Commit Graph

Select branches

Hide Pull Requests

QModels

add-onnx-demo

bge-m3-embed

bge-m3-sparse

clip-export

coderabbitai/docstrings/1qjwpXImqUbctAAqCo87f6k5J01PCjoyTKpxSYoTq

cuda-warnings

debug-gpu-ci

dependabot/pip/pip-75f0befae6

deprecate-bm25

dev

dev-workflow

draft_tmp

dynamic_quantization

e5-small-v2

enable-io-binding

feature/image-mask-support

fix-gpu-fragmentation

fix-tar-vulnerability

fix-unsafe-max-context

gh-pages

gpu

gpu-runtime-debug

main

mean_pooling

mypy_pyright

only-ubuntu-gpu-workflow

onnx-pipeline

opened-images-support

remove-pystemmer

removed-gcs

speedup-parallel-processor

support-custom-model-idea

support_custom_model

text-splitter

token-embeddings

update-colmodernvbert

#1

#100

#101

#102

#103

#105

#108

#109

#111

#112

#113

#115

#116

#118

#119

#120

#121

#124

#125

#128

#129

#13

#130

#134

#135

#138

#139

#143

#144

#146

#147

#148

#149

#15

#150

#151

#152

#153

#154

#155

#156

#157

#158

#160

#161

#162

#163

#164

#165

#167

#168

#169

#171

#172

#173

#175

#176

#177

#179

#18

#180

#181

#182

#183

#186

#188

#189

#190

#193

#194

#195

#196

#197

#198

#199

#2

#200

#201

#202

#205

#206

#207

#209

#211

#213

#214

#215

#219

#220

#221

#223

#224

#225

#226

#227

#228

#23

#230

#231

#232

#234

#235

#237

#239

#24

#244

#245

#246

#248

#25

#250

#253

#256

#257

#258

#26

#260

#262

#263

#265

#27

#270

#271

#274

#275

#277

#278

#28

#280

#285

#286

#287

#290

#291

#293

#295

#298

#299

#3

#300

#301

#302

#303

#304

#304

#306

#307

#309

#31

#311

#315

#317

#318

#319

#32

#324

#330

#331

#333

#336

#337

#339

#34

#340

#341

#344

#350

#352

#355

#358

#361

#362

#363

#364

#365

#366

#367

#370

#371

#378

#379

#38

#380

#381

#386

#387

#389

#390

#391

#392

#393

#394

#397

#398

#399

#400

#403

#404

#405

#406

#408

#413

#415

#416

#419

#420

#421

#422

#423

#423

#425

#427

#428

#429

#430

#431

#436

#438

#439

#44

#440

#441

#443

#445

#446

#448

#449

#450

#451

#453

#454

#455

#457

#458

#459

#460

#461

#463

#464

#468

#469

#47

#470

#471

#472

#473

#474

#475

#478

#479

#48

#480

#481

#482

#484

#486

#487

#488

#489

#490

#491

#492

#493

#493

#496

#499

#500

#500

#503

#504

#506

#513

#514

#516

#517

#518

#518

#521

#522

#523

#524

#525

#525

#533

#534

#537

#54

#541

#542

#543

#543

#545

#547

#55

#550

#551

#552

#552

#556

#557

#561

#561

#562

#562

#563

#563

#564

#566

#567

#57

#573

#574

#577

#578

#580

#582

#583

#585

#586

#588

#589

#590

#591

#592

#593

#595

#595

#598

#598

#599

#60

#600

#601

#602

#602

#605

#609

#61

#611

#612

#614

#617

#622

#622

#623

#624

#625

#629

#631

#631

#633

#634

#636

#637

#637

#638

#638

#639

#639

#640

#642

#643

#643

#644

#645

#646

#647

#65

#651

#652

#653

#653

#655

#656

#657

#658

#659

#66

#660

#661

#662

#663

#664

#665

#666

#667

#668

#67

#670

#671

#672

#673

#674

#676

#677

#677

#678

#68

#680

#681

#682

#683

#684

#684

#687

#690

#691

#691

#692

#693

#694

#695

#696

#697

#698

#699

#7

#700

#702

#704

#705

#707

#708

#708

#709

#709

#71

#710

#711

#713

#714

#715

#716

#717

#718

#720

#721

#722

#723

#725

#726

#727

#728

#729

#730

#731

#732

#733

#734

#735

#736

#737

#738

#739

#740

#741

#743

#744

#744

#746

#747

#747

#748

#75

#750

#751

#753

#754

#755

#755

#756

#756

#757

#758

#758

#759

#759

#76

#760

#760

#761

#761

#762

#762

#763

#763

#764

#764

#765

#765

#77

#8

#80

#90

#91

#93

#94

#96

#98

#99

0.0.3a1

0.0.5

0.0.5a1

0.0.5a2

0.1.0

push

v0.1.0

v0.1.1

v0.1.2

v0.1.3

v0.2.0

v0.2.1

v0.2.2

v0.2.3

v0.2.4

v0.2.5

v0.2.6

v0.2.7

v0.2.7-gpu

v0.3.0

v0.3.0-gpu

v0.3.1

v0.3.1-gpu

v0.3.2

v0.3.2-gpu

v0.3.3

v0.3.3-gpu

v0.3.4

v0.3.4-gpu

v0.3.5

v0.3.5-gpu

v0.3.6

v0.3.6-gpu

v0.4.0

v0.4.0-gpu

v0.4.1

v0.4.1-gpu

v0.4.2

v0.4.2-gpu

v0.5.0

v0.5.0-gpu

v0.5.1

v0.5.1-gpu

v0.6.0

v0.6.0-gpu

v0.6.1

v0.6.1-gpu

v0.7.0

v0.7.0-gpu

v0.7.1

v0.7.1-gpu

v0.7.2

v0.7.2-gpu

v0.7.3

v0.7.3-gpu

v0.7.4

v0.7.4-gpu

v0.8.0

v0.8.0-gpu

v0.8.1

v0.8.1-gpu

Mono Color

• 219185e677 pass embed arguments in passage_embed method generall 2023-10-16 14:57:51 +02:00
• f28087c71a * fix(embedding.py): change dim value from 384 to 512 for the "BAAI/bge-small-zh-v1.5" model * fix(test_onnx_embeddings.py): add canonical vector values for the "BAAI/bge-small-zh-v1.5" NirantK 2023-10-16 18:23:02 +05:30
• 0203b0ae9e * feat(embedding.py): add support for BAAI/bge-small-zh-v1.5 Chinese model NirantK 2023-10-16 18:20:56 +05:30
• f02d713e93 Merge pull request #24 from qdrant/streaming-inference v0.1.0 0.1.0 Andrey Vasnetsov 2023-10-16 14:31:40 +02:00
• c901da0820 Merge pull request #26 from qdrant/add_model_size Andrey Vasnetsov 2023-10-16 14:26:13 +02:00
• f79de09ff7 Merge branch 'streaming-inference' into add_model_size Nirant 2023-10-16 17:54:33 +05:30
• 7799180b18 * fix(embedding.py): update return type of list_supported_models method to include Union[int, float] for values in the dictionary NirantK 2023-10-16 17:52:43 +05:30
• e24ea64e21 * test(test_onnx_embeddings.py): skip specific model if size_in_GB is greater than 1 NirantK 2023-10-16 17:52:35 +05:30
• 299c76c099 * feat(embedding.py): add size_in_GB information for each model NirantK 2023-10-16 17:50:28 +05:30
• 35ec40b3a3 review fixes generall 2023-10-16 14:19:58 +02:00
• b35cb28eeb * refactor(embedding.py): reorder import statements in alphabetical order * feat(embedding.py): add optional 'threads' parameter to DefaultEmbedding constructor NirantK 2023-10-16 17:39:21 +05:30
• c953a083cc Merge branch 'main' into streaming-inference Nirant 2023-10-16 17:33:36 +05:30
• 66c5cf76c6 Merge pull request #25 from qdrant/support-v1.5-models Nirant 2023-10-16 17:29:33 +05:30
• 9e5d37846c * feat(embedding.py): add support for BAAI/bge-small-en-v1.5 and BAAI/bge-base-en-v1.5 models * feat(embedding.py): change default model to v1.5 NirantK 2023-10-16 17:08:58 +05:30
• c719fc696d disable large models on non-ubuntu CI generall 2023-10-16 13:27:28 +02:00
• 24dc24b02d implement data-parallel inference and up version generall 2023-10-16 13:07:07 +02:00
• c408b7e13e * chore(main.html): add utm parameters to Qdrant Cloud link NirantK 2023-10-10 19:01:49 +05:30
• d2bdfee4e0 * docs(examples): update comparison notebook with more accurate description of embeddings similarity NirantK 2023-10-10 17:56:25 +05:30
• ac4375516f Rename nbs; add Cosine similarity check NirantK 2023-10-10 17:55:37 +05:30
• ca6f9d629a Add skeleton NirantK 2023-10-05 19:20:01 +05:30
• e0e7e5721e Add generator note to the comment in Python block NirantK 2023-10-05 19:17:32 +05:30
• bc402694bd Update code to handle Generator NirantK 2023-10-05 19:17:18 +05:30
• 3139fb7275 Merge pull request #15 from qdrant/v0.0.5 0.0.5 Nirant 2023-10-05 16:46:26 +05:30
• 3fbc878ddd bump version 0.0.5 generall 2023-10-04 10:20:58 +02:00
• fa8684f7ef Merge pull request #13 from qdrant/0.5-suggestions Andrey Vasnetsov 2023-10-04 10:04:06 +02:00
• 288cee1d16 upd dependencies generall 2023-10-03 21:35:46 +02:00
• 8c6d4d2b52 remove optimum + more test + fix batching embed + ci on other machines generall 2023-10-03 21:19:58 +02:00
• 050d80ab51 * chore(docs): update index.md with FastEmbed library information and usage examples * feat(docs): add installation instructions for FastEmbed with Qdrant Client 0.0.5a2 NirantK 2023-09-28 10:52:38 +05:30
• 49c2b3e7a9 * chore(docs): update installation command for fastembed in Getting Started.ipynb * fix(docs): remove unnecessary casting of generator to list in code cell NirantK 2023-09-28 10:43:14 +05:30
• 5e2ced87f5 * chore(README.md): update links and fix formatting in README.md NirantK 2023-09-27 18:00:19 +05:30
• ba1a12a0f0 * docs(README.md): update description of FastEmbed library * fix(README.md): fix typo in the description of FastEmbed library NirantK 2023-09-27 17:59:21 +05:30
• 983964c432 * docs(README.md): update links and descriptions in the README file * feat(README.md): add usage example with Qdrant client NirantK 2023-09-27 17:57:51 +05:30
• 4949158eff * chore(Usage_With_Qdrant.ipynb): update notebook title and remove experimental note * docs(Usage_With_Qdrant.ipynb): add support for qdrant-client[fastembed] installation NirantK 2023-09-27 17:53:05 +05:30
• c68c1029a4 * docs(README.md): add link to supported models dosc NirantK 2023-09-27 17:44:01 +05:30
• dd2a9e9bcc * docs(Supported_Models.ipynb): update model descriptions NirantK 2023-09-27 17:41:39 +05:30
• 71289926c0 * feat(Supported_Models.ipynb): add example notebook for supported models NirantK 2023-09-27 17:40:40 +05:30
• 85a9cc08ec * chore(embedding.py): add list_supported_models method to Embedding class NirantK 2023-09-27 17:39:42 +05:30
• 589105c84c * fix(embedding.py): handle single string input in embed_documents method NirantK 2023-09-27 17:27:56 +05:30
• ac6b8c9402 * chore(pyproject.toml): add onnx dependency to the project NirantK 2023-09-27 13:26:27 +05:30
• b28ff3f8d6 * chore(pyproject.toml): update version from 0.0.4 to 0.0.5a1 * chore(pyproject.toml): remove onnxruntime-silicon dependency for macOS NirantK 2023-09-26 21:25:59 +05:30
• 7fdd48c3e2 * fix(embedding.py): update NotImplementedError message to provide more specific information * fix(embedding.py): update ValueError message to provide more specific reasons for the error push 0.0.5a1 NirantK 2023-09-25 17:40:55 +05:30
• 547130a4c3 Move throughput comparison to docs NirantK 2023-09-25 17:40:38 +05:30
• f51afec563 * chore(README.md): remove unnecessary section heading "Under the hood" * docs(README.md): update bullet point description in "Why fast?" section * docs(README.md): update bullet point description in "Why light?" section * docs(README.md): update bullet point description in NirantK 2023-09-25 17:32:04 +05:30
• 250ccf98aa * docs(README.md): add section on similar work and reference to Ilyas M.'s tweet about using FlagEmbeddings with Optimum over CUDA NirantK 2023-09-25 17:30:56 +05:30
• 4da2be9c44 Remove the else, it's cleaner NirantK 2023-09-25 17:15:44 +05:30
• 206a633eb1 Fix for # https://github.com/pytorch/pytorch/issues/100974 NirantK 2023-09-25 17:12:03 +05:30
• c0787c0aeb * fix(embedding.py): replace torch.nn.functional.normalize with custom normalize function NirantK 2023-09-25 16:59:37 +05:30
• 5dfdddbdb6 Another attempt at fixing versions NirantK 2023-09-25 16:53:14 +05:30
• 4d6d27cffb * test(test_onnx_embeddings.py): remove unnecessary list conversion in embeddings assignment NirantK 2023-09-25 16:50:52 +05:30
• 54a88d0028 update lock NirantK 2023-09-25 16:48:23 +05:30
• 6810141e87 * fix(embedding.py): fix model_name splitting to correctly extract the model name * fix(embedding.py): handle PermissionError when downloading fast_model_name.tar.gz and try simple_model_name.tar.gz as a fallback * fix(embedding.py): raise ValueError if neither fast_model_name.tar.gz nor simple are valid NirantK 2023-09-25 16:45:39 +05:30
• 464b12ab15 * chore(pyproject.toml): update optimum dependency version to be greater than 1.12.0 NirantK 2023-09-25 16:14:24 +05:30
• 633fbde726 * fix(embedding.py): rename file model_optimized.onnx to model.onnx if it exists * fix(embedding.py): revert back to the default model to avoid confusion NirantK 2023-09-25 16:05:22 +05:30
• 3cf17b8707 Rename nbs to fooling_around NirantK 2023-09-25 15:56:41 +05:30
• e1c1792532 * refactor(embedding.py): remove unused imports and variables NirantK 2023-09-25 15:56:25 +05:30
• 24be1d946f update the default embedding model NirantK 2023-09-25 15:55:27 +05:30
• 3149694c04 Utility script version of the notebook NirantK 2023-09-25 15:33:44 +05:30
• f007b19272 Add optimum as a dependency NirantK 2023-09-25 15:33:28 +05:30
• 9c3fd66adf Replace ONNXRuntime with Optimum Usage NirantK 2023-09-25 15:33:18 +05:30
• eaafd59277 wip NirantK 2023-09-18 22:29:39 +05:30
• 34f9982af3 add benchmarking NirantK 2023-09-18 18:32:50 +05:30
• 0ab82da4aa * chore(.gitignore): add qdrant_storage/ directory to the gitignore file NirantK 2023-09-18 17:24:31 +05:30
• 6f284f6466 * feat(docs): update execution counts in Binary Quantization from Scratch.ipynb * fix(docs): fix typo in Binary Quantization from Scratch.ipynb * feat(docs): add outputs to code cells in Binary Quantization from Scratch.ipynb NirantK 2023-09-18 08:47:28 +05:30
• ac989e249a Add BQ with Qdrant draft NirantK 2023-09-18 08:47:11 +05:30
• 5906ef63d6 * chore(.gitignore): add ignore rule for experimental .bin files in docs/experimental directory NirantK 2023-09-18 08:46:58 +05:30
• b72cae1e9b * chore(docs): rename HF_vs_FastEmbed.ipynb to 02_HF_vs_FastEmbed.ipynb NirantK 2023-09-18 08:46:13 +05:30
• ecfaba9e60 Fix yield/iterator issue NirantK 2023-09-18 08:42:34 +05:30
• fc0341333e * chore(docs): remove experimental notebook for 1M Embedding Creation NirantK 2023-09-18 08:41:58 +05:30
• 3023996074 * fix(embedding.py): add support for ONNX runtime session options NirantK 2023-09-18 08:30:44 +05:30
• 296346a1a9 * chore(embedding.py): refactor FlagEmbedding class to use separate method for ONNX embedding * feat(embedding.py): add support for ONNXProviders.Metal in FlagEmbedding constructor NirantK 2023-09-18 08:08:20 +05:30
• a335c8898f Remove attention pooling NirantK 2023-09-18 07:45:12 +05:30
• 5afa103d45 Remove attention pooling NirantK 2023-09-18 07:35:52 +05:30
• e1e5975193 * docs(experimental): rename Binary Quantization.ipynb to Binary Quantization from Scratch.ipynb NirantK 2023-09-15 15:33:28 +05:30
• a7a599d932 * chore(main.html): update Discord server link and name to Qdrant Discord server NirantK 2023-09-13 20:53:21 +05:30
• 9c5d32f271 move nbs NirantK 2023-09-07 15:25:32 +05:30
• defbe0cce2 Merge pull request #8 from qdrant/add_qdrant_client_example Nirant 2023-09-07 15:22:43 +05:30
• 1292ded017 Add Qdrant Usage back to the example NirantK 2023-09-07 15:19:46 +05:30
• 9cd13a890e Merge pull request #7 from Rishav-hub/patch-1 Nirant 2023-09-07 15:14:01 +05:30
• bcf3cee8b8 Updated the hyperlink for "Retrieval with FastEmbed" Rishav Dash 2023-09-03 13:37:14 +05:30
• 728ac49a91 * docs(experimental): update headings in Binary Quantization.ipyn, add emoji everywhere NirantK 2023-08-25 14:11:03 +05:30
• 3d1b80e9de * docs(experimental): fix typo in Binary Quantization.ipynb * chore(experimental): update description of binary transformation step NirantK 2023-08-25 14:06:16 +05:30
• 86e3b12e84 Improved readability NirantK 2023-08-25 14:05:21 +05:30
• e62ed5edb2 * chore(docs): rename "Binary Quantisation.ipynb" to "Binary Quantization.ipynb" * docs(experimental/Binary Quantization.ipynb): update markdown headings * docs(experimental/Binary Quantization.ipynb): update markdown heading for loading data NirantK 2023-08-25 13:58:45 +05:30
• ee87685fa5 * docs(experimental): add table with sampling rate, limit, and accuracy for binary quantisation NirantK 2023-08-25 13:54:36 +05:30
• 750c9b340e * chore(Binary Quantisation.ipynb): update execution counts to null * refactor(Binary Quantisation.ipynb): remove unnecessary outputs NirantK 2023-08-25 13:54:31 +05:30
• 5a16ce8c63 * chore(docs): rename notebook files * - Rename '03_HF_vs_FastEmbed.ipynb' to 'HF_vs_FastEmbed.ipynb' * - Rename '01_Retrieval_with_FastEmbed.ipynb' to 'Retrieval_with_FastEmbed NirantK 2023-08-25 13:41:32 +05:30
• 5f229b2bc3 Binary Quantisation NirantK 2023-08-25 13:40:23 +05:30
• 743a095a93 * chore(docs): update HF_vs_FastEmbed.ipynb and 04_1M_Embedding_Creation.ipynb * * HF_vs_FastEmbed.ipynb: * - Add code to calculate embeddings using mean pooling with attention weighting * - Fix variable name error in line 4 * * NirantK 2023-08-25 12:59:22 +05:30
• 1bd639b817 * chore(docs): rename 02_Usage_with_Qdrant.ipynb to FastEmbed_Usage_with_Qdrant.ipynb in the experimental folder NirantK 2023-08-25 12:56:38 +05:30
• 399d11eb8a * chore(.gitignore): add rule to ignore experimental .parquet files in docs/experimental directory NirantK 2023-08-25 12:56:25 +05:30
• ac0f3315ed Cleaner notebook NirantK 2023-08-25 01:06:24 +05:30
• df2152ef52 * docs(mkdocs.yml): add information about the original creator in the copyright section NirantK 2023-08-25 00:59:55 +05:30
• 135a4524ac * refactor(docs/examples): rename files for better organization and numbering * rename(docs/examples): Rename 'Retrieval with FastEmbed.ipynb' to '01_Retrieval_with_FastEmbed.ipynb' * rename(docs/examples): Rename 'Usage with Qdrant.ipynb NirantK 2023-08-25 00:57:39 +05:30
• 9e0d3c5e3a * chore(01_ONNX_Port.ipynb): fix formatting and remove unnecessary lines NirantK 2023-08-25 00:54:47 +05:30
• 2f0e9a8507 * feat(examples): add 1M Embedding Creation notebook NirantK 2023-08-25 00:54:23 +05:30
• 7479640a7b * (feat) HFvsFastEmbed.ipynb: Add new nb example NirantK 2023-08-25 00:54:18 +05:30
• 38d449ba71 * chore(docs): fix formatting and remove extra newlines in Retrieval with FastEmbed.ipynb and Usage with Qdrant.ipynb examples NirantK 2023-08-25 00:38:54 +05:30
• 64bd1d2ff8 * chore(docs): fix formatting in Getting Started.ipynb * refactor(docs): improve code readability in Getting Started.ipynb NirantK 2023-08-25 00:38:36 +05:30
• 30ecdd838f * chore(embedding.py): fix indentation and remove unnecessary comments NirantK 2023-08-25 00:37:54 +05:30
• 03b23af0a0 * refactor(test_onnx_embeddings.py): rename test_onnx_embeddigns.py to test_onnx_embeddings.py * chore(test_onnx_embeddings.py): remove unnecessary line breaks and whitespace * test(test_onnx_inference): add test case for onnx inference NirantK 2023-08-25 00:37:31 +05:30