-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathparse.ts
More file actions
287 lines (266 loc) · 6.11 KB
/
Copy pathparse.ts
File metadata and controls
287 lines (266 loc) · 6.11 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
// File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
import { APIResource } from '../core/resource';
import { APIPromise } from '../core/api-promise';
import { type Uploadable } from '../core/uploads';
import { buildHeaders } from '../internal/headers';
import { RequestOptions } from '../internal/request-options';
export class Parse extends APIResource {
/**
* Converts raw text, source code, web/data, PDF, Microsoft Office, and image bytes
* into LLM-usable Markdown.
*/
handle(
body: Uploadable,
params: ParseHandleParams,
options?: RequestOptions,
): APIPromise<ParseHandleResponse> {
const {
client,
extension,
includeImages,
includeLinks,
ocr,
pdf,
shortenBase64Images,
tags,
useMainContentOnly,
zdr,
} = params;
return this._client.post('/parse', {
body: body,
query: {
client,
extension,
includeImages,
includeLinks,
ocr,
pdf,
shortenBase64Images,
tags,
useMainContentOnly,
zdr,
},
...options,
headers: buildHeaders([{ 'Content-Type': 'application/octet-stream' }, options?.headers]),
});
}
}
export interface ParseHandleResponse {
/**
* Input bytes converted to GitHub Flavored Markdown
*/
markdown: string;
/**
* Indicates success
*/
success: true;
/**
* Detected content type used for parsing
*/
type:
| 'html'
| 'xml'
| 'json'
| 'jsonl'
| 'text'
| 'csv'
| 'tsv'
| 'markdown'
| 'yaml'
| 'python'
| 'java'
| 'javascript'
| 'php'
| 'shell'
| 'ruby'
| 'typescript'
| 'rtf'
| 'srt'
| 'css'
| 'scss'
| 'less'
| 'stylus'
| 'sass'
| 'svg'
| 'pdf'
| 'docx'
| 'doc'
| 'xlsx'
| 'xls'
| 'pptx'
| 'ppt'
| 'jpg'
| 'png'
| 'gif'
| 'bmp'
| 'tiff'
| 'webp'
| 'ppm'
| 'pbm'
| 'pgm'
| 'pnm';
/**
* Metadata about the API key used for the request. Included in every response
* whenever a valid API key is provided, even when the response status is not 200.
*/
key_metadata?: ParseHandleResponse.KeyMetadata;
}
export namespace ParseHandleResponse {
/**
* Metadata about the API key used for the request. Included in every response
* whenever a valid API key is provided, even when the response status is not 200.
*/
export interface KeyMetadata {
/**
* The number of credits consumed by this request.
*/
credits_consumed: number;
/**
* The number of credits remaining for your organization after this request.
*/
credits_remaining: number;
}
}
export interface ParseHandleParams {
/**
* Query param: Optional client identifier used for usage attribution.
*/
client?: string;
/**
* Query param: Optional file extension hint, such as pdf, docx, xlsx, pptx, html,
* json, csv, md, py, rtf, jpg, png, or txt.
*/
extension?:
| 'txt'
| 'text'
| 'md'
| 'markdown'
| 'html'
| 'htm'
| 'xhtml'
| 'xml'
| 'rss'
| 'atom'
| 'csv'
| 'tsv'
| 'yaml'
| 'yml'
| 'py'
| 'java'
| 'js'
| 'jsx'
| 'mjs'
| 'cjs'
| 'json'
| 'jsonl'
| 'ndjson'
| 'php'
| 'sh'
| 'bash'
| 'zsh'
| 'fish'
| 'rb'
| 'ts'
| 'tsx'
| 'rtf'
| 'srt'
| 'css'
| 'scss'
| 'less'
| 'styl'
| 'sass'
| 'svg'
| 'pdf'
| 'docx'
| 'doc'
| 'xlsx'
| 'xlsm'
| 'xlsb'
| 'xltx'
| 'xltm'
| 'xls'
| 'pptx'
| 'pptm'
| 'ppsx'
| 'ppsm'
| 'potx'
| 'potm'
| 'ppt'
| 'pps'
| 'pot'
| 'jpg'
| 'jpeg'
| 'jpe'
| 'png'
| 'gif'
| 'bmp'
| 'tiff'
| 'tif'
| 'webp'
| 'ppm'
| 'pbm'
| 'pgm'
| 'pnm';
/**
* Query param: Include image references in Markdown output
*/
includeImages?: boolean | 'true' | 'false';
/**
* Query param: Preserve hyperlinks in Markdown output
*/
includeLinks?: boolean | 'true' | 'false';
/**
* Query param: When true for PDF inputs, detect and OCR images embedded in the
* selected pages, inserting recognized text at each image's position in page
* reading order while preserving the PDF text layer. pdf.start/pdf.end limit the
* inclusive page range. When false, all OCR is disabled, including the automatic
* scanned-PDF fallback.
*/
ocr?: boolean | 'true' | 'false';
/**
* Query param: PDF page-range options as a JSON object, e.g. {"start": 2, "end":
* 5}.
*/
pdf?: ParseHandleParams.Pdf;
/**
* Query param: Shorten base64-encoded image data in the Markdown output
*/
shortenBase64Images?: boolean | 'true' | 'false';
/**
* Query param: Optional comma-separated caller-defined tags for tracking this
* request. Tags are recorded on the request's usage log and can be used to filter
* usage on the dashboard usage page. Up to 20 tags, each 1-50 characters.
*/
tags?: Array<string>;
/**
* Query param: Extract only the main content from HTML-like inputs
*/
useMainContentOnly?: boolean | 'true' | 'false';
/**
* Query param: Set to enabled to bypass shared caches and omit request and
* response content from retained usage logs. Requires zero data retention to be
* enabled for your organization (contact support@context.dev), otherwise the
* request fails with ZDR_NOT_ENABLED. Successful ZDR responses include
* X-Context-ZDR: true.
*/
zdr?: 'enabled' | 'disabled';
}
export namespace ParseHandleParams {
/**
* PDF page-range options as a JSON object, e.g. {"start": 2, "end": 5}.
*/
export interface Pdf {
/**
* Last 1-based PDF page to parse. When omitted, parsing ends at the last page.
* Must be greater than or equal to start when both are provided.
*/
end?: number;
/**
* First 1-based PDF page to parse. When omitted, parsing starts at the first page.
*/
start?: number;
}
}
export declare namespace Parse {
export { type ParseHandleResponse as ParseHandleResponse, type ParseHandleParams as ParseHandleParams };
}