summaryrefslogtreecommitdiffstats
path: root/src/rag/loader.rs
AgeCommit message (Collapse)AuthorLines
2024-12-04feat: `--file/.file` accept file formats in document_loaders (#1033)sigoden-77/+0
2024-12-04refactor: do not refresh documents when `.edit rag-docs` (#1032)sigoden-69/+0
2024-11-04refactor: save RAG document path as an absolute path (#965)sigoden-8/+17
2024-09-08feat: tolerate failure to load some rag files (#846)sigoden-3/+42
2024-08-12feat: support builtin website crawling (recursive_url) (#786)sigoden-12/+11
2024-07-10refactor: fetch image as data url (#694)sigoden-2/+2
2024-07-10feat: `--file/.file` can load dirs (#693)sigoden-119/+4
2024-07-03refactor: update config.example.yaml and readme, fix typos (#682)sigoden-1/+1
2024-07-02refactor: improve RAG (#675)sigoden-1/+1
2024-07-01feat: support `.rebuild rag` repl command(#672)sigoden-147/+93
2024-06-28feat: `.file`/`--file` support URLs (#665)sigoden-113/+9
2024-06-27refactor: smart document splitter (#662)sigoden-25/+42
2024-06-27feat: implement native rag url loader (#660)sigoden-8/+55
2024-06-26feat: rag load websites (#655)sigoden-21/+180
2024-06-26feat: custom rag document loaders (#650)sigoden-41/+36
2024-06-12refactor: load pdf/docx files (#592)sigoden-31/+39
2024-06-05feat: support RAG (#560)sigoden-0/+146
* feat: support RAG * support more embeddings models and implement concurrent embedding api * show the progress of addings paths * ignore embedding context when saving message * embedding model max_chunk_size => default_chunk_size * support pdf and pandoc formats (docx, epub, ipynb)