Commit Graph

22 Commits

Author SHA1 Message Date
George
e11f66bb55 refactoring: update imports in notebooks (#173)
* new: simplify imports

* refactoring: update import

* refactoring: update imports in notebooks

* fix: fix notebook output

* Re-run notebook with revised imports

---------

Co-authored-by: Nirant Kasliwal <nirant.bits@gmail.com>
2024-04-01 17:02:13 +05:30
Nirant
d817da2e01 Add Splade v1 (#144)
* Add SPLADE v1

* WIP SPLADE Export errors

* add ONNX model to HF hub and use that

* Update sentences in Converting_SPLADE_to_ONNX.ipynb

* Remove unnecessary files and directories

* Rename var in TextEmbedding class to use EMBEDDING_MODEL_TYPE

* Add SPLADE to list of text embeddings

* Add SPLADE model support for text embedding

* Fix deprecation warning in embedding.py

* Add test for batch embedding with sparse embeddings

* Refactor import statement in test_sparse_embeddings.py

* Rename nbs

* Update vocab size in SPLADE model

* Fix canonical vector lookup in test_text_onnx_embeddings.py

* review refactoring

* restore list_supported_models in OnnxTextEmbedding

* Remove unused method _preprocess_onnx_input() in SpladePP class

* Update SPLADE_PP_en_v1 source in splade_pp.py

* Refactor onnx_model.py to change base model behavior

* extend tests to sparse values as well as indicies

* chore: pre-commit hooks

---------

Co-authored-by: generall <andrey@vasnetsov.com>
Co-authored-by: Anush008 <anushshetty90@gmail.com>
2024-03-13 18:04:44 +05:30
Nirant
9ffde58df6 Getting Started Improvements (#138)
* Update FastEmbed README.md

* Rewrite GettingStarted to use TextEmbedding instead of DefaultEmbedding

* Improve grammar

* Update Getting Started.ipynb with model information and document format
2024-03-07 17:01:11 +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
a14aab8ef4 * refactor(Getting Started.ipynb): simplify code for initializing DefaultEmbedding class 2023-10-18 20:48:51 +05:30
NirantK
49c2b3e7a9 * chore(docs): update installation command for fastembed in Getting Started.ipynb
* fix(docs): remove unnecessary casting of generator to list in code cell
2023-09-28 10:43:14 +05:30
NirantK
64bd1d2ff8 * chore(docs): fix formatting in Getting Started.ipynb
* refactor(docs): improve code readability in Getting Started.ipynb
2023-08-25 00:38:36 +05:30
NirantK
bd0fd1f7e9 * chore(docs): update Getting Started.ipynb
* - Change section title from "What is happening under the hood?" to "Let's think step by step"
* - Add a new subsection titled "Setup"
* - Update the description in the code block from "FlagEmbedding" to
2023-08-24 17:05:46 +05:30
NirantK
32f204cc7b Remove outputs 2023-08-24 16:50:17 +05:30
NirantK
2a56e17f1e * chore(docs): update Getting Started.ipynb
* - Update execution count for code cells
* - Add output for code cells
* - Update package installation command
* - Update import statement for embedding class
* - Update model name in embedding initialization
* - Remove unnecessary tip section
2023-08-24 16:49:57 +05:30
NirantK
eb2317f425 * chore(docs): update comments in Getting Started.ipynb
* fix(embedding.py): update method names in FlagEmbedding and OpenAIEmbedding
2023-08-23 09:51:38 +05:30
NirantK
2017fdc22a * fix(docs): change method name from encode to embed in DefaultEmbedding class
* fix(README.md): change method name from encode to embed in Embedding class
* fix(docs/Getting Started.ipynb): change method name from encode to embed in Embedding class
2023-08-23 09:49:48 +05:30
NirantK
13f5ae8b56 * docs(Getting Started.ipynb): update code comments and add a tip for initializing the DefaultEmbedding class
* docs(Getting Started.ipynb): update code comments to initialize the FlagEmbedding class
2023-08-22 21:14:33 +05:30
NirantK
b0f8a33a4f * docs(Getting Started.ipynb): add instructions for initializing DefaultEmbedding class without parameters 2023-08-22 21:02:25 +05:30
NirantK
38fc2940b8 * docs(Getting Started.ipynb): fix formatting and punctuation in the document list section 2023-08-22 21:02:17 +05:30
NirantK
22a8260c1a * docs(Getting Started.ipynb): update installation instructions and quick start guide
* docs(Getting Started.ipynb): update section headings and explanations
* docs(Getting Started.ipynb): update section heading and explanation
2023-08-22 20:53:22 +05:30
NirantK
0e039e503c * chore(docs): update example list of documents to encode in Getting Started.ipynb
* - Change the first document from "query: Hello, World!" to "passage: Hello, World!"
* - Add a new document "query: Hello, World!" as a separate embedding
2023-08-22 15:26:22 +05:30
NirantK
b1449eddaa * docs(Getting Started.ipynb): update title to include emoji and change "Getting Started" to " Getting Started"
* docs(index.md): update title to include emoji and update description to include "retrieval augmented generation" and mention support for
2023-08-22 15:02:46 +05:30
NirantK
e9efa037f3 * docs(Getting Started.ipynb): remove unnecessary code execution outputs 2023-08-22 11:15:33 +05:30
NirantK
479aee5f32 * docs(Getting Started.ipynb): update documentation for preparing documents
* - Add information about the format of the list of documents
* - Specify that documents must be strings
* - Provide instructions for working with queries and passages in retrieval tasks
2023-08-22 11:12:14 +05:30
NirantK
7a23b15c0b * feat(Getting Started.ipynb): add guide 2023-08-22 11:10:53 +05:30
NirantK
a9542a8d8c * docs(Usage.ipynb): rename file to Getting Started.ipynb
* feat(Getting Started.ipynb): add introductory markdown cell with instructions for using the fastembed package
2023-08-21 19:23:21 +05:30