xberg 1.0.4

High-performance document intelligence library for Rust. Extract text, metadata, and structured data from PDFs, Office documents, images, and 98 formats and 306 programming languages via tree-sitter code intelligence with async/sync APIs.
Documentation
# sha256 manifest for the xberg-io/embedding-models preset fleet (self-hosted, weights unmodified).
# Format: <sha256>  <repo-relative path>. Pins the exact bytes each preset resolves to.
7135149f7cffa1a573466c6e4d8423ed73b62fd2332c575bf738a0d033f70df7  all-MiniLM-L6-v2/config.json
afdb6f1a0e45b715d0bb9b11772f032c399babd23bfc31fed1c170afc848bdb1  all-MiniLM-L6-v2/model_quantized.onnx
b6d346be366a7d1d48332dbc9fdf3bf8960b5d879522b7799ddba59e76237ee3  all-MiniLM-L6-v2/special_tokens_map.json
da0e79933b9ed51798a3ae27893d3c5fa4a201126cef75586296df9b4d2c62a0  all-MiniLM-L6-v2/tokenizer.json
9261e7d79b44c8195c1cada2b453e55b00aeb81e907a6664974b4d7776172ab3  all-MiniLM-L6-v2/tokenizer_config.json
d83c21fa7366994560727112ef0a31d8a2ec1c280c2a3e66326fdb877f64c91e  bge-base-en-v1.5/config.json
9bc579acdba21c253c62a9bf866891355a63ffa3442b52c8a37d75b2ccb91848  bge-base-en-v1.5/model.onnx
b6d346be366a7d1d48332dbc9fdf3bf8960b5d879522b7799ddba59e76237ee3  bge-base-en-v1.5/special_tokens_map.json
d241a60d5e8f04cc1b2b3e9ef7a4921b27bf526d9f6050ab90f9267a1f9e5c66  bge-base-en-v1.5/tokenizer.json
9261e7d79b44c8195c1cada2b453e55b00aeb81e907a6664974b4d7776172ab3  bge-base-en-v1.5/tokenizer_config.json
7bd757258c7418221da95ff1853bae50ef5d1bee3e8c01a96611243a52aa7299  bge-large-en-v1.5/config.json
69ed3f810d3b6d13f70dff9ca89966f39c0a0e877fb88211be7bcc070df2a2ce  bge-large-en-v1.5/model.onnx
b6d346be366a7d1d48332dbc9fdf3bf8960b5d879522b7799ddba59e76237ee3  bge-large-en-v1.5/special_tokens_map.json
d241a60d5e8f04cc1b2b3e9ef7a4921b27bf526d9f6050ab90f9267a1f9e5c66  bge-large-en-v1.5/tokenizer.json
9261e7d79b44c8195c1cada2b453e55b00aeb81e907a6664974b4d7776172ab3  bge-large-en-v1.5/tokenizer_config.json
9dab198f24c8c0879e481cf7822005d5ecbceedbacb390ffafa594e28d31bac4  multilingual-e5-base/config.json
84a4d426f7e87a6bf5bf195f0bae2c4a7d15f675b23ca96f42fab8326d7a77aa  multilingual-e5-base/model.onnx
06e405a36dfe4b9604f484f6a1e619af1a7f7d09e34a8555eb0b77b66318067f  multilingual-e5-base/special_tokens_map.json
62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626  multilingual-e5-base/tokenizer.json
efb5c0d09722e5fe59a462cd2a9976ee216d55b037597d997cd3fe833216da15  multilingual-e5-base/tokenizer_config.json
8ba54dc3d35d7194f5178a4194b649f146753e02dabd22bdca5c5cbac15069ed  gte-modernbert-base/config.json
947f31df7effaeec4edb57c50e4ed7e0f2034d9336063f92615b92e3e0d24d78  gte-modernbert-base/model.onnx
ea97ecdbcc73713039d8d64dbb05e3689495c96657fbd9a18f5bed381be81049  gte-modernbert-base/special_tokens_map.json
6c8aaa9a542084f2457eab775d4eeb51f92a70c0fd9de28d5edb0ddec3c08d30  gte-modernbert-base/tokenizer.json
9654072f7c873161814043cf08cb5ed72f71d0b935abcd4e267935cb34352c21  gte-modernbert-base/tokenizer_config.json
ad1ea2341193d02dcb2452edadfa2b32bf6cced2b34cf8dc0b664e1ca8232b96  arctic-embed-m-v2.0/model.onnx
90e502378d93ea574242f86a0e4723535098e5f6b702c3eaeb72047458095a06  arctic-embed-m-v2.0/model.onnx.data
75b9d88e432355e8cd63d27dd67c06c1e6b71719afe26baf25d373a25ba03167  arctic-embed-m-v2.0/config.json
bc5c1151948923156f20bcafd54fd796705d693f8d7b56c83aec49d651f6d602  arctic-embed-m-v2.0/tokenizer.json
b1449792f701a91db4634a7f107191dab3a50b987a7d1a12bf501dd2f5aa0c13  arctic-embed-m-v2.0/tokenizer_config.json
8c785abebea9ae3257b61681b4e6fd8365ceafde980c21970d001e834cf10835  arctic-embed-m-v2.0/special_tokens_map.json
efe3c38bf8a1d81f37904a7f8c74ec28b8ea920da9511b42abcb6736953d246d  qwen3-embedding-0.6b/model.onnx
15d02a315e3b95296700c73d72a436e79facf4e17d919345bed730e98433bcb4  qwen3-embedding-0.6b/model.onnx.data
51dd3453f12fcaa966c67311f87c9724263a4fa825121306cbf24c108cb7407c  qwen3-embedding-0.6b/config.json
def76fb086971c7867b829c23a26261e38d9d74e02139253b38aeb9df8b4b50a  qwen3-embedding-0.6b/tokenizer.json
443bfa629eb16387a12edbf92a76f6a6f10b2af3b53d87ba1550adfcf45f7fa0  qwen3-embedding-0.6b/tokenizer_config.json
76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd  qwen3-embedding-0.6b/special_tokens_map.json
f65d0f325faadc1e121c319e2faa41170d3fa07d8c89abd48ca5358d9a223de2  potion-base-8m/model.safetensors
e67e803f624fb4d67dea1c730d06e1067e1b14d830e2c2202569e3ef0f70bb50  potion-base-8m/tokenizer.json
2a6ac0e9aaa356a68a5688070db78fc3a464fefe85d2f06a1905ce3718687553  potion-base-8m/config.json
6725995e3ab3039857ff5bd99178a7cdf42863abb04449e7bb31feb1f55fe567  potion-base-8m/tokenizer_config.json
a9e8fb6f99fb0b8803f0e6942fdf4d95d6645204620b67dc3310a1024bcbac59  potion-base-8m/special_tokens_map.json
1394523a67ddd404a825428018c0582a6998bcfa044ecbcbf1f4d71adb94c61c  potion-base-8m/vocab.txt