Class: Rafflesia::Datasets

Inherits:
Object
  • Object
show all
Defined in:
lib/rafflesia/datasets.rb

Instance Method Summary collapse

Constructor Details

#initialize(client) ⇒ Datasets

Returns a new instance of Datasets.



9
10
11
 
# File 'lib/rafflesia/datasets.rb', line 9

def initialize(client)
  @client = client
end

Instance Method Details

#buildsBuild(input_dir:, compact: nil, compact_shard_size: nil, dataset_name: nil, dataset_version: nil, dry_run: nil, from_manifest_path: nil, input_paths: nil, manifest_path: nil, max_failure_count: nil, output_dir: nil, pocket_backend: nil, pocket_cache_mode: nil, profile: nil, recursive: nil, response_mode: nil, resume: nil, source: nil, tables: nil, target_namespace: nil, threshold: nil, request_options: {}) ⇒ Rafflesia::EnvelopeDatasetBuildData

POST /v1/datasets/builds/build

Parameters:

  • compact (Boolean, nil) (defaults to: nil)
  • compact_shard_size (Integer, nil) (defaults to: nil)
  • dataset_name (String, nil) (defaults to: nil)
  • dataset_version (String, nil) (defaults to: nil)
  • dry_run (Boolean, nil) (defaults to: nil)
  • from_manifest_path (String, nil) (defaults to: nil) —

    Optional source dataset manifest to reuse matching structures and table artifacts from while materializing requested missing tables into a new manifest.

  • input_dir (String)
  • input_paths (Array<String>, nil) (defaults to: nil)
  • manifest_path (String, nil) (defaults to: nil)
  • max_failure_count (Integer, nil) (defaults to: nil)
  • output_dir (String, nil) (defaults to: nil)
  • pocket_backend (Rafflesia::Types::DatasetBuildRequestPocketBackend, nil) (defaults to: nil)
  • pocket_cache_mode (Rafflesia::Types::DatasetBuildRequestPocketCacheMode, nil) (defaults to: nil)
  • profile (Boolean, nil) (defaults to: nil)
  • recursive (Boolean, nil) (defaults to: nil)
  • response_mode (Rafflesia::Types::DatasetBuildRequestResponseMode, nil) (defaults to: nil) —

    Response payload mode; full includes the inline manifest, summary/compact returns counts, object refs, table summaries, and manifest_path without embedding the manifest rows

  • resume (Boolean, nil) (defaults to: nil)
  • source (String, nil) (defaults to: nil)
  • tables (Array<String>, nil) (defaults to: nil)
  • target_namespace (String, nil) (defaults to: nil)
  • threshold (Float, nil) (defaults to: nil)
  • request_options (Hash) (defaults to: {}) —

    (see Rafflesia::Types::RequestOptions)

Returns:



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
 
# File 'lib/rafflesia/datasets.rb', line 37

def buildsBuild(
  input_dir:,
  compact: nil,
  compact_shard_size: nil,
  dataset_name: nil,
  dataset_version: nil,
  dry_run: nil,
  from_manifest_path: nil,
  input_paths: nil,
  manifest_path: nil,
  max_failure_count: nil,
  output_dir: nil,
  pocket_backend: nil,
  pocket_cache_mode: nil,
  profile: nil,
  recursive: nil,
  response_mode: nil,
  resume: nil,
  source: nil,
  tables: nil,
  target_namespace: nil,
  threshold: nil,
  request_options: {}
)
  body = {
    'compact' => compact,
    'compact_shard_size' => compact_shard_size,
    'dataset_name' => dataset_name,
    'dataset_version' => dataset_version,
    'dry_run' => dry_run,
    'from_manifest_path' => from_manifest_path,
    'input_dir' => input_dir,
    'input_paths' => input_paths,
    'manifest_path' => manifest_path,
    'max_failure_count' => max_failure_count,
    'output_dir' => output_dir,
    'pocket_backend' => pocket_backend,
    'pocket_cache_mode' => pocket_cache_mode,
    'profile' => profile,
    'recursive' => recursive,
    'response_mode' => response_mode,
    'resume' => resume,
    'source' => source,
    'tables' => tables,
    'target_namespace' => target_namespace,
    'threshold' => threshold
  }.compact
  response = @client.request(
    method: :post,
    path: '/v1/datasets/builds/build',
    auth: true,
    body: body,
    request_options: request_options
  )
  result = Rafflesia::EnvelopeDatasetBuildData.new(response.body)
  result.last_response = Rafflesia::Types::ApiResponse.new(http_status: response.code.to_i, http_headers: response.each_header.to_h, request_id: response["x-request-id"])
  result
end

#compact(manifest_path:, output_dir: nil, output_manifest_path: nil, replace: nil, shard_size: nil, request_options: {}) ⇒ Rafflesia::EnvelopeDatasetCompactData

POST /v1/datasets/compact

Parameters:

  • manifest_path (String)
  • output_dir (String, nil) (defaults to: nil)
  • output_manifest_path (String, nil) (defaults to: nil)
  • replace (Boolean, nil) (defaults to: nil)
  • shard_size (Integer, nil) (defaults to: nil)
  • request_options (Hash) (defaults to: {}) —

    (see Rafflesia::Types::RequestOptions)

Returns:



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
 
# File 'lib/rafflesia/datasets.rb', line 104

def compact(
  manifest_path:,
  output_dir: nil,
  output_manifest_path: nil,
  replace: nil,
  shard_size: nil,
  request_options: {}
)
  body = {
    'manifest_path' => manifest_path,
    'output_dir' => output_dir,
    'output_manifest_path' => output_manifest_path,
    'replace' => replace,
    'shard_size' => shard_size
  }.compact
  response = @client.request(
    method: :post,
    path: '/v1/datasets/compact',
    auth: true,
    body: body,
    request_options: request_options
  )
  result = Rafflesia::EnvelopeDatasetCompactData.new(response.body)
  result.last_response = Rafflesia::Types::ApiResponse.new(http_status: response.code.to_i, http_headers: response.each_header.to_h, request_id: response["x-request-id"])
  result
end

#comparisonsCompare(manifest_path_a:, manifest_path_b:, request_options: {}) ⇒ Rafflesia::EnvelopeDatasetCompareData

POST /v1/datasets/comparisons/compare

Parameters:

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

    (see Rafflesia::Types::RequestOptions)

Returns:



136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
 
# File 'lib/rafflesia/datasets.rb', line 136

def comparisonsCompare(
  manifest_path_a:,
  manifest_path_b:,
  request_options: {}
)
  body = {
    'manifest_path_a' => manifest_path_a,
    'manifest_path_b' => manifest_path_b
  }
  response = @client.request(
    method: :post,
    path: '/v1/datasets/comparisons/compare',
    auth: true,
    body: body,
    request_options: request_options
  )
  result = Rafflesia::EnvelopeDatasetCompareData.new(response.body)
  result.last_response = Rafflesia::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(limit: nil, request_options: {}) ⇒ Rafflesia::EnvelopeDatasetListData

GET /v1/datasets/list

Parameters:

  • limit (Integer, nil) (defaults to: nil)
  • request_options (Hash) (defaults to: {}) —

    (see Rafflesia::Types::RequestOptions)

Returns:



161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
 
# File 'lib/rafflesia/datasets.rb', line 161

def list(
  limit: nil,
  request_options: {}
)
  params = {
    'limit' => limit
  }.compact
  response = @client.request(
    method: :get,
    path: '/v1/datasets/list',
    auth: true,
    params: params,
    request_options: request_options
  )
  result = Rafflesia::EnvelopeDatasetListData.new(response.body)
  result.last_response = Rafflesia::Types::ApiResponse.new(http_status: response.code.to_i, http_headers: response.each_header.to_h, request_id: response["x-request-id"])
  result
end

#manifestsInspect(manifest_path:, request_options: {}) ⇒ Rafflesia::EnvelopeDatasetManifestInspectData

POST /v1/datasets/manifests/inspect

Parameters:

  • manifest_path (String) —

    Dataset manifest JSON path.

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

    (see Rafflesia::Types::RequestOptions)

Returns:



184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
 
# File 'lib/rafflesia/datasets.rb', line 184

def manifestsInspect(
  manifest_path:,
  request_options: {}
)
  body = {
    'manifest_path' => manifest_path
  }
  response = @client.request(
    method: :post,
    path: '/v1/datasets/manifests/inspect',
    auth: true,
    body: body,
    request_options: request_options
  )
  result = Rafflesia::EnvelopeDatasetManifestInspectData.new(response.body)
  result.last_response = Rafflesia::Types::ApiResponse.new(http_status: response.code.to_i, http_headers: response.each_header.to_h, request_id: response["x-request-id"])
  result
end

#manifestsScan(root:, dataset_name: nil, failure_free: nil, limit: nil, require_tables: nil, sort: nil, version_contains: nil, version_prefix: nil, request_options: {}) ⇒ Rafflesia::EnvelopeDatasetManifestScanData

POST /v1/datasets/manifests/scan

Parameters:

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

    Only include manifests whose dataset_name equals this value.

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

    Only include manifests with zero recorded build failures and at least one non-empty table artifact.

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

    Maximum matched manifests to return after sorting.

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

    Only include manifests that contain every one of these table families.

  • root (String) —

    Directory scanned recursively for dataset manifest JSON files (typically a lake root).

  • sort (Rafflesia::Types::DatasetManifestScanRequestSort, nil) (defaults to: nil) —

    Ordering: modified (freshest file first, default) or version (dataset_version descending).

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

    Only include manifests whose dataset_version contains this substring.

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

    Only include manifests whose dataset_version starts with this prefix.

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

    (see Rafflesia::Types::RequestOptions)

Returns:



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
 
# File 'lib/rafflesia/datasets.rb', line 214

def manifestsScan(
  root:,
  dataset_name: nil,
  failure_free: nil,
  limit: nil,
  require_tables: nil,
  sort: nil,
  version_contains: nil,
  version_prefix: nil,
  request_options: {}
)
  body = {
    'dataset_name' => dataset_name,
    'failure_free' => failure_free,
    'limit' => limit,
    'require_tables' => require_tables,
    'root' => root,
    'sort' => sort,
    'version_contains' => version_contains,
    'version_prefix' => version_prefix
  }.compact
  response = @client.request(
    method: :post,
    path: '/v1/datasets/manifests/scan',
    auth: true,
    body: body,
    request_options: request_options
  )
  result = Rafflesia::EnvelopeDatasetManifestScanData.new(response.body)
  result.last_response = Rafflesia::Types::ApiResponse.new(http_status: response.code.to_i, http_headers: response.each_header.to_h, request_id: response["x-request-id"])
  result
end

#relationReleasesObjectsUpload(expected_sha_256:, expected_size_bytes:, kind: nil, request_options: {}) ⇒ Hash{String => Object}

Stream one verified immutable relation-release object.

Parameters:

  • expected_sha_256 (String)
  • expected_size_bytes (Integer)
  • kind (String, nil) (defaults to: nil)
  • request_options (Hash) (defaults to: {}) —

    (see Rafflesia::Types::RequestOptions)

Returns:

  • (Hash{String => Object}) 


253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
 
# File 'lib/rafflesia/datasets.rb', line 253

def relationReleasesObjectsUpload(
  expected_sha_256:,
  expected_size_bytes:,
  kind: nil,
  request_options: {}
)
  params = {
    'expected_sha256' => expected_sha_256,
    'expected_size_bytes' => expected_size_bytes,
    'kind' => kind
  }.compact
  response = @client.request(
    method: :put,
    path: '/v1/datasets/relation-releases/objects/upload',
    auth: true,
    params: params,
    request_options: request_options
  )
  JSON.parse(response.body)
end

#relationReleasesPublish(artifacts:, database:, release:, release_digest:, created_at: nil, dataset_kind: nil, dry_run: nil, manifest_object_id: nil, manifest_path: nil, manifest_sha_256: nil, manifest_size_bytes: nil, source: nil, request_options: {}) ⇒ Rafflesia::EnvelopeRelationReleasePublicationData

POST /v1/datasets/relation-releases/publish

Parameters:

  • artifacts (Array<Rafflesia::RelationReleasePublicationArtifact>, nil)
  • created_at (String, nil) (defaults to: nil)
  • database (String)
  • dataset_kind (String, nil) (defaults to: nil)
  • dry_run (Boolean, nil) (defaults to: nil) —

    Validate the immutable publication without uploading objects, materializing ClickHouse relations, or publishing the catalog release.

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

    Immutable content-addressed release manifest uploaded before the atomic release commit.

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

    Compatibility-only server-local path to the release manifest. Remote publishers should use manifest_object_id.

  • manifest_sha_256 (String, nil) (defaults to: nil) —

    Expected SHA-256 digest for manifest_object_id.

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

    Expected byte size for manifest_object_id.

  • release (String)
  • release_digest (String)
  • source (String, nil) (defaults to: nil)
  • request_options (Hash) (defaults to: {}) —

    (see Rafflesia::Types::RequestOptions)

Returns:



289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
 
# File 'lib/rafflesia/datasets.rb', line 289

def relationReleasesPublish(
  artifacts:,
  database:,
  release:,
  release_digest:,
  created_at: nil,
  dataset_kind: nil,
  dry_run: nil,
  manifest_object_id: nil,
  manifest_path: nil,
  manifest_sha_256: nil,
  manifest_size_bytes: nil,
  source: nil,
  request_options: {}
)
  body = {
    'artifacts' => artifacts,
    'created_at' => created_at,
    'database' => database,
    'dataset_kind' => dataset_kind,
    'dry_run' => dry_run,
    'manifest_object_id' => manifest_object_id,
    'manifest_path' => manifest_path,
    'manifest_sha256' => manifest_sha_256,
    'manifest_size_bytes' => manifest_size_bytes,
    'release' => release,
    'release_digest' => release_digest,
    'source' => source
  }.compact
  response = @client.request(
    method: :post,
    path: '/v1/datasets/relation-releases/publish',
    auth: true,
    body: body,
    request_options: request_options
  )
  result = Rafflesia::EnvelopeRelationReleasePublicationData.new(response.body)
  result.last_response = Rafflesia::Types::ApiResponse.new(http_status: response.code.to_i, http_headers: response.each_header.to_h, request_id: response["x-request-id"])
  result
end

#releasesAudit(audit_object_id: nil, corpus: nil, object_store_root: nil, ref: nil, release_id: nil, request_options: {}) ⇒ Rafflesia::EnvelopeCorpusReleaseAuditData

POST /v1/datasets/releases/audit

Parameters:

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

    Content-addressed audit object id to decode directly.

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

    Immutable corpus name. Required when ref and audit_object_id are omitted.

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

    Optional local or object-storage root. Defaults to the API server's release data root.

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

    Optional immutable release ref formatted as corpus:release_id. When set, the audit chain for the corpus is searched for this release.

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

    Immutable release id. Required with corpus when ref and audit_object_id are omitted.

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

    (see Rafflesia::Types::RequestOptions)

Returns:



338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
 
# File 'lib/rafflesia/datasets.rb', line 338

def releasesAudit(
  audit_object_id: nil,
  corpus: nil,
  object_store_root: nil,
  ref: nil,
  release_id: nil,
  request_options: {}
)
  body = {
    'audit_object_id' => audit_object_id,
    'corpus' => corpus,
    'object_store_root' => object_store_root,
    'ref' => ref,
    'release_id' => release_id
  }.compact
  response = @client.request(
    method: :post,
    path: '/v1/datasets/releases/audit',
    auth: true,
    body: body,
    request_options: request_options
  )
  result = Rafflesia::EnvelopeCorpusReleaseAuditData.new(response.body)
  result.last_response = Rafflesia::Types::ApiResponse.new(http_status: response.code.to_i, http_headers: response.each_header.to_h, request_id: response["x-request-id"])
  result
end

#releasesBackfill(corpus: nil, dry_run: nil, limit: nil, object_store_root: nil, publish_aliases: nil, request_options: {}) ⇒ Rafflesia::EnvelopeCorpusReleaseBackfillData

POST /v1/datasets/releases/backfill

Parameters:

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

    Optional corpus name. When omitted, all corpora under the release root are scanned.

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

    When true, inspect release manifests without writing catalog rows.

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

    Maximum release manifests to scan. Defaults to 1000.

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

    Optional local or object-storage release root. Defaults to the API server's release data root.

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

    When true, sync object-store current pointers into catalog aliases. Defaults to true unless dry_run is set.

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

    (see Rafflesia::Types::RequestOptions)

Returns:



373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
 
# File 'lib/rafflesia/datasets.rb', line 373

def releasesBackfill(
  corpus: nil,
  dry_run: nil,
  limit: nil,
  object_store_root: nil,
  publish_aliases: nil,
  request_options: {}
)
  body = {
    'corpus' => corpus,
    'dry_run' => dry_run,
    'limit' => limit,
    'object_store_root' => object_store_root,
    'publish_aliases' => publish_aliases
  }.compact
  response = @client.request(
    method: :post,
    path: '/v1/datasets/releases/backfill',
    auth: true,
    body: body,
    request_options: request_options
  )
  result = Rafflesia::EnvelopeCorpusReleaseBackfillData.new(response.body)
  result.last_response = Rafflesia::Types::ApiResponse.new(http_status: response.code.to_i, http_headers: response.each_header.to_h, request_id: response["x-request-id"])
  result
end

#releasesBenchmark(corpus:, calibrated_query_profiles_path: nil, calibrated_sequence_planner_mode: nil, candidate_rank_strategy: nil, exact_rerank: nil, exact_rerank_backend: nil, exact_rerank_rank_key: nil, family: nil, foldseek_binary_path: nil, input_path: nil, kmer_size: nil, max_bytes_per_query: nil, max_bytes_per_query_increase: nil, max_candidates: nil, max_candidates_grid: nil, max_final_recall_regression: nil, max_hits: nil, max_latency_ms: nil, max_latency_ms_increase: nil, max_object_bytes_total: nil, max_object_reads_increase: nil, max_object_reads_per_query: nil, max_object_reads_total: nil, max_postings_per_block: nil, max_query_posting_blocks: nil, max_query_posting_blocks_grid: nil, max_shards: nil, max_shards_grid: nil, max_token_frequency: nil, max_verifications: nil, max_verifications_grid: nil, min_candidate_pool_recall: nil, min_final_recall_at_k: nil, min_hit_rate_at_k: nil, min_mean_recall_at_k: nil, minimizer_window: nil, object_store_root: nil, payload_records_per_block: nil, planner_delta_artifact_path: nil, postings_range_coalesce_gap_bytes: nil, postings_range_coalesce_gap_bytes_grid: nil, postings_range_coalesce_max_span_bytes: nil, postings_range_coalesce_max_span_bytes_grid: nil, previous_query_profile_audit_path: nil, queries_jsonl_path: nil, query_mode: nil, query_profile_audit_engine: nil, query_profile_audit_limit: nil, query_profile_audit_output_dir: nil, query_profile_audit_timeout_ms: nil, query_profile_audit_write_markdown: nil, query_profile_max_result_set_ids: nil, query_profiles_path: nil, release_prefix: nil, rerank_limit: nil, routing_mode: nil, routing_mode_grid: nil, routing_shard_count: nil, routing_shard_layout: nil, run_planner_calibration_loop: nil, run_structure_pair_geometry_ab: nil, sequence_planner_calibration_output_path: nil, sequence_planner_calibration_path: nil, sequence_planner_mode: nil, similar_kmer_max_variants: nil, similar_kmer_threshold: nil, simulated_read_latency_ms: nil, structure_coordinate_paths: nil, structure_gram_size: nil, structure_pair_geometry_evidence_jsonl_path: nil, structure_pair_geometry_evidence_tsv_path: nil, structure_pair_geometry_max_query_tokens: nil, structure_pair_geometry_min_shared_pairs: nil, structure_pair_geometry_shift_bins: nil, structure_pair_geometry_summary_path: nil, structure_search_preset: nil, structure_token_extractor: nil, structure_tokens_path: nil, target_shard_score_coverage: nil, target_shard_score_coverage_grid: nil, tmalign_binary_path: nil, ungapped_diagonal_top_n: nil, use_structure_pair_geometry: nil, verification_band: nil, request_options: {}) ⇒ Rafflesia::EnvelopeCorpusReleaseBenchmarkData

POST /v1/datasets/releases/benchmark

Parameters:

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

    Optional output path for calibrated rerun query profiles. Defaults beside query_profiles_path.

  • calibrated_sequence_planner_mode (Rafflesia::Types::CorpuReleaseBenchmarkRequestCalibratedSequencePlannerMode, nil) (defaults to: nil) —

    Planner mode for the calibrated rerun. Defaults to v7.

  • candidate_rank_strategy (Rafflesia::Types::CorpuReleaseBenchmarkRequestCandidateRankStrategy, nil) (defaults to: nil) —

    Candidate ranking key used before optional verification.

  • corpus (String) —

    Benchmark corpus name.

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

    When true for structure_prefilter benchmarks, exact-rerank benchmark queries with a pairwise structure aligner.

  • exact_rerank_backend (Rafflesia::Types::CorpuReleaseBenchmarkRequestExactRerankBackend, nil) (defaults to: nil) —

    Pairwise backend used by exact_rerank benchmark searches. Defaults to tmalign unless a preset fills it.

  • exact_rerank_rank_key (Rafflesia::Types::CorpuReleaseBenchmarkRequestExactRerankRankKey, nil) (defaults to: nil) —

    Measurement used to order exact_rerank benchmark hits.

  • family (Rafflesia::Types::CorpuReleaseBenchmarkRequestFamily, nil) (defaults to: nil) —

    Search family to build and benchmark. Defaults to sequence_prefilter.

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

    Optional absolute Foldseek binary path used for 3Di-compatible raw-structure token extraction in structure_prefilter builds.

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

    Input FASTA path for seed or sequence_prefilter families. For structure_prefilter, this may be a structure-token TSV path, a raw PDB/mmCIF file, or a directory of raw PDB/mmCIF files.

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

    k-mer size used by seed and sequence prefilter releases.

  • max_bytes_per_query (Float, nil) (defaults to: nil) —

    Optional query-profile audit gate limiting max bytes read per query.

  • max_bytes_per_query_increase (Float, nil) (defaults to: nil) —

    Optional previous-run comparison gate limiting max bytes-per-query increase.

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

    Optional cap on ranked candidates before max_hits.

  • max_candidates_grid (Array<Integer>, nil) (defaults to: nil) —

    Candidate caps to sweep; overrides max_candidates when set.

  • max_final_recall_regression (Float, nil) (defaults to: nil) —

    Optional previous-run comparison gate limiting recall regression.

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

    Maximum hits requested per recall query.

  • max_latency_ms (Float, nil) (defaults to: nil) —

    Optional query-profile audit gate limiting max latency per query.

  • max_latency_ms_increase (Float, nil) (defaults to: nil) —

    Optional previous-run comparison gate limiting max latency increase.

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

    Optional gate limiting object bytes per benchmark row.

  • max_object_reads_increase (Float, nil) (defaults to: nil) —

    Optional previous-run comparison gate limiting max object-read increase.

  • max_object_reads_per_query (Float, nil) (defaults to: nil) —

    Optional query-profile audit gate limiting max object reads per query.

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

    Optional gate limiting object reads per benchmark row.

  • max_postings_per_block (Array<Integer>, nil) (defaults to: nil) —

    Postings block sizes to sweep.

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

    Optional cap on selected query posting blocks.

  • max_query_posting_blocks_grid (Array<Integer>, nil) (defaults to: nil) —

    Posting-block caps to sweep; use 0 for uncapped.

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

    Optional cap on routed shards per query.

  • max_shards_grid (Array<Integer>, nil) (defaults to: nil) —

    Routed shard caps to sweep; use 0 for uncapped.

  • max_token_frequency (Array<Integer>, nil) (defaults to: nil) —

    Token-frequency caps to sweep. Use 0 for uncapped.

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

    Optional cap on candidates aligned in verification modes.

  • max_verifications_grid (Array<Integer>, nil) (defaults to: nil) —

    Verification caps to sweep; overrides max_verifications when set.

  • min_candidate_pool_recall (Float, nil) (defaults to: nil) —

    Optional query-profile audit gate requiring minimum candidate-pool recall.

  • min_final_recall_at_k (Float, nil) (defaults to: nil) —

    Optional query-profile audit gate requiring minimum final recall@k.

  • min_hit_rate_at_k (Float, nil) (defaults to: nil) —

    Optional gate requiring every benchmark row with recall data to meet this hit-rate@k threshold.

  • min_mean_recall_at_k (Float, nil) (defaults to: nil) —

    Optional gate requiring every benchmark row with recall data to meet this mean recall@k threshold.

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

    Minimizer window used by the sequence prefilter family.

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

    Optional local object-store root. Defaults to the API server's release data root.

  • payload_records_per_block (Array<Integer>, nil) (defaults to: nil) —

    Payload block sizes to sweep.

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

    Optional output path for the planner calibration delta artifact. Defaults beside query_profiles_path.

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

    Maximum gap in bytes between postings ranges that may be coalesced.

  • postings_range_coalesce_gap_bytes_grid (Array<Integer>, nil) (defaults to: nil) —

    Postings range-coalescing gap values to sweep.

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

    Maximum fused postings range span in bytes.

  • postings_range_coalesce_max_span_bytes_grid (Array<Integer>, nil) (defaults to: nil) —

    Postings range-coalescing max-span values to sweep.

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

    Optional previous audit.json path for run-to-run planner regression comparison.

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

    Optional recall query JSONL path. Each line contains query_id, sequence or structure_tokens, and expected_ids.

  • query_mode (Rafflesia::Types::CorpuReleaseBenchmarkRequestQueryMode, nil) (defaults to: nil) —

    Query mode used by recall benchmark searches.

  • query_profile_audit_engine (Rafflesia::Types::CorpuReleaseBenchmarkRequestQueryProfileAuditEngine, nil) (defaults to: nil) —

    Audit engine for query_profiles_path. Defaults to duckdb.

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

    Maximum rows per query-profile audit detail section.

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

    Optional output directory for audit.json and audit.md generated from query_profiles_path.

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

    Optional query-profile audit timeout in milliseconds.

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

    Whether to write audit.md alongside audit.json.

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

    Maximum retained IDs per result_sets array during profile validation; 0 uses backend default.

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

    Optional output path for Biosearch query-profile JSONL generated by the release benchmark. Sequence benchmarks write sequence_query_profile.v1; structure benchmarks write structure_query_profile.v1. Defaults under the local object-store root.

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

    Prefix used for immutable release ids produced by the sweep.

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

    Maximum structure benchmark candidates to exact-rerank. Defaults to max_hits.

  • routing_mode (Rafflesia::Types::CorpuReleaseBenchmarkRequestRoutingMode, nil) (defaults to: nil) —

    Router selection mode for sharded benchmark searches.

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

    Router modes to sweep.

  • routing_shard_count (Array<Integer>, nil) (defaults to: nil) —

    Router shard counts to sweep. Defaults to 1 when omitted.

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

    Router shard assignment layouts to sweep: record_id_hash, token_minhash, or biological_minhash.

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

    When true for sequence_prefilter benchmarks, run baseline queries, compile a read-yield calibration profile, rerun calibrated queries, and write a planner-delta artifact.

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

    When true for structure_prefilter, run baseline and residue-pair geometry searches over the same compiled release and emit comparison evidence artifacts.

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

    Optional output path for the benchmark-derived planner calibration profile. Defaults beside query_profiles_path.

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

    Optional input JSON planner calibration profile used by v7/v8 sequence benchmark searches.

  • sequence_planner_mode (Rafflesia::Types::CorpuReleaseBenchmarkRequestSequencePlannerMode, nil) (defaults to: nil) —

    Planner mode used by sequence_prefilter benchmark searches.

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

    Maximum similar posting grams retained per query gram when similar_kmer_threshold is set.

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

    Optional 3Di substitution-matrix threshold for expanding query grams to similar posting grams in structure_prefilter benchmarks.

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

    Optional fixed read latency injected into object-store reads.

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

    Optional structure_prefilter record id to raw PDB/mmCIF path map. Stored with every generated release so exact rerank can use release coordinates without caller-supplied targets.

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

    Structure-token gram size used by the structure prefilter family.

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

    Optional output path for per-query baseline-vs-pair-geometry JSONL evidence. Defaults beside query_profiles_path.

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

    Optional output path for per-query baseline-vs-pair-geometry TSV evidence. Defaults beside query_profiles_path.

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

    Maximum residue-pair query tokens selected by increasing posting frequency. Defaults to max_query_posting_blocks, then 256.

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

    Minimum shared residue-pair tokens required for pair-only candidate promotion. Defaults to 1.

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

    When true, expand residue-pair query tokens to adjacent sequence-distance bins.

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

    Optional output path for the structure pair-geometry comparison summary JSON. Defaults beside query_profiles_path.

  • structure_search_preset (Rafflesia::Types::CorpuReleaseBenchmarkRequestStructureSearchPreset, nil) (defaults to: nil) —

    Optional structure_prefilter search preset that fills unset candidate-generation and verification knobs in benchmark searches.

  • structure_token_extractor (Rafflesia::Types::CorpuReleaseBenchmarkRequestStructureTokenExtractor, nil) (defaults to: nil) —

    Structure-token extractor for raw structure_prefilter inputs. auto preserves current behavior: use foldseek when foldseek_binary_path is set, otherwise use the native geometry tokenizer.

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

    Input structure-token TSV path for the structure_prefilter family. Each row is ''.

  • target_shard_score_coverage (Float, nil) (defaults to: nil) —

    Adaptive routing target score coverage.

  • target_shard_score_coverage_grid (Array<Float>, nil) (defaults to: nil) —

    Adaptive routing score-coverage targets to sweep; use 0 for unset.

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

    Optional absolute TM-align binary path used for structure_prefilter exact_rerank benchmark queries.

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

    Maximum candidate diagonals rescored by ungapped 3Di matrix HSP when candidate_rank_strategy is ungapped_3di_matrix.

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

    When true, benchmark structure_prefilter candidate generation with deterministic residue-pair geometry postings.

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

    Optional diagonal band for bounded verification alignment.

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

    (see Rafflesia::Types::RequestOptions)

Returns:



487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
 
# File 'lib/rafflesia/datasets.rb', line 487

def releasesBenchmark(
  corpus:,
  calibrated_query_profiles_path: nil,
  calibrated_sequence_planner_mode: nil,
  candidate_rank_strategy: nil,
  exact_rerank: nil,
  exact_rerank_backend: nil,
  exact_rerank_rank_key: nil,
  family: nil,
  foldseek_binary_path: nil,
  input_path: nil,
  kmer_size: nil,
  max_bytes_per_query: nil,
  max_bytes_per_query_increase: nil,
  max_candidates: nil,
  max_candidates_grid: nil,
  max_final_recall_regression: nil,
  max_hits: nil,
  max_latency_ms: nil,
  max_latency_ms_increase: nil,
  max_object_bytes_total: nil,
  max_object_reads_increase: nil,
  max_object_reads_per_query: nil,
  max_object_reads_total: nil,
  max_postings_per_block: nil,
  max_query_posting_blocks: nil,
  max_query_posting_blocks_grid: nil,
  max_shards: nil,
  max_shards_grid: nil,
  max_token_frequency: nil,
  max_verifications: nil,
  max_verifications_grid: nil,
  min_candidate_pool_recall: nil,
  min_final_recall_at_k: nil,
  min_hit_rate_at_k: nil,
  min_mean_recall_at_k: nil,
  minimizer_window: nil,
  object_store_root: nil,
  payload_records_per_block: nil,
  planner_delta_artifact_path: nil,
  postings_range_coalesce_gap_bytes: nil,
  postings_range_coalesce_gap_bytes_grid: nil,
  postings_range_coalesce_max_span_bytes: nil,
  postings_range_coalesce_max_span_bytes_grid: nil,
  previous_query_profile_audit_path: nil,
  queries_jsonl_path: nil,
  query_mode: nil,
  query_profile_audit_engine: nil,
  query_profile_audit_limit: nil,
  query_profile_audit_output_dir: nil,
  query_profile_audit_timeout_ms: nil,
  query_profile_audit_write_markdown: nil,
  query_profile_max_result_set_ids: nil,
  query_profiles_path: nil,
  release_prefix: nil,
  rerank_limit: nil,
  routing_mode: nil,
  routing_mode_grid: nil,
  routing_shard_count: nil,
  routing_shard_layout: nil,
  run_planner_calibration_loop: nil,
  run_structure_pair_geometry_ab: nil,
  sequence_planner_calibration_output_path: nil,
  sequence_planner_calibration_path: nil,
  sequence_planner_mode: nil,
  similar_kmer_max_variants: nil,
  similar_kmer_threshold: nil,
  simulated_read_latency_ms: nil,
  structure_coordinate_paths: nil,
  structure_gram_size: nil,
  structure_pair_geometry_evidence_jsonl_path: nil,
  structure_pair_geometry_evidence_tsv_path: nil,
  structure_pair_geometry_max_query_tokens: nil,
  structure_pair_geometry_min_shared_pairs: nil,
  structure_pair_geometry_shift_bins: nil,
  structure_pair_geometry_summary_path: nil,
  structure_search_preset: nil,
  structure_token_extractor: nil,
  structure_tokens_path: nil,
  target_shard_score_coverage: nil,
  target_shard_score_coverage_grid: nil,
  tmalign_binary_path: nil,
  ungapped_diagonal_top_n: nil,
  use_structure_pair_geometry: nil,
  verification_band: nil,
  request_options: {}
)
  body = {
    'calibrated_query_profiles_path' => calibrated_query_profiles_path,
    'calibrated_sequence_planner_mode' => calibrated_sequence_planner_mode,
    'candidate_rank_strategy' => candidate_rank_strategy,
    'corpus' => corpus,
    'exact_rerank' => exact_rerank,
    'exact_rerank_backend' => exact_rerank_backend,
    'exact_rerank_rank_key' => exact_rerank_rank_key,
    'family' => family,
    'foldseek_binary_path' => foldseek_binary_path,
    'input_path' => input_path,
    'kmer_size' => kmer_size,
    'max_bytes_per_query' => max_bytes_per_query,
    'max_bytes_per_query_increase' => max_bytes_per_query_increase,
    'max_candidates' => max_candidates,
    'max_candidates_grid' => max_candidates_grid,
    'max_final_recall_regression' => max_final_recall_regression,
    'max_hits' => max_hits,
    'max_latency_ms' => max_latency_ms,
    'max_latency_ms_increase' => max_latency_ms_increase,
    'max_object_bytes_total' => max_object_bytes_total,
    'max_object_reads_increase' => max_object_reads_increase,
    'max_object_reads_per_query' => max_object_reads_per_query,
    'max_object_reads_total' => max_object_reads_total,
    'max_postings_per_block' => max_postings_per_block,
    'max_query_posting_blocks' => max_query_posting_blocks,
    'max_query_posting_blocks_grid' => max_query_posting_blocks_grid,
    'max_shards' => max_shards,
    'max_shards_grid' => max_shards_grid,
    'max_token_frequency' => max_token_frequency,
    'max_verifications' => max_verifications,
    'max_verifications_grid' => max_verifications_grid,
    'min_candidate_pool_recall' => min_candidate_pool_recall,
    'min_final_recall_at_k' => min_final_recall_at_k,
    'min_hit_rate_at_k' => min_hit_rate_at_k,
    'min_mean_recall_at_k' => min_mean_recall_at_k,
    'minimizer_window' => minimizer_window,
    'object_store_root' => object_store_root,
    'payload_records_per_block' => payload_records_per_block,
    'planner_delta_artifact_path' => planner_delta_artifact_path,
    'postings_range_coalesce_gap_bytes' => postings_range_coalesce_gap_bytes,
    'postings_range_coalesce_gap_bytes_grid' => postings_range_coalesce_gap_bytes_grid,
    'postings_range_coalesce_max_span_bytes' => postings_range_coalesce_max_span_bytes,
    'postings_range_coalesce_max_span_bytes_grid' => postings_range_coalesce_max_span_bytes_grid,
    'previous_query_profile_audit_path' => previous_query_profile_audit_path,
    'queries_jsonl_path' => queries_jsonl_path,
    'query_mode' => query_mode,
    'query_profile_audit_engine' => query_profile_audit_engine,
    'query_profile_audit_limit' => query_profile_audit_limit,
    'query_profile_audit_output_dir' => query_profile_audit_output_dir,
    'query_profile_audit_timeout_ms' => query_profile_audit_timeout_ms,
    'query_profile_audit_write_markdown' => query_profile_audit_write_markdown,
    'query_profile_max_result_set_ids' => query_profile_max_result_set_ids,
    'query_profiles_path' => query_profiles_path,
    'release_prefix' => release_prefix,
    'rerank_limit' => rerank_limit,
    'routing_mode' => routing_mode,
    'routing_mode_grid' => routing_mode_grid,
    'routing_shard_count' => routing_shard_count,
    'routing_shard_layout' => routing_shard_layout,
    'run_planner_calibration_loop' => run_planner_calibration_loop,
    'run_structure_pair_geometry_ab' => run_structure_pair_geometry_ab,
    'sequence_planner_calibration_output_path' => sequence_planner_calibration_output_path,
    'sequence_planner_calibration_path' => sequence_planner_calibration_path,
    'sequence_planner_mode' => sequence_planner_mode,
    'similar_kmer_max_variants' => similar_kmer_max_variants,
    'similar_kmer_threshold' => similar_kmer_threshold,
    'simulated_read_latency_ms' => simulated_read_latency_ms,
    'structure_coordinate_paths' => structure_coordinate_paths,
    'structure_gram_size' => structure_gram_size,
    'structure_pair_geometry_evidence_jsonl_path' => structure_pair_geometry_evidence_jsonl_path,
    'structure_pair_geometry_evidence_tsv_path' => structure_pair_geometry_evidence_tsv_path,
    'structure_pair_geometry_max_query_tokens' => structure_pair_geometry_max_query_tokens,
    'structure_pair_geometry_min_shared_pairs' => structure_pair_geometry_min_shared_pairs,
    'structure_pair_geometry_shift_bins' => structure_pair_geometry_shift_bins,
    'structure_pair_geometry_summary_path' => structure_pair_geometry_summary_path,
    'structure_search_preset' => structure_search_preset,
    'structure_token_extractor' => structure_token_extractor,
    'structure_tokens_path' => structure_tokens_path,
    'target_shard_score_coverage' => target_shard_score_coverage,
    'target_shard_score_coverage_grid' => target_shard_score_coverage_grid,
    'tmalign_binary_path' => tmalign_binary_path,
    'ungapped_diagonal_top_n' => ungapped_diagonal_top_n,
    'use_structure_pair_geometry' => use_structure_pair_geometry,
    'verification_band' => verification_band
  }.compact
  response = @client.request(
    method: :post,
    path: '/v1/datasets/releases/benchmark',
    auth: true,
    body: body,
    request_options: request_options
  )
  result = Rafflesia::EnvelopeCorpusReleaseBenchmarkData.new(response.body)
  result.last_response = Rafflesia::Types::ApiResponse.new(http_status: response.code.to_i, http_headers: response.each_header.to_h, request_id: response["x-request-id"])
  result
end

#releasesGcPlan(corpus:, dry_run: nil, limit: nil, plan_id: nil, retain_last: nil, request_options: {}) ⇒ Rafflesia::EnvelopeCorpusReleaseGcPlanData

POST /v1/datasets/releases/gc-plan

Parameters:

  • corpus (String) —

    Corpus whose catalog releases should be considered for GC.

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

    Keep true for a planning-only run. This primitive does not delete object bytes.

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

    Maximum release catalog rows to inspect. Defaults to 1000.

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

    Optional stable GC plan id. Defaults to a deterministic timestamped id.

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

    Keep at least this many newest releases in addition to current and pinned releases. Defaults to 2.

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

    (see Rafflesia::Types::RequestOptions)

Returns:



680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
 
# File 'lib/rafflesia/datasets.rb', line 680

def releasesGcPlan(
  corpus:,
  dry_run: nil,
  limit: nil,
  plan_id: nil,
  retain_last: nil,
  request_options: {}
)
  body = {
    'corpus' => corpus,
    'dry_run' => dry_run,
    'limit' => limit,
    'plan_id' => plan_id,
    'retain_last' => retain_last
  }.compact
  response = @client.request(
    method: :post,
    path: '/v1/datasets/releases/gc-plan',
    auth: true,
    body: body,
    request_options: request_options
  )
  result = Rafflesia::EnvelopeCorpusReleaseGcPlanData.new(response.body)
  result.last_response = Rafflesia::Types::ApiResponse.new(http_status: response.code.to_i, http_headers: response.each_header.to_h, request_id: response["x-request-id"])
  result
end

#releasesHistory(corpus:, include_audit_payload: nil, limit: nil, object_store_root: nil, request_options: {}) ⇒ Rafflesia::EnvelopeCorpusReleaseHistoryData

POST /v1/datasets/releases/history

Parameters:

  • corpus (String) —

    Immutable corpus name whose current-pointer audit chain should be listed.

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

    Include each decoded audit object payload in the response.

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

    Maximum publish-audit entries to follow backward from the current pointer. Defaults to 100.

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

    Optional local or object-storage root. Defaults to the API server's release data root.

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

    (see Rafflesia::Types::RequestOptions)

Returns:



714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
 
# File 'lib/rafflesia/datasets.rb', line 714

def releasesHistory(
  corpus:,
  include_audit_payload: nil,
  limit: nil,
  object_store_root: nil,
  request_options: {}
)
  body = {
    'corpus' => corpus,
    'include_audit_payload' => include_audit_payload,
    'limit' => limit,
    'object_store_root' => object_store_root
  }.compact
  response = @client.request(
    method: :post,
    path: '/v1/datasets/releases/history',
    auth: true,
    body: body,
    request_options: request_options
  )
  result = Rafflesia::EnvelopeCorpusReleaseHistoryData.new(response.body)
  result.last_response = Rafflesia::Types::ApiResponse.new(http_status: response.code.to_i, http_headers: response.each_header.to_h, request_id: response["x-request-id"])
  result
end

#releasesList(corpus: nil, limit: nil, object_store_root: nil, request_options: {}) ⇒ Rafflesia::EnvelopeCorpusReleaseListData

POST /v1/datasets/releases/list

Parameters:

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

    Optional corpus name. When omitted, all local corpora under the release root are listed.

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

    Maximum release records returned after deterministic sorting. Defaults to 100.

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

    Optional local object-store root. Defaults to the API server's release data root.

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

    (see Rafflesia::Types::RequestOptions)

Returns:



745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
 
# File 'lib/rafflesia/datasets.rb', line 745

def releasesList(
  corpus: nil,
  limit: nil,
  object_store_root: nil,
  request_options: {}
)
  body = {
    'corpus' => corpus,
    'limit' => limit,
    'object_store_root' => object_store_root
  }.compact
  response = @client.request(
    method: :post,
    path: '/v1/datasets/releases/list',
    auth: true,
    body: body,
    request_options: request_options
  )
  result = Rafflesia::EnvelopeCorpusReleaseListData.new(response.body)
  result.last_response = Rafflesia::Types::ApiResponse.new(http_status: response.code.to_i, http_headers: response.each_header.to_h, request_id: response["x-request-id"])
  result
end

#releasesPublishCurrent(corpus: nil, expected_previous_ref: nil, max_object_bytes: nil, max_object_reads: nil, object_store_root: nil, reason: nil, ref: nil, release_id: nil, require_no_previous: nil, require_zero_materialization: nil, smoke_family: nil, smoke_max_hits: nil, smoke_query: nil, smoke_query_structure_path: nil, request_options: {}) ⇒ Rafflesia::EnvelopeCorpusReleasePublishCurrentData

POST /v1/datasets/releases/publish-current

Parameters:

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

    Immutable corpus name. Required when ref is omitted.

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

    Optional compare-and-swap guard requiring the current pointer to match this ref before publishing.

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

    Optional hard object-byte budget for the smoke search.

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

    Optional hard object-read budget for the smoke search.

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

    Optional local or object-storage root. Defaults to the API server's release data root.

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

    Optional operator reason stored in the current pointer.

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

    Optional immutable release ref formatted as corpus:release_id.

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

    Immutable release id. Required when ref is omitted.

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

    Require that no current pointer already exists before publishing.

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

    Require the smoke search to materialize zero database bytes.

  • smoke_family (Rafflesia::Types::CorpuReleasePublishCurrentRequestSmokeFamily, nil) (defaults to: nil) —

    Optional family used for smoke search. Defaults to the first release family.

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

    Maximum smoke-search hits. Defaults to 1.

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

    Optional sequence or token query used to prove the newly current release can be searched.

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

    Optional raw PDB/mmCIF query path used to smoke-test structure_prefilter releases.

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

    (see Rafflesia::Types::RequestOptions)

Returns:



785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
 
# File 'lib/rafflesia/datasets.rb', line 785

def releasesPublishCurrent(
  corpus: nil,
  expected_previous_ref: nil,
  max_object_bytes: nil,
  max_object_reads: nil,
  object_store_root: nil,
  reason: nil,
  ref: nil,
  release_id: nil,
  require_no_previous: nil,
  require_zero_materialization: nil,
  smoke_family: nil,
  smoke_max_hits: nil,
  smoke_query: nil,
  smoke_query_structure_path: nil,
  request_options: {}
)
  body = {
    'corpus' => corpus,
    'expected_previous_ref' => expected_previous_ref,
    'max_object_bytes' => max_object_bytes,
    'max_object_reads' => max_object_reads,
    'object_store_root' => object_store_root,
    'reason' => reason,
    'ref' => ref,
    'release_id' => release_id,
    'require_no_previous' => require_no_previous,
    'require_zero_materialization' => require_zero_materialization,
    'smoke_family' => smoke_family,
    'smoke_max_hits' => smoke_max_hits,
    'smoke_query' => smoke_query,
    'smoke_query_structure_path' => smoke_query_structure_path
  }.compact
  response = @client.request(
    method: :post,
    path: '/v1/datasets/releases/publish-current',
    auth: true,
    body: body,
    request_options: request_options
  )
  result = Rafflesia::EnvelopeCorpusReleasePublishCurrentData.new(response.body)
  result.last_response = Rafflesia::Types::ApiResponse.new(http_status: response.code.to_i, http_headers: response.each_header.to_h, request_id: response["x-request-id"])
  result
end

#releasesSearch(candidate_rank_strategy: nil, corpus: nil, exact_rerank: nil, exact_rerank_backend: nil, exact_rerank_rank_key: nil, family: nil, foldseek_binary_path: nil, max_candidates: nil, max_hits: nil, max_object_bytes: nil, max_object_reads: nil, max_query_posting_blocks: nil, max_shards: nil, max_verifications: nil, object_store_root: nil, postings_range_coalesce_gap_bytes: nil, postings_range_coalesce_max_span_bytes: nil, query: nil, query_mode: nil, query_sequence: nil, query_structure_file_name: nil, query_structure_object_id: nil, query_structure_path: nil, ref: nil, release_id: nil, require_zero_materialization: nil, rerank_limit: nil, routing_mode: nil, sequence_planner_calibration_path: nil, sequence_planner_mode: nil, similar_kmer_max_variants: nil, similar_kmer_threshold: nil, structure_pair_geometry_max_query_tokens: nil, structure_pair_geometry_min_shared_pairs: nil, structure_pair_geometry_shift_bins: nil, structure_reverse_correction: nil, structure_search_preset: nil, structure_token_extractor: nil, target_shard_score_coverage: nil, target_structure_objects: nil, target_structure_paths: nil, tmalign_binary_path: nil, ungapped_diagonal_top_n: nil, use_structure_pair_geometry: nil, verification_band: nil, request_options: {}) ⇒ Rafflesia::EnvelopeCorpusReleaseSearchData

POST /v1/datasets/releases/search

Parameters:

  • candidate_rank_strategy (Rafflesia::Types::CorpuReleaseSearchRequestCandidateRankStrategy, nil) (defaults to: nil) —

    Candidate ranking key before optional verification. Defaults to shared_token_count.

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

    Immutable corpus name. Required when ref is omitted.

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

    When true for structure_prefilter, rerank returned candidates with a pairwise structure aligner using caller-supplied target_structure_paths, target_structure_objects, or release-stored coordinates.

  • exact_rerank_backend (Rafflesia::Types::CorpuReleaseSearchRequestExactRerankBackend, nil) (defaults to: nil) —

    Pairwise backend used by exact_rerank. Defaults to tmalign unless a preset fills it.

  • exact_rerank_rank_key (Rafflesia::Types::CorpuReleaseSearchRequestExactRerankRankKey, nil) (defaults to: nil) —

    Measurement used to order exact_rerank hits. Defaults to the backend's measured primary structural score.

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

    Search family inside the release. Defaults to seed. Supported values are seed, sequence_prefilter, and structure_prefilter.

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

    Optional absolute Foldseek binary path used for query structure-token extraction.

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

    Optional cap on ranked candidates before max_hits; truncation is reported in warnings.

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

    Maximum number of hits returned; defaults to 10.

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

    Optional object-byte budget. The release router uses it for pre-read planning when possible, and the server enforces it against observed bytes.

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

    Optional object-read budget. The release router uses it for pre-read planning when possible, and the server enforces it against observed reads.

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

    Optional cap on selected query posting blocks; truncation is reported in warnings.

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

    Optional cap on routed release shards read for sharded corpus releases.

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

    Optional cap on candidates aligned in verification modes.

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

    Optional local object-store root. Defaults to the API server's release data root.

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

    Maximum gap in bytes between postings ranges that may be coalesced.

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

    Maximum fused postings range span in bytes.

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

    Query sequence, sequence ID, local FASTA path, structure-token string, or local structure-token file depending on family.

  • query_mode (Rafflesia::Types::CorpuReleaseSearchRequestQueryMode, nil) (defaults to: nil) —

    Release-contract query mode. Verification modes use in-process alignment kernels for supported families while keeping candidate-generation warnings explicit. Defaults to candidate_only.

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

    Optional one-letter amino-acid sequence aligned to a structure-token query for structure_prefilter verification.

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

    Stable filename used when staging query_structure_object_id for structure-token extraction.

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

    Optional raw PDB/mmCIF query object id for the structure_prefilter family. The server derives structure tokens before querying.

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

    Optional raw PDB/mmCIF query path for the structure_prefilter family. The server derives structure tokens before querying.

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

    Optional immutable release ref formatted as corpus:release_id, corpus:current, or corpus:latest.

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

    Immutable release id. Required when ref is omitted.

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

    Require the release-native path to materialize zero database bytes.

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

    Maximum returned candidates to exact-rerank. Defaults to max_hits.

  • routing_mode (Rafflesia::Types::CorpuReleaseSearchRequestRoutingMode, nil) (defaults to: nil) —

    Router selection mode for sharded corpus releases. Defaults to auto.

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

    Optional local JSON planner calibration profile produced by a release benchmark. Used by v7/v8 sequence planners.

  • sequence_planner_mode (Rafflesia::Types::CorpuReleaseSearchRequestSequencePlannerMode, nil) (defaults to: nil) —

    Planner mode for sequence_prefilter searches. Defaults to v4 unless a sequence_planner_calibration_path is provided.

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

    Maximum similar posting grams retained per query gram when similar_kmer_threshold is set. Defaults to all matching grams.

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

    Optional 3Di substitution-matrix threshold for expanding query grams to similar posting grams in structure_prefilter.

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

    Maximum residue-pair query tokens selected by increasing posting frequency. Defaults to max_query_posting_blocks, then 256.

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

    Minimum shared residue-pair tokens required for pair-only candidate promotion. Defaults to 1.

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

    When true, expand residue-pair query tokens to adjacent sequence-distance bins to test boundary-shift tolerance.

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

    When true, subtract a reverse-query 3Di/AA alignment score during native structure verification. This is Foldseek-inspired correction evidence, not exact upstream neural-net calibration.

  • structure_search_preset (Rafflesia::Types::CorpuReleaseSearchRequestStructureSearchPreset, nil) (defaults to: nil) —

    Optional structure_prefilter search preset that fills unset candidate-generation and verification knobs from measured 3Di Pareto policies.

  • structure_token_extractor (Rafflesia::Types::CorpuReleaseSearchRequestStructureTokenExtractor, nil) (defaults to: nil) —

    Structure-token extractor for raw structure queries. auto preserves current behavior: use foldseek when foldseek_binary_path is set, otherwise use the native geometry tokenizer.

  • target_shard_score_coverage (Float, nil) (defaults to: nil) —

    Adaptive router target coverage over query-token shard scores, in (0,1].

  • target_structure_objects (Hash{String => Rafflesia::CorpuReleaseStructureInputObject}, nil) (defaults to: nil) —

    Optional hit id to raw PDB/mmCIF object map used by exact_rerank.

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

    Optional hit id to local PDB/mmCIF path map used by exact_rerank.

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

    Optional absolute TM-align binary path used for exact_rerank.

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

    Maximum candidate diagonals rescored by ungapped 3Di matrix HSP when candidate_rank_strategy is ungapped_3di_matrix. Defaults to 4.

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

    When true, augment structure_prefilter candidate generation with deterministic residue-pair geometry postings.

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

    Optional diagonal band for bounded verification alignment.

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

    (see Rafflesia::Types::RequestOptions)

Returns:



878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
 
# File 'lib/rafflesia/datasets.rb', line 878

def releasesSearch(
  candidate_rank_strategy: nil,
  corpus: nil,
  exact_rerank: nil,
  exact_rerank_backend: nil,
  exact_rerank_rank_key: nil,
  family: nil,
  foldseek_binary_path: nil,
  max_candidates: nil,
  max_hits: nil,
  max_object_bytes: nil,
  max_object_reads: nil,
  max_query_posting_blocks: nil,
  max_shards: nil,
  max_verifications: nil,
  object_store_root: nil,
  postings_range_coalesce_gap_bytes: nil,
  postings_range_coalesce_max_span_bytes: nil,
  query: nil,
  query_mode: nil,
  query_sequence: nil,
  query_structure_file_name: nil,
  query_structure_object_id: nil,
  query_structure_path: nil,
  ref: nil,
  release_id: nil,
  require_zero_materialization: nil,
  rerank_limit: nil,
  routing_mode: nil,
  sequence_planner_calibration_path: nil,
  sequence_planner_mode: nil,
  similar_kmer_max_variants: nil,
  similar_kmer_threshold: nil,
  structure_pair_geometry_max_query_tokens: nil,
  structure_pair_geometry_min_shared_pairs: nil,
  structure_pair_geometry_shift_bins: nil,
  structure_reverse_correction: nil,
  structure_search_preset: nil,
  structure_token_extractor: nil,
  target_shard_score_coverage: nil,
  target_structure_objects: nil,
  target_structure_paths: nil,
  tmalign_binary_path: nil,
  ungapped_diagonal_top_n: nil,
  use_structure_pair_geometry: nil,
  verification_band: nil,
  request_options: {}
)
  body = {
    'candidate_rank_strategy' => candidate_rank_strategy,
    'corpus' => corpus,
    'exact_rerank' => exact_rerank,
    'exact_rerank_backend' => exact_rerank_backend,
    'exact_rerank_rank_key' => exact_rerank_rank_key,
    'family' => family,
    'foldseek_binary_path' => foldseek_binary_path,
    'max_candidates' => max_candidates,
    'max_hits' => max_hits,
    'max_object_bytes' => max_object_bytes,
    'max_object_reads' => max_object_reads,
    'max_query_posting_blocks' => max_query_posting_blocks,
    'max_shards' => max_shards,
    'max_verifications' => max_verifications,
    'object_store_root' => object_store_root,
    'postings_range_coalesce_gap_bytes' => postings_range_coalesce_gap_bytes,
    'postings_range_coalesce_max_span_bytes' => postings_range_coalesce_max_span_bytes,
    'query' => query,
    'query_mode' => query_mode,
    'query_sequence' => query_sequence,
    'query_structure_file_name' => query_structure_file_name,
    'query_structure_object_id' => query_structure_object_id,
    'query_structure_path' => query_structure_path,
    'ref' => ref,
    'release_id' => release_id,
    'require_zero_materialization' => require_zero_materialization,
    'rerank_limit' => rerank_limit,
    'routing_mode' => routing_mode,
    'sequence_planner_calibration_path' => sequence_planner_calibration_path,
    'sequence_planner_mode' => sequence_planner_mode,
    'similar_kmer_max_variants' => similar_kmer_max_variants,
    'similar_kmer_threshold' => similar_kmer_threshold,
    'structure_pair_geometry_max_query_tokens' => structure_pair_geometry_max_query_tokens,
    'structure_pair_geometry_min_shared_pairs' => structure_pair_geometry_min_shared_pairs,
    'structure_pair_geometry_shift_bins' => structure_pair_geometry_shift_bins,
    'structure_reverse_correction' => structure_reverse_correction,
    'structure_search_preset' => structure_search_preset,
    'structure_token_extractor' => structure_token_extractor,
    'target_shard_score_coverage' => target_shard_score_coverage,
    'target_structure_objects' => target_structure_objects,
    'target_structure_paths' => target_structure_paths,
    'tmalign_binary_path' => tmalign_binary_path,
    'ungapped_diagonal_top_n' => ungapped_diagonal_top_n,
    'use_structure_pair_geometry' => use_structure_pair_geometry,
    'verification_band' => verification_band
  }.compact
  response = @client.request(
    method: :post,
    path: '/v1/datasets/releases/search',
    auth: true,
    body: body,
    request_options: request_options
  )
  result = Rafflesia::EnvelopeCorpusReleaseSearchData.new(response.body)
  result.last_response = Rafflesia::Types::ApiResponse.new(http_status: response.code.to_i, http_headers: response.each_header.to_h, request_id: response["x-request-id"])
  result
end

#releasesShow(corpus: nil, include_evidence_channels: nil, include_manifest: nil, include_runtime_contract: nil, object_store_root: nil, ref: nil, release_id: nil, request_options: {}) ⇒ Rafflesia::EnvelopeCorpusReleaseShowData

POST /v1/datasets/releases/show

Parameters:

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

    Immutable corpus name. Required when ref is omitted.

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

    Include typed evidence-channel contracts derived from the release manifest.

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

    Include the parsed release manifest in the response.

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

    Include release evidence-channel and cost-contract observations derived from the release manifest.

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

    Optional local object-store root. Defaults to the API server's release data root.

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

    Optional immutable release ref formatted as corpus:release_id, corpus:current, or corpus:latest.

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

    Immutable release id. Required when ref is omitted.

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

    (see Rafflesia::Types::RequestOptions)

Returns:



995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
 
# File 'lib/rafflesia/datasets.rb', line 995

def releasesShow(
  corpus: nil,
  include_evidence_channels: nil,
  include_manifest: nil,
  include_runtime_contract: nil,
  object_store_root: nil,
  ref: nil,
  release_id: nil,
  request_options: {}
)
  body = {
    'corpus' => corpus,
    'include_evidence_channels' => include_evidence_channels,
    'include_manifest' => include_manifest,
    'include_runtime_contract' => include_runtime_contract,
    'object_store_root' => object_store_root,
    'ref' => ref,
    'release_id' => release_id
  }.compact
  response = @client.request(
    method: :post,
    path: '/v1/datasets/releases/show',
    auth: true,
    body: body,
    request_options: request_options
  )
  result = Rafflesia::EnvelopeCorpusReleaseShowData.new(response.body)
  result.last_response = Rafflesia::Types::ApiResponse.new(http_status: response.code.to_i, http_headers: response.each_header.to_h, request_id: response["x-request-id"])
  result
end

#releasesValidate(corpus: nil, max_object_bytes: nil, max_object_reads: nil, object_store_root: nil, ref: nil, release_id: nil, require_zero_materialization: nil, smoke_family: nil, smoke_max_hits: nil, smoke_query: nil, smoke_query_structure_path: nil, request_options: {}) ⇒ Rafflesia::EnvelopeCorpusReleaseValidateData

POST /v1/datasets/releases/validate

Parameters:

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

    Immutable corpus name. Required when ref is omitted.

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

    Optional hard object-byte budget for the smoke search.

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

    Optional hard object-read budget for the smoke search.

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

    Optional local or object-storage root. Defaults to the API server's release data root.

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

    Optional immutable release ref formatted as corpus:release_id, including corpus:current.

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

    Immutable release id. Required when ref is omitted.

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

    Require the smoke search to materialize zero database bytes.

  • smoke_family (Rafflesia::Types::CorpuReleaseValidateRequestSmokeFamily, nil) (defaults to: nil) —

    Optional family used for smoke search. Defaults to the first release family.

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

    Maximum smoke-search hits. Defaults to 1.

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

    Optional sequence or token query used to prove the release can be searched.

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

    Optional raw PDB/mmCIF query path used to smoke-test structure_prefilter releases.

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

    (see Rafflesia::Types::RequestOptions)

Returns:



1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
 
# File 'lib/rafflesia/datasets.rb', line 1040

def releasesValidate(
  corpus: nil,
  max_object_bytes: nil,
  max_object_reads: nil,
  object_store_root: nil,
  ref: nil,
  release_id: nil,
  require_zero_materialization: nil,
  smoke_family: nil,
  smoke_max_hits: nil,
  smoke_query: nil,
  smoke_query_structure_path: nil,
  request_options: {}
)
  body = {
    'corpus' => corpus,
    'max_object_bytes' => max_object_bytes,
    'max_object_reads' => max_object_reads,
    'object_store_root' => object_store_root,
    'ref' => ref,
    'release_id' => release_id,
    'require_zero_materialization' => require_zero_materialization,
    'smoke_family' => smoke_family,
    'smoke_max_hits' => smoke_max_hits,
    'smoke_query' => smoke_query,
    'smoke_query_structure_path' => smoke_query_structure_path
  }.compact
  response = @client.request(
    method: :post,
    path: '/v1/datasets/releases/validate',
    auth: true,
    body: body,
    request_options: request_options
  )
  result = Rafflesia::EnvelopeCorpusReleaseValidateData.new(response.body)
  result.last_response = Rafflesia::Types::ApiResponse.new(http_status: response.code.to_i, http_headers: response.each_header.to_h, request_id: response["x-request-id"])
  result
end

#show(name:, version: nil, request_options: {}) ⇒ Rafflesia::EnvelopeDatasetShowData

GET /v1/datasets/show

Parameters:

  • name (String)
  • version (String, nil) (defaults to: nil)
  • request_options (Hash) (defaults to: {}) —

    (see Rafflesia::Types::RequestOptions)

Returns:



1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
 
# File 'lib/rafflesia/datasets.rb', line 1084

def show(
  name:,
  version: nil,
  request_options: {}
)
  params = {
    'name' => name,
    'version' => version
  }.compact
  response = @client.request(
    method: :get,
    path: '/v1/datasets/show',
    auth: true,
    params: params,
    request_options: request_options
  )
  result = Rafflesia::EnvelopeDatasetShowData.new(response.body)
  result.last_response = Rafflesia::Types::ApiResponse.new(http_status: response.code.to_i, http_headers: response.each_header.to_h, request_id: response["x-request-id"])
  result
end

#sourceSnapshotsFetch(artifact_kind:, max_bytes:, source:, url:, version:, expected_etag: nil, expected_md_5: nil, expected_sha_256: nil, expected_size_bytes: nil, request_options: {}) ⇒ Rafflesia::EnvelopeDatasetSourceSnapshotFetchData

POST /v1/datasets/source-snapshots/fetch

Parameters:

  • artifact_kind (String) —

    Artifact kind allowed by the selected source profile.

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

    Expected strong HTTP entity tag from a prior preflight when the upstream publishes no checksum. Sent as If-Match; Rafflesia still computes SHA-256 as the content identity.

  • expected_md_5 (String, nil) (defaults to: nil) —

    Expected upstream MD5 digest when that is the only checksum published by the source. Rafflesia always computes and records SHA-256 as the content identity.

  • expected_sha_256 (String, nil) (defaults to: nil) —

    Expected SHA-256 digest, with or without the sha256: prefix. At least one expected checksum is required.

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

    Optional exact byte length checked before storing the artifact.

  • max_bytes (Integer) —

    Required explicit download ceiling. The fetch stops before exceeding it.

  • source (String) —

    Source profile name returned by datasets source-snapshots profiles.

  • url (String) —

    Exact HTTPS artifact URL on an allowlisted official host and path.

  • version (String) —

    Pinned upstream release label recorded in provenance.

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

    (see Rafflesia::Types::RequestOptions)

Returns:



1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
 
# File 'lib/rafflesia/datasets.rb', line 1117

def sourceSnapshotsFetch(
  artifact_kind:,
  max_bytes:,
  source:,
  url:,
  version:,
  expected_etag: nil,
  expected_md_5: nil,
  expected_sha_256: nil,
  expected_size_bytes: nil,
  request_options: {}
)
  body = {
    'artifact_kind' => artifact_kind,
    'expected_etag' => expected_etag,
    'expected_md5' => expected_md_5,
    'expected_sha256' => expected_sha_256,
    'expected_size_bytes' => expected_size_bytes,
    'max_bytes' => max_bytes,
    'source' => source,
    'url' => url,
    'version' => version
  }.compact
  response = @client.request(
    method: :post,
    path: '/v1/datasets/source-snapshots/fetch',
    auth: true,
    body: body,
    request_options: request_options
  )
  result = Rafflesia::EnvelopeDatasetSourceSnapshotFetchData.new(response.body)
  result.last_response = Rafflesia::Types::ApiResponse.new(http_status: response.code.to_i, http_headers: response.each_header.to_h, request_id: response["x-request-id"])
  result
end

#sourceSnapshotsImport(source:, version:, batch_rows: nil, checkpoint_path: nil, database: nil, format: nil, import_mode: nil, input_object_id: nil, input_path: nil, output_dir: nil, parser: nil, release: nil, resume: nil, request_options: {}) ⇒ Rafflesia::EnvelopeDatasetSourceSnapshotImportData

POST /v1/datasets/source-snapshots/import

Parameters:

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

    Rows per durable Parquet checkpoint part in streaming mode. Defaults to 50000.

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

    Explicit streaming checkpoint JSON path. Defaults below output_dir and is never server-side query state.

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

    Logical database name carried into the emitted records relation. Defaults to source.

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

    Input format. Defaults to fasta.

  • import_mode (Rafflesia::Types::DatasetSourceSnapshotImportRequestImportMode, nil) (defaults to: nil) —

    catalog preserves the small-catalog entry manifest; streaming reads bounded batches and is required for full UniProt releases. Defaults to catalog for compatibility.

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

    Object id containing FASTA bytes to import instead of input_path.

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

    Local FASTA path to import as the source snapshot.

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

    Directory for local relation artifacts. Defaults under the server data root.

  • parser (Rafflesia::Types::DatasetSourceSnapshotImportRequestParser, nil) (defaults to: nil) —

    Header parser used for alias extraction. Defaults from source.

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

    Immutable release carried into the emitted records relation. Defaults to version.

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

    Resume a streaming import from its explicit checkpoint after verifying the immutable input hash and parameters.

  • source (String) —

    Source database name, for example uniprot.

  • version (String) —

    Immutable source database version or release label.

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

    (see Rafflesia::Types::RequestOptions)

Returns:



1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
 
# File 'lib/rafflesia/datasets.rb', line 1168

def sourceSnapshotsImport(
  source:,
  version:,
  batch_rows: nil,
  checkpoint_path: nil,
  database: nil,
  format: nil,
  import_mode: nil,
  input_object_id: nil,
  input_path: nil,
  output_dir: nil,
  parser: nil,
  release: nil,
  resume: nil,
  request_options: {}
)
  body = {
    'batch_rows' => batch_rows,
    'checkpoint_path' => checkpoint_path,
    'database' => database,
    'format' => format,
    'import_mode' => import_mode,
    'input_object_id' => input_object_id,
    'input_path' => input_path,
    'output_dir' => output_dir,
    'parser' => parser,
    'release' => release,
    'resume' => resume,
    'source' => source,
    'version' => version
  }.compact
  response = @client.request(
    method: :post,
    path: '/v1/datasets/source-snapshots/import',
    auth: true,
    body: body,
    request_options: request_options
  )
  result = Rafflesia::EnvelopeDatasetSourceSnapshotImportData.new(response.body)
  result.last_response = Rafflesia::Types::ApiResponse.new(http_status: response.code.to_i, http_headers: response.each_header.to_h, request_id: response["x-request-id"])
  result
end

#sourceSnapshotsIngest(allow_duplicate: nil, dry_run: nil, ingest_mode: nil, manifest_object_id: nil, ref: nil, source: nil, version: nil, request_options: {}) ⇒ Rafflesia::EnvelopeDatasetSourceSnapshotIngestData

POST /v1/datasets/source-snapshots/ingest

Parameters:

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

    Insert rows even when this ingestion id already succeeded.

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

    Return the deterministic ClickHouse ingest plan without mutating ClickHouse.

  • ingest_mode (Rafflesia::Types::DatasetSourceSnapshotIngestRequestIngestMode, nil) (defaults to: nil)
  • manifest_object_id (String, nil) (defaults to: nil) —

    Object id containing a source snapshot manifest.

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

    Immutable source snapshot ref formatted source:version.

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

    Source database name. Required when ref and manifest_object_id are omitted.

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

    Source database version. Required when ref and manifest_object_id are omitted.

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

    (see Rafflesia::Types::RequestOptions)

Returns:



1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
 
# File 'lib/rafflesia/datasets.rb', line 1221

def sourceSnapshotsIngest(
  allow_duplicate: nil,
  dry_run: nil,
  ingest_mode: nil,
  manifest_object_id: nil,
  ref: nil,
  source: nil,
  version: nil,
  request_options: {}
)
  body = {
    'allow_duplicate' => allow_duplicate,
    'dry_run' => dry_run,
    'ingest_mode' => ingest_mode,
    'manifest_object_id' => manifest_object_id,
    'ref' => ref,
    'source' => source,
    'version' => version
  }.compact
  response = @client.request(
    method: :post,
    path: '/v1/datasets/source-snapshots/ingest',
    auth: true,
    body: body,
    request_options: request_options
  )
  result = Rafflesia::EnvelopeDatasetSourceSnapshotIngestData.new(response.body)
  result.last_response = Rafflesia::Types::ApiResponse.new(http_status: response.code.to_i, http_headers: response.each_header.to_h, request_id: response["x-request-id"])
  result
end

#sourceSnapshotsPreflight(artifact_kind:, source:, url:, additional_working_bytes: nil, minimum_free_bytes: nil, request_options: {}) ⇒ Rafflesia::EnvelopeDatasetSourceSnapshotPreflightData

POST /v1/datasets/source-snapshots/preflight

Parameters:

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

    Caller-supplied extra local working-space requirement for later import or normalization.

  • artifact_kind (String) —

    Artifact kind allowed by the selected source profile.

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

    Local free-space reserve that must remain after acquisition. Defaults to 10 GiB.

  • source (String) —

    Source profile name returned by datasets source-snapshots profiles.

  • url (String) —

    Exact HTTPS artifact URL on an allowlisted official host and path.

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

    (see Rafflesia::Types::RequestOptions)

Returns:



1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
 
# File 'lib/rafflesia/datasets.rb', line 1260

def sourceSnapshotsPreflight(
  artifact_kind:,
  source:,
  url:,
  additional_working_bytes: nil,
  minimum_free_bytes: nil,
  request_options: {}
)
  body = {
    'additional_working_bytes' => additional_working_bytes,
    'artifact_kind' => artifact_kind,
    'minimum_free_bytes' => minimum_free_bytes,
    'source' => source,
    'url' => url
  }.compact
  response = @client.request(
    method: :post,
    path: '/v1/datasets/source-snapshots/preflight',
    auth: true,
    body: body,
    request_options: request_options
  )
  result = Rafflesia::EnvelopeDatasetSourceSnapshotPreflightData.new(response.body)
  result.last_response = Rafflesia::Types::ApiResponse.new(http_status: response.code.to_i, http_headers: response.each_header.to_h, request_id: response["x-request-id"])
  result
end

#sourceSnapshotsProfiles(request_options: {}) ⇒ Rafflesia::EnvelopeDatasetSourceSnapshotProfileListData

GET /v1/datasets/source-snapshots/profiles

Parameters:

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

    (see Rafflesia::Types::RequestOptions)

Returns:



1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
 
# File 'lib/rafflesia/datasets.rb', line 1290

def sourceSnapshotsProfiles(request_options: {})
  response = @client.request(
    method: :get,
    path: '/v1/datasets/source-snapshots/profiles',
    auth: true,
    request_options: request_options
  )
  result = Rafflesia::EnvelopeDatasetSourceSnapshotProfileListData.new(response.body)
  result.last_response = Rafflesia::Types::ApiResponse.new(http_status: response.code.to_i, http_headers: response.each_header.to_h, request_id: response["x-request-id"])
  result
end

#sourceSnapshotsShow(include_manifest: nil, manifest_object_id: nil, ref: nil, source: nil, version: nil, request_options: {}) ⇒ Rafflesia::EnvelopeDatasetSourceSnapshotShowData

POST /v1/datasets/source-snapshots/show

Parameters:

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

    Include the parsed source snapshot manifest in the response.

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

    Object id containing a source snapshot manifest.

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

    Immutable source snapshot ref formatted source:version.

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

    Source database name. Required when ref and manifest_object_id are omitted.

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

    Source database version. Required when ref and manifest_object_id are omitted.

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

    (see Rafflesia::Types::RequestOptions)

Returns:



1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
 
# File 'lib/rafflesia/datasets.rb', line 1310

def sourceSnapshotsShow(
  include_manifest: nil,
  manifest_object_id: nil,
  ref: nil,
  source: nil,
  version: nil,
  request_options: {}
)
  body = {
    'include_manifest' => include_manifest,
    'manifest_object_id' => manifest_object_id,
    'ref' => ref,
    'source' => source,
    'version' => version
  }.compact
  response = @client.request(
    method: :post,
    path: '/v1/datasets/source-snapshots/show',
    auth: true,
    body: body,
    request_options: request_options
  )
  result = Rafflesia::EnvelopeDatasetSourceSnapshotShowData.new(response.body)
  result.last_response = Rafflesia::Types::ApiResponse.new(http_status: response.code.to_i, http_headers: response.each_header.to_h, request_id: response["x-request-id"])
  result
end

#sourceSnapshotsStatus(manifest_object_id: nil, ref: nil, source: nil, version: nil, request_options: {}) ⇒ Rafflesia::EnvelopeDatasetSourceSnapshotStatusData

POST /v1/datasets/source-snapshots/status

Parameters:

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

    Object id containing a source snapshot manifest.

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

    Immutable source snapshot ref formatted source:version.

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

    Source database name. Required when ref and manifest_object_id are omitted.

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

    Source database version. Required when ref and manifest_object_id are omitted.

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

    (see Rafflesia::Types::RequestOptions)

Returns:



1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
 
# File 'lib/rafflesia/datasets.rb', line 1344

def sourceSnapshotsStatus(
  manifest_object_id: nil,
  ref: nil,
  source: nil,
  version: nil,
  request_options: {}
)
  body = {
    'manifest_object_id' => manifest_object_id,
    'ref' => ref,
    'source' => source,
    'version' => version
  }.compact
  response = @client.request(
    method: :post,
    path: '/v1/datasets/source-snapshots/status',
    auth: true,
    body: body,
    request_options: request_options
  )
  result = Rafflesia::EnvelopeDatasetSourceSnapshotStatusData.new(response.body)
  result.last_response = Rafflesia::Types::ApiResponse.new(http_status: response.code.to_i, http_headers: response.each_header.to_h, request_id: response["x-request-id"])
  result
end

#sourceSnapshotsValidate(manifest_object_id: nil, ref: nil, require_catalog: nil, require_relation: nil, source: nil, version: nil, request_options: {}) ⇒ Rafflesia::EnvelopeDatasetSourceSnapshotValidateData

POST /v1/datasets/source-snapshots/validate

Parameters:

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

    Object id containing a source snapshot manifest.

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

    Immutable source snapshot ref formatted source:version.

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

    Require the sequence catalog manifest object to be reachable.

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

    Require the published source_sequence_records relation to be reachable and row-count consistent.

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

    Source database name. Required when ref and manifest_object_id are omitted.

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

    Source database version. Required when ref and manifest_object_id are omitted.

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

    (see Rafflesia::Types::RequestOptions)

Returns:



1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
 
# File 'lib/rafflesia/datasets.rb', line 1378

def sourceSnapshotsValidate(
  manifest_object_id: nil,
  ref: nil,
  require_catalog: nil,
  require_relation: nil,
  source: nil,
  version: nil,
  request_options: {}
)
  body = {
    'manifest_object_id' => manifest_object_id,
    'ref' => ref,
    'require_catalog' => require_catalog,
    'require_relation' => require_relation,
    'source' => source,
    'version' => version
  }.compact
  response = @client.request(
    method: :post,
    path: '/v1/datasets/source-snapshots/validate',
    auth: true,
    body: body,
    request_options: request_options
  )
  result = Rafflesia::EnvelopeDatasetSourceSnapshotValidateData.new(response.body)
  result.last_response = Rafflesia::Types::ApiResponse.new(http_status: response.code.to_i, http_headers: response.each_header.to_h, request_id: response["x-request-id"])
  result
end

#validationValidate(manifest_path:, require_no_failures: nil, require_source_files: nil, skip_row_count_check: nil, tables: nil, request_options: {}) ⇒ Rafflesia::EnvelopeDatasetValidateData

POST /v1/datasets/validation/validate

Parameters:

  • manifest_path (String)
  • require_no_failures (Boolean, nil) (defaults to: nil)
  • require_source_files (Boolean, nil) (defaults to: nil)
  • skip_row_count_check (Boolean, nil) (defaults to: nil)
  • tables (Array<String>, nil) (defaults to: nil)
  • request_options (Hash) (defaults to: {}) —

    (see Rafflesia::Types::RequestOptions)

Returns:



1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
 
# File 'lib/rafflesia/datasets.rb', line 1415

def validationValidate(
  manifest_path:,
  require_no_failures: nil,
  require_source_files: nil,
  skip_row_count_check: nil,
  tables: nil,
  request_options: {}
)
  body = {
    'manifest_path' => manifest_path,
    'require_no_failures' => require_no_failures,
    'require_source_files' => require_source_files,
    'skip_row_count_check' => skip_row_count_check,
    'tables' => tables
  }.compact
  response = @client.request(
    method: :post,
    path: '/v1/datasets/validation/validate',
    auth: true,
    body: body,
    request_options: request_options
  )
  result = Rafflesia::EnvelopeDatasetValidateData.new(response.body)
  result.last_response = Rafflesia::Types::ApiResponse.new(http_status: response.code.to_i, http_headers: response.each_header.to_h, request_id: response["x-request-id"])
  result
end