langchain 0.2.18 → 0.3.0-rc.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (338) hide show
  1. package/dist/agents/openai_functions/index.cjs +2 -2
  2. package/dist/agents/openai_functions/index.js +2 -2
  3. package/dist/chains/combine_documents/stuff.cjs +2 -2
  4. package/dist/chains/combine_documents/stuff.js +2 -2
  5. package/dist/chains/openai_functions/openapi.cjs +3 -1
  6. package/dist/chains/openai_functions/openapi.js +3 -1
  7. package/dist/load/import_constants.cjs +2 -39
  8. package/dist/load/import_constants.js +2 -39
  9. package/dist/load/import_map.cjs +2 -3
  10. package/dist/load/import_map.d.ts +0 -1
  11. package/dist/load/import_map.js +0 -1
  12. package/dist/smith/config.d.ts +1 -5
  13. package/package.json +31 -854
  14. package/dist/document_loaders/fs/chatgpt.cjs +0 -90
  15. package/dist/document_loaders/fs/chatgpt.d.ts +0 -8
  16. package/dist/document_loaders/fs/chatgpt.js +0 -86
  17. package/dist/document_loaders/fs/csv.cjs +0 -73
  18. package/dist/document_loaders/fs/csv.d.ts +0 -65
  19. package/dist/document_loaders/fs/csv.js +0 -69
  20. package/dist/document_loaders/fs/docx.cjs +0 -58
  21. package/dist/document_loaders/fs/docx.d.ts +0 -25
  22. package/dist/document_loaders/fs/docx.js +0 -54
  23. package/dist/document_loaders/fs/epub.cjs +0 -103
  24. package/dist/document_loaders/fs/epub.d.ts +0 -33
  25. package/dist/document_loaders/fs/epub.js +0 -99
  26. package/dist/document_loaders/fs/notion.cjs +0 -26
  27. package/dist/document_loaders/fs/notion.d.ts +0 -12
  28. package/dist/document_loaders/fs/notion.js +0 -22
  29. package/dist/document_loaders/fs/obsidian.cjs +0 -247
  30. package/dist/document_loaders/fs/obsidian.d.ts +0 -28
  31. package/dist/document_loaders/fs/obsidian.js +0 -240
  32. package/dist/document_loaders/fs/openai_whisper_audio.cjs +0 -49
  33. package/dist/document_loaders/fs/openai_whisper_audio.d.ts +0 -23
  34. package/dist/document_loaders/fs/openai_whisper_audio.js +0 -45
  35. package/dist/document_loaders/fs/pdf.cjs +0 -148
  36. package/dist/document_loaders/fs/pdf.d.ts +0 -49
  37. package/dist/document_loaders/fs/pdf.js +0 -144
  38. package/dist/document_loaders/fs/pptx.cjs +0 -46
  39. package/dist/document_loaders/fs/pptx.d.ts +0 -25
  40. package/dist/document_loaders/fs/pptx.js +0 -42
  41. package/dist/document_loaders/fs/srt.cjs +0 -57
  42. package/dist/document_loaders/fs/srt.d.ts +0 -32
  43. package/dist/document_loaders/fs/srt.js +0 -50
  44. package/dist/document_loaders/fs/unstructured.cjs +0 -338
  45. package/dist/document_loaders/fs/unstructured.d.ts +0 -125
  46. package/dist/document_loaders/fs/unstructured.js +0 -333
  47. package/dist/document_loaders/web/apify_dataset.cjs +0 -130
  48. package/dist/document_loaders/web/apify_dataset.d.ts +0 -85
  49. package/dist/document_loaders/web/apify_dataset.js +0 -126
  50. package/dist/document_loaders/web/assemblyai.cjs +0 -200
  51. package/dist/document_loaders/web/assemblyai.d.ts +0 -95
  52. package/dist/document_loaders/web/assemblyai.js +0 -193
  53. package/dist/document_loaders/web/azure_blob_storage_container.cjs +0 -73
  54. package/dist/document_loaders/web/azure_blob_storage_container.d.ts +0 -46
  55. package/dist/document_loaders/web/azure_blob_storage_container.js +0 -69
  56. package/dist/document_loaders/web/azure_blob_storage_file.cjs +0 -124
  57. package/dist/document_loaders/web/azure_blob_storage_file.d.ts +0 -53
  58. package/dist/document_loaders/web/azure_blob_storage_file.js +0 -97
  59. package/dist/document_loaders/web/browserbase.cjs +0 -93
  60. package/dist/document_loaders/web/browserbase.d.ts +0 -48
  61. package/dist/document_loaders/web/browserbase.js +0 -86
  62. package/dist/document_loaders/web/cheerio.cjs +0 -118
  63. package/dist/document_loaders/web/cheerio.d.ts +0 -77
  64. package/dist/document_loaders/web/cheerio.js +0 -114
  65. package/dist/document_loaders/web/college_confidential.cjs +0 -41
  66. package/dist/document_loaders/web/college_confidential.d.ts +0 -25
  67. package/dist/document_loaders/web/college_confidential.js +0 -37
  68. package/dist/document_loaders/web/confluence.cjs +0 -190
  69. package/dist/document_loaders/web/confluence.d.ts +0 -114
  70. package/dist/document_loaders/web/confluence.js +0 -186
  71. package/dist/document_loaders/web/couchbase.cjs +0 -95
  72. package/dist/document_loaders/web/couchbase.d.ts +0 -32
  73. package/dist/document_loaders/web/couchbase.js +0 -91
  74. package/dist/document_loaders/web/figma.cjs +0 -102
  75. package/dist/document_loaders/web/figma.d.ts +0 -82
  76. package/dist/document_loaders/web/figma.js +0 -98
  77. package/dist/document_loaders/web/firecrawl.cjs +0 -95
  78. package/dist/document_loaders/web/firecrawl.d.ts +0 -50
  79. package/dist/document_loaders/web/firecrawl.js +0 -88
  80. package/dist/document_loaders/web/gitbook.cjs +0 -110
  81. package/dist/document_loaders/web/gitbook.d.ts +0 -55
  82. package/dist/document_loaders/web/gitbook.js +0 -106
  83. package/dist/document_loaders/web/github.cjs +0 -615
  84. package/dist/document_loaders/web/github.d.ts +0 -203
  85. package/dist/document_loaders/web/github.js +0 -608
  86. package/dist/document_loaders/web/hn.cjs +0 -90
  87. package/dist/document_loaders/web/hn.d.ts +0 -42
  88. package/dist/document_loaders/web/hn.js +0 -86
  89. package/dist/document_loaders/web/imsdb.cjs +0 -44
  90. package/dist/document_loaders/web/imsdb.d.ts +0 -23
  91. package/dist/document_loaders/web/imsdb.js +0 -40
  92. package/dist/document_loaders/web/notionapi.cjs +0 -404
  93. package/dist/document_loaders/web/notionapi.d.ts +0 -133
  94. package/dist/document_loaders/web/notionapi.js +0 -392
  95. package/dist/document_loaders/web/notiondb.cjs +0 -199
  96. package/dist/document_loaders/web/notiondb.d.ts +0 -56
  97. package/dist/document_loaders/web/notiondb.js +0 -195
  98. package/dist/document_loaders/web/pdf.cjs +0 -140
  99. package/dist/document_loaders/web/pdf.d.ts +0 -35
  100. package/dist/document_loaders/web/pdf.js +0 -136
  101. package/dist/document_loaders/web/playwright.cjs +0 -89
  102. package/dist/document_loaders/web/playwright.d.ts +0 -58
  103. package/dist/document_loaders/web/playwright.js +0 -85
  104. package/dist/document_loaders/web/puppeteer.cjs +0 -139
  105. package/dist/document_loaders/web/puppeteer.d.ts +0 -82
  106. package/dist/document_loaders/web/puppeteer.js +0 -135
  107. package/dist/document_loaders/web/recursive_url.cjs +0 -198
  108. package/dist/document_loaders/web/recursive_url.d.ts +0 -33
  109. package/dist/document_loaders/web/recursive_url.js +0 -194
  110. package/dist/document_loaders/web/s3.cjs +0 -164
  111. package/dist/document_loaders/web/s3.d.ts +0 -78
  112. package/dist/document_loaders/web/s3.js +0 -137
  113. package/dist/document_loaders/web/searchapi.cjs +0 -150
  114. package/dist/document_loaders/web/searchapi.d.ts +0 -76
  115. package/dist/document_loaders/web/searchapi.js +0 -146
  116. package/dist/document_loaders/web/serpapi.cjs +0 -127
  117. package/dist/document_loaders/web/serpapi.d.ts +0 -62
  118. package/dist/document_loaders/web/serpapi.js +0 -123
  119. package/dist/document_loaders/web/sitemap.cjs +0 -118
  120. package/dist/document_loaders/web/sitemap.d.ts +0 -41
  121. package/dist/document_loaders/web/sitemap.js +0 -114
  122. package/dist/document_loaders/web/sonix_audio.cjs +0 -68
  123. package/dist/document_loaders/web/sonix_audio.d.ts +0 -36
  124. package/dist/document_loaders/web/sonix_audio.js +0 -64
  125. package/dist/document_loaders/web/sort_xyz_blockchain.cjs +0 -157
  126. package/dist/document_loaders/web/sort_xyz_blockchain.d.ts +0 -78
  127. package/dist/document_loaders/web/sort_xyz_blockchain.js +0 -153
  128. package/dist/document_loaders/web/youtube.cjs +0 -116
  129. package/dist/document_loaders/web/youtube.d.ts +0 -55
  130. package/dist/document_loaders/web/youtube.js +0 -112
  131. package/dist/experimental/tools/pyinterpreter.cjs +0 -248
  132. package/dist/experimental/tools/pyinterpreter.d.ts +0 -18
  133. package/dist/experimental/tools/pyinterpreter.js +0 -244
  134. package/dist/retrievers/self_query/chroma.cjs +0 -48
  135. package/dist/retrievers/self_query/chroma.d.ts +0 -26
  136. package/dist/retrievers/self_query/chroma.js +0 -44
  137. package/dist/retrievers/self_query/pinecone.cjs +0 -47
  138. package/dist/retrievers/self_query/pinecone.d.ts +0 -26
  139. package/dist/retrievers/self_query/pinecone.js +0 -43
  140. package/dist/retrievers/self_query/supabase.cjs +0 -278
  141. package/dist/retrievers/self_query/supabase.d.ts +0 -109
  142. package/dist/retrievers/self_query/supabase.js +0 -274
  143. package/dist/retrievers/self_query/supabase_utils.cjs +0 -264
  144. package/dist/retrievers/self_query/supabase_utils.d.ts +0 -101
  145. package/dist/retrievers/self_query/supabase_utils.js +0 -259
  146. package/dist/retrievers/self_query/vectara.cjs +0 -143
  147. package/dist/retrievers/self_query/vectara.d.ts +0 -42
  148. package/dist/retrievers/self_query/vectara.js +0 -139
  149. package/dist/retrievers/self_query/weaviate.cjs +0 -201
  150. package/dist/retrievers/self_query/weaviate.d.ts +0 -99
  151. package/dist/retrievers/self_query/weaviate.js +0 -197
  152. package/dist/types/assemblyai-types.cjs +0 -2
  153. package/dist/types/assemblyai-types.d.ts +0 -4
  154. package/dist/types/assemblyai-types.js +0 -1
  155. package/document_loaders/fs/chatgpt.cjs +0 -1
  156. package/document_loaders/fs/chatgpt.d.cts +0 -1
  157. package/document_loaders/fs/chatgpt.d.ts +0 -1
  158. package/document_loaders/fs/chatgpt.js +0 -1
  159. package/document_loaders/fs/csv.cjs +0 -1
  160. package/document_loaders/fs/csv.d.cts +0 -1
  161. package/document_loaders/fs/csv.d.ts +0 -1
  162. package/document_loaders/fs/csv.js +0 -1
  163. package/document_loaders/fs/docx.cjs +0 -1
  164. package/document_loaders/fs/docx.d.cts +0 -1
  165. package/document_loaders/fs/docx.d.ts +0 -1
  166. package/document_loaders/fs/docx.js +0 -1
  167. package/document_loaders/fs/epub.cjs +0 -1
  168. package/document_loaders/fs/epub.d.cts +0 -1
  169. package/document_loaders/fs/epub.d.ts +0 -1
  170. package/document_loaders/fs/epub.js +0 -1
  171. package/document_loaders/fs/notion.cjs +0 -1
  172. package/document_loaders/fs/notion.d.cts +0 -1
  173. package/document_loaders/fs/notion.d.ts +0 -1
  174. package/document_loaders/fs/notion.js +0 -1
  175. package/document_loaders/fs/obsidian.cjs +0 -1
  176. package/document_loaders/fs/obsidian.d.cts +0 -1
  177. package/document_loaders/fs/obsidian.d.ts +0 -1
  178. package/document_loaders/fs/obsidian.js +0 -1
  179. package/document_loaders/fs/openai_whisper_audio.cjs +0 -1
  180. package/document_loaders/fs/openai_whisper_audio.d.cts +0 -1
  181. package/document_loaders/fs/openai_whisper_audio.d.ts +0 -1
  182. package/document_loaders/fs/openai_whisper_audio.js +0 -1
  183. package/document_loaders/fs/pdf.cjs +0 -1
  184. package/document_loaders/fs/pdf.d.cts +0 -1
  185. package/document_loaders/fs/pdf.d.ts +0 -1
  186. package/document_loaders/fs/pdf.js +0 -1
  187. package/document_loaders/fs/pptx.cjs +0 -1
  188. package/document_loaders/fs/pptx.d.cts +0 -1
  189. package/document_loaders/fs/pptx.d.ts +0 -1
  190. package/document_loaders/fs/pptx.js +0 -1
  191. package/document_loaders/fs/srt.cjs +0 -1
  192. package/document_loaders/fs/srt.d.cts +0 -1
  193. package/document_loaders/fs/srt.d.ts +0 -1
  194. package/document_loaders/fs/srt.js +0 -1
  195. package/document_loaders/fs/unstructured.cjs +0 -1
  196. package/document_loaders/fs/unstructured.d.cts +0 -1
  197. package/document_loaders/fs/unstructured.d.ts +0 -1
  198. package/document_loaders/fs/unstructured.js +0 -1
  199. package/document_loaders/web/apify_dataset.cjs +0 -1
  200. package/document_loaders/web/apify_dataset.d.cts +0 -1
  201. package/document_loaders/web/apify_dataset.d.ts +0 -1
  202. package/document_loaders/web/apify_dataset.js +0 -1
  203. package/document_loaders/web/assemblyai.cjs +0 -1
  204. package/document_loaders/web/assemblyai.d.cts +0 -1
  205. package/document_loaders/web/assemblyai.d.ts +0 -1
  206. package/document_loaders/web/assemblyai.js +0 -1
  207. package/document_loaders/web/azure_blob_storage_container.cjs +0 -1
  208. package/document_loaders/web/azure_blob_storage_container.d.cts +0 -1
  209. package/document_loaders/web/azure_blob_storage_container.d.ts +0 -1
  210. package/document_loaders/web/azure_blob_storage_container.js +0 -1
  211. package/document_loaders/web/azure_blob_storage_file.cjs +0 -1
  212. package/document_loaders/web/azure_blob_storage_file.d.cts +0 -1
  213. package/document_loaders/web/azure_blob_storage_file.d.ts +0 -1
  214. package/document_loaders/web/azure_blob_storage_file.js +0 -1
  215. package/document_loaders/web/browserbase.cjs +0 -1
  216. package/document_loaders/web/browserbase.d.cts +0 -1
  217. package/document_loaders/web/browserbase.d.ts +0 -1
  218. package/document_loaders/web/browserbase.js +0 -1
  219. package/document_loaders/web/cheerio.cjs +0 -1
  220. package/document_loaders/web/cheerio.d.cts +0 -1
  221. package/document_loaders/web/cheerio.d.ts +0 -1
  222. package/document_loaders/web/cheerio.js +0 -1
  223. package/document_loaders/web/college_confidential.cjs +0 -1
  224. package/document_loaders/web/college_confidential.d.cts +0 -1
  225. package/document_loaders/web/college_confidential.d.ts +0 -1
  226. package/document_loaders/web/college_confidential.js +0 -1
  227. package/document_loaders/web/confluence.cjs +0 -1
  228. package/document_loaders/web/confluence.d.cts +0 -1
  229. package/document_loaders/web/confluence.d.ts +0 -1
  230. package/document_loaders/web/confluence.js +0 -1
  231. package/document_loaders/web/couchbase.cjs +0 -1
  232. package/document_loaders/web/couchbase.d.cts +0 -1
  233. package/document_loaders/web/couchbase.d.ts +0 -1
  234. package/document_loaders/web/couchbase.js +0 -1
  235. package/document_loaders/web/figma.cjs +0 -1
  236. package/document_loaders/web/figma.d.cts +0 -1
  237. package/document_loaders/web/figma.d.ts +0 -1
  238. package/document_loaders/web/figma.js +0 -1
  239. package/document_loaders/web/firecrawl.cjs +0 -1
  240. package/document_loaders/web/firecrawl.d.cts +0 -1
  241. package/document_loaders/web/firecrawl.d.ts +0 -1
  242. package/document_loaders/web/firecrawl.js +0 -1
  243. package/document_loaders/web/gitbook.cjs +0 -1
  244. package/document_loaders/web/gitbook.d.cts +0 -1
  245. package/document_loaders/web/gitbook.d.ts +0 -1
  246. package/document_loaders/web/gitbook.js +0 -1
  247. package/document_loaders/web/github.cjs +0 -1
  248. package/document_loaders/web/github.d.cts +0 -1
  249. package/document_loaders/web/github.d.ts +0 -1
  250. package/document_loaders/web/github.js +0 -1
  251. package/document_loaders/web/hn.cjs +0 -1
  252. package/document_loaders/web/hn.d.cts +0 -1
  253. package/document_loaders/web/hn.d.ts +0 -1
  254. package/document_loaders/web/hn.js +0 -1
  255. package/document_loaders/web/imsdb.cjs +0 -1
  256. package/document_loaders/web/imsdb.d.cts +0 -1
  257. package/document_loaders/web/imsdb.d.ts +0 -1
  258. package/document_loaders/web/imsdb.js +0 -1
  259. package/document_loaders/web/notionapi.cjs +0 -1
  260. package/document_loaders/web/notionapi.d.cts +0 -1
  261. package/document_loaders/web/notionapi.d.ts +0 -1
  262. package/document_loaders/web/notionapi.js +0 -1
  263. package/document_loaders/web/notiondb.cjs +0 -1
  264. package/document_loaders/web/notiondb.d.cts +0 -1
  265. package/document_loaders/web/notiondb.d.ts +0 -1
  266. package/document_loaders/web/notiondb.js +0 -1
  267. package/document_loaders/web/pdf.cjs +0 -1
  268. package/document_loaders/web/pdf.d.cts +0 -1
  269. package/document_loaders/web/pdf.d.ts +0 -1
  270. package/document_loaders/web/pdf.js +0 -1
  271. package/document_loaders/web/playwright.cjs +0 -1
  272. package/document_loaders/web/playwright.d.cts +0 -1
  273. package/document_loaders/web/playwright.d.ts +0 -1
  274. package/document_loaders/web/playwright.js +0 -1
  275. package/document_loaders/web/puppeteer.cjs +0 -1
  276. package/document_loaders/web/puppeteer.d.cts +0 -1
  277. package/document_loaders/web/puppeteer.d.ts +0 -1
  278. package/document_loaders/web/puppeteer.js +0 -1
  279. package/document_loaders/web/recursive_url.cjs +0 -1
  280. package/document_loaders/web/recursive_url.d.cts +0 -1
  281. package/document_loaders/web/recursive_url.d.ts +0 -1
  282. package/document_loaders/web/recursive_url.js +0 -1
  283. package/document_loaders/web/s3.cjs +0 -1
  284. package/document_loaders/web/s3.d.cts +0 -1
  285. package/document_loaders/web/s3.d.ts +0 -1
  286. package/document_loaders/web/s3.js +0 -1
  287. package/document_loaders/web/searchapi.cjs +0 -1
  288. package/document_loaders/web/searchapi.d.cts +0 -1
  289. package/document_loaders/web/searchapi.d.ts +0 -1
  290. package/document_loaders/web/searchapi.js +0 -1
  291. package/document_loaders/web/serpapi.cjs +0 -1
  292. package/document_loaders/web/serpapi.d.cts +0 -1
  293. package/document_loaders/web/serpapi.d.ts +0 -1
  294. package/document_loaders/web/serpapi.js +0 -1
  295. package/document_loaders/web/sitemap.cjs +0 -1
  296. package/document_loaders/web/sitemap.d.cts +0 -1
  297. package/document_loaders/web/sitemap.d.ts +0 -1
  298. package/document_loaders/web/sitemap.js +0 -1
  299. package/document_loaders/web/sonix_audio.cjs +0 -1
  300. package/document_loaders/web/sonix_audio.d.cts +0 -1
  301. package/document_loaders/web/sonix_audio.d.ts +0 -1
  302. package/document_loaders/web/sonix_audio.js +0 -1
  303. package/document_loaders/web/sort_xyz_blockchain.cjs +0 -1
  304. package/document_loaders/web/sort_xyz_blockchain.d.cts +0 -1
  305. package/document_loaders/web/sort_xyz_blockchain.d.ts +0 -1
  306. package/document_loaders/web/sort_xyz_blockchain.js +0 -1
  307. package/document_loaders/web/youtube.cjs +0 -1
  308. package/document_loaders/web/youtube.d.cts +0 -1
  309. package/document_loaders/web/youtube.d.ts +0 -1
  310. package/document_loaders/web/youtube.js +0 -1
  311. package/experimental/tools/pyinterpreter.cjs +0 -1
  312. package/experimental/tools/pyinterpreter.d.cts +0 -1
  313. package/experimental/tools/pyinterpreter.d.ts +0 -1
  314. package/experimental/tools/pyinterpreter.js +0 -1
  315. package/memory/index.cjs +0 -1
  316. package/memory/index.d.cts +0 -1
  317. package/memory/index.d.ts +0 -1
  318. package/memory/index.js +0 -1
  319. package/retrievers/self_query/chroma.cjs +0 -1
  320. package/retrievers/self_query/chroma.d.cts +0 -1
  321. package/retrievers/self_query/chroma.d.ts +0 -1
  322. package/retrievers/self_query/chroma.js +0 -1
  323. package/retrievers/self_query/pinecone.cjs +0 -1
  324. package/retrievers/self_query/pinecone.d.cts +0 -1
  325. package/retrievers/self_query/pinecone.d.ts +0 -1
  326. package/retrievers/self_query/pinecone.js +0 -1
  327. package/retrievers/self_query/supabase.cjs +0 -1
  328. package/retrievers/self_query/supabase.d.cts +0 -1
  329. package/retrievers/self_query/supabase.d.ts +0 -1
  330. package/retrievers/self_query/supabase.js +0 -1
  331. package/retrievers/self_query/vectara.cjs +0 -1
  332. package/retrievers/self_query/vectara.d.cts +0 -1
  333. package/retrievers/self_query/vectara.d.ts +0 -1
  334. package/retrievers/self_query/vectara.js +0 -1
  335. package/retrievers/self_query/weaviate.cjs +0 -1
  336. package/retrievers/self_query/weaviate.d.cts +0 -1
  337. package/retrievers/self_query/weaviate.d.ts +0 -1
  338. package/retrievers/self_query/weaviate.js +0 -1
@@ -1,203 +0,0 @@
1
- import { Ignore } from "ignore";
2
- import { Document } from "@langchain/core/documents";
3
- import { AsyncCaller, AsyncCallerParams } from "@langchain/core/utils/async_caller";
4
- import { BaseDocumentLoader } from "../base.js";
5
- import { UnknownHandling } from "../fs/directory.js";
6
- /**
7
- * @deprecated - Import from "@langchain/community/document_loaders/web/github" instead. This entrypoint will be removed in 0.3.0.
8
- *
9
- * An interface that represents a file in a GitHub repository. It has
10
- * properties for the file name, path, SHA, size, URLs, type, and links.
11
- */
12
- export interface GithubFile {
13
- name: string;
14
- path: string;
15
- sha: string;
16
- size: number;
17
- url: string;
18
- html_url: string;
19
- git_url: string;
20
- download_url: string;
21
- type: string;
22
- _links: {
23
- self: string;
24
- git: string;
25
- html: string;
26
- };
27
- }
28
- /**
29
- * @deprecated - Import from "@langchain/community/document_loaders/web/github" instead. This entrypoint will be removed in 0.3.0.
30
- *
31
- * An interface that represents the parameters for the GithubRepoLoader
32
- * class. It extends the AsyncCallerParams interface and adds additional
33
- * properties specific to the GitHub repository loader.
34
- */
35
- export interface GithubRepoLoaderParams extends AsyncCallerParams {
36
- /**
37
- * The base URL of the GitHub instance.
38
- * To be used when you are not targeting github.com, e.g. a GitHub Enterprise instance.
39
- */
40
- baseUrl?: string;
41
- /**
42
- * The API endpoint URL of the GitHub instance.
43
- * To be used when you are not targeting github.com, e.g. a GitHub Enterprise instance.
44
- */
45
- apiUrl?: string;
46
- branch?: string;
47
- recursive?: boolean;
48
- /**
49
- * Set to true to recursively process submodules. Is only effective, when recursive=true.
50
- */
51
- processSubmodules?: boolean;
52
- unknown?: UnknownHandling;
53
- accessToken?: string;
54
- ignoreFiles?: (string | RegExp)[];
55
- ignorePaths?: string[];
56
- verbose?: boolean;
57
- /**
58
- * The maximum number of concurrent calls that can be made. Defaults to 2.
59
- */
60
- maxConcurrency?: number;
61
- /**
62
- * The maximum number of retries that can be made for a single call,
63
- * with an exponential backoff between each attempt. Defaults to 2.
64
- */
65
- maxRetries?: number;
66
- }
67
- /**
68
- * @deprecated - Import from "@langchain/community/document_loaders/web/github" instead. This entrypoint will be removed in 0.3.0.
69
- *
70
- * A class that extends the BaseDocumentLoader and implements the
71
- * GithubRepoLoaderParams interface. It represents a document loader for
72
- * loading files from a GitHub repository.
73
- */
74
- export declare class GithubRepoLoader extends BaseDocumentLoader implements GithubRepoLoaderParams {
75
- baseUrl: string;
76
- apiUrl: string;
77
- private readonly owner;
78
- private readonly repo;
79
- private readonly initialPath;
80
- private headers;
81
- branch: string;
82
- recursive: boolean;
83
- processSubmodules: boolean;
84
- unknown: UnknownHandling;
85
- accessToken?: string;
86
- ignoreFiles: (string | RegExp)[];
87
- ignore?: Ignore;
88
- verbose?: boolean;
89
- maxConcurrency?: number;
90
- maxRetries?: number;
91
- protected caller: AsyncCaller;
92
- ignorePaths?: string[];
93
- private submoduleInfos;
94
- constructor(githubUrl: string, { accessToken, baseUrl, apiUrl, branch, recursive, processSubmodules, unknown, ignoreFiles, ignorePaths, verbose, maxConcurrency, maxRetries, ...rest }?: GithubRepoLoaderParams);
95
- /**
96
- * Extracts the owner, repository, and path from a GitHub URL.
97
- * @param url The GitHub URL to extract information from.
98
- * @returns An object containing the owner, repository, and path extracted from the GitHub URL.
99
- */
100
- private extractOwnerAndRepoAndPath;
101
- /**
102
- * Fetches the files from the GitHub repository and creates Document
103
- * instances for each file. It also handles error handling based on the
104
- * unknown handling option.
105
- * @returns A promise that resolves to an array of Document instances.
106
- */
107
- load(): Promise<Document[]>;
108
- /**
109
- * Asynchronously streams documents from the entire GitHub repository.
110
- * It is suitable for situations where processing large repositories in a memory-efficient manner is required.
111
- * @yields Yields a Promise that resolves to a Document object for each file or submodule content found in the repository.
112
- */
113
- loadAsStream(): AsyncGenerator<Document, void, undefined>;
114
- /**
115
- * Loads the information about Git submodules from the repository, if available.
116
- */
117
- private getSubmoduleInfo;
118
- /**
119
- * Parses the given content of a .gitmodules file. Furthermore, queries the current SHA ref of all submodules.
120
- * Returns the submodule information as array.
121
- * @param gitmodulesContent the content of a .gitmodules file
122
- */
123
- private parseGitmodules;
124
- /**
125
- * Loads the documents of the given submodule. Uses the same parameters as for the current repository.
126
- * External submodules, i.e. submodules pointing to another GitHub instance, are ignored.
127
- * @param submoduleInfo the info about the submodule to be loaded
128
- */
129
- private loadSubmodule;
130
- /**
131
- * Asynchronously processes and streams the contents of a specified submodule in the GitHub repository.
132
- * @param submoduleInfo the info about the submodule to be loaded
133
- * @yields Yields a Promise that resolves to a Document object for each file found in the submodule.
134
- */
135
- private loadSubmoduleAsStream;
136
- /**
137
- * Determines whether a file or directory should be ignored based on its
138
- * path and type.
139
- * @param path The path of the file or directory.
140
- * @param fileType The type of the file or directory.
141
- * @returns A boolean indicating whether the file or directory should be ignored.
142
- */
143
- protected shouldIgnore(path: string, fileType: string): boolean;
144
- /**
145
- * Takes the file info and wrap it in a promise that will resolve to the file content and metadata
146
- * @param file
147
- * @returns
148
- */
149
- private fetchFileContentWrapper;
150
- /**
151
- * Maps a list of files / directories to a list of promises that will fetch the file / directory contents
152
- */
153
- private getCurrentDirectoryFilePromises;
154
- /**
155
- * Begins the process of fetching the contents of the repository
156
- */
157
- private processRepo;
158
- /**
159
- * Asynchronously processes the contents of the entire GitHub repository,
160
- * streaming each file as a Document object.
161
- * @param path The path of the directory to process.
162
- * @yields Yields a Promise that resolves to a Document object for each file found in the repository.
163
- */
164
- private processRepoAsStream;
165
- /**
166
- * Fetches the contents of a directory and maps the file / directory paths
167
- * to promises that will fetch the file / directory contents.
168
- * @param path The path of the directory to process.
169
- * @returns A promise that resolves to an array of promises that will fetch the file / directory contents.
170
- */
171
- private processDirectory;
172
- /**
173
- * Asynchronously processes the contents of a given directory in the GitHub repository,
174
- * streaming each file as a Document object.
175
- * @param path The path of the directory to process.
176
- * @yields Yields a Promise that resolves to a Document object for each file in the directory.
177
- */
178
- private processDirectoryAsStream;
179
- /**
180
- * Fetches the files from a GitHub repository.
181
- * If the path denotes a single file, the resulting array contains only one element.
182
- * @param path The path of the repository to fetch the files from.
183
- * @returns A promise that resolves to an array of GithubFile instances.
184
- */
185
- private fetchRepoFiles;
186
- /**
187
- * Fetches the content of a file from a GitHub repository.
188
- * @param file The file to fetch the content from.
189
- * @returns A promise that resolves to the content of the file.
190
- */
191
- private fetchFileContent;
192
- /**
193
- * Handles errors based on the unknown handling option.
194
- * @param message The error message.
195
- * @returns void
196
- */
197
- private handleError;
198
- /**
199
- * Logs the given message to the console, if parameter 'verbose' is set to true.
200
- * @param message the message to be logged.
201
- */
202
- private log;
203
- }