Class: Retab::Extractions

Inherits:
Object
  • Object
show all
Defined in:
lib/retab/extractions.rb

Instance Method Summary collapse

Constructor Details

#initialize(client) ⇒ Extractions

Returns a new instance of Extractions.



9
10
11
 
# File 'lib/retab/extractions.rb', line 9

def initialize(client)
  @client = client
end

Instance Method Details

#create(document:, json_schema:, model: nil, instructions: nil, n_consensus: nil, metadata: nil, additional_messages: nil, bust_cache: nil, stream: nil, background: nil, chunking_keys: nil, request_options: {}) ⇒ Retab::Extraction

Create Extraction

Parameters:

  • document (Retab::MimeData, Pathname, IO, String, Hash)
  • json_schema (Hash{String => Object}) —

    JSON schema describing the structured output

  • model (String, nil) (defaults to: nil) —

    The model to use for the extraction

  • instructions (String, nil) (defaults to: nil) —

    Free-form instructions appended to the system prompt to steer the extraction.

  • n_consensus (Integer, nil) (defaults to: nil) —

    Number of consensus extraction runs to perform. Uses deterministic single-pass when set to 1.

  • metadata (Hash{String => String}, nil) (defaults to: nil) —

    User-defined metadata to associate with this extraction

  • additional_messages (Array<Hash{String => Object}>, nil) (defaults to: nil) —

    Additional chat messages forwarded to the extraction model.

  • bust_cache (Boolean, nil) (defaults to: nil) —

    If true, skip the LLM cache and force a fresh completion

  • stream (Boolean, nil) (defaults to: nil)
  • background (Boolean, nil) (defaults to: nil) —

    If true, run asynchronously: returns immediately with status ‘queued’ and an empty output. Poll GET /v1/<primitive>/id until status is terminal. Mutually exclusive with stream.

  • chunking_keys (Hash{String => String}, nil) (defaults to: nil)
  • request_options (Hash) (defaults to: {}) —

    (see Retab::Types::RequestOptions)

Returns:



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
 
# File 'lib/retab/extractions.rb', line 115

def create(
  document:,
  json_schema:,
  model: nil,
  instructions: nil,
  n_consensus: nil,
  metadata: nil,
  additional_messages: nil,
  bust_cache: nil,
  stream: nil,
  background: nil,
  chunking_keys: nil,
  request_options: {}
)
  document = Retab::MimeData.coerce(document, client: @client) unless document.nil?
  body = {
    "document" => document,
    "json_schema" => json_schema,
    "model" => model,
    "instructions" => instructions,
    "n_consensus" => n_consensus,
    "metadata" => metadata,
    "additional_messages" => additional_messages,
    "bust_cache" => bust_cache,
    "stream" => stream,
    "background" => background,
    "chunking_keys" => chunking_keys
  }.compact
  response = @client.request(
    method: :post,
    path: "/v1/extractions",
    auth: true,
    body: body,
    request_options: request_options
  )
  result = Retab::Extraction.new(response.body)
  result.last_response = Retab::Types::ApiResponse.new(
    http_status: response.code.to_i,
    http_headers: response.each_header.to_h,
    request_id: response["x-request-id"]
  )
  result
end

#create_extraction_cancel(extraction_id:, request_options: {}) ⇒ Retab::Extraction

Cancel Extraction

Parameters:

  • extraction_id (String)
  • request_options (Hash) (defaults to: {}) —

    (see Retab::Types::RequestOptions)

Returns:



261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
 
# File 'lib/retab/extractions.rb', line 261

def create_extraction_cancel(
  extraction_id:,
  request_options: {}
)
  response = @client.request(
    method: :post,
    path: "/v1/extractions/#{Retab::Util.encode_path(extraction_id)}/cancel",
    auth: true,
    request_options: request_options
  )
  result = Retab::Extraction.new(response.body)
  result.last_response = Retab::Types::ApiResponse.new(
    http_status: response.code.to_i,
    http_headers: response.each_header.to_h,
    request_id: response["x-request-id"]
  )
  result
end

#create_stream(document:, json_schema:, model: nil, instructions: nil, n_consensus: nil, metadata: nil, additional_messages: nil, bust_cache: nil, stream: nil, background: nil, chunking_keys: nil, request_options: {}) ⇒ void

This method returns an undefined value.

Create Extraction Stream

Parameters:

  • document (Retab::MimeData, Pathname, IO, String, Hash)
  • json_schema (Hash{String => Object}) —

    JSON schema describing the structured output

  • model (String, nil) (defaults to: nil) —

    The model to use for the extraction

  • instructions (String, nil) (defaults to: nil) —

    Free-form instructions appended to the system prompt to steer the extraction.

  • n_consensus (Integer, nil) (defaults to: nil) —

    Number of consensus extraction runs to perform. Uses deterministic single-pass when set to 1.

  • metadata (Hash{String => String}, nil) (defaults to: nil) —

    User-defined metadata to associate with this extraction

  • additional_messages (Array<Hash{String => Object}>, nil) (defaults to: nil) —

    Additional chat messages forwarded to the extraction model.

  • bust_cache (Boolean, nil) (defaults to: nil) —

    If true, skip the LLM cache and force a fresh completion

  • stream (Boolean, nil) (defaults to: nil)
  • background (Boolean, nil) (defaults to: nil) —

    If true, run asynchronously: returns immediately with status ‘queued’ and an empty output. Poll GET /v1/<primitive>/id until status is terminal. Mutually exclusive with stream.

  • chunking_keys (Hash{String => String}, nil) (defaults to: nil)
  • request_options (Hash) (defaults to: {}) —

    (see Retab::Types::RequestOptions)



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
 
# File 'lib/retab/extractions.rb', line 173

def create_stream(
  document:,
  json_schema:,
  model: nil,
  instructions: nil,
  n_consensus: nil,
  metadata: nil,
  additional_messages: nil,
  bust_cache: nil,
  stream: nil,
  background: nil,
  chunking_keys: nil,
  request_options: {}
)
  document = Retab::MimeData.coerce(document, client: @client) unless document.nil?
  body = {
    "document" => document,
    "json_schema" => json_schema,
    "model" => model,
    "instructions" => instructions,
    "n_consensus" => n_consensus,
    "metadata" => metadata,
    "additional_messages" => additional_messages,
    "bust_cache" => bust_cache,
    "stream" => stream,
    "background" => background,
    "chunking_keys" => chunking_keys
  }.compact
  @client.request(
    method: :post,
    path: "/v1/extractions/stream",
    auth: true,
    body: body,
    request_options: request_options
  )
  nil
end

#delete(extraction_id:, request_options: {}) ⇒ void

This method returns an undefined value.

Delete Extraction

Parameters:

  • extraction_id (String)
  • request_options (Hash) (defaults to: {}) —

    (see Retab::Types::RequestOptions)



244
245
246
247
248
249
250
251
252
253
254
255
 
# File 'lib/retab/extractions.rb', line 244

def delete(
  extraction_id:,
  request_options: {}
)
  @client.request(
    method: :delete,
    path: "/v1/extractions/#{Retab::Util.encode_path(extraction_id)}",
    auth: true,
    request_options: request_options
  )
  nil
end

#get(extraction_id:, include_output: true, request_options: {}) ⇒ Retab::Extraction

Get Extraction

Parameters:

  • extraction_id (String)
  • include_output (Boolean, nil) (defaults to: true) —

    When false, returns a cheap status-only projection (no output), served from cache for in-flight background runs.

  • request_options (Hash) (defaults to: {}) —

    (see Retab::Types::RequestOptions)

Returns:



216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
 
# File 'lib/retab/extractions.rb', line 216

def get(
  extraction_id:,
  include_output: true,
  request_options: {}
)
  params = {
    "include_output" => include_output
  }.compact
  response = @client.request(
    method: :get,
    path: "/v1/extractions/#{Retab::Util.encode_path(extraction_id)}",
    auth: true,
    params: params,
    request_options: request_options
  )
  result = Retab::Extraction.new(response.body)
  result.last_response = Retab::Types::ApiResponse.new(
    http_status: response.code.to_i,
    http_headers: response.each_header.to_h,
    request_id: response["x-request-id"]
  )
  result
end

#list(before: nil, after: nil, limit: 10, order: "desc", filename: nil, filename_regex: nil, filename_contains: nil, document_type: nil, status: nil, from_date: nil, to_date: nil, metadata: nil, request_options: {}) ⇒ Retab::PaginatedList<Retab::Extraction>

List Extractions

Parameters:

  • before (String, nil) (defaults to: nil)
  • after (String, nil) (defaults to: nil)
  • limit (Integer, nil) (defaults to: 10)
  • order (Retab::Types::ExtractionsOrder, nil) (defaults to: "desc")
  • filename (String, nil) (defaults to: nil)
  • filename_regex (String, nil) (defaults to: nil) —

    Deprecated alias for prefix filename filtering. Regex patterns are rejected.

  • filename_contains (String, nil) (defaults to: nil) —

    Plain-text search over the filename.

  • document_type (Array<String>, nil) (defaults to: nil) —

    Filter by document type. Can be repeated. Accepted values: bmp, csv, doc, docm, docx, dotm, dotx, eml, gif, heic, heif, htm, html, jpeg, jpg, json, md, mhtml, msg, odp, ods, odt, ots, ott, pdf, png, ppt, pptx, rtf, svg, tif, tiff, tsv, txt, webp, xlam, xls, xlsb, xlsm, xlsx, xltm, xltx, xml, yaml, yml.

  • status (Retab::Types::ExtractionsStatus, nil) (defaults to: nil)
  • from_date (String, nil) (defaults to: nil)
  • to_date (String, nil) (defaults to: nil)
  • metadata (String, nil) (defaults to: nil)
  • request_options (Hash) (defaults to: {}) —

    (see Retab::Types::RequestOptions)

Returns:



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
 
# File 'lib/retab/extractions.rb', line 28

def list(
  before: nil,
  after: nil,
  limit: 10,
  order: "desc",
  filename: nil,
  filename_regex: nil,
  filename_contains: nil,
  document_type: nil,
  status: nil,
  from_date: nil,
  to_date: nil,
  metadata: nil,
  request_options: {}
)
  params = {
    "before" => before,
    "after" => after,
    "limit" => limit,
    "order" => order,
    "filename" => filename,
    "filename_regex" => filename_regex,
    "filename_contains" => filename_contains,
    "document_type" => document_type,
    "status" => status,
    "from_date" => from_date,
    "to_date" => to_date,
    "metadata" => metadata
  }.compact
  response = @client.request(
    method: :get,
    path: "/v1/extractions",
    auth: true,
    params: params,
    request_options: request_options
  )
  fetch_next = -> (cursor) {
    list(
      before: before,
      after: cursor,
      limit: limit,
      order: order,
      filename: filename,
      filename_regex: filename_regex,
      filename_contains: filename_contains,
      document_type: document_type,
      status: status,
      from_date: from_date,
      to_date: to_date,
      metadata: metadata,
      request_options: request_options
    )
  }
  Retab::PaginatedList.from_response(
    response,
    model: Retab::Extraction,
    filters: {
      before: before,
      limit: limit,
      order: order,
      filename: filename,
      filename_regex: filename_regex,
      filename_contains: filename_contains,
      document_type: document_type,
      status: status,
      from_date: from_date,
      to_date: to_date,
      metadata: metadata
    },
    fetch_next: fetch_next
  )
end

#sources(extraction_id:, request_options: {}) ⇒ Retab::SourcesResponse

Get Extraction Sources

Parameters:

  • extraction_id (String)
  • request_options (Hash) (defaults to: {}) —

    (see Retab::Types::RequestOptions)

Returns:



284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
 
# File 'lib/retab/extractions.rb', line 284

def sources(
  extraction_id:,
  request_options: {}
)
  response = @client.request(
    method: :get,
    path: "/v1/extractions/#{Retab::Util.encode_path(extraction_id)}/sources",
    auth: true,
    request_options: request_options
  )
  result = Retab::SourcesResponse.new(response.body)
  result.last_response = Retab::Types::ApiResponse.new(
    http_status: response.code.to_i,
    http_headers: response.each_header.to_h,
    request_id: response["x-request-id"]
  )
  result
end