upstream-archive/fastembed
1
0
Fork 0
mirror of https://github.com/qdrant/fastembed.git synced 2026-07-25 20:21:10 -05:00
Code Issues Packages Projects Releases Wiki Activity
355 Commits 38 Branches 59 Tags
dynamic_quantization
Commit Graph

41 Commits

Author SHA1 Message Date
Anush
1e298a00b3 feat: Added gte-large, nomic-text 1.5, cleanup (#130) 2024-02-21 17:54:32 +05:30
Armaghan
406f432edc feat: Support sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 (#129) 
* feat: Support sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2

* test: Include sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2

* docs: supported models update
 2024-02-21 13:35:49 +05:30
Anush
98141cc8d3 feat: Added nomic-embed-text-v1 support + formatting changes + import fixes (#118) 
* feat: Added nomic-embed-text-v1 support

* chore: xenova/nomic-embed-text-v1 -> nomic-ai/nomic-embed-text-v1

---------

Co-authored-by: Nirant <NirantK@users.noreply.github.com>
 2024-02-19 14:17:33 +05:30
Nirant
81bab0cd1d Make 0.2.1 Release + Update docs (#116) 
* Update version from 0.2.0 (yanked) to 0.2.1

* Update text embedding to include prefix for passages and queries

* Update supported models to use the latest API

* * fix(text_embedding_base.py): remove unnecessary prefix from texts in embed method
* feat(text_embedding_base.py): update query_embed method to updated instruction for the v1.5 model

* Remove comparison, since the ranking is identical even with varying embedding

* Refactor text embedding query handling
 2024-02-08 09:06:00 +05:30
Nirant
973da354ae Fix query to align with Qdrant mixin usage (#115) 
* fix: query in text_embedding_base to work with both Iterable and str as users might supply both

* Fix Qdrant query to align with future usage

* * refactor(text_embedding_base.py): change query parameter type from str to Union[str, Iterable[str]] in query_embed method

* Update return type of query_embed method

* Update return type in TextEmbeddingBase
 2024-02-07 22:01:31 +05:30
Anush
96f7d83d33 feat: Support xenova/multilingual-e5-large, xenova/paraphrase-multili… (#103) 
* feat: Support xenova/multilingual-e5-large, xenova/paraphrase-multilingual-mpnet-base-v2

* chore: updated exclude_token_type_ids check

* docs: supported models update
 2024-02-02 15:16:35 +05:30
Anush
9b63427118 chore: pre-commit formatting (#91) 
* chore: formatting

* chore: formatting

* chore: remove other hooks

* Update poetry lock

---------

Co-authored-by: Nirant Kasliwal <nirant.bits@gmail.com>
 2024-01-16 15:06:54 +05:30
Nirant
55379539ef * chore(docs): update Getting Started.ipynb with progressbar + New Models 
* * feat(Supported_Models.ipynb): add support for BAAI/bge-small-zh-v1.5 model
* feat(Supported_Models.ipynb): add support for jinaai/jina-embeddings-v2-base-en model
* feat(Supported_Models.ip

* * chore(docs): update Getting Started.ipynb with progressbar
 2023-12-13 14:17:25 +05:30
NirantK
299042d592 * docs(examples): add explanation of Qdrant Client usage with FastEmbed library and Qdrant API 2023-10-30 23:01:26 +05:30
Nirant
f8f8316fea Merge pull request #38 from qdrant/explain_cossim 
* docs(examples): update FastEmbed_vs_HF_Comparison.ipynb
 2023-10-19 22:56:04 +05:30
NirantK
4999fa17b5 * docs(examples): update FastEmbed_vs_HF_Comparison.ipynb 
with cosine similarity values for BAAI/bge-small-en and BAAI/bge-small-en-v1.5 embeddings
 2023-10-19 22:49:25 +05:30
NirantK
ad297c4f13 * chore(Usage_With_Qdrant.ipynb): remove unnecessary outputs in code cells 2023-10-18 23:03:52 +05:30
NirantK
c1fdaf3303 * chore(Supported_Models.ipynb): update supported models table 
* feat(Supported_Models.ipynb): add size_in_GB column to supported models table
 2023-10-18 23:02:50 +05:30
NirantK
b61f8a48cc Update to v1.5 model 2023-10-18 20:49:31 +05:30
NirantK
d2bdfee4e0 * docs(examples): update comparison notebook with more accurate description of embeddings similarity 2023-10-10 17:56:25 +05:30
NirantK
ac4375516f Rename nbs; add Cosine similarity check 2023-10-10 17:55:37 +05:30
NirantK
bc402694bd Update code to handle Generator 2023-10-05 19:17:18 +05:30
NirantK
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
 2023-09-27 17:53:05 +05:30
NirantK
dd2a9e9bcc * docs(Supported_Models.ipynb): update model descriptions 2023-09-27 17:41:39 +05:30
NirantK
71289926c0 * feat(Supported_Models.ipynb): add example notebook for supported models 2023-09-27 17:40:40 +05:30
NirantK
547130a4c3 Move throughput comparison to docs 2023-09-25 17:40:38 +05:30
NirantK
b72cae1e9b * chore(docs): rename HF_vs_FastEmbed.ipynb to 02_HF_vs_FastEmbed.ipynb 2023-09-18 08:46:13 +05:30
NirantK
ecfaba9e60 Fix yield/iterator issue 2023-09-18 08:42:34 +05:30
NirantK
5afa103d45 Remove attention pooling 2023-09-18 07:35:52 +05:30
NirantK
9c5d32f271 move nbs 2023-09-07 15:25:32 +05:30
NirantK
1292ded017 Add Qdrant Usage back to the example 2023-09-07 15:19:46 +05:30
NirantK
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
 2023-08-25 13:41:32 +05:30
NirantK
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
*
*
 2023-08-25 12:59:22 +05:30
NirantK
1bd639b817 * chore(docs): rename 02_Usage_with_Qdrant.ipynb to FastEmbed_Usage_with_Qdrant.ipynb in the experimental folder 2023-08-25 12:56:38 +05:30
NirantK
ac0f3315ed Cleaner notebook 2023-08-25 01:06:24 +05:30
NirantK
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
 2023-08-25 00:57:39 +05:30
NirantK
2f0e9a8507 * feat(examples): add 1M Embedding Creation notebook 2023-08-25 00:54:23 +05:30
NirantK
7479640a7b * (feat) HFvsFastEmbed.ipynb: Add new nb example 2023-08-25 00:54:18 +05:30
NirantK
38d449ba71 * chore(docs): fix formatting and remove extra newlines in Retrieval with FastEmbed.ipynb and Usage with Qdrant.ipynb examples 2023-08-25 00:38:54 +05:30
NirantK
4a25dd4240 * chore(Usage with Qdrant.ipynb): update notebook title and add note about experimental status 
* chore(Usage with Qdrant.ipynb): update installation instructions for fastembed and qdrant-client
 2023-08-23 18:31:48 +05:30
NirantK
bb87a61f92 * feat(Usage with Qdrant.ipynb): add output of document ids after adding documents to collection 
* docs(Usage with Qdrant.ipynb): add explanation for document ids
 2023-08-23 13:12:50 +05:30
NirantK
52747aa64e * feat(Usage with Qdrant.ipynb): add Usage with Qdrant notebook example 2023-08-23 12:52:38 +05:30
NirantK
43e8f9678f * docs(examples/Retrieval with FastEmbed.ipynb): update tip message to include headings for query and passage embeddings 2023-08-23 12:52:22 +05:30
NirantK
cf0e2023f5 * docs(examples): rename 01_Retrieval.ipynb to Retrieval with FastEmbed.ipynb 2023-08-23 11:21:44 +05:30
NirantK
9fc1f1447d * fix(docs): update example notebook for retrieval with FastEmbed 2023-08-23 11:19:19 +05:30
NirantK
ba5ada631a * feat(docs): add example notebook for retrieval with FastEmbed and Qdrant 2023-08-23 11:18:05 +05:30