scrapex 1.0.0-beta.1 → 1.0.0-beta.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (52) hide show
  1. package/dist/embeddings/index.cjs +52 -0
  2. package/dist/embeddings/index.d.cts +3 -0
  3. package/dist/embeddings/index.d.mts +3 -0
  4. package/dist/embeddings/index.mjs +4 -0
  5. package/dist/embeddings-BjNTQSG9.cjs +1455 -0
  6. package/dist/embeddings-BjNTQSG9.cjs.map +1 -0
  7. package/dist/embeddings-Bsymy_jA.mjs +1215 -0
  8. package/dist/embeddings-Bsymy_jA.mjs.map +1 -0
  9. package/dist/enhancer-Cs_WyWtJ.cjs +219 -0
  10. package/dist/enhancer-Cs_WyWtJ.cjs.map +1 -0
  11. package/dist/enhancer-INx5NlgO.mjs +177 -0
  12. package/dist/enhancer-INx5NlgO.mjs.map +1 -0
  13. package/dist/{enhancer-j0xqKDJm.cjs → http-base-CHLf-Tco.cjs} +36 -199
  14. package/dist/http-base-CHLf-Tco.cjs.map +1 -0
  15. package/dist/{enhancer-ByjRD-t5.mjs → http-base-DM7YNo6X.mjs} +25 -176
  16. package/dist/http-base-DM7YNo6X.mjs.map +1 -0
  17. package/dist/{index-CDgcRnig.d.cts → index-Bvseqli-.d.cts} +1 -1
  18. package/dist/{index-CDgcRnig.d.cts.map → index-Bvseqli-.d.cts.map} +1 -1
  19. package/dist/{index-piS5wtki.d.mts → index-CIFjNySr.d.mts} +1 -1
  20. package/dist/{index-piS5wtki.d.mts.map → index-CIFjNySr.d.mts.map} +1 -1
  21. package/dist/index-D6qfjmZQ.d.mts +401 -0
  22. package/dist/index-D6qfjmZQ.d.mts.map +1 -0
  23. package/dist/index-RFSpP5g8.d.cts +401 -0
  24. package/dist/index-RFSpP5g8.d.cts.map +1 -0
  25. package/dist/index.cjs +39 -1074
  26. package/dist/index.cjs.map +1 -1
  27. package/dist/index.d.cts +3 -260
  28. package/dist/index.d.cts.map +1 -1
  29. package/dist/index.d.mts +3 -260
  30. package/dist/index.d.mts.map +1 -1
  31. package/dist/index.mjs +4 -1039
  32. package/dist/index.mjs.map +1 -1
  33. package/dist/llm/index.cjs +7 -6
  34. package/dist/llm/index.cjs.map +1 -1
  35. package/dist/llm/index.d.cts +1 -1
  36. package/dist/llm/index.d.mts +1 -1
  37. package/dist/llm/index.mjs +2 -1
  38. package/dist/llm/index.mjs.map +1 -1
  39. package/dist/parsers/index.d.cts +1 -1
  40. package/dist/parsers/index.d.mts +1 -1
  41. package/dist/parsers/index.mjs +1 -1
  42. package/dist/{parsers-CwkYnyWY.mjs → parsers-DsawHeo0.mjs} +1 -1
  43. package/dist/{parsers-CwkYnyWY.mjs.map → parsers-DsawHeo0.mjs.map} +1 -1
  44. package/dist/{types-CadAXrme.d.mts → types-BOcHQU9s.d.mts} +308 -151
  45. package/dist/types-BOcHQU9s.d.mts.map +1 -0
  46. package/dist/{types-DPEtPihB.d.cts → types-DutdBpqd.d.cts} +308 -151
  47. package/dist/types-DutdBpqd.d.cts.map +1 -0
  48. package/package.json +1 -1
  49. package/dist/enhancer-ByjRD-t5.mjs.map +0 -1
  50. package/dist/enhancer-j0xqKDJm.cjs.map +0 -1
  51. package/dist/types-CadAXrme.d.mts.map +0 -1
  52. package/dist/types-DPEtPihB.d.cts.map +0 -1
@@ -0,0 +1,52 @@
1
+ const require_http_base = require('../http-base-CHLf-Tco.cjs');
2
+ const require_embeddings = require('../embeddings-BjNTQSG9.cjs');
3
+
4
+ exports.CircuitBreaker = require_http_base.CircuitBreaker;
5
+ exports.CircuitOpenError = require_http_base.CircuitOpenError;
6
+ exports.HttpEmbeddingProvider = require_embeddings.HttpEmbeddingProvider;
7
+ exports.InMemoryEmbeddingCache = require_embeddings.InMemoryEmbeddingCache;
8
+ exports.RateLimiter = require_http_base.RateLimiter;
9
+ exports.Semaphore = require_http_base.Semaphore;
10
+ exports.TRANSFORMERS_MODELS = require_embeddings.TRANSFORMERS_MODELS;
11
+ exports.aggregateVectors = require_embeddings.aggregateVectors;
12
+ exports.chunkText = require_embeddings.chunkText;
13
+ exports.containsPii = require_embeddings.containsPii;
14
+ exports.cosineSimilarity = require_embeddings.cosineSimilarity;
15
+ exports.createAzureEmbedding = require_embeddings.createAzureEmbedding;
16
+ exports.createCohereEmbedding = require_embeddings.createCohereEmbedding;
17
+ exports.createEmbeddingProvider = require_embeddings.createEmbeddingProvider;
18
+ exports.createHttpEmbedding = require_embeddings.createHttpEmbedding;
19
+ exports.createHuggingFaceEmbedding = require_embeddings.createHuggingFaceEmbedding;
20
+ exports.createNoOpCache = require_embeddings.createNoOpCache;
21
+ exports.createOllamaEmbedding = require_embeddings.createOllamaEmbedding;
22
+ exports.createOpenAIEmbedding = require_embeddings.createOpenAIEmbedding;
23
+ exports.createPiiRedactor = require_embeddings.createPiiRedactor;
24
+ exports.createTimeoutSignal = require_http_base.createTimeoutSignal;
25
+ exports.createTokenizer = require_embeddings.createTokenizer;
26
+ exports.createTransformersEmbedding = require_embeddings.createTransformersEmbedding;
27
+ exports.dotProduct = require_embeddings.dotProduct;
28
+ exports.embed = require_embeddings.embed;
29
+ exports.embedScrapedData = require_embeddings.embedScrapedData;
30
+ exports.estimateTokens = require_embeddings.estimateTokens;
31
+ exports.euclideanDistance = require_embeddings.euclideanDistance;
32
+ exports.generateCacheKey = require_embeddings.generateCacheKey;
33
+ exports.generateChecksum = require_embeddings.generateChecksum;
34
+ exports.generateEmbeddings = require_embeddings.generateEmbeddings;
35
+ exports.getChunkingStats = require_embeddings.getChunkingStats;
36
+ exports.getDefaultCache = require_embeddings.getDefaultCache;
37
+ exports.getDefaultModel = require_embeddings.getDefaultModel;
38
+ exports.getDimensions = require_embeddings.getDimensions;
39
+ exports.heuristicTokenCount = require_embeddings.heuristicTokenCount;
40
+ exports.isEmbeddingProvider = require_embeddings.isEmbeddingProvider;
41
+ exports.isRetryableError = require_http_base.isRetryableError;
42
+ exports.needsChunking = require_embeddings.needsChunking;
43
+ exports.normalizeVector = require_embeddings.normalizeVector;
44
+ exports.previewInput = require_embeddings.previewInput;
45
+ exports.redactPii = require_embeddings.redactPii;
46
+ exports.resetDefaultCache = require_embeddings.resetDefaultCache;
47
+ exports.selectInput = require_embeddings.selectInput;
48
+ exports.validateCachedResult = require_embeddings.validateCachedResult;
49
+ exports.validateInput = require_embeddings.validateInput;
50
+ exports.withResilience = require_http_base.withResilience;
51
+ exports.withRetry = require_http_base.withRetry;
52
+ exports.withTimeout = require_http_base.withTimeout;
@@ -0,0 +1,3 @@
1
+ import { A as HttpEmbeddingProvider, B as withResilience, C as RateLimitConfig, D as SafetyConfig, E as RetryConfig, F as CircuitOpenError, H as withTimeout, I as RateLimiter, L as Semaphore, O as TextChunk, P as CircuitBreaker, R as createTimeoutSignal, S as PiiRedactionConfig, T as ResilienceState, V as withRetry, _ as EmbeddingSkipped, a as EmbedRequest, b as EmbeddingSuccessSingle, c as EmbeddingCache, d as EmbeddingInputType, f as EmbeddingMetrics, g as EmbeddingResult, h as EmbeddingProviderConfig, i as CircuitState, j as createHttpEmbedding, k as HttpEmbeddingConfig, l as EmbeddingCacheConfig, m as EmbeddingProvider, n as CircuitBreakerConfig, o as EmbedResponse, p as EmbeddingOptions, r as CircuitBreakerState, s as EmbeddingAggregation, t as ChunkingConfig, u as EmbeddingInputConfig, v as EmbeddingSource, w as ResilienceConfig, x as OutputConfig, y as EmbeddingSuccessMultiple, z as isRetryableError } from "../types-DutdBpqd.cjs";
2
+ import { A as createNoOpCache, B as euclideanDistance, C as createTokenizer, D as needsChunking, E as heuristicTokenCount, F as validateCachedResult, H as normalizeVector, I as AggregationResult, L as aggregateVectors, M as generateChecksum, N as getDefaultCache, O as CacheStats, P as resetDefaultCache, R as cosineSimilarity, S as chunkText, T as getChunkingStats, V as getDimensions, _ as generateEmbeddings, a as createEmbeddingProvider, b as selectInput, c as createAzureEmbedding, d as createOllamaEmbedding, f as createOpenAIEmbedding, g as embedScrapedData, h as embed, i as redactPii, j as generateCacheKey, k as InMemoryEmbeddingCache, l as createCohereEmbedding, m as getDefaultModel, n as containsPii, o as isEmbeddingProvider, p as createTransformersEmbedding, r as createPiiRedactor, s as TRANSFORMERS_MODELS, t as RedactionResult, u as createHuggingFaceEmbedding, v as InputValidation, w as estimateTokens, x as validateInput, y as previewInput, z as dotProduct } from "../index-RFSpP5g8.cjs";
3
+ export { AggregationResult, CacheStats, ChunkingConfig, CircuitBreaker, CircuitBreakerConfig, CircuitBreakerState, CircuitOpenError, CircuitState, EmbedRequest, EmbedResponse, EmbeddingAggregation, EmbeddingCache, EmbeddingCacheConfig, EmbeddingInputConfig, EmbeddingInputType, EmbeddingMetrics, EmbeddingOptions, EmbeddingProvider, EmbeddingProviderConfig, EmbeddingResult, EmbeddingSkipped, EmbeddingSource, EmbeddingSuccessMultiple, EmbeddingSuccessSingle, HttpEmbeddingConfig, HttpEmbeddingProvider, InMemoryEmbeddingCache, InputValidation, OutputConfig, PiiRedactionConfig, RateLimitConfig, RateLimiter, RedactionResult, ResilienceConfig, ResilienceState, RetryConfig, SafetyConfig, Semaphore, TRANSFORMERS_MODELS, TextChunk, aggregateVectors, chunkText, containsPii, cosineSimilarity, createAzureEmbedding, createCohereEmbedding, createEmbeddingProvider, createHttpEmbedding, createHuggingFaceEmbedding, createNoOpCache, createOllamaEmbedding, createOpenAIEmbedding, createPiiRedactor, createTimeoutSignal, createTokenizer, createTransformersEmbedding, dotProduct, embed, embedScrapedData, estimateTokens, euclideanDistance, generateCacheKey, generateChecksum, generateEmbeddings, getChunkingStats, getDefaultCache, getDefaultModel, getDimensions, heuristicTokenCount, isEmbeddingProvider, isRetryableError, needsChunking, normalizeVector, previewInput, redactPii, resetDefaultCache, selectInput, validateCachedResult, validateInput, withResilience, withRetry, withTimeout };
@@ -0,0 +1,3 @@
1
+ import { A as HttpEmbeddingProvider, B as withResilience, C as RateLimitConfig, D as SafetyConfig, E as RetryConfig, F as CircuitOpenError, H as withTimeout, I as RateLimiter, L as Semaphore, O as TextChunk, P as CircuitBreaker, R as createTimeoutSignal, S as PiiRedactionConfig, T as ResilienceState, V as withRetry, _ as EmbeddingSkipped, a as EmbedRequest, b as EmbeddingSuccessSingle, c as EmbeddingCache, d as EmbeddingInputType, f as EmbeddingMetrics, g as EmbeddingResult, h as EmbeddingProviderConfig, i as CircuitState, j as createHttpEmbedding, k as HttpEmbeddingConfig, l as EmbeddingCacheConfig, m as EmbeddingProvider, n as CircuitBreakerConfig, o as EmbedResponse, p as EmbeddingOptions, r as CircuitBreakerState, s as EmbeddingAggregation, t as ChunkingConfig, u as EmbeddingInputConfig, v as EmbeddingSource, w as ResilienceConfig, x as OutputConfig, y as EmbeddingSuccessMultiple, z as isRetryableError } from "../types-BOcHQU9s.mjs";
2
+ import { A as createNoOpCache, B as euclideanDistance, C as createTokenizer, D as needsChunking, E as heuristicTokenCount, F as validateCachedResult, H as normalizeVector, I as AggregationResult, L as aggregateVectors, M as generateChecksum, N as getDefaultCache, O as CacheStats, P as resetDefaultCache, R as cosineSimilarity, S as chunkText, T as getChunkingStats, V as getDimensions, _ as generateEmbeddings, a as createEmbeddingProvider, b as selectInput, c as createAzureEmbedding, d as createOllamaEmbedding, f as createOpenAIEmbedding, g as embedScrapedData, h as embed, i as redactPii, j as generateCacheKey, k as InMemoryEmbeddingCache, l as createCohereEmbedding, m as getDefaultModel, n as containsPii, o as isEmbeddingProvider, p as createTransformersEmbedding, r as createPiiRedactor, s as TRANSFORMERS_MODELS, t as RedactionResult, u as createHuggingFaceEmbedding, v as InputValidation, w as estimateTokens, x as validateInput, y as previewInput, z as dotProduct } from "../index-D6qfjmZQ.mjs";
3
+ export { AggregationResult, CacheStats, ChunkingConfig, CircuitBreaker, CircuitBreakerConfig, CircuitBreakerState, CircuitOpenError, CircuitState, EmbedRequest, EmbedResponse, EmbeddingAggregation, EmbeddingCache, EmbeddingCacheConfig, EmbeddingInputConfig, EmbeddingInputType, EmbeddingMetrics, EmbeddingOptions, EmbeddingProvider, EmbeddingProviderConfig, EmbeddingResult, EmbeddingSkipped, EmbeddingSource, EmbeddingSuccessMultiple, EmbeddingSuccessSingle, HttpEmbeddingConfig, HttpEmbeddingProvider, InMemoryEmbeddingCache, InputValidation, OutputConfig, PiiRedactionConfig, RateLimitConfig, RateLimiter, RedactionResult, ResilienceConfig, ResilienceState, RetryConfig, SafetyConfig, Semaphore, TRANSFORMERS_MODELS, TextChunk, aggregateVectors, chunkText, containsPii, cosineSimilarity, createAzureEmbedding, createCohereEmbedding, createEmbeddingProvider, createHttpEmbedding, createHuggingFaceEmbedding, createNoOpCache, createOllamaEmbedding, createOpenAIEmbedding, createPiiRedactor, createTimeoutSignal, createTokenizer, createTransformersEmbedding, dotProduct, embed, embedScrapedData, estimateTokens, euclideanDistance, generateCacheKey, generateChecksum, generateEmbeddings, getChunkingStats, getDefaultCache, getDefaultModel, getDimensions, heuristicTokenCount, isEmbeddingProvider, isRetryableError, needsChunking, normalizeVector, previewInput, redactPii, resetDefaultCache, selectInput, validateCachedResult, validateInput, withResilience, withRetry, withTimeout };
@@ -0,0 +1,4 @@
1
+ import { a as Semaphore, c as withResilience, i as RateLimiter, l as withRetry, n as CircuitBreaker, o as createTimeoutSignal, r as CircuitOpenError, s as isRetryableError, u as withTimeout } from "../http-base-DM7YNo6X.mjs";
2
+ import { A as generateCacheKey, B as normalizeVector, C as createTokenizer, D as needsChunking, E as heuristicTokenCount, F as aggregateVectors, I as cosineSimilarity, L as dotProduct, M as getDefaultCache, N as resetDefaultCache, O as InMemoryEmbeddingCache, P as validateCachedResult, R as euclideanDistance, S as chunkText, T as getChunkingStats, _ as createHttpEmbedding, a as createPiiRedactor, b as selectInput, c as isEmbeddingProvider, d as createCohereEmbedding, f as createHuggingFaceEmbedding, g as HttpEmbeddingProvider, h as createTransformersEmbedding, i as containsPii, j as generateChecksum, k as createNoOpCache, l as TRANSFORMERS_MODELS, m as createOpenAIEmbedding, n as embedScrapedData, o as redactPii, p as createOllamaEmbedding, r as generateEmbeddings, s as createEmbeddingProvider, t as embed, u as createAzureEmbedding, v as getDefaultModel, w as estimateTokens, x as validateInput, y as previewInput, z as getDimensions } from "../embeddings-Bsymy_jA.mjs";
3
+
4
+ export { CircuitBreaker, CircuitOpenError, HttpEmbeddingProvider, InMemoryEmbeddingCache, RateLimiter, Semaphore, TRANSFORMERS_MODELS, aggregateVectors, chunkText, containsPii, cosineSimilarity, createAzureEmbedding, createCohereEmbedding, createEmbeddingProvider, createHttpEmbedding, createHuggingFaceEmbedding, createNoOpCache, createOllamaEmbedding, createOpenAIEmbedding, createPiiRedactor, createTimeoutSignal, createTokenizer, createTransformersEmbedding, dotProduct, embed, embedScrapedData, estimateTokens, euclideanDistance, generateCacheKey, generateChecksum, generateEmbeddings, getChunkingStats, getDefaultCache, getDefaultModel, getDimensions, heuristicTokenCount, isEmbeddingProvider, isRetryableError, needsChunking, normalizeVector, previewInput, redactPii, resetDefaultCache, selectInput, validateCachedResult, validateInput, withResilience, withRetry, withTimeout };