xberg 1.1.0

High-performance document intelligence library for Rust. Extract text, metadata, and structured data from PDFs, Office documents, images, and 107 formats and 371 programming languages via tree-sitter code intelligence with async/sync APIs.
Documentation
1
2
3
4
5
6
7
8
9
10
11
12
# sha256 manifest for the xberg-io/late-interaction-models preset fleet (self-hosted, weights unmodified).
# Format: <sha256>  <repo-relative path>. Pins the exact bytes each preset resolves to.
8a7ef3067ec44d7909d28daaf0cd52a6739a25e689252789b0927c593e17b121  colbert-small-v1/config.json
bd4bee8b055ed7a8e8b6e401792ae6e9137d9712c35eaa16f915ba69cae6d633  colbert-small-v1/model.onnx
5d5b662e421ea9fac075174bb0688ee0d9431699900b90662acd44b2a350503a  colbert-small-v1/special_tokens_map.json
d241a60d5e8f04cc1b2b3e9ef7a4921b27bf526d9f6050ab90f9267a1f9e5c66  colbert-small-v1/tokenizer.json
0b29c7bfc889e53b36d9dd3e686dd4300f6525110eaa98c76a5dafceb2029f53  colbert-small-v1/tokenizer_config.json
cc5aff32dc950b8b9c44ac3f3e7f42af74056abc7b18cfbb5e05054c26195526  gte-moderncolbert-v1/model.onnx
f47533385eb5335c47d20eac32321d1fb4b75ec1d07435184176962e5d3c4fd9  gte-moderncolbert-v1/config.json
23abe2a8f5640f8836c24cead7b76e77613b846824d7540151c6d90d7c2f4869  gte-moderncolbert-v1/tokenizer.json
c687151fe628695cfd10eae03bbb97c98613843cbf89b6d8a9c6050cf8ec28fb  gte-moderncolbert-v1/tokenizer_config.json
6edfb9d64c0d7e5cbaa53516e90280fe1f42ba5ea7923d005a5f9b6e082142cf  gte-moderncolbert-v1/special_tokens_map.json