v0.5.0

Features 📖

#403 - Drop Python 3.8 support by @joein
#404 - Add Python 3.13 support by @joein
#406 - Improve models cache progress bar by @hh-space-invader
#422 - Add multi-GPU example by @hh-space-invader
#425 - Provide user warning when specifying providers and CUDA by @hh-space-invader

---

Models 🧠

#405 - Support jina embeddings v2 models by @hh-space-invader
#408 - Add jina clip v1 model by @hh-space-invader
#415 - Added support for the thenlper/gte-base model by @hh-space-invader
#419 - Introduced parallel processing and pair-wise API for cross-encoders by @I8dNLo
#429 - All models now support Hugging Face (hf) compatibility by @I8dNLo

---

Fixes 🐛

#413 - Fix ColBERT model shape mismatch by @hh-space-invader

v0.4.2

Change Log

Features 📖

• #380 - add NOTICE file to support models with restrictive licenses by @hh-space-invader @joein
• #362 - unlock numpy v2 by @amietn
• #375 - add jina rerankers by @hh-space-invader

Models 🧠

• #378 - jinaai/jina-colbert-v2 by @hh-space-invader
• #375 - jinaai/jina-reranker-v1-tiny-en, jinaai/jina-reranker-v1-turbo-en, jinaai/jina-reranker-v2-base-multilingual by @hh-space-invader

Fixes 🐛

• #337 - temporarily restrict onnxruntime to <1.20 due to recent problems by @hh-space-invader

v0.4.1

Change Log

Features 📢

• #366 - replace pystemmer with py-rust-stemmers by @I8dNLo

v0.4.0

Change Log

Features 📢

• #355 - add rerankers support by @celinehoang177 @joein @I8dNLo
• #358 - add multi-gpu support by @joein @generall @hh-space-invader
• #364 - add license info to models descriptions by @hh-space-invader

Models 🧠

• #355 - rerankers ms-marco-MiniLM-L-6-v2, ms-marco-MiniLM-L-12-v2, bge-reranker-base by @celinehoang177

Fixes 🐛

• #337 - lowercasing words in bm25 by @n0x29a
• #339 - fix bm25 preprocessing by @I8dNLo
• #340 - fix hanging of the main process when child processes got unexpectedly killed by @hh-space-invader

Thanks to everyone who contributed to the current release
@celinehoang177 @I8dNLo @generall @hh-space-invader @n0x29a @joein

v0.3.5

Change Log

Features 📢

• #315 - accept PIL images as input in image models by @I8dNLo

Models 🧠

• #301 - jinaai/jina-embeddings-v2-base-code by @Anush008
• #318 - added a set of new languages to BM25 @I8dNLo
• #330 - answerdotai/answerai-colbert-small-v1 by @I8dNLo

Fixes 🐛

• #319 - fix cutting model_max_length down in the case of context windows larger than 512 by @I8dNLo

Thanks to everyone who contributed to the current release
@I8dNLo @Anush008 @mrscoopers

v0.3.4

0.3.4

Features 🪄

• #291 - Add Unicom models by @I8dNLo
• #293 - Add retry logic for model downloading by @joein

Bug fixes 🦟

• #280 - Fix pooling for nomic models by @I8dNLo

v0.3.1

What's Changed

Features

• Add support for jinaai/jina-embeddings-v2-base-de by @deichrenner in #270
• Add BM25 by @joein in #274

Fixes

• Fix None cache directory in parallel mode by @joein in #277
• Fix hybrid search example for pydantic v1 by @joein in #263
• Fix MiniLM by @I8dNLo in #275
• Fix parameter propagation in parallel mode, fix bm42 parallel by @joein in #274
• Pin Numpy <2 by @Anush008 in #278

Docs

• Replace Data Source by @NirantK in #206
• Add examples with supported type of models into readme by @generall in #271

New Contributors

• @deichrenner made their first contribution in #270. Thank you.

Full Changelog: v0.3.0...v0.3.1

v0.3.0

Changelog

Features 🪄

• #219 support for ImageEmbedding by @joein
• #219 CLIP image and text embeddings by @joein
• #246 Resnet50 by @I8dNLo
• #248 support for late interaction embeddings (ColBERT) by @joein
• #235 Bm42 (sparse embeddings with attention) by @generall

---

Fixes 🪛

• #250 #244 unlock huggingface-hub, tokenizers and ruff dependencies, allow versions <1.0 by @joein

---

Full Changelog: v0.2.7...v0.3.0

v0.2.7

Changelog

Features 🪄

• #214 Add onnx providers setter by @joein
• #224 add gpu support by @joein
• #230 update tokenizers by @joein
• #201 speed up model downloading by fine-graining file selection by @Anush008 @joein

---

Fixes 🪛

• #179 fix model cache invalidation if gcs downloading was interrupted by @joein
• #223 allow using fastembed behind a firewall utilising cached on disk models by @Thiru-GVT @joein

---

New models 🏆

• #207 Snowlake models by @Anush008
• #201 nomic-ai/nomic-embed-text-v1.5-Q by @Anush008

---

Various documentation, workflow and notebooks improvements by @NirantK @generall @arunppsg

---

Full Changelog: v0.2.6...v0.2.7

v0.2.6

What's Changed

• feat: support mixedbread-ai/mxbai-embed-large-v1 by @yuvraj-wale in #158
• fix: case-insensitive check model_management.py by @Anush008 in #160
• Add misspelled version of SPLADE++ model for English by @NirantK in #161
• Hybrid Search Tutorial by @NirantK in #165
• fix: unify existing patterns, remove redundant by @joein in #168
• Fix spladepp parallelism by @joein in #169
• Update ruff by @joein in #172
• new: simplify imports by @joein in #171
• fix: fix model sizes in supported models lists by @joein in #167
• Update size_in_GB for BAAI/bge-small-en-v1.5 model by @NirantK in #176
• refactoring: update imports in notebooks by @joein in #173

New Contributors

• @yuvraj-wale made their first contribution in #158
• @joein made their first contribution in #168

Full Changelog: v0.2.5...v0.2.6