Commit Graph

38 Commits (04f824ea365898d23e00e77650e785e0c6d49b82)

Author SHA1 Message Date
Idan 897b4ef2cd Fixed a bug with reading md files 1 year ago
Anton Larin 84168e22d0 add missing variable after testin and minor fixes. 1 year ago
Anton Larin 6d5b698c39 fix arc53/DocsGPT#199 1 year ago
Anton Larin dd9f1abcea fix arc53/DocsGPT#199 1 year ago
Anton Larin b4bd34fb96 fix arc53/DocsGPT#199 1 year ago
Nazih Kalo da5d62cc1c updating the bulk ingest file metadata to account for parsers that output lists 1 year ago
Anton Larin 962becb9a5
Linting
* validate python formatting on every build with Ruff
* fix lint warnings
1 year ago
Anton Larin 168648e789 Proper PEP8 formatting 1 year ago
Pavel ce8f0ef9e1
Merge pull request #168 from arc53/feature/backend-uploads
Feature/backend uploads
2 years ago
Pavel 4532b6cd8c print minus 2 years ago
Pavel 53424a5c19 Added cli commands 2 years ago
Pavel b6c02c850a token ingeest 2 years ago
Pavel bac25112b7 v1 2 years ago
Alex 1d2162705d uploads backend first 2 years ago
Alex ac0224b687 mdx format 2 years ago
Alex 1f02f3b376 Update rst_parser.py 2 years ago
Alex f7d7244588 chunks rst 2 years ago
Alex 1af4ca2340
Merge pull request #129 from arc53/code-ingestion
Code_to_dict
2 years ago
Pavel 2c364d3c00 Code_to_dict
3 languages added, works well with python. Java and Js require additional revieving
2 years ago
Alex 5c2a537393
Merge pull request #116 from arc53/code-ingestion
Code ingestion
2 years ago
Pavel 0fb28e5213 Calc + structure 2 years ago
Manan 524e0f6f01 fix | Chunk creation error when
title not the first element in HTML
2 years ago
Manan 16eb503e36 Added HTML Support. read, clean-up, filter return 2 years ago
Manan e8baa46eb6 Merge branch 'main' of https://github.com/arc53/DocsGPT into main 2 years ago
Manan d0b472ad38 Implemented html_parser: cleaning & chunk creation 2 years ago
Alex 4d1ff8238d switching between llms 2 years ago
Alex f9fe3f2f48 Merge branch 'main' into custom-llm 2 years ago
EricGao888 aeac186484 Add retry strategy to increase stability 2 years ago
冯不游 b83589a308 feat: add support for directory list
example: `python ingest.py --dir inputs1 --dir another --dir ../inputs`,
the outputs will be in `outputs/input_folder_name/`
2 years ago
冯不游 636783ca8a fix: avoid second error issue 2 years ago
冯不游 458f2a3ff3 fix: restore index back when continue process 2 years ago
Alex 046fbebf56 Enable other llm's 2 years ago
Alex e88ff885fe
Merge pull request #75 from arc53/rst-interpreters 2 years ago
Pavel b1a6ebffba Directives + Interpreted
Some additional filters for rst parsing
2 years ago
Alex 205be538a3 fix dbqa, with new chain type, also fix for doc export 2 years ago
Alex 9228005a7e chunked embedding 2 years ago
vintro 2a203aa547
Create __init__.py
otherwise running `python ingest.py` complains about `parser` not being a package
2 years ago
Alex d642782a5a move folder 2 years ago