module ContextDev
|
|
|
63
73
|
override.returns(
|
|
64
74
|
{
|
|
65
75
|
url: String,
|
|
76
|
+
include_frames: T::Boolean,
|
|
66
77
|
max_age_ms: Integer,
|
|
67
78
|
parse_pdf: T::Boolean,
|
|
68
79
|
request_options: ContextDev::RequestOptions
|
|
@@ -16,6 +16,13 @@ module ContextDev
|
|
|
16
16
|
sig { returns(String) }
|
|
17
17
|
attr_accessor :url
|
|
18
18
|
|
|
19
|
+
# When true, the contents of iframes are rendered to Markdown.
|
|
20
|
+
sig { returns(T.nilable(T::Boolean)) }
|
|
21
|
+
attr_reader :include_frames
|
|
22
|
+
|
|
23
|
+
sig { params(include_frames: T::Boolean).void }
|
|
24
|
+
attr_writer :include_frames
|
|
25
|
+
|
|
19
26
|
# Include image references in Markdown output
|
|
20
27
|
sig { returns(T.nilable(T::Boolean)) }
|
|
21
28
|
attr_reader :include_images
|
|
@@ -66,6 +73,7 @@ module ContextDev
|
|
|
66
73
|
sig do
|
|
67
74
|
params(
|
|
68
75
|
url: String,
|
|
76
|
+
include_frames: T::Boolean,
|
|
69
77
|
include_images: T::Boolean,
|
|
70
78
|
include_links: T::Boolean,
|
|
71
79
|
max_age_ms: Integer,
|
|
@@ -79,6 +87,8 @@ module ContextDev
|
|
|
79
87
|
# Full URL to scrape into LLM usable Markdown (must include http:// or https://
|
|
80
88
|
# protocol)
|
|
81
89
|
url:,
|
|
90
|
+
# When true, the contents of iframes are rendered to Markdown.
|
|
91
|
+
include_frames: nil,
|
|
82
92
|
# Include image references in Markdown output
|
|
83
93
|
include_images: nil,
|
|
84
94
|
# Preserve hyperlinks in Markdown output
|
|
@@ -104,6 +114,7 @@ module ContextDev
|
|
|
104
114
|
override.returns(
|
|
105
115
|
{
|
|
106
116
|
url: String,
|
|
117
|
+
include_frames: T::Boolean,
|
|
107
118
|
include_images: T::Boolean,
|
|
108
119
|
include_links: T::Boolean,
|
|
109
120
|
max_age_ms: Integer,
|
|
@@ -103,6 +103,7 @@ module ContextDev
|
|
|
103
103
|
params(
|
|
104
104
|
url: String,
|
|
105
105
|
follow_subdomains: T::Boolean,
|
|
106
|
+
include_frames: T::Boolean,
|
|
106
107
|
include_images: T::Boolean,
|
|
107
108
|
include_links: T::Boolean,
|
|
108
109
|
max_age_ms: Integer,
|
|
@@ -122,6 +123,9 @@ module ContextDev
|
|
|
122
123
|
# docs.example.com when starting from example.com). www and apex are always
|
|
123
124
|
# treated as equivalent.
|
|
124
125
|
follow_subdomains: nil,
|
|
126
|
+
# When true, the contents of iframes are rendered to Markdown for each crawled
|
|
127
|
+
# page.
|
|
128
|
+
include_frames: nil,
|
|
125
129
|
# Include image references in the Markdown output
|
|
126
130
|
include_images: nil,
|
|
127
131
|
# Preserve hyperlinks in the Markdown output
|
|
@@ -153,6 +157,7 @@ module ContextDev
|
|
|
153
157
|
sig do
|
|
154
158
|
params(
|
|
155
159
|
url: String,
|
|
160
|
+
include_frames: T::Boolean,
|
|
156
161
|
max_age_ms: Integer,
|
|
157
162
|
parse_pdf: T::Boolean,
|
|
158
163
|
request_options: ContextDev::RequestOptions::OrHash
|
|
@@ -161,6 +166,8 @@ module ContextDev
|
|
|
161
166
|
def web_scrape_html(
|
|
162
167
|
# Full URL to scrape (must include http:// or https:// protocol)
|
|
163
168
|
url:,
|
|
169
|
+
# When true, iframes are rendered inline into the returned HTML.
|
|
170
|
+
include_frames: nil,
|
|
164
171
|
# Return a cached result if a prior scrape for the same parameters exists and is
|
|
165
172
|
# younger than this many milliseconds. Defaults to 1 day (86400000 ms) when
|
|
166
173
|
# omitted. Max is 30 days (2592000000 ms). Set to 0 to always scrape fresh.
|
|
@@ -193,6 +200,7 @@ module ContextDev
|
|
|
193
200
|
sig do
|
|
194
201
|
params(
|
|
195
202
|
url: String,
|
|
203
|
+
include_frames: T::Boolean,
|
|
196
204
|
include_images: T::Boolean,
|
|
197
205
|
include_links: T::Boolean,
|
|
198
206
|
max_age_ms: Integer,
|
|
@@ -206,6 +214,8 @@ module ContextDev
|
|
|
206
214
|
# Full URL to scrape into LLM usable Markdown (must include http:// or https://
|
|
207
215
|
# protocol)
|
|
208
216
|
url:,
|
|
217
|
+
# When true, the contents of iframes are rendered to Markdown.
|
|
218
|
+
include_frames: nil,
|
|
209
219
|
# Include image references in Markdown output
|
|
210
220
|
include_images: nil,
|
|
211
221
|
# Preserve hyperlinks in Markdown output
|
|
@@ -4,6 +4,7 @@ module ContextDev
|
|
|
4
4
|
{
|
|
5
5
|
url: String,
|
|
6
6
|
follow_subdomains: bool,
|
|
7
|
+
include_frames: bool,
|
|
7
8
|
include_images: bool,
|
|
8
9
|
include_links: bool,
|
|
9
10
|
max_age_ms: Integer,
|
|
@@ -26,6 +27,10 @@ module ContextDev
|
|
|
26
27
|
|
|
27
28
|
def follow_subdomains=: (bool) -> bool
|
|
28
29
|
|
|
30
|
+
attr_reader include_frames: bool?
|
|
31
|
+
|
|
32
|
+
def include_frames=: (bool) -> bool
|
|
33
|
+
|
|
29
34
|
attr_reader include_images: bool?
|
|
30
35
|
|
|
31
36
|
def include_images=: (bool) -> bool
|
|
@@ -65,6 +70,7 @@ module ContextDev
|
|
|
65
70
|
def initialize: (
|
|
66
71
|
url: String,
|
|
67
72
|
?follow_subdomains: bool,
|
|
73
|
+
?include_frames: bool,
|
|
68
74
|
?include_images: bool,
|
|
69
75
|
?include_links: bool,
|
|
70
76
|
?max_age_ms: Integer,
|
|
@@ -80,6 +86,7 @@ module ContextDev
|
|
|
80
86
|
def to_hash: -> {
|
|
81
87
|
url: String,
|
|
82
88
|
follow_subdomains: bool,
|
|
89
|
+
include_frames: bool,
|
|
83
90
|
include_images: bool,
|
|
84
91
|
include_links: bool,
|
|
85
92
|
max_age_ms: Integer,
|
|
@@ -1,7 +1,12 @@
|
|
|
1
1
|
module ContextDev
|
|
2
2
|
module Models
|
|
3
3
|
type web_web_scrape_html_params =
|
|
4
|
-
{
|
|
4
|
+
{
|
|
5
|
+
url: String,
|
|
6
|
+
include_frames: bool,
|
|
7
|
+
max_age_ms: Integer,
|
|
8
|
+
parse_pdf: bool
|
|
9
|
+
}
|
|
5
10
|
& ContextDev::Internal::Type::request_parameters
|
|
6
11
|
|
|
7
12
|
class WebWebScrapeHTMLParams < ContextDev::Internal::Type::BaseModel
|
|
@@ -10,6 +15,10 @@ module ContextDev
|
|
|
10
15
|
|
|
11
16
|
attr_accessor url: String
|
|
12
17
|
|
|
18
|
+
attr_reader include_frames: bool?
|
|
19
|
+
|
|
20
|
+
def include_frames=: (bool) -> bool
|
|
21
|
+
|
|
13
22
|
attr_reader max_age_ms: Integer?
|
|
14
23
|
|
|
15
24
|
def max_age_ms=: (Integer) -> Integer
|
|
@@ -20,6 +29,7 @@ module ContextDev
|
|
|
20
29
|
|
|
21
30
|
def initialize: (
|
|
22
31
|
url: String,
|
|
32
|
+
?include_frames: bool,
|
|
23
33
|
?max_age_ms: Integer,
|
|
24
34
|
?parse_pdf: bool,
|
|
25
35
|
?request_options: ContextDev::request_opts
|
|
@@ -27,6 +37,7 @@ module ContextDev
|
|
|
27
37
|
|
|
28
38
|
def to_hash: -> {
|
|
29
39
|
url: String,
|
|
40
|
+
include_frames: bool,
|
|
30
41
|
max_age_ms: Integer,
|
|
31
42
|
parse_pdf: bool,
|
|
32
43
|
request_options: ContextDev::RequestOptions
|
|
@@ -3,6 +3,7 @@ module ContextDev
|
|
|
3
3
|
type web_web_scrape_md_params =
|
|
4
4
|
{
|
|
5
5
|
url: String,
|
|
6
|
+
include_frames: bool,
|
|
6
7
|
include_images: bool,
|
|
7
8
|
include_links: bool,
|
|
8
9
|
max_age_ms: Integer,
|
|
@@ -18,6 +19,10 @@ module ContextDev
|
|
|
18
19
|
|
|
19
20
|
attr_accessor url: String
|
|
20
21
|
|
|
22
|
+
attr_reader include_frames: bool?
|
|
23
|
+
|
|
24
|
+
def include_frames=: (bool) -> bool
|
|
25
|
+
|
|
21
26
|
attr_reader include_images: bool?
|
|
22
27
|
|
|
23
28
|
def include_images=: (bool) -> bool
|
|
@@ -44,6 +49,7 @@ module ContextDev
|
|
|
44
49
|
|
|
45
50
|
def initialize: (
|
|
46
51
|
url: String,
|
|
52
|
+
?include_frames: bool,
|
|
47
53
|
?include_images: bool,
|
|
48
54
|
?include_links: bool,
|
|
49
55
|
?max_age_ms: Integer,
|
|
@@ -55,6 +61,7 @@ module ContextDev
|
|
|
55
61
|
|
|
56
62
|
def to_hash: -> {
|
|
57
63
|
url: String,
|
|
64
|
+
include_frames: bool,
|
|
58
65
|
include_images: bool,
|
|
59
66
|
include_links: bool,
|
|
60
67
|
max_age_ms: Integer,
|
|
@@ -27,6 +27,7 @@ module ContextDev
|
|
|
27
27
|
def web_crawl_md: (
|
|
28
28
|
url: String,
|
|
29
29
|
?follow_subdomains: bool,
|
|
30
|
+
?include_frames: bool,
|
|
30
31
|
?include_images: bool,
|
|
31
32
|
?include_links: bool,
|
|
32
33
|
?max_age_ms: Integer,
|
|
@@ -41,6 +42,7 @@ module ContextDev
|
|
|
41
42
|
|
|
42
43
|
def web_scrape_html: (
|
|
43
44
|
url: String,
|
|
45
|
+
?include_frames: bool,
|
|
44
46
|
?max_age_ms: Integer,
|
|
45
47
|
?parse_pdf: bool,
|
|
46
48
|
?request_options: ContextDev::request_opts
|
|
@@ -53,6 +55,7 @@ module ContextDev
|
|
|
53
55
|
|
|
54
56
|
def web_scrape_md: (
|
|
55
57
|
url: String,
|
|
58
|
+
?include_frames: bool,
|
|
56
59
|
?include_images: bool,
|
|
57
60
|
?include_links: bool,
|
|
58
61
|
?max_age_ms: Integer,
|