Commit Graph

  • 80b9b1d03e Better logs during ingestion Iván Martínez 2023-05-20 12:11:21 +02:00
  • 4a0e0d2e70 Use chunk_size variable in logs. Make vectorstore check more flexible Iván Martínez 2023-05-20 12:02:40 +02:00
  • fca1128fba Merge branch 'maozdemir-main' Iván Martínez 2023-05-20 11:49:15 +02:00
  • 7180d4386b Merge branch 'main' of https://github.com/maozdemir/privateGPT into maozdemir-main Iván Martínez 2023-05-20 11:48:29 +02:00
  • a86641cdec Readme small fixes following review and formatting Iván Martínez 2023-05-20 11:22:45 +02:00
  • fc50eb1b89 Merge branch 'abhiruka-main' Iván Martínez 2023-05-20 11:21:35 +02:00
  • cb7c96b31d Add progress bar to load_documents function Enhanced the load_documents() function by adding a progress bar using the tqdm library. This change improves user experience by providing real-time feedback on the progress of document loading. Now, users can easily track the progress of this operation, especially when loading a large number of documents. jiangzhuo 2023-05-19 03:18:41 +09:00
  • e3b769d33a Optimize load_documents function with multiprocessing jiangzhuo 2023-05-19 02:35:20 +09:00
  • 04f6706bbb Make scripts executeable, add basic pre-commit setup MDW 2023-05-18 02:08:52 +02:00
  • 20554a7c9d Merge pull request #292 from jiangzhuo/feature/multiprocessing-for-document-loading Iván Martínez 2023-05-20 10:57:42 +02:00
  • b30cd52136 Merge pull request #271 from mdeweerd/executable_python Iván Martínez 2023-05-20 10:49:20 +02:00
  • be1bcbca37 Merge branch 'imartinez:main' into main Abhiruka 2023-05-20 07:42:26 +08:00
  • f8805c80f8 Update as per the feedback. - moved args parser inside main - assigned empty list to docs. - Updated README.md. abhiruka 2023-05-20 07:40:05 +08:00
  • 7f918a9fa1 Make scripts executeable, add basic pre-commit setup MDW 2023-05-18 02:08:52 +02:00
  • 22945bc91d Merge pull request #299 from mdeweerd/elm_extended Iván Martínez 2023-05-19 21:40:42 +02:00
  • 9fb7f07e3c "Refactored main function to take hide_source and mute_stream parameters for controlling output. Added argparse for command-line argument parsing. StreamingStdOutCallbackHandler and source document display are now optional based on user input. Introduced parse_arguments function to handle command-line arguments. Also, updated README.md to reflect these changes." abhiruka 2023-05-19 23:18:31 +08:00
  • 4cda348cf8 Fix #294 (tested) MDW 2023-05-19 16:23:09 +02:00
  • ba0dbe8d1c Add progress bar to load_documents function Enhanced the load_documents() function by adding a progress bar using the tqdm library. This change improves user experience by providing real-time feedback on the progress of document loading. Now, users can easily track the progress of this operation, especially when loading a large number of documents. jiangzhuo 2023-05-19 03:18:41 +09:00
  • 81b221bccb Optimize load_documents function with multiprocessing jiangzhuo 2023-05-19 02:35:20 +09:00
  • a862ff2be6 Add fallback for plain elm #294 #290 MDW 2023-05-19 01:04:42 +02:00
  • ad64589c8f Merge pull request #231 from milescattini/patch-1 Iván Martínez 2023-05-18 23:51:36 +02:00
  • b9f8dc312f Merge pull request #254 from Fabio3rs/formatOffice97-2003 Iván Martínez 2023-05-18 23:49:40 +02:00
  • 1590c5890f Update requirements Iván Martínez 2023-05-18 23:23:11 +02:00
  • 7844553ca1 Implement a way of ingesting more documents Move environment variables to the global scope Add a better check for vectorstore existence Introduced a new function for better readability Co-authored-by: Pulp <51127079+PulpCattel@users.noreply.github.com> impulsivus 2023-05-18 17:23:45 +03:00
  • 42046c5ec0 Merge pull request #268 from vilaca/dotenv-called-twice Iván Martínez 2023-05-18 15:15:17 +02:00
  • 2360728fab Fix Typo in Mac on Intel milescattini 2023-05-18 18:02:54 +10:00
  • ec126b51d8 Fix loader mapping order Fabio Rossini Sluzala 2023-05-17 22:38:30 -03:00
  • 79a3c00313 remove duplicate vilaca 2023-05-17 23:45:27 +01:00
  • 652401cf29 Add the formats to the README.md Fabio Rossini Sluzala 2023-05-17 13:53:46 -03:00
  • 66a9f9cde0 Add .doc .ppt (Word and PowerPoint 97/2003 formats) Fabio Rossini Sluzala 2023-05-17 12:04:16 -03:00
  • 355b4be7c0 Merge pull request #224 from imartinez/feature/sentence-transformers-embeddings Iván Martínez 2023-05-17 10:56:34 +02:00
  • 83797ec08b Merge pull request #240 from zishon89us/patch-1 Iván Martínez 2023-05-17 09:25:14 +02:00
  • dd144bba16 pypandoc-binary replacing pandoc-binary Zeeshan Hassan Memon 2023-05-17 11:27:43 +05:00
  • 380b119581 Add fix for clang install of non m1 mac milescattini 2023-05-17 11:48:35 +10:00
  • 90798f1986 Merge branch 'main' into feature/sentence-transformers-embeddings Iván Martínez 2023-05-17 01:00:13 +02:00
  • bf3bddfbb6 More loaders, generic method Iván Martínez 2023-05-16 20:44:30 +02:00
  • fdb45741e5 Merge pull request #211 from mdeweerd/extra_loaders Iván Martínez 2023-05-17 00:39:37 +02:00
  • 23d24c88e9 Update code to use sentence-transformers through huggingfaceembeddings Iván Martínez 2023-05-17 00:32:41 +02:00
  • 8a5b2f453b Use faster and better embeddings: sentenceTransformers Iván Martínez 2023-05-17 00:19:21 +02:00
  • 2217b5f0e3 More loaders, generic method Iván Martínez 2023-05-16 20:44:30 +02:00
  • b6f007dbb8 Update issue templates Iván Martínez 2023-05-16 20:44:30 +02:00
  • 9e94a3cd40 Update issue templates Iván Martínez 2023-05-16 20:12:34 +02:00
  • f42d3e0ce2 Merge pull request #168 from andreakiro/fix/requirements Iván Martínez 2023-05-16 19:32:11 +02:00
  • 7ae80e6629 add python-dotenv to requirements Andrea Pinto 2023-05-15 19:19:10 +02:00
  • 5a695e9767 Merge pull request #93 from katojunichi893/main Iván Martínez 2023-05-14 10:55:12 +02:00
  • a061270bf0 Merge pull request #105 from koushkv/patch-1 Iván Martínez 2023-05-14 10:42:25 +02:00
  • 7612193031 Merge pull request #64 from FluffyDietEngine/main Iván Martínez 2023-05-14 10:39:38 +02:00
  • 9c3832c156 Update README.md katojunichi893 2023-05-14 17:36:40 +09:00
  • 2dac62c5aa fixed a typo Koushik 2023-05-14 10:26:13 +05:30
  • 24e464f51b Update README.md ひかる 2023-05-14 04:18:17 +09:00
  • b76a240714 Merge pull request #74 from andreakiro/fix/load-documents Iván Martínez 2023-05-13 10:36:57 +02:00
  • d0aa57178a ingest unlimited number of documents Andrea Pinto 2023-05-12 15:36:20 +02:00
  • 271673ffcc Merge pull request #68 from andreakiro/readme/updates Iván Martínez 2023-05-12 11:33:51 +02:00
  • 034fde4c3e Merge pull request #67 from andreakiro/fix/persist-dir Iván Martínez 2023-05-12 11:31:53 +02:00
  • 718b67715c note on instructions for .env Andrea Pinto 2023-05-12 11:15:51 +02:00
  • 01f55441e7 fix persist db directory at ingestion Andrea Pinto 2023-05-12 10:37:10 +02:00
  • 6419d0aa1c added library for parsing PDFs Santhosh Solomon 2023-05-12 09:33:05 +05:30
  • 39df61ca07 Merge pull request #58 from sorin/sorin-fix-env Iván Martínez 2023-05-12 00:37:05 +02:00
  • 544ddd9631 load .env Sorin Neacsu 2023-05-11 15:34:17 -07:00
  • e947ca1d0f load .env Sorin Neacsu 2023-05-11 15:33:56 -07:00
  • bc7ce4395b Merge pull request #53 from alxspiker/main Iván Martínez 2023-05-11 23:22:27 +02:00
  • 39d00b840d Update README.md alxspiker 2023-05-11 15:05:07 -06:00
  • 9722ef4356 Update README.md alxspiker 2023-05-11 15:01:57 -06:00
  • 51f01d850a Update README.md alxspiker 2023-05-11 14:53:10 -06:00
  • f60dbb520e Merge branch 'main' into main alxspiker 2023-05-11 14:34:13 -06:00
  • 52ae6c0866 .env + LlamaCpp + PDF/CSV + Ingest All alxspiker 2023-05-11 14:24:39 -06:00
  • 56c1be36ad Merge pull request #44 from R-Y-M-R/Fix/DisableChromaTelemetry Iván Martínez 2023-05-11 19:38:43 +02:00
  • 9c0321235b Merge pull request #39 from R-Y-M-R/Update/Requirements Iván Martínez 2023-05-11 19:35:31 +02:00
  • 85528db743 Update langchain to 0.0.166 R-Y-M-R 2023-05-11 12:37:00 -04:00
  • f12ea568e5 Use constants.py file R-Y-M-R 2023-05-11 10:29:07 -04:00
  • 8c6a81a07f Fix: Disable Chroma Telemetry R-Y-M-R 2023-05-11 10:17:18 -04:00
  • 918b384e38 Update langchain and llama versions R-Y-M-R 2023-05-11 09:50:40 -04:00
  • 60225698b6 Merge pull request #35 from R-Y-M-R/Fix/urllib3 Iván Martínez 2023-05-11 14:32:28 +02:00
  • 54d14a6cb6 Resolve #17: Add urllib3 fix to requirements.txt R-Y-M-R 2023-05-11 06:26:04 -04:00
  • 2841fe45e1 Merge pull request #22 from 0mlml/patch-1 Iván Martínez 2023-05-10 14:52:11 +02:00
  • e3769a060e Fix typo in README.md Max 2023-05-10 08:17:39 -04:00
  • 026b9f895c Use RecursiveCharacterTextSplitter to avoid llama_tokenize: too many tokens error during ingestion Iván Martínez 2023-05-09 00:20:42 +02:00
  • 75a1141743 Update README.md Iván Martínez 2023-05-08 23:49:54 +02:00
  • 34cb82c784 Update README.md Iván Martínez 2023-05-08 23:47:09 +02:00
  • ab30465be7 Update README.md Iván Martínez 2023-05-08 23:44:43 +02:00
  • bdd8c8748b Update dependencies. Remove custom gpt4all_j wrapper. Iván Martínez 2023-05-08 23:41:57 +02:00
  • 92244a90b4 Use a different text splitter to improve results. Ingest takes an argument pointing to the doc to ingest. Iván Martínez 2023-05-05 17:32:31 +02:00
  • a05186b598 Merge pull request #3 from mkinney/main Iván Martínez 2023-05-04 08:33:15 +02:00
  • 5128704a8e pin pygptj Mike Kinney 2023-05-03 23:29:31 -07:00
  • 77447e50c0 Complete readme. Fixed reference in gpt4all_j wrapper Iván martínez 2023-05-02 20:22:04 +02:00
  • 55338b8f6e End-to-end working version Iván martínez 2023-05-02 19:35:40 +02:00
  • 51dae80058 Initial commit Iván Martínez 2023-05-02 11:15:31 +02:00