chore: updated model file path

test: nomic-ai/nomic-embed-text-v1.5-Q
Merge branch 'removed-gcs' into QModels
2026-09-22 05:57:51 -05:00 · 2024-04-17 02:30:02 +05:30 · 2024-04-17 02:23:24 +05:30 · 2024-04-17 02:14:28 +05:30 · 2024-04-17 02:13:58 +05:30 · 2024-04-17 02:10:55 +05:30
39 changed files with 3068 additions and 2309 deletions
@@ -0,0 +1,56 @@
+name: Bug/New Model Request
+description: File a bug report/Request a new Model
+title: "[Bug/Model Request]: "
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for taking the time to fill out this bug report!
+  - type: textarea
+    id: what-happened
+    attributes:
+      label: What happened?
+      description: Also tell us, what did you expect to happen?
+      placeholder: Tell us what you see!
+      value: "A bug happened!"
+    validations:
+      required: true
+  - type: textarea
+    id: Python version
+    attributes:
+      label: What Python version are you on? e.g. python --version
+      description: Also tell us, what package manager are you using e.g. conda, pip, poetry?
+      placeholder: Python3.10
+    validations:
+      required: true
+  - type: dropdown
+    id: version
+    attributes:
+      label: Version
+      description: What version of FastEmbed are you running? python -c "import fastembed; print(fastembed.__version__)". If you're not on the latest, please upgrade and see if the problem persists.
+      options:
+        - 0.2.6 (Latest)
+        - 0.2.5
+        - 0.2.4 
+        - 0.2.3 
+        - 0.2.2
+        - 0.2.1
+        - 0.1.x 
+      default: 0
+    validations:
+      required: true
+  - type: dropdown
+    id: os
+    attributes:
+      label: What os are you seeing the problem on?
+      multiple: true
+      options:
+        - Linux
+        - MacOS
+        - Windows
+  - type: textarea
+    id: logs
+    attributes:
+      label: Relevant stack traces and/or logs
+      description: Please copy and paste any relevant raised exceptions. This will be automatically formatted into code, so no need for backticks.
+      render: shell
@@ -0,0 +1,5 @@
+blank_issues_enabled: false
+contact_links:
+  - name: GitHub Community Support
+    url: https://github.com/qdrant/fastembed/discussions
+    about: Please ask and answer questions here.
@@ -85,28 +85,8 @@ ipython_config.py
 # pyenv
 #   For a library or package, you might want to ignore these files since the code is
 #   intended to run in multiple environments; otherwise, check them in:
-# .python-version
+.python-version

-# pipenv
-#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
-#   However, in case of collaboration, if having platform-specific dependencies or dependencies
-#   having no cross-platform support, pipenv may install dependencies that don't work, or not
-#   install all needed dependencies.
-#Pipfile.lock
-
-# poetry
-#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
-#   This is especially recommended for binary packages to ensure reproducibility, and is more
-#   commonly ignored for libraries.
-#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
-#poetry.lock
-
-# pdm
-#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
-#pdm.lock
-#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
-#   in version control.
-#   https://pdm.fming.dev/#use-with-ide
 .pdm.toml

 # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
@@ -152,21 +132,11 @@ dmypy.json
 # Cython debug symbols
 cython_debug/

-# PyCharm
-#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
-#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
-#  and can be added to the global gitignore or merged into this file.  For a more nuclear
-#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-#.idea/
+.idea/
 .DS_Store
-nbs/*.tar.gz
 *.tar.gz
-nbs/fast-*/*
-local_cache/*/*
-*/local_cache/*/*
-*/*/local_cache/*/*
+**/local_cache/
 docs/experimental/*.parquet
 docs/experimental/*.bin
 qdrant_storage/*
-fooling_around/*
-experiments/models/*
+experiments/models/*
@@ -1,6 +1,6 @@
 repos:
  - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.1.13
+    rev: v0.3.4
    hooks:
      - id: ruff
        types_or: [ python, pyi, jupyter ]
@@ -0,0 +1,78 @@
+# Contributing to FastEmbed!
+
+:+1::tada: First off, thanks for taking the time to contribute! :tada::+1:
+
+The following is a set of guidelines for contributing to FastEmbed. These are mostly guidelines, not rules. Use your best judgment, and feel free to propose changes to this document in a pull request.
+
+## Table Of Contents
+
+[I don't want to read this whole thing, I just have a question!!!](#i-dont-want-to-read-this-whole-thing-i-just-have-a-question)
+
+[How Can I Contribute?](#how-can-i-contribute)
+  * [Your First Code Contribution](#your-first-code-contribution)
+  * [Adding New Models](#adding-new-models)
+
+[Styleguides](#styleguides)
+  * [Code Lint](#code-lint)
+  * [Pre-Commit Hooks](#pre-commit-hooks)
+ 
+## I don't want to read this whole thing I just have a question!!!
+
+> **Note:** Please don't file an issue to ask a question. You'll get faster results by using the resources below:
+
+* [FastEmbed Docs](https://qdrant.github.io/fastembed/)
+* [Qdrant Discord](https://discord.gg/Qy6HCJK9Dc)
+
+## How Can I Contribute?
+
+## How Do I Submit A (Good) Bug Report?
+
+Bugs are tracked as [GitHub issues](https://guides.github.com/features/issues/). 
+
+Explain the problem and include additional details to help maintainers reproduce the problem:
+
+* **Use a clear and descriptive title** for the issue to identify the problem.
+* **Describe the exact steps which reproduce the problem** in as many details as possible. For example, start by explaining how you are using FastEmbed, e.g. with Langchain, Qdrant Client, Llama Index and which command exactly you used. When listing steps, **don't just say what you did, but explain how you did it**.
+* **Provide specific examples to demonstrate the steps**. Include links to files or GitHub projects, or copy/pasteable snippets, which you use in those examples. If you're providing snippets in the issue, use [Markdown code blocks](https://help.github.com/articles/markdown-basics/#multiple-lines).
+* **Describe the behavior you observed after following the steps** and point out what exactly is the problem with that behavior.
+* **Explain which behavior you expected to see instead and why.**
+* **If the problem is related to performance or memory**, include a [call stack profile capture](https://github.com/joerick/pyinstrument) and your observations. 
+
+Include details about your configuration and environment:
+
+* **Which version of FastEmbed are you using?** You can get the exact version by running `python -c "import fastembed; print(fastembed.__version__)"`.
+* **What's the name and version of the OS you're using**?
+* **Which packages do you have installed?** You can get that list by running `pip freeze`
+
+### Your First Code Contribution
+
+Unsure where to begin contributing to FastEmbed? You can start by looking through these `good-first-issue`issues:
+
+* [Good First Issue](https://github.com/qdrant/fastembed/labels/good%20first%20issue) - issues which should only require a few lines of code, and a test or two. These are a great way to get started with FastEmbed. This includes adding new models which are already tested and ready on Huggingface Hub. 
+
+## Pull Requests
+
+The best way to learn about the mechanics of FastEmbed is to start working on it. 
+
+### Your First Code Contribution
+Your first code contribution can be small bug fixes:
+1. This PR adds a small bug fix for a single input: https://github.com/qdrant/fastembed/pull/148
+2. This PR adds a check for the right file location and extension, specific to an OS: https://github.com/qdrant/fastembed/pull/128
+
+Even documentation improvements and tests are most welcome:
+1. This PR fixes a README link: https://github.com/qdrant/fastembed/pull/143
+
+### Adding New Models
+1. Open Requests for New Models are [here](https://github.com/qdrant/fastembed/labels/model%20request). 
+2. There are quite a few pull requests that were merged for this purpose and you can use them as a reference. Here is an example: https://github.com/qdrant/fastembed/pull/129
+3. Make sure to add tests for the new model
+    - The CANONICAL_VECTOR values must come from a reference implementation usually from Huggingface Transformers or Sentence Transformers
+    - Here is a reference [Colab Notebook](https://colab.research.google.com/drive/1tNdV3DsiwsJzu2AXnUnoeF5av1Hp8HF1?usp=sharing) for how we will evaluate whether your VECTOR values in the test are correct or not.
+
+## Styleguides
+
+### Code Lint
+We use ruff for code linting. It should be installed with poetry since it's a dev dependency.
+
+### Pre-Commit Hooks
+We use pre-commit hooks to ensure that the code is linted before it's committed. You can install pre-commit hooks by running `pre-commit install` in the root directory of the project.
@@ -2,7 +2,7 @@

 FastEmbed is a lightweight, fast, Python library built for embedding generation. We [support popular text models](https://qdrant.github.io/fastembed/examples/Supported_Models/). Please [open a GitHub issue](https://github.com/qdrant/fastembed/issues/new) if you want us to add a new model.

-The default text embedding (`TextEmbedding`) model is Flag Embedding, the top model in the [MTEB](https://huggingface.co/spaces/mteb/leaderboard) leaderboard. It supports "query" and "passage" prefixes for the input text. Here is an example for [Retrieval Embedding Generation](https://qdrant.github.io/fastembed/examples/Retrieval_with_FastEmbed/) and how to use [FastEmbed with Qdrant](https://qdrant.github.io/fastembed/examples/Usage_With_Qdrant/).
+The default text embedding (`TextEmbedding`) model is Flag Embedding, presented in the [MTEB](https://huggingface.co/spaces/mteb/leaderboard) leaderboard. It supports "query" and "passage" prefixes for the input text. Here is an example for [Retrieval Embedding Generation](https://qdrant.github.io/fastembed/examples/Retrieval_with_FastEmbed/) and how to use [FastEmbed with Qdrant](https://qdrant.github.io/fastembed/examples/Usage_With_Qdrant/).

 ## 📈 Why FastEmbed?

@@ -23,7 +23,6 @@ pip install fastembed
 ## 📖 Quickstart

 ```python
-import numpy as np
 from fastembed import TextEmbedding
 from typing import List

@@ -80,7 +80,7 @@
    "print(\"The model BAAI/bge-small-en-v1.5 is ready to use.\")\n",
    "\n",
    "embeddings_generator = embedding_model.embed(documents)  # reminder this is a generator\n",
-    "embeddings_list = list(embedding_model.embed(documents))\n",
+    "embeddings_list = list(embeddings_generator)\n",
    "# you can also convert the generator to a list, and that to a numpy array\n",
    "len(embeddings_list[0])  # Vector of 384 dimensions"
   ]
@@ -22,19 +22,34 @@
  },
  {
   "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 20,
   "metadata": {
    "id": "rOTVBRFAj2U-"
   },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
+      "To disable this warning, you can either:\n",
+      "\t- Avoid using `tokenizers` before the fork if possible\n",
+      "\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n"
+     ]
+    }
+   ],
   "source": [
    "!pip install -U fastembed datasets qdrant-client peft transformers accelerate bitsandbytes -qq"
   ]
  },
  {
   "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 21,
   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-30T00:45:24.814968Z",
+     "start_time": "2024-03-30T00:45:24.811138Z"
+    },
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
@@ -43,23 +58,25 @@
   },
   "outputs": [],
   "source": [
-    "from datasets import load_dataset\n",
-    "from fastembed import TextEmbedding\n",
-    "from qdrant_client import QdrantClient\n",
-    "from qdrant_client.http.models import PointStruct, VectorParams, Distance\n",
-    "from peft import AutoPeftModelForCausalLM\n",
-    "from transformers import AutoTokenizer\n",
    "from typing import List\n",
-    "import numpy as np"
+    "\n",
+    "import numpy as np\n",
+    "from datasets import load_dataset\n",
+    "from peft import AutoPeftModelForCausalLM\n",
+    "from qdrant_client import QdrantClient\n",
+    "from qdrant_client.models import PointStruct, VectorParams, Distance\n",
+    "from transformers import AutoTokenizer\n",
+    "\n",
+    "from fastembed import TextEmbedding"
   ]
  },
  {
   "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
-    "hf_token = \"<YOUR_HF_TOKEN_HERE>\"  # Get your token from https://huggingface.co/settings/token, needed for Gemma weights"
+    "hf_token = <YOUR_HF_TOKEN_HERE>  # Get your token from https://huggingface.co/settings/token, needed for Gemma weights"
   ]
  },
  {
@@ -82,7 +99,7 @@
   "outputs": [],
   "source": [
    "embedding_model = \"sentence-transformers/paraphrase-multilingual-mpnet-base-v2\"\n",
-    "model_id = \"Telugu-LLM-Labs/Indic-gemma-7b-finetuned-sft-Navarasa\""
+    "model_id = \"Telugu-LLM-Labs/Indic-gemma-2b-finetuned-sft-Navarasa\""
   ]
  },
  {
@@ -445,7 +462,8 @@
   "provenance": []
  },
  "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
   "name": "python3"
  },
  "language_info": {
@@ -0,0 +1,384 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Introduction to SPLADE with FastEmbed\n",
+    "\n",
+    "In this notebook, we will explore how to generate Sparse Vectors -- in particular a variant of the [SPLADE](https://arxiv.org/abs/2107.05720).\n",
+    "\n",
+    "> 💡 The original [naver/SPLADE](https://github.com/naver/splade) models were licensed CC BY-NC-SA 4.0 -- Not for Commercial Use. This [SPLADE++](https://huggingface.co/prithivida/Splade_PP_en_v1) model is Apache License and hence, licensed for commercial use. \n",
+    "\n",
+    "## Outline:\n",
+    "1. [What is SPLADE?](#What-is-SPLADE?)\n",
+    "2. [Setting up the environment](#Setting-up-the-environment)\n",
+    "3. [Generating SPLADE vectors with FastEmbed](#Generating-SPLADE-vectors-with-FastEmbed)\n",
+    "4. [Understanding SPLADE vectors](#Understanding-SPLADE-vectors)\n",
+    "5. [Observations and Design Choices](#Observations-and-Model-Design-Choices)\n",
+    "\n",
+    "\n",
+    "## What is SPLADE?\n",
+    "\n",
+    "SPLADE was a novel method for _learning_ sparse vectors for text representation. This model beats BM25 -- the underlying approach for the Elastic/Lucene family of implementations. Thus making it highly effective for tasks such as information retrieval, document classification, and more. \n",
+    "\n",
+    "The key advantage of SPLADE is its ability to generate sparse vectors, which are more efficient and interpretable than dense vectors. This makes SPLADE a powerful tool for handling large-scale text data.\n",
+    "\n",
+    "## Setting up the environment\n",
+    "\n",
+    "This notebook uses few dependencies, which are installed below: "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# !pip install -q fastembed"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Let's get started! 🚀"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-30T00:49:20.516644Z",
+     "start_time": "2024-03-30T00:49:20.188543Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from fastembed import SparseTextEmbedding, SparseEmbedding\n",
+    "from typing import List"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "> You can find the list of all supported Sparse Embedding models by calling this API: `SparseTextEmbedding.list_supported_models()`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-30T00:49:22.366294Z",
+     "start_time": "2024-03-30T00:49:22.362384Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'model': 'prithvida/Splade_PP_en_v1',\n",
+       "  'vocab_size': 30522,\n",
+       "  'description': 'Misspelled version of the model. Retained for backward compatibility. Independent Implementation of SPLADE++ Model for English',\n",
+       "  'size_in_GB': 0.532,\n",
+       "  'sources': {'hf': 'Qdrant/SPLADE_PP_en_v1'}},\n",
+       " {'model': 'prithivida/Splade_PP_en_v1',\n",
+       "  'vocab_size': 30522,\n",
+       "  'description': 'Independent Implementation of SPLADE++ Model for English',\n",
+       "  'size_in_GB': 0.532,\n",
+       "  'sources': {'hf': 'Qdrant/SPLADE_PP_en_v1'}}]"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "SparseTextEmbedding.list_supported_models()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-30T00:49:27.193530Z",
+     "start_time": "2024-03-30T00:49:26.139248Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "2aa47b26ab01475e8d3577433037f685",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Fetching 9 files:   0%|          | 0/9 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "model_name = \"prithvida/Splade_PP_en_v1\"\n",
+    "# This triggers the model download\n",
+    "model = SparseTextEmbedding(model_name=model_name)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-30T00:49:28.624109Z",
+     "start_time": "2024-03-30T00:49:28.399960Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "documents: List[str] = [\n",
+    "    \"Chandrayaan-3 is India's third lunar mission\",\n",
+    "    \"It aimed to land a rover on the Moon's surface - joining the US, China and Russia\",\n",
+    "    \"The mission is a follow-up to Chandrayaan-2, which had partial success\",\n",
+    "    \"Chandrayaan-3 will be launched by the Indian Space Research Organisation (ISRO)\",\n",
+    "    \"The estimated cost of the mission is around $35 million\",\n",
+    "    \"It will carry instruments to study the lunar surface and atmosphere\",\n",
+    "    \"Chandrayaan-3 landed on the Moon's surface on 23rd August 2023\",\n",
+    "    \"It consists of a lander named Vikram and a rover named Pragyan similar to Chandrayaan-2. Its propulsion module would act like an orbiter.\",\n",
+    "    \"The propulsion module carries the lander and rover configuration until the spacecraft is in a 100-kilometre (62 mi) lunar orbit\",\n",
+    "    \"The mission used GSLV Mk III rocket for its launch\",\n",
+    "    \"Chandrayaan-3 was launched from the Satish Dhawan Space Centre in Sriharikota\",\n",
+    "    \"Chandrayaan-3 was launched earlier in the year 2023\",\n",
+    "]\n",
+    "sparse_embeddings_list: List[SparseEmbedding] = list(\n",
+    "    model.embed(documents, batch_size=6)\n",
+    ")  # batch_size is optional, notice the generator"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-30T00:49:29.646340Z",
+     "start_time": "2024-03-30T00:49:29.643411Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "SparseEmbedding(values=array([0.05297208, 0.01963477, 0.36459631, 1.38508618, 0.71776593,\n",
+       "       0.12667948, 0.46230844, 0.446771  , 0.26897505, 1.01519883,\n",
+       "       1.5655334 , 0.29412213, 1.53102326, 0.59785569, 1.1001817 ,\n",
+       "       0.02079751, 0.09955651, 0.44249091, 0.09747757, 1.53519952,\n",
+       "       1.36765671, 0.15740395, 0.49882549, 0.38629025, 0.76612782,\n",
+       "       1.25805044, 0.39058095, 0.27236196, 0.45152301, 0.48262018,\n",
+       "       0.26085234, 1.35912788, 0.70710695, 1.71639752]), indices=array([ 1010,  1011,  1016,  1017,  2001,  2018,  2034,  2093,  2117,\n",
+       "        2319,  2353,  2509,  2634,  2686,  2796,  2817,  2922,  2959,\n",
+       "        3003,  3148,  3260,  3390,  3462,  3523,  3822,  4231,  4316,\n",
+       "        4774,  5590,  5871,  6416, 11926, 12076, 16469]))"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "index = 0\n",
+    "sparse_embeddings_list[index]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The previous output is a SparseEmbedding object for the first document in our list.\n",
+    "\n",
+    "It contains two arrays: values and indices. \n",
+    "- The 'values' array represents the weights of the features (tokens) in the document.\n",
+    "- The 'indices' array represents the indices of these features in the model's vocabulary.\n",
+    "\n",
+    "Each pair of corresponding values and indices represents a token and its weight in the document."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-30T00:49:31.549533Z",
+     "start_time": "2024-03-30T00:49:31.546398Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Token at index 1010 has weight 0.05297207832336426\n",
+      "Token at index 1011 has weight 0.01963476650416851\n",
+      "Token at index 1016 has weight 0.36459630727767944\n",
+      "Token at index 1017 has weight 1.385086178779602\n",
+      "Token at index 2001 has weight 0.7177659273147583\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Let's print the first 5 features and their weights for better understanding.\n",
+    "for i in range(5):\n",
+    "    print(f\"Token at index {sparse_embeddings_list[0].indices[i]} has weight {sparse_embeddings_list[0].values[i]}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Understanding SPLADE vectors\n",
+    "\n",
+    "This is still a little abstract, so let's use the tokenizer vocab to make sense of these indices."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-30T00:49:36.203640Z",
+     "start_time": "2024-03-30T00:49:34.889654Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "from transformers import AutoTokenizer\n",
+    "\n",
+    "tokenizer = AutoTokenizer.from_pretrained(SparseTextEmbedding.list_supported_models()[0][\"sources\"][\"hf\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-30T00:49:36.210049Z",
+     "start_time": "2024-03-30T00:49:36.206825Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{\n",
+      "    \"chandra\": 1.7163975238800049,\n",
+      "    \"third\": 1.5655333995819092,\n",
+      "    \"##ya\": 1.535199522972107,\n",
+      "    \"india\": 1.5310232639312744,\n",
+      "    \"3\": 1.385086178779602,\n",
+      "    \"mission\": 1.3676567077636719,\n",
+      "    \"lunar\": 1.3591278791427612,\n",
+      "    \"moon\": 1.2580504417419434,\n",
+      "    \"indian\": 1.1001816987991333,\n",
+      "    \"##an\": 1.015198826789856,\n",
+      "    \"3rd\": 0.7661278247833252,\n",
+      "    \"was\": 0.7177659273147583,\n",
+      "    \"spacecraft\": 0.7071069478988647,\n",
+      "    \"space\": 0.5978556871414185,\n",
+      "    \"flight\": 0.4988254904747009,\n",
+      "    \"satellite\": 0.4826201796531677,\n",
+      "    \"first\": 0.46230843663215637,\n",
+      "    \"expedition\": 0.4515230059623718,\n",
+      "    \"three\": 0.4467709958553314,\n",
+      "    \"fourth\": 0.44249090552330017,\n",
+      "    \"vehicle\": 0.390580952167511,\n",
+      "    \"iii\": 0.3862902522087097,\n",
+      "    \"2\": 0.36459630727767944,\n",
+      "    \"##3\": 0.2941221296787262,\n",
+      "    \"planet\": 0.27236196398735046,\n",
+      "    \"second\": 0.26897504925727844,\n",
+      "    \"missions\": 0.2608523368835449,\n",
+      "    \"launched\": 0.15740394592285156,\n",
+      "    \"had\": 0.12667948007583618,\n",
+      "    \"largest\": 0.09955651313066483,\n",
+      "    \"leader\": 0.09747757017612457,\n",
+      "    \",\": 0.05297207832336426,\n",
+      "    \"study\": 0.02079751156270504,\n",
+      "    \"-\": 0.01963476650416851\n",
+      "}\n"
+     ]
+    }
+   ],
+   "source": [
+    "def get_tokens_and_weights(sparse_embedding, tokenizer):\n",
+    "    token_weight_dict = {}\n",
+    "    for i in range(len(sparse_embedding.indices)):\n",
+    "        token = tokenizer.decode([sparse_embedding.indices[i]])\n",
+    "        weight = sparse_embedding.values[i]\n",
+    "        token_weight_dict[token] = weight\n",
+    "\n",
+    "    # Sort the dictionary by weights\n",
+    "    token_weight_dict = dict(sorted(token_weight_dict.items(), key=lambda item: item[1], reverse=True))\n",
+    "    return token_weight_dict\n",
+    "\n",
+    "\n",
+    "# Test the function with the first SparseEmbedding\n",
+    "print(json.dumps(get_tokens_and_weights(sparse_embeddings_list[index], tokenizer), indent=4))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Observations and Model Design Choices\n",
+    "\n",
+    "1. The relative order of importance is quite useful. The most important tokens in the sentence have the highest weights.\n",
+    "1. **Term Expansion**: The model can expand the terms in the document. This means that the model can generate weights for tokens that are not present in the document but are related to the tokens in the document. This is a powerful feature that allows the model to capture the context of the document. Here, you'll see that the model has added the tokens '3' from 'third' and 'moon' from 'lunar' to the sparse vector.\n",
+    "\n",
+    "### Design Choices\n",
+    "\n",
+    "1. The weights are not normalized. This means that the sum of the weights is not 1 or 100. This is a common practice in sparse embeddings, as it allows the model to capture the importance of each token in the document.\n",
+    "1. Tokens are included in the sparse vector only if they are present in the model's vocabulary. This means that the model will not generate a weight for tokens that it has not seen during training.\n",
+    "1. Tokens do not map to words directly -- allowing you to gracefully handle typo errors and out-of-vocabulary tokens."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "fst",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
@@ -3,13 +3,36 @@
  {
   "cell_type": "code",
   "execution_count": 1,
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-30T11:18:52.052764Z",
+     "start_time": "2024-03-30T11:18:52.039616Z"
+    }
+   },
   "outputs": [],
   "source": [
    "%load_ext autoreload\n",
    "%autoreload 2"
   ]
  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "from fastembed import SparseTextEmbedding, TextEmbedding"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Supported Text Embedding Models"
+   ]
+  },
  {
   "cell_type": "code",
   "execution_count": 6,
@@ -40,214 +63,161 @@
       "      <th>dim</th>\n",
       "      <th>description</th>\n",
       "      <th>size_in_GB</th>\n",
-       "      <th>sources</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
-       "      <td>BAAI/bge-base-en</td>\n",
-       "      <td>768</td>\n",
-       "      <td>Base English model</td>\n",
-       "      <td>0.50</td>\n",
-       "      <td>{'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-bge-base-en.tar.gz'}</td>\n",
+       "      <td>BAAI/bge-small-en-v1.5</td>\n",
+       "      <td>384</td>\n",
+       "      <td>Fast and Default English model</td>\n",
+       "      <td>0.067</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
-       "      <td>BAAI/bge-base-en-v1.5</td>\n",
-       "      <td>768</td>\n",
-       "      <td>Base English model, v1.5</td>\n",
-       "      <td>0.44</td>\n",
-       "      <td>{'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-bge-base-en-v1.5.tar.gz', 'hf': 'qdrant/bge-base-en-v1.5-onnx-q'}</td>\n",
+       "      <td>BAAI/bge-small-zh-v1.5</td>\n",
+       "      <td>512</td>\n",
+       "      <td>Fast and recommended Chinese model</td>\n",
+       "      <td>0.090</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
-       "      <td>BAAI/bge-large-en-v1.5-quantized</td>\n",
-       "      <td>1024</td>\n",
-       "      <td>Large English model, v1.5</td>\n",
-       "      <td>1.34</td>\n",
-       "      <td>{'hf': 'qdrant/bge-large-en-v1.5-onnx-q'}</td>\n",
+       "      <td>sentence-transformers/all-MiniLM-L6-v2</td>\n",
+       "      <td>384</td>\n",
+       "      <td>Sentence Transformer model, MiniLM-L6-v2</td>\n",
+       "      <td>0.090</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
-       "      <td>BAAI/bge-large-en-v1.5</td>\n",
-       "      <td>1024</td>\n",
-       "      <td>Large English model, v1.5</td>\n",
-       "      <td>1.34</td>\n",
-       "      <td>{'hf': 'qdrant/bge-large-en-v1.5-onnx'}</td>\n",
+       "      <td>jinaai/jina-embeddings-v2-small-en</td>\n",
+       "      <td>512</td>\n",
+       "      <td>English embedding model supporting 8192 sequen...</td>\n",
+       "      <td>0.120</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>BAAI/bge-small-en</td>\n",
       "      <td>384</td>\n",
       "      <td>Fast English model</td>\n",
-       "      <td>0.20</td>\n",
-       "      <td>{'url': 'https://storage.googleapis.com/qdrant-fastembed/BAAI-bge-small-en.tar.gz'}</td>\n",
+       "      <td>0.130</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
-       "      <td>BAAI/bge-small-en-v1.5</td>\n",
-       "      <td>384</td>\n",
-       "      <td>Fast and Default English model</td>\n",
-       "      <td>0.13</td>\n",
-       "      <td>{'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-bge-small-en-v1.5.tar.gz', 'hf': 'qdrant/bge-small-en-v1.5-onnx-q'}</td>\n",
+       "      <td>BAAI/bge-base-en-v1.5</td>\n",
+       "      <td>768</td>\n",
+       "      <td>Base English model, v1.5</td>\n",
+       "      <td>0.210</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
-       "      <td>BAAI/bge-small-zh-v1.5</td>\n",
-       "      <td>512</td>\n",
-       "      <td>Fast and recommended Chinese model</td>\n",
-       "      <td>0.10</td>\n",
-       "      <td>{'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-bge-small-zh-v1.5.tar.gz'}</td>\n",
+       "      <td>sentence-transformers/paraphrase-multilingual-...</td>\n",
+       "      <td>384</td>\n",
+       "      <td>Sentence Transformer model, paraphrase-multili...</td>\n",
+       "      <td>0.220</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
-       "      <td>sentence-transformers/all-MiniLM-L6-v2</td>\n",
-       "      <td>384</td>\n",
-       "      <td>Sentence Transformer model, MiniLM-L6-v2</td>\n",
-       "      <td>0.09</td>\n",
-       "      <td>{'url': 'https://storage.googleapis.com/qdrant-fastembed/sentence-transformers-all-MiniLM-L6-v2.tar.gz', 'hf': 'qdrant/all-MiniLM-L6-v2-onnx'}</td>\n",
+       "      <td>BAAI/bge-base-en</td>\n",
+       "      <td>768</td>\n",
+       "      <td>Base English model</td>\n",
+       "      <td>0.420</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>nomic-ai/nomic-embed-text-v1</td>\n",
       "      <td>768</td>\n",
       "      <td>8192 context length english model</td>\n",
-       "      <td>0.54</td>\n",
-       "      <td>{'hf': 'nomic-ai/nomic-embed-text-v1'}</td>\n",
+       "      <td>0.520</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>nomic-ai/nomic-embed-text-v1.5</td>\n",
       "      <td>768</td>\n",
       "      <td>8192 context length english model</td>\n",
-       "      <td>0.54</td>\n",
-       "      <td>{'hf': 'nomic-ai/nomic-embed-text-v1.5'}</td>\n",
+       "      <td>0.520</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
-       "      <td>thenlper/gte-large</td>\n",
-       "      <td>1024</td>\n",
-       "      <td>Large general text embeddings model</td>\n",
-       "      <td>1.34</td>\n",
-       "      <td>{'hf': 'qdrant/gte-large-onnx'}</td>\n",
+       "      <td>jinaai/jina-embeddings-v2-base-en</td>\n",
+       "      <td>768</td>\n",
+       "      <td>English embedding model supporting 8192 sequen...</td>\n",
+       "      <td>0.520</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
-       "      <td>intfloat/multilingual-e5-large</td>\n",
+       "      <td>mixedbread-ai/mxbai-embed-large-v1</td>\n",
       "      <td>1024</td>\n",
-       "      <td>Multilingual model, e5-large. Recommend using this model for non-English languages</td>\n",
-       "      <td>2.24</td>\n",
-       "      <td>{'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-multilingual-e5-large.tar.gz', 'hf': 'qdrant/multilingual-e5-large-onnx'}</td>\n",
+       "      <td>MixedBread Base sentence embedding model, does...</td>\n",
+       "      <td>0.640</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
-       "      <td>sentence-transformers/paraphrase-multilingual-mpnet-base-v2</td>\n",
+       "      <td>sentence-transformers/paraphrase-multilingual-...</td>\n",
       "      <td>768</td>\n",
-       "      <td>Sentence-transformers model for tasks like clustering or semantic search</td>\n",
-       "      <td>1.11</td>\n",
-       "      <td>{'hf': 'xenova/paraphrase-multilingual-mpnet-base-v2'}</td>\n",
+       "      <td>Sentence-transformers model for tasks like clu...</td>\n",
+       "      <td>1.000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
-       "      <td>sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2</td>\n",
-       "      <td>384</td>\n",
-       "      <td>Sentence Transformer model, paraphrase-multilingual-MiniLM-L12-v2</td>\n",
-       "      <td>0.46</td>\n",
-       "      <td>{'hf': 'qdrant/paraphrase-multilingual-MiniLM-L12-v2-onnx-Q'}</td>\n",
+       "      <td>BAAI/bge-large-en-v1.5</td>\n",
+       "      <td>1024</td>\n",
+       "      <td>Large English model, v1.5</td>\n",
+       "      <td>1.200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
-       "      <td>jinaai/jina-embeddings-v2-base-en</td>\n",
-       "      <td>768</td>\n",
-       "      <td>English embedding model supporting 8192 sequence length</td>\n",
-       "      <td>0.55</td>\n",
-       "      <td>{'hf': 'xenova/jina-embeddings-v2-base-en'}</td>\n",
+       "      <td>thenlper/gte-large</td>\n",
+       "      <td>1024</td>\n",
+       "      <td>Large general text embeddings model</td>\n",
+       "      <td>1.200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
-       "      <td>jinaai/jina-embeddings-v2-small-en</td>\n",
-       "      <td>512</td>\n",
-       "      <td>English embedding model supporting 8192 sequence length</td>\n",
-       "      <td>0.13</td>\n",
-       "      <td>{'hf': 'xenova/jina-embeddings-v2-small-en'}</td>\n",
+       "      <td>intfloat/multilingual-e5-large</td>\n",
+       "      <td>1024</td>\n",
+       "      <td>Multilingual model, e5-large. Recommend using ...</td>\n",
+       "      <td>2.240</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
-       "                                                          model   dim  \\\n",
-       "0                                              BAAI/bge-base-en   768   \n",
-       "1                                         BAAI/bge-base-en-v1.5   768   \n",
-       "2                              BAAI/bge-large-en-v1.5-quantized  1024   \n",
-       "3                                        BAAI/bge-large-en-v1.5  1024   \n",
-       "4                                             BAAI/bge-small-en   384   \n",
-       "5                                        BAAI/bge-small-en-v1.5   384   \n",
-       "6                                        BAAI/bge-small-zh-v1.5   512   \n",
-       "7                        sentence-transformers/all-MiniLM-L6-v2   384   \n",
-       "8                                  nomic-ai/nomic-embed-text-v1   768   \n",
-       "9                                nomic-ai/nomic-embed-text-v1.5   768   \n",
-       "10                                           thenlper/gte-large  1024   \n",
-       "11                               intfloat/multilingual-e5-large  1024   \n",
-       "12  sentence-transformers/paraphrase-multilingual-mpnet-base-v2   768   \n",
-       "13  sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2   384   \n",
-       "14                            jinaai/jina-embeddings-v2-base-en   768   \n",
-       "15                           jinaai/jina-embeddings-v2-small-en   512   \n",
+       "                                                model   dim  \\\n",
+       "0                              BAAI/bge-small-en-v1.5   384   \n",
+       "1                              BAAI/bge-small-zh-v1.5   512   \n",
+       "2              sentence-transformers/all-MiniLM-L6-v2   384   \n",
+       "3                  jinaai/jina-embeddings-v2-small-en   512   \n",
+       "4                                   BAAI/bge-small-en   384   \n",
+       "5                               BAAI/bge-base-en-v1.5   768   \n",
+       "6   sentence-transformers/paraphrase-multilingual-...   384   \n",
+       "7                                    BAAI/bge-base-en   768   \n",
+       "8                        nomic-ai/nomic-embed-text-v1   768   \n",
+       "9                      nomic-ai/nomic-embed-text-v1.5   768   \n",
+       "10                  jinaai/jina-embeddings-v2-base-en   768   \n",
+       "11                 mixedbread-ai/mxbai-embed-large-v1  1024   \n",
+       "12  sentence-transformers/paraphrase-multilingual-...   768   \n",
+       "13                             BAAI/bge-large-en-v1.5  1024   \n",
+       "14                                 thenlper/gte-large  1024   \n",
+       "15                     intfloat/multilingual-e5-large  1024   \n",
       "\n",
-       "                                                                           description  \\\n",
-       "0                                                                   Base English model   \n",
-       "1                                                             Base English model, v1.5   \n",
-       "2                                                            Large English model, v1.5   \n",
-       "3                                                            Large English model, v1.5   \n",
-       "4                                                                   Fast English model   \n",
-       "5                                                       Fast and Default English model   \n",
-       "6                                                   Fast and recommended Chinese model   \n",
-       "7                                             Sentence Transformer model, MiniLM-L6-v2   \n",
-       "8                                                    8192 context length english model   \n",
-       "9                                                    8192 context length english model   \n",
-       "10                                                 Large general text embeddings model   \n",
-       "11  Multilingual model, e5-large. Recommend using this model for non-English languages   \n",
-       "12            Sentence-transformers model for tasks like clustering or semantic search   \n",
-       "13                   Sentence Transformer model, paraphrase-multilingual-MiniLM-L12-v2   \n",
-       "14                             English embedding model supporting 8192 sequence length   \n",
-       "15                             English embedding model supporting 8192 sequence length   \n",
-       "\n",
-       "    size_in_GB  \\\n",
-       "0         0.50   \n",
-       "1         0.44   \n",
-       "2         1.34   \n",
-       "3         1.34   \n",
-       "4         0.20   \n",
-       "5         0.13   \n",
-       "6         0.10   \n",
-       "7         0.09   \n",
-       "8         0.54   \n",
-       "9         0.54   \n",
-       "10        1.34   \n",
-       "11        2.24   \n",
-       "12        1.11   \n",
-       "13        0.46   \n",
-       "14        0.55   \n",
-       "15        0.13   \n",
-       "\n",
-       "                                                                                                                                           sources  \n",
-       "0                                                               {'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-bge-base-en.tar.gz'}  \n",
-       "1                  {'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-bge-base-en-v1.5.tar.gz', 'hf': 'qdrant/bge-base-en-v1.5-onnx-q'}  \n",
-       "2                                                                                                        {'hf': 'qdrant/bge-large-en-v1.5-onnx-q'}  \n",
-       "3                                                                                                          {'hf': 'qdrant/bge-large-en-v1.5-onnx'}  \n",
-       "4                                                              {'url': 'https://storage.googleapis.com/qdrant-fastembed/BAAI-bge-small-en.tar.gz'}  \n",
-       "5                {'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-bge-small-en-v1.5.tar.gz', 'hf': 'qdrant/bge-small-en-v1.5-onnx-q'}  \n",
-       "6                                                         {'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-bge-small-zh-v1.5.tar.gz'}  \n",
-       "7   {'url': 'https://storage.googleapis.com/qdrant-fastembed/sentence-transformers-all-MiniLM-L6-v2.tar.gz', 'hf': 'qdrant/all-MiniLM-L6-v2-onnx'}  \n",
-       "8                                                                                                           {'hf': 'nomic-ai/nomic-embed-text-v1'}  \n",
-       "9                                                                                                         {'hf': 'nomic-ai/nomic-embed-text-v1.5'}  \n",
-       "10                                                                                                                 {'hf': 'qdrant/gte-large-onnx'}  \n",
-       "11         {'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-multilingual-e5-large.tar.gz', 'hf': 'qdrant/multilingual-e5-large-onnx'}  \n",
-       "12                                                                                          {'hf': 'xenova/paraphrase-multilingual-mpnet-base-v2'}  \n",
-       "13                                                                                   {'hf': 'qdrant/paraphrase-multilingual-MiniLM-L12-v2-onnx-Q'}  \n",
-       "14                                                                                                     {'hf': 'xenova/jina-embeddings-v2-base-en'}  \n",
-       "15                                                                                                    {'hf': 'xenova/jina-embeddings-v2-small-en'}  "
+       "                                          description  size_in_GB  \n",
+       "0                      Fast and Default English model       0.067  \n",
+       "1                  Fast and recommended Chinese model       0.090  \n",
+       "2            Sentence Transformer model, MiniLM-L6-v2       0.090  \n",
+       "3   English embedding model supporting 8192 sequen...       0.120  \n",
+       "4                                  Fast English model       0.130  \n",
+       "5                            Base English model, v1.5       0.210  \n",
+       "6   Sentence Transformer model, paraphrase-multili...       0.220  \n",
+       "7                                  Base English model       0.420  \n",
+       "8                   8192 context length english model       0.520  \n",
+       "9                   8192 context length english model       0.520  \n",
+       "10  English embedding model supporting 8192 sequen...       0.520  \n",
+       "11  MixedBread Base sentence embedding model, does...       0.640  \n",
+       "12  Sentence-transformers model for tasks like clu...       1.000  \n",
+       "13                          Large English model, v1.5       1.200  \n",
+       "14                Large general text embeddings model       1.200  \n",
+       "15  Multilingual model, e5-large. Recommend using ...       2.240  "
      ]
     },
     "execution_count": 6,
@@ -256,17 +226,108 @@
    }
   ],
   "source": [
-    "from fastembed import TextEmbedding\n",
-    "import pandas as pd\n",
-    "\n",
-    "pd.set_option(\"display.max_colwidth\", None)\n",
-    "pd.DataFrame(TextEmbedding.list_supported_models())"
+    "supported_models = (\n",
+    "    pd.DataFrame(TextEmbedding.list_supported_models())\n",
+    "    .sort_values(\"size_in_GB\")\n",
+    "    .drop(columns=\"sources\")\n",
+    "    .reset_index(drop=True)\n",
+    ")\n",
+    "supported_models"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Supported Sparse Text Embedding Models"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-30T11:19:01.564291Z",
+     "start_time": "2024-03-30T11:19:01.538768Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>model</th>\n",
+       "      <th>vocab_size</th>\n",
+       "      <th>description</th>\n",
+       "      <th>size_in_GB</th>\n",
+       "      <th>sources</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>prithvida/Splade_PP_en_v1</td>\n",
+       "      <td>30522</td>\n",
+       "      <td>Misspelled version of the model. Retained for ...</td>\n",
+       "      <td>0.532</td>\n",
+       "      <td>{'hf': 'Qdrant/SPLADE_PP_en_v1'}</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>prithivida/Splade_PP_en_v1</td>\n",
+       "      <td>30522</td>\n",
+       "      <td>Independent Implementation of SPLADE++ Model f...</td>\n",
+       "      <td>0.532</td>\n",
+       "      <td>{'hf': 'Qdrant/SPLADE_PP_en_v1'}</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                        model  vocab_size  \\\n",
+       "0   prithvida/Splade_PP_en_v1       30522   \n",
+       "1  prithivida/Splade_PP_en_v1       30522   \n",
+       "\n",
+       "                                         description  size_in_GB  \\\n",
+       "0  Misspelled version of the model. Retained for ...       0.532   \n",
+       "1  Independent Implementation of SPLADE++ Model f...       0.532   \n",
+       "\n",
+       "                            sources  \n",
+       "0  {'hf': 'Qdrant/SPLADE_PP_en_v1'}  \n",
+       "1  {'hf': 'Qdrant/SPLADE_PP_en_v1'}  "
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "pd.DataFrame(SparseTextEmbedding.list_supported_models())"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
-   "display_name": "fst",
+   "display_name": "Python 3.8.18 ('base')",
   "language": "python",
   "name": "python3"
  },
@@ -282,7 +343,12 @@
   "pygments_lexer": "ipython3",
   "version": "3.10.13"
  },
-  "orig_nbformat": 4
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "c4a27af61e455bc18dcf16f5867a2ff0402fa12b01dd0f6ce3a79ae73ad15e91"
+   }
+  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
@@ -3,22 +3,7 @@
  {
   "cell_type": "markdown",
   "metadata": {},
-   "source": [
-    "# Binary Quantization of OpenAI Embedding\n",
-    "---\n",
-    "\n",
-    "In the world of large-scale data retrieval and processing, efficiency is crucial. With the exponential growth of data, the ability to retrieve information quickly and accurately can significantly affect system performance. This blog post explores a technique known as binary quantization applied to OpenAI embeddings, demonstrating how it can enhance **retrieval latency by 20x** or more.\n",
-    "\n",
-    "## What Are OpenAI Embeddings?\n",
-    "OpenAI embeddings are numerical representations of textual information. They transform text into a vector space where semantically similar texts are mapped close together. This mathematical representation enables computers to understand and process human language more effectively.\n",
-    "\n",
-    "## Binary Quantization\n",
-    "Binary quantization is a method which converts continuous numerical values into binary values (0 or 1). It simplifies the data structure, allowing faster computations. Here's a brief overview of the binary quantization process applied to OpenAI embeddings:\n",
-    "\n",
-    "1. **Load Embeddings**: OpenAI embeddings are loaded from parquet files.\n",
-    "2. **Binary Transformation**: The continuous valued vectors are converted into binary form. Here, values greater than 0 are set to 1, and others remain 0.\n",
-    "3. **Comparison & Retrieval**: Binary vectors are used for comparison using logical XOR operations and other efficient algorithms."
-   ]
+   "source": []
  },
  {
   "cell_type": "markdown",
@@ -0,0 +1,377 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Binary Quantization with Qdrant & OpenAI Embedding\n",
+    "\n",
+    "---\n",
+    "In the world of large-scale data retrieval and processing, efficiency is crucial. With the exponential growth of data, the ability to retrieve information quickly and accurately can significantly affect system performance. This blog post explores a technique known as binary quantization applied to OpenAI embeddings, demonstrating how it can enhance **retrieval latency by 20x** or more.\n",
+    "\n",
+    "## What Are OpenAI Embeddings?\n",
+    "OpenAI embeddings are numerical representations of textual information. They transform text into a vector space where semantically similar texts are mapped close together. This mathematical representation enables computers to understand and process human language more effectively.\n",
+    "\n",
+    "## Binary Quantization\n",
+    "Binary quantization is a method which converts continuous numerical values into binary values (0 or 1). It simplifies the data structure, allowing faster computations. Here's a brief overview of the binary quantization process applied to OpenAI embeddings:\n",
+    "\n",
+    "1. **Load Embeddings**: OpenAI embeddings are loaded from parquet files.\n",
+    "2. **Binary Transformation**: The continuous valued vectors are converted into binary form. Here, values greater than 0 are set to 1, and others remain 0.\n",
+    "3. **Comparison & Retrieval**: Binary vectors are used for comparison using logical XOR operations and other efficient algorithms.\n",
+    "\n",
+    "Binary Quantization is a promising approach to improve retrieval speeds and reduce memory footprint of vector search engines. In this notebook we will show how to use Qdrant to perform binary quantization of vectors and perform fast similarity search on the resulting index.\n",
+    "\n",
+    "## Table of Contents\n",
+    "1. Imports\n",
+    "2. Download and Slice Dataset\n",
+    "3. Create Qdrant Collection\n",
+    "4. Indexing\n",
+    "5. Search\n",
+    "\n",
+    "## 1. Imports"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-04-01T16:33:03.013948Z",
+     "start_time": "2024-04-01T16:33:01.019043Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "!pip install qdrant-client pandas dataset --quiet --upgrade"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-04-01T16:33:03.914729Z",
+     "start_time": "2024-04-01T16:33:03.015394Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/joein/work/qdrant/fastembed/venv/lib/python3.11/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "import random\n",
+    "import time\n",
+    "\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from qdrant_client import QdrantClient, models\n",
+    "\n",
+    "random.seed(37)\n",
+    "np.random.seed(37)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 2. Download and Slice Dataset\n",
+    "\n",
+    "We will be using the [dbpedia-entities](https://huggingface.co/datasets/Qdrant/dbpedia-entities-openai3-text-embedding-3-small-1536-100K) dataset from the [HuggingFace Datasets](https://huggingface.co/datasets) library. This contains 100K vectors of 1536 dimensions each"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-04-01T16:33:09.085853Z",
+     "start_time": "2024-04-01T16:33:03.912688Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "100000"
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import datasets\n",
+    "\n",
+    "dataset = datasets.load_dataset(\n",
+    "    \"Qdrant/dbpedia-entities-openai3-text-embedding-3-small-1536-100K\", split=\"train\"\n",
+    ")\n",
+    "len(dataset)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-04-01T16:33:09.176212Z",
+     "start_time": "2024-04-01T16:33:09.084550Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "True"
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "client = QdrantClient(\n",
+    "    prefer_grpc=True,\n",
+    ")\n",
+    "\n",
+    "collection_name = \"binary-quantization\"\n",
+    "client.recreate_collection(\n",
+    "    collection_name=collection_name,\n",
+    "    vectors_config=models.VectorParams(\n",
+    "        size=1536,\n",
+    "        distance=models.Distance.DOT,\n",
+    "        on_disk=True,\n",
+    "    ),\n",
+    "    quantization_config=models.BinaryQuantization(\n",
+    "        binary=models.BinaryQuantizationConfig(always_ram=True),\n",
+    "    ),\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-04-01T16:34:13.383986Z",
+     "start_time": "2024-04-01T16:33:09.175725Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "def iter_dataset(dataset):\n",
+    "    for point in dataset:\n",
+    "        yield point[\"openai\"], {\"text\": point[\"text\"]}\n",
+    "\n",
+    "\n",
+    "vectors, payload = zip(*iter_dataset(dataset))\n",
+    "client.upload_collection(\n",
+    "    collection_name=collection_name,\n",
+    "    vectors=vectors,\n",
+    "    payload=payload,\n",
+    "    parallel=max(1, (os.cpu_count() // 2)),\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-04-01T16:34:13.390886Z",
+     "start_time": "2024-04-01T16:34:13.385961Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "{'status': <CollectionStatus.YELLOW: 'yellow'>,\n 'optimizer_status': <OptimizersStatusOneOf.OK: 'ok'>,\n 'vectors_count': 116640,\n 'indexed_vectors_count': 43520,\n 'points_count': 116640,\n 'segments_count': 6,\n 'config': {'params': {'vectors': {'size': 1536,\n    'distance': <Distance.DOT: 'Dot'>,\n    'hnsw_config': None,\n    'quantization_config': None,\n    'on_disk': True},\n   'shard_number': 1,\n   'sharding_method': None,\n   'replication_factor': 1,\n   'write_consistency_factor': 1,\n   'read_fan_out_factor': None,\n   'on_disk_payload': True,\n   'sparse_vectors': None},\n  'hnsw_config': {'m': 16,\n   'ef_construct': 100,\n   'full_scan_threshold': 10000,\n   'max_indexing_threads': 0,\n   'on_disk': False,\n   'payload_m': None},\n  'optimizer_config': {'deleted_threshold': 0.2,\n   'vacuum_min_vector_number': 1000,\n   'default_segment_number': 0,\n   'max_segment_size': None,\n   'memmap_threshold': None,\n   'indexing_threshold': 20000,\n   'flush_interval_sec': 5,\n   'max_optimization_threads': None},\n  'wal_config': {'wal_capacity_mb': 32, 'wal_segments_ahead': 0},\n  'quantization_config': {'binary': {'always_ram': True}}},\n 'payload_schema': {}}"
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "collection_info = client.get_collection(collection_name=f\"{collection_name}\")\n",
+    "collection_info.dict()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Oversampling vs Recall\n",
+    "\n",
+    "### Preparing a query dataset\n",
+    "\n",
+    "For the purpose of this illustration, we'll take a few vectors which we know are already in the index and query them. We should get the same vectors back as results from the Qdrant index. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-04-01T16:34:13.453626Z",
+     "start_time": "2024-04-01T16:34:13.391567Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "[89391,\n 79659,\n 12006,\n 80978,\n 87219,\n 97885,\n 83155,\n 67504,\n 4645,\n 82711,\n 48395,\n 57375,\n 69208,\n 14136,\n 89515,\n 59880,\n 78730,\n 36952,\n 49620,\n 96486,\n 55473,\n 58179,\n 18926,\n 6489,\n 11931,\n 54146,\n 9850,\n 71259,\n 37825,\n 47331,\n 84964,\n 92399,\n 56669,\n 77042,\n 73744,\n 47993,\n 83780,\n 92429,\n 75114,\n 4463,\n 69030,\n 81185,\n 27950,\n 66217,\n 54652,\n 8260,\n 1151,\n 993,\n 85954,\n 66863,\n 47303,\n 8992,\n 92688,\n 76030,\n 29472,\n 3077,\n 42454,\n 46120,\n 69140,\n 20877,\n 2844,\n 95423,\n 1770,\n 28568,\n 96448,\n 94227,\n 40837,\n 91684,\n 29785,\n 66936,\n 85121,\n 39546,\n 81910,\n 5514,\n 37068,\n 35731,\n 93990,\n 26685,\n 63076,\n 18762,\n 27922,\n 34916,\n 80976,\n 83189,\n 6328,\n 57508,\n 58860,\n 13758,\n 72976,\n 85030,\n 332,\n 34963,\n 85009,\n 31344,\n 11560,\n 58108,\n 85163,\n 17064,\n 44712,\n 45962]"
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "query_indices = random.sample(range(len(dataset)), 100)\n",
+    "query_dataset = dataset[query_indices]\n",
+    "query_indices"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-04-01T16:34:13.453928Z",
+     "start_time": "2024-04-01T16:34:13.452405Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "## Add Gaussian noise to any vector\n",
+    "\n",
+    "\n",
+    "def add_noise(vector, noise=0.05):\n",
+    "    return vector + noise * np.random.randn(*vector.shape)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-04-01T16:34:13.457839Z",
+     "start_time": "2024-04-01T16:34:13.455431Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "def correct(results, text):\n",
+    "    return text in [x.payload[\"text\"] for x in results]\n",
+    "\n",
+    "\n",
+    "def count_correct(query_dataset, limit=1, oversampling=1, rescore=False):\n",
+    "    correct_results = 0\n",
+    "    for query_vector, text in zip(query_dataset[\"openai\"], query_dataset[\"text\"]):\n",
+    "        results = client.search(\n",
+    "            collection_name=collection_name,\n",
+    "            query_vector=add_noise(np.array(query_vector)),\n",
+    "            limit=limit,\n",
+    "            search_params=models.SearchParams(\n",
+    "                quantization=models.QuantizationSearchParams(\n",
+    "                    rescore=rescore,\n",
+    "                    oversampling=oversampling,\n",
+    "                )\n",
+    "            ),\n",
+    "        )\n",
+    "        correct_results += correct(results, text)\n",
+    "    return correct_results"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-04-01T16:40:48.347002Z",
+     "start_time": "2024-04-01T16:40:42.228551Z"
+    },
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "limit_grid = [1, 3, 10, 20, 50]\n",
+    "oversampling_grid = [1.0, 3.0, 5.0]\n",
+    "rescore_grid = [False, True]\n",
+    "results = []\n",
+    "\n",
+    "for limit in limit_grid:\n",
+    "    for oversampling in oversampling_grid:\n",
+    "        for rescore in rescore_grid:\n",
+    "            start = time.perf_counter()\n",
+    "            correct_results = count_correct(\n",
+    "                query_dataset, limit=limit, oversampling=oversampling, rescore=rescore\n",
+    "            )\n",
+    "            end = time.perf_counter()\n",
+    "            results.append(\n",
+    "                {\n",
+    "                    \"limit\": limit,\n",
+    "                    \"oversampling\": oversampling,\n",
+    "                    \"candidates\": int(oversampling * limit),\n",
+    "                    \"rescore\": rescore,\n",
+    "                    \"accuracy\": correct_results / 100,\n",
+    "                    \"total queries\": len(query_dataset[\"text\"]),\n",
+    "                    \"time\": end - start,\n",
+    "                }\n",
+    "            )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-04-01T16:41:55.445405Z",
+     "start_time": "2024-04-01T16:41:55.442687Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>candidates</th>\n      <th>rescore</th>\n      <th>accuracy</th>\n      <th>time</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>1</td>\n      <td>False</td>\n      <td>0.90</td>\n      <td>0.221826</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>1</td>\n      <td>True</td>\n      <td>0.91</td>\n      <td>0.134167</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>3</td>\n      <td>False</td>\n      <td>0.88</td>\n      <td>0.115299</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>3</td>\n      <td>True</td>\n      <td>0.97</td>\n      <td>0.209320</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>5</td>\n      <td>False</td>\n      <td>0.84</td>\n      <td>0.154485</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>5</td>\n      <td>True</td>\n      <td>0.91</td>\n      <td>0.124424</td>\n    </tr>\n    <tr>\n      <th>6</th>\n      <td>3</td>\n      <td>False</td>\n      <td>0.99</td>\n      <td>0.121695</td>\n    </tr>\n    <tr>\n      <th>7</th>\n      <td>3</td>\n      <td>True</td>\n      <td>0.96</td>\n      <td>0.123257</td>\n    </tr>\n    <tr>\n      <th>8</th>\n      <td>9</td>\n      <td>False</td>\n      <td>0.94</td>\n      <td>0.119629</td>\n    </tr>\n    <tr>\n      <th>9</th>\n      <td>9</td>\n      <td>True</td>\n      <td>0.98</td>\n      <td>0.119372</td>\n    </tr>\n    <tr>\n      <th>10</th>\n      <td>15</td>\n      <td>False</td>\n      <td>0.90</td>\n      <td>0.121621</td>\n    </tr>\n    <tr>\n      <th>11</th>\n      <td>15</td>\n      <td>True</td>\n      <td>0.97</td>\n      <td>0.125466</td>\n    </tr>\n    <tr>\n      <th>12</th>\n      <td>10</td>\n      <td>False</td>\n      <td>0.93</td>\n      <td>0.135910</td>\n    </tr>\n    <tr>\n      <th>13</th>\n      <td>10</td>\n      <td>True</td>\n      <td>0.95</td>\n      <td>0.138135</td>\n    </tr>\n    <tr>\n      <th>14</th>\n      <td>30</td>\n      <td>False</td>\n      <td>0.94</td>\n      <td>0.177928</td>\n    </tr>\n    <tr>\n      <th>15</th>\n      <td>30</td>\n      <td>True</td>\n      <td>0.98</td>\n      <td>0.254588</td>\n    </tr>\n    <tr>\n      <th>16</th>\n      <td>50</td>\n      <td>False</td>\n      <td>0.94</td>\n      <td>0.268659</td>\n    </tr>\n    <tr>\n      <th>17</th>\n      <td>50</td>\n      <td>True</td>\n      <td>0.96</td>\n      <td>0.269792</td>\n    </tr>\n    <tr>\n      <th>18</th>\n      <td>20</td>\n      <td>False</td>\n      <td>0.96</td>\n      <td>0.249941</td>\n    </tr>\n    <tr>\n      <th>19</th>\n      <td>20</td>\n      <td>True</td>\n      <td>0.96</td>\n      <td>0.247138</td>\n    </tr>\n    <tr>\n      <th>20</th>\n      <td>60</td>\n      <td>False</td>\n      <td>0.97</td>\n      <td>0.251301</td>\n    </tr>\n    <tr>\n      <th>21</th>\n      <td>60</td>\n      <td>True</td>\n      <td>0.98</td>\n      <td>0.256504</td>\n    </tr>\n    <tr>\n      <th>22</th>\n      <td>100</td>\n      <td>False</td>\n      <td>0.98</td>\n      <td>0.270049</td>\n    </tr>\n    <tr>\n      <th>23</th>\n      <td>100</td>\n      <td>True</td>\n      <td>0.97</td>\n      <td>0.248972</td>\n    </tr>\n    <tr>\n      <th>24</th>\n      <td>50</td>\n      <td>False</td>\n      <td>0.97</td>\n      <td>0.306356</td>\n    </tr>\n    <tr>\n      <th>25</th>\n      <td>50</td>\n      <td>True</td>\n      <td>0.98</td>\n      <td>0.257544</td>\n    </tr>\n    <tr>\n      <th>26</th>\n      <td>150</td>\n      <td>False</td>\n      <td>0.98</td>\n      <td>0.238811</td>\n    </tr>\n    <tr>\n      <th>27</th>\n      <td>150</td>\n      <td>True</td>\n      <td>0.99</td>\n      <td>0.263939</td>\n    </tr>\n    <tr>\n      <th>28</th>\n      <td>250</td>\n      <td>False</td>\n      <td>0.99</td>\n      <td>0.256558</td>\n    </tr>\n    <tr>\n      <th>29</th>\n      <td>250</td>\n      <td>True</td>\n      <td>1.00</td>\n      <td>0.335823</td>\n    </tr>\n  </tbody>\n</table>\n</div>",
+      "text/plain": "    candidates  rescore  accuracy      time\n0            1    False      0.90  0.221826\n1            1     True      0.91  0.134167\n2            3    False      0.88  0.115299\n3            3     True      0.97  0.209320\n4            5    False      0.84  0.154485\n5            5     True      0.91  0.124424\n6            3    False      0.99  0.121695\n7            3     True      0.96  0.123257\n8            9    False      0.94  0.119629\n9            9     True      0.98  0.119372\n10          15    False      0.90  0.121621\n11          15     True      0.97  0.125466\n12          10    False      0.93  0.135910\n13          10     True      0.95  0.138135\n14          30    False      0.94  0.177928\n15          30     True      0.98  0.254588\n16          50    False      0.94  0.268659\n17          50     True      0.96  0.269792\n18          20    False      0.96  0.249941\n19          20     True      0.96  0.247138\n20          60    False      0.97  0.251301\n21          60     True      0.98  0.256504\n22         100    False      0.98  0.270049\n23         100     True      0.97  0.248972\n24          50    False      0.97  0.306356\n25          50     True      0.98  0.257544\n26         150    False      0.98  0.238811\n27         150     True      0.99  0.263939\n28         250    False      0.99  0.256558\n29         250     True      1.00  0.335823"
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df = pd.DataFrame(results)\n",
+    "df[[\"candidates\", \"rescore\", \"accuracy\", \"time\"]]\n",
+    "# df.to_csv(\"candidates-rescore-time.csv\", index=False)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
@@ -39,15 +39,7 @@
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\u001b[32m2024-02-07 22:20:57.013\u001b[0m | \u001b[33m\u001b[1mWARNING \u001b[0m | \u001b[36mfastembed.embedding\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m7\u001b[0m - \u001b[33m\u001b[1mDefaultEmbedding, FlagEmbedding, JinaEmbedding are deprecated. Use TextEmbedding instead.\u001b[0m\n"
-     ]
-    }
-   ],
+   "outputs": [],
   "source": [
    "from typing import List\n",
    "import numpy as np\n",
@@ -92,7 +84,7 @@
    "    \"His life has been depicted in various films, TV shows, and books\",\n",
    "]\n",
    "# Initialize the DefaultEmbedding class with the desired parameters\n",
-    "embedding_model = TextEmbedding(model_name=\"BAAI/bge-small-en\", max_length=512)\n",
+    "embedding_model = TextEmbedding(model_name=\"BAAI/bge-small-en\")\n",
    "\n",
    "# We'll use the passage_embed method to get the embeddings for the documents\n",
    "embeddings: List[np.ndarray] = list(\n",
@@ -140,7 +132,7 @@
    {
     "data": {
      "text/plain": [
-       "(array([-0.04393955,  0.04452892, -0.00760788, -0.03399807,  0.01951348],\n",
+       "(array([-0.06002192,  0.04322132, -0.00545516, -0.04419701, -0.00542277],\n",
       "       dtype=float32),\n",
       " array([-0.06002192,  0.04322132, -0.00545516, -0.04419701, -0.00542277],\n",
       "       dtype=float32))"
@@ -183,7 +175,7 @@
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
-   "version": "3.11.5"
+   "version": "3.10.13"
  },
  "orig_nbformat": 4
 },
@@ -1,3 +1,7 @@
-from fastembed.text.text_embedding import TextEmbedding
+import importlib.metadata

-__all__ = ["TextEmbedding"]
+from fastembed.text import TextEmbedding
+from fastembed.sparse import SparseTextEmbedding, SparseEmbedding
+
+__version__ = importlib.metadata.version("fastembed")
+__all__ = ["TextEmbedding", "SparseTextEmbedding", "SparseEmbedding"]
@@ -1,31 +1,4 @@
-import os
-import shutil
-import tarfile
-from pathlib import Path
-from typing import List, Optional, Dict, Any
-
-import requests
-from huggingface_hub import snapshot_download
-from huggingface_hub.utils import RepositoryNotFoundError
-from tqdm import tqdm
-from loguru import logger
-
-
-def locate_model_file(model_dir: Path, file_names: List[str]) -> Path:
-    """
-    Find model path for both TransformerJS style `onnx`  subdirectory structure and direct model weights structure used
-    by Optimum and Qdrant
-    """
-    if not model_dir.is_dir():
-        raise ValueError(f"Provided model path '{model_dir}' is not a directory.")
-
-    for file_name in file_names:
-        file_paths = [path for path in model_dir.rglob(file_name) if path.is_file()]
-
-        if file_paths:
-            return file_paths[0]
-
-    raise ValueError(f"Could not find either of {', '.join(file_names)} in {model_dir}")
+from typing import List, Dict, Any


 class ModelManagement:
@@ -53,174 +26,7 @@ class ModelManagement:
            Dict[str, Any]: The model description.
        """
        for model in cls.list_supported_models():
-            if model_name == model["model"]:
+            if model_name.lower() == model["model"].lower():
                return model

        raise ValueError(f"Model {model_name} is not supported in {cls.__name__}.")
-
-    @classmethod
-    def download_file_from_gcs(cls, url: str, output_path: str, show_progress: bool = True) -> str:
-        """
-        Downloads a file from Google Cloud Storage.
-
-        Args:
-            url (str): The URL to download the file from.
-            output_path (str): The path to save the downloaded file to.
-            show_progress (bool, optional): Whether to show a progress bar. Defaults to True.
-
-        Returns:
-            str: The path to the downloaded file.
-        """
-
-        if os.path.exists(output_path):
-            return output_path
-        response = requests.get(url, stream=True)
-
-        # Handle HTTP errors
-        if response.status_code == 403:
-            raise PermissionError(
-                "Authentication Error: You do not have permission to access this resource. "
-                "Please check your credentials."
-            )
-
-        # Get the total size of the file
-        total_size_in_bytes = int(response.headers.get("content-length", 0))
-
-        # Warn if the total size is zero
-        if total_size_in_bytes == 0:
-            print(f"Warning: Content-length header is missing or zero in the response from {url}.")
-
-        show_progress = total_size_in_bytes and show_progress
-
-        with tqdm(total=total_size_in_bytes, unit="iB", unit_scale=True, disable=not show_progress) as progress_bar:
-            with open(output_path, "wb") as file:
-                for chunk in response.iter_content(chunk_size=1024):
-                    if chunk:  # Filter out keep-alive new chunks
-                        progress_bar.update(len(chunk))
-                        file.write(chunk)
-        return output_path
-
-    @classmethod
-    def download_files_from_huggingface(cls, hf_source_repo: str, cache_dir: Optional[str] = None) -> str:
-        """
-        Downloads a model from HuggingFace Hub.
-        Args:
-            hf_source_repo (str): Name of the model on HuggingFace Hub, e.g. "qdrant/all-MiniLM-L6-v2-onnx".
-            cache_dir (Optional[str]): The path to the cache directory.
-        Returns:
-            Path: The path to the model directory.
-        """
-
-        return snapshot_download(
-            repo_id=hf_source_repo,
-            ignore_patterns=["model.safetensors", "pytorch_model.bin"],
-            cache_dir=cache_dir,
-        )
-
-    @classmethod
-    def decompress_to_cache(cls, targz_path: str, cache_dir: str):
-        """
-        Decompresses a .tar.gz file to a cache directory.
-
-        Args:
-            targz_path (str): Path to the .tar.gz file.
-            cache_dir (str): Path to the cache directory.
-
-        Returns:
-            cache_dir (str): Path to the cache directory.
-        """
-        # Check if targz_path exists and is a file
-        if not os.path.isfile(targz_path):
-            raise ValueError(f"{targz_path} does not exist or is not a file.")
-
-        # Check if targz_path is a .tar.gz file
-        if not targz_path.endswith(".tar.gz"):
-            raise ValueError(f"{targz_path} is not a .tar.gz file.")
-
-        try:
-            # Open the tar.gz file
-            with tarfile.open(targz_path, "r:gz") as tar:
-                # Extract all files into the cache directory
-                tar.extractall(path=cache_dir)
-        except tarfile.TarError as e:
-            # If any error occurs while opening or extracting the tar.gz file,
-            # delete the cache directory (if it was created in this function)
-            # and raise the error again
-            if "tmp" in cache_dir:
-                shutil.rmtree(cache_dir)
-            raise ValueError(f"An error occurred while decompressing {targz_path}: {e}")
-
-        return cache_dir
-
-    @classmethod
-    def retrieve_model_gcs(cls, model_name: str, source_url: str, cache_dir: str) -> Path:
-        fast_model_name = f"fast-{model_name.split('/')[-1]}"
-
-        cache_tmp_dir = Path(cache_dir) / "tmp"
-        model_tmp_dir = cache_tmp_dir / fast_model_name
-        model_dir = Path(cache_dir) / fast_model_name
-
-        # check if the model_dir and the model files are both present for macOS
-        if model_dir.exists() and len(list(model_dir.glob("*"))) > 0:
-            return model_dir
-
-        if model_tmp_dir.exists():
-            shutil.rmtree(model_tmp_dir)
-
-        cache_tmp_dir.mkdir(parents=True, exist_ok=True)
-
-        model_tar_gz = Path(cache_dir) / f"{fast_model_name}.tar.gz"
-
-        cls.download_file_from_gcs(
-            source_url,
-            output_path=str(model_tar_gz),
-        )
-
-        cls.decompress_to_cache(targz_path=str(model_tar_gz), cache_dir=str(cache_tmp_dir))
-        assert model_tmp_dir.exists(), f"Could not find {model_tmp_dir} in {cache_tmp_dir}"
-
-        model_tar_gz.unlink()
-        # Rename from tmp to final name is atomic
-        model_tmp_dir.rename(model_dir)
-
-        return model_dir
-
-    @classmethod
-    def download_model(cls, model: Dict[str, Any], cache_dir: Path) -> Path:
-        """
-        Downloads a model from HuggingFace Hub or Google Cloud Storage.
-
-        Args:
-            model (Dict[str, Any]): The model description.
-                Example:
-                ```
-                {
-                    "model": "BAAI/bge-base-en-v1.5",
-                    "dim": 768,
-                    "description": "Base English model, v1.5",
-                    "size_in_GB": 0.44,
-                    "sources": {
-                        "url": "https://storage.googleapis.com/qdrant-fastembed/fast-bge-base-en-v1.5.tar.gz",
-                        "hf": "qdrant/bge-base-en-v1.5-onnx-q",
-                    }
-                }
-                ```
-            cache_dir (str): The path to the cache directory.
-
-        Returns:
-            Path: The path to the downloaded model directory.
-        """
-
-        hf_source = model.get("sources", {}).get("hf")
-        url_source = model.get("sources", {}).get("url")
-
-        if hf_source:
-            try:
-                return Path(cls.download_files_from_huggingface(hf_source, cache_dir=str(cache_dir)))
-            except (EnvironmentError, RepositoryNotFoundError, ValueError) as e:
-                logger.error(f"Could not download model from HuggingFace: {e}" "Falling back to other sources.")
-
-        if url_source:
-            return cls.retrieve_model_gcs(model["model"], url_source, str(cache_dir))
-
-        raise ValueError(f"Could not download model {model['model']} from any source.")
@@ -3,24 +3,25 @@ from pathlib import Path

 import numpy as np
 from tokenizers import Tokenizer, AddedToken
+from huggingface_hub import hf_hub_download


-def load_tokenizer(model_dir: Path, max_length: int = 512) -> Tokenizer:
-    config_path = model_dir / "config.json"
-    if not config_path.exists():
-        raise ValueError(f"Could not find config.json in {model_dir}")
+def load_tokenizer(repo_id: str, cache_dir: Path, max_length: int = 512) -> Tokenizer:
+    config_path = hf_hub_download(
+        repo_id=repo_id, filename="config.json", cache_dir=str(cache_dir)
+    )

-    tokenizer_path = model_dir / "tokenizer.json"
-    if not tokenizer_path.exists():
-        raise ValueError(f"Could not find tokenizer.json in {model_dir}")
+    tokenizer_path = hf_hub_download(
+        repo_id=repo_id, filename="tokenizer.json", cache_dir=str(cache_dir)
+    )

-    tokenizer_config_path = model_dir / "tokenizer_config.json"
-    if not tokenizer_config_path.exists():
-        raise ValueError(f"Could not find tokenizer_config.json in {model_dir}")
+    tokenizer_config_path = hf_hub_download(
+        repo_id=repo_id, filename="tokenizer_config.json", cache_dir=str(cache_dir)
+    )

-    tokens_map_path = model_dir / "special_tokens_map.json"
-    if not tokens_map_path.exists():
-        raise ValueError(f"Could not find special_tokens_map.json in {model_dir}")
+    tokens_map_path = hf_hub_download(
+        repo_id=repo_id, filename="special_tokens_map.json", cache_dir=str(cache_dir)
+    )

    with open(str(config_path)) as config_file:
        config = json.load(config_file)
@@ -33,7 +34,9 @@ def load_tokenizer(model_dir: Path, max_length: int = 512) -> Tokenizer:

    tokenizer = Tokenizer.from_file(str(tokenizer_path))
    tokenizer.enable_truncation(max_length=min(tokenizer_config["model_max_length"], max_length))
-    tokenizer.enable_padding(pad_id=config.get("pad_token_id", 0), pad_token=tokenizer_config["pad_token"])
+    tokenizer.enable_padding(
+        pad_id=config.get("pad_token_id", 0), pad_token=tokenizer_config["pad_token"]
+    )

    for token in tokens_map.values():
        if isinstance(token, str):
@@ -6,11 +6,12 @@ from typing import Any, Dict, Generic, Iterable, List, Optional, Tuple, Type, Ty
 import numpy as np
 import onnxruntime as ort

-from fastembed.common.model_management import locate_model_file
 from fastembed.common.models import load_tokenizer
 from fastembed.common.utils import iter_batch
 from fastembed.parallel_processor import ParallelWorkerPool, Worker

+from huggingface_hub import hf_hub_download
+
 # Holds type of the embedding result
 T = TypeVar("T")

@@ -34,21 +35,40 @@ class OnnxModel(Generic[T]):
        """
        return onnx_input

-    def load_onnx_model(self, model_dir: Path, threads: Optional[int], max_length: int) -> None:
-        model_path = locate_model_file(model_dir, ["model.onnx", "model_optimized.onnx"])
+    def load_onnx_model(
+        self, model_description: dict, threads: Optional[int], cache_dir: Path
+    ) -> None:
+        repo_id = model_description["sources"]["hf"]
+        model_file = model_description.get("model_file", "model.onnx")
+
+        # Some models require additional repo files.
+        # For eg: intfloat/multilingual-e5-large requires the model.onnx_data file.
+        # These can be specified within the "additional_files" option when describing the model properties
+        if additional_files := model_description.get("additional_files"):
+            for file in additional_files:
+                hf_hub_download(repo_id=repo_id, filename=file, cache_dir=str(cache_dir))
+
+        model_path = hf_hub_download(
+            repo_id=repo_id, filename=model_file, cache_dir=str(cache_dir)
+        )

        # List of Execution Providers: https://onnxruntime.ai/docs/execution-providers
        onnx_providers = ["CPUExecutionProvider"]

        so = ort.SessionOptions()
+        if os.getenv("SLURM_JOB_ID") is not None:
+            so.intra_op_num_threads = int(os.getenv("SLURM_CPUS_ON_NODE"))
+            so.inter_op_num_threads = int(os.getenv("SLURM_CPUS_ON_NODE"))
        so.graph_optimization_level = ort.GraphOptimizationLevel.ORT_ENABLE_ALL

        if threads is not None:
            so.intra_op_num_threads = threads
            so.inter_op_num_threads = threads

-        self.tokenizer = load_tokenizer(model_dir=model_dir, max_length=max_length)
-        self.model = ort.InferenceSession(str(model_path), providers=onnx_providers, sess_options=so)
+        self.tokenizer = load_tokenizer(repo_id, cache_dir)
+        self.model = ort.InferenceSession(
+            str(model_path), providers=onnx_providers, sess_options=so
+        )

    def onnx_embed(self, documents: List[str]) -> Tuple[np.ndarray, np.ndarray]:
        encoded = self.tokenizer.encode_batch(documents)
@@ -58,7 +78,9 @@ class OnnxModel(Generic[T]):
        onnx_input = {
            "input_ids": np.array(input_ids, dtype=np.int64),
            "attention_mask": np.array(attention_mask, dtype=np.int64),
-            "token_type_ids": np.array([np.zeros(len(e), dtype=np.int64) for e in input_ids], dtype=np.int64),
+            "token_type_ids": np.array(
+                [np.zeros(len(e), dtype=np.int64) for e in input_ids], dtype=np.int64
+            ),
        }

        onnx_input = self._preprocess_onnx_input(onnx_input)
@@ -97,7 +119,9 @@ class OnnxModel(Generic[T]):
                "model_name": model_name,
                "cache_dir": cache_dir,
            }
-            pool = ParallelWorkerPool(parallel, self._get_worker_class(), start_method=start_method)
+            pool = ParallelWorkerPool(
+                parallel, self._get_worker_class(), start_method=start_method
+            )
            for batch in pool.ordered_map(iter_batch(documents, batch_size), **params):
                yield from self._post_process_onnx_output(batch)

@@ -2,10 +2,11 @@ from typing import Optional

 from loguru import logger

-from fastembed.text.text_embedding import TextEmbedding
+from fastembed import TextEmbedding

 logger.warning(
-    "DefaultEmbedding, FlagEmbedding, JinaEmbedding are deprecated." "Use from fastembed import TextEmbedding instead."
+    "DefaultEmbedding, FlagEmbedding, JinaEmbedding are deprecated."
+    "Use from fastembed import TextEmbedding instead."
 )

 DefaultEmbedding = TextEmbedding
@@ -128,7 +128,9 @@ class ParallelWorkerPool:
                yield buffer.pop(next_expected)
                next_expected += 1

-    def semi_ordered_map(self, stream: Iterable[Any], *args: Any, **kwargs: Any) -> Iterable[Tuple[int, Any]]:
+    def semi_ordered_map(
+        self, stream: Iterable[Any], *args: Any, **kwargs: Any
+    ) -> Iterable[Tuple[int, Any]]:
        try:
            self.start(**kwargs)

@@ -0,0 +1,4 @@
+from fastembed.sparse.sparse_embedding_base import SparseEmbedding
+from fastembed.sparse.sparse_text_embedding import SparseTextEmbedding
+
+__all__ = ["SparseEmbedding", "SparseTextEmbedding"]
@@ -22,7 +22,13 @@ class SparseEmbedding:


 class SparseTextEmbeddingBase(ModelManagement):
-    def __init__(self, model_name: str, cache_dir: Optional[str] = None, threads: Optional[int] = None, **kwargs):
+    def __init__(
+        self,
+        model_name: str,
+        cache_dir: Optional[str] = None,
+        threads: Optional[int] = None,
+        **kwargs,
+    ):
        self.model_name = model_name
        self.cache_dir = cache_dir
        self.threads = threads
@@ -48,7 +48,7 @@ class SparseTextEmbedding(SparseTextEmbeddingBase):

        for EMBEDDING_MODEL_TYPE in self.EMBEDDINGS_REGISTRY:
            supported_models = EMBEDDING_MODEL_TYPE.list_supported_models()
-            if any(model_name == model["model"] for model in supported_models):
+            if any(model_name.lower() == model["model"].lower() for model in supported_models):
                self.model = EMBEDDING_MODEL_TYPE(model_name, cache_dir, threads, **kwargs)
                return

@@ -1,4 +1,4 @@
-from typing import Any, Dict, Iterable, List, Optional, Tuple, Union
+from typing import Any, Dict, Iterable, List, Optional, Tuple, Union, Type

 import numpy as np

@@ -8,30 +8,42 @@ from fastembed.sparse.sparse_embedding_base import SparseEmbedding, SparseTextEm

 supported_splade_models = [
    {
-        "model": "prithvida/SPLADE_PP_en_v1",
+        "model": "prithvida/Splade_PP_en_v1",
+        "vocab_size": 30522,
+        "description": "Misspelled version of the model. Retained for backward compatibility. Independent Implementation of SPLADE++ Model for English",
+        "size_in_GB": 0.532,
+        "sources": {
+            "hf": "Qdrant/SPLADE_PP_en_v1",
+        },
+        "model_file": "model.onnx",
+    },
+    {
+        "model": "prithivida/Splade_PP_en_v1",
        "vocab_size": 30522,
        "description": "Independent Implementation of SPLADE++ Model for English",
        "size_in_GB": 0.532,
        "sources": {
            "hf": "Qdrant/SPLADE_PP_en_v1",
        },
+        "model_file": "model.onnx",
    },
 ]


 class SpladePP(SparseTextEmbeddingBase, OnnxModel[SparseEmbedding]):
    @classmethod
-    def _post_process_onnx_output(cls, output: Tuple[np.ndarray, np.ndarray]) -> Iterable[SparseEmbedding]:
+    def _post_process_onnx_output(
+        cls, output: Tuple[np.ndarray, np.ndarray]
+    ) -> Iterable[SparseEmbedding]:
        logits, attention_mask = output
        relu_log = np.log(1 + np.maximum(logits, 0))

        weighted_log = relu_log * np.expand_dims(attention_mask, axis=-1)

-        max_val = np.max(weighted_log, axis=1)
+        scores = np.max(weighted_log, axis=1)

        # Score matrix of shape (batch_size, vocab_size)
        # Most of the values are 0, only a few are non-zero
-        scores = np.squeeze(max_val)
        for row_scores in scores:
            indices = row_scores.nonzero()[0]
            scores = row_scores[indices]
@@ -67,14 +79,11 @@ class SpladePP(SparseTextEmbeddingBase, OnnxModel[SparseEmbedding]):

        super().__init__(model_name, cache_dir, threads, **kwargs)

-        self.model_name = model_name
-        self._model_description = self._get_model_description(model_name)
-
-        self._cache_dir = define_cache_dir(cache_dir)
-        self._model_dir = self.download_model(self._model_description, self._cache_dir)
-        self._max_length = 512
-
-        self.load_onnx_model(self._model_dir, self.threads, self._max_length)
+        self.load_onnx_model(
+            self._get_model_description(model_name),
+            threads,
+            define_cache_dir(cache_dir),
+        )

    def embed(
        self,
@@ -100,12 +109,16 @@ class SpladePP(SparseTextEmbeddingBase, OnnxModel[SparseEmbedding]):
        """
        yield from self._embed_documents(
            model_name=self.model_name,
-            cache_dir=str(self._cache_dir),
+            cache_dir=str(self.cache_dir),
            documents=documents,
            batch_size=batch_size,
            parallel=parallel,
        )

+    @classmethod
+    def _get_worker_class(cls) -> Type[EmbeddingWorker]:
+        return SpladePPEmbeddingWorker
+

 class SpladePPEmbeddingWorker(EmbeddingWorker):
    def init_embedding(
@@ -0,0 +1,3 @@
+from fastembed.text.text_embedding import TextEmbedding
+
+__all__ = ["TextEmbedding"]
@@ -12,18 +12,20 @@ supported_multilingual_e5_models = [
        "description": "Multilingual model, e5-large. Recommend using this model for non-English languages",
        "size_in_GB": 2.24,
        "sources": {
-            "url": "https://storage.googleapis.com/qdrant-fastembed/fast-multilingual-e5-large.tar.gz",
            "hf": "qdrant/multilingual-e5-large-onnx",
        },
+        "model_file": "model.onnx",
+        "additional_files": ["model.onnx_data"],
    },
    {
        "model": "sentence-transformers/paraphrase-multilingual-mpnet-base-v2",
        "dim": 768,
        "description": "Sentence-transformers model for tasks like clustering or semantic search",
-        "size_in_GB": 1.11,
+        "size_in_GB": 1.00,
        "sources": {
            "hf": "xenova/paraphrase-multilingual-mpnet-base-v2",
        },
+        "model_file": "onnx/model.onnx",
    },
 ]

@@ -11,15 +11,17 @@ supported_jina_models = [
        "model": "jinaai/jina-embeddings-v2-base-en",
        "dim": 768,
        "description": "English embedding model supporting 8192 sequence length",
-        "size_in_GB": 0.55,
+        "size_in_GB": 0.52,
        "sources": {"hf": "xenova/jina-embeddings-v2-base-en"},
+        "model_file": "onnx/model.onnx",
    },
    {
        "model": "jinaai/jina-embeddings-v2-small-en",
        "dim": 512,
        "description": "English embedding model supporting 8192 sequence length",
-        "size_in_GB": 0.13,
+        "size_in_GB": 0.12,
        "sources": {"hf": "xenova/jina-embeddings-v2-small-en"},
+        "model_file": "onnx/model.onnx",
    },
 ]

@@ -49,7 +51,9 @@ class JinaOnnxEmbedding(OnnxTextEmbedding):
        return supported_jina_models

    @classmethod
-    def _post_process_onnx_output(cls, output: Tuple[np.ndarray, np.ndarray]) -> Iterable[np.ndarray]:
+    def _post_process_onnx_output(
+        cls, output: Tuple[np.ndarray, np.ndarray]
+    ) -> Iterable[np.ndarray]:
        embeddings, attn_mask = output
        return normalize(cls.mean_pooling(embeddings, attn_mask)).astype(np.float32)

@@ -12,137 +12,132 @@ supported_onnx_models = [
        "model": "BAAI/bge-base-en",
        "dim": 768,
        "description": "Base English model",
-        "size_in_GB": 0.5,
+        "size_in_GB": 0.42,
        "sources": {
-            "url": "https://storage.googleapis.com/qdrant-fastembed/fast-bge-base-en.tar.gz",
+            "hf": "yashvardhan7/bge-base-en-onnx",
        },
+        "model_file": "onnx/model.onnx",
    },
    {
        "model": "BAAI/bge-base-en-v1.5",
        "dim": 768,
        "description": "Base English model, v1.5",
-        "size_in_GB": 0.44,
+        "size_in_GB": 0.21,
        "sources": {
-            "url": "https://storage.googleapis.com/qdrant-fastembed/fast-bge-base-en-v1.5.tar.gz",
            "hf": "qdrant/bge-base-en-v1.5-onnx-q",
        },
-    },
-    {
-        "model": "BAAI/bge-large-en-v1.5-quantized",
-        "dim": 1024,
-        "description": "Large English model, v1.5",
-        "size_in_GB": 1.34,
-        "sources": {
-            "hf": "qdrant/bge-large-en-v1.5-onnx-q",
-        },
+        "model_file": "model_optimized.onnx",
    },
    {
        "model": "BAAI/bge-large-en-v1.5",
        "dim": 1024,
        "description": "Large English model, v1.5",
-        "size_in_GB": 1.34,
+        "size_in_GB": 1.20,
        "sources": {
            "hf": "qdrant/bge-large-en-v1.5-onnx",
        },
+        "model_file": "model.onnx",
    },
    {
        "model": "BAAI/bge-small-en",
        "dim": 384,
        "description": "Fast English model",
-        "size_in_GB": 0.2,
+        "size_in_GB": 0.13,
        "sources": {
-            "url": "https://storage.googleapis.com/qdrant-fastembed/BAAI-bge-small-en.tar.gz",
+            "hf": "ggrn/bge-small-en",
        },
+        "model_file": "onnx/model.onnx",
    },
-    # {
-    #     "model": "BAAI/bge-small-en",
-    #     "dim": 384,
-    #     "description": "Fast English model",
-    #     "size_in_GB": 0.2,
-    #     "hf_sources": [],
-    #     "compressed_url_sources": [
-    #         "https://storage.googleapis.com/qdrant-fastembed/fast-bge-small-en.tar.gz",
-    #         "https://storage.googleapis.com/qdrant-fastembed/BAAI-bge-small-en.tar.gz"
-    #     ]
-    # },
    {
        "model": "BAAI/bge-small-en-v1.5",
        "dim": 384,
        "description": "Fast and Default English model",
-        "size_in_GB": 0.13,
+        "size_in_GB": 0.067,
        "sources": {
-            "url": "https://storage.googleapis.com/qdrant-fastembed/fast-bge-small-en-v1.5.tar.gz",
            "hf": "qdrant/bge-small-en-v1.5-onnx-q",
        },
+        "model_file": "model_optimized.onnx",
    },
    {
        "model": "BAAI/bge-small-zh-v1.5",
        "dim": 512,
        "description": "Fast and recommended Chinese model",
-        "size_in_GB": 0.1,
+        "size_in_GB": 0.09,
        "sources": {
-            "url": "https://storage.googleapis.com/qdrant-fastembed/fast-bge-small-zh-v1.5.tar.gz",
+            "hf": "Xenova/bge-small-zh-v1.5",
        },
+        "model_file": "onnx/model.onnx",
    },
-    {  # todo: it is not a flag embedding
+    {
        "model": "sentence-transformers/all-MiniLM-L6-v2",
        "dim": 384,
        "description": "Sentence Transformer model, MiniLM-L6-v2",
        "size_in_GB": 0.09,
        "sources": {
-            "url": "https://storage.googleapis.com/qdrant-fastembed/sentence-transformers-all-MiniLM-L6-v2.tar.gz",
            "hf": "qdrant/all-MiniLM-L6-v2-onnx",
        },
+        "model_file": "model.onnx",
    },
    {
        "model": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
        "dim": 384,
        "description": "Sentence Transformer model, paraphrase-multilingual-MiniLM-L12-v2",
-        "size_in_GB": 0.46,
+        "size_in_GB": 0.22,
        "sources": {
            "hf": "qdrant/paraphrase-multilingual-MiniLM-L12-v2-onnx-Q",
        },
+        "model_file": "model_optimized.onnx",
    },
    {
        "model": "nomic-ai/nomic-embed-text-v1",
        "dim": 768,
        "description": "8192 context length english model",
-        "size_in_GB": 0.54,
+        "size_in_GB": 0.52,
        "sources": {
            "hf": "nomic-ai/nomic-embed-text-v1",
        },
+        "model_file": "onnx/model.onnx",
    },
    {
        "model": "nomic-ai/nomic-embed-text-v1.5",
        "dim": 768,
        "description": "8192 context length english model",
-        "size_in_GB": 0.54,
+        "size_in_GB": 0.52,
        "sources": {
            "hf": "nomic-ai/nomic-embed-text-v1.5",
        },
+        "model_file": "onnx/model.onnx",
+    },
+    {
+        "model": "nomic-ai/nomic-embed-text-v1.5-Q",
+        "dim": 768,
+        "description": "Quantized 8192 context length english model",
+        "size_in_GB": 0.13,
+        "sources": {
+            "hf": "nomic-ai/nomic-embed-text-v1.5",
+        },
+        "model_file": "onnx/model_quantized.onnx",
    },
    {
        "model": "thenlper/gte-large",
        "dim": 1024,
        "description": "Large general text embeddings model",
-        "size_in_GB": 1.34,
+        "size_in_GB": 1.20,
        "sources": {
            "hf": "qdrant/gte-large-onnx",
        },
+        "model_file": "model.onnx",
+    },
+    {
+        "model": "mixedbread-ai/mxbai-embed-large-v1",
+        "dim": 1024,
+        "description": "MixedBread Base sentence embedding model, does well on MTEB",
+        "size_in_GB": 0.64,
+        "sources": {
+            "hf": "mixedbread-ai/mxbai-embed-large-v1",
+        },
+        "model_file": "onnx/model.onnx",
    },
-    # {
-    #     "model": "sentence-transformers/all-MiniLM-L6-v2",
-    #     "dim": 384,
-    #     "description": "Sentence Transformer model, MiniLM-L6-v2",
-    #     "size_in_GB": 0.09,
-    #     "hf_sources": [
-    #         "qdrant/all-MiniLM-L6-v2-onnx"
-    #     ],
-    #     "compressed_url_sources": [
-    #         "https://storage.googleapis.com/qdrant-fastembed/fast-all-MiniLM-L6-v2.tar.gz",
-    #         "https://storage.googleapis.com/qdrant-fastembed/sentence-transformers-all-MiniLM-L6-v2.tar.gz"
-    #     ]
-    # }
 ]


@@ -180,14 +175,11 @@ class OnnxTextEmbedding(TextEmbeddingBase, OnnxModel[np.ndarray]):

        super().__init__(model_name, cache_dir, threads, **kwargs)

-        self.model_name = model_name
-        self._model_description = self._get_model_description(model_name)
-
-        self._cache_dir = define_cache_dir(cache_dir)
-        self._model_dir = self.download_model(self._model_description, self._cache_dir)
-        self._max_length = 512
-
-        self.load_onnx_model(self._model_dir, self.threads, self._max_length)
+        self.load_onnx_model(
+            self._get_model_description(model_name),
+            threads,
+            define_cache_dir(cache_dir),
+        )

    def embed(
        self,
@@ -213,7 +205,7 @@ class OnnxTextEmbedding(TextEmbeddingBase, OnnxModel[np.ndarray]):
        """
        yield from self._embed_documents(
            model_name=self.model_name,
-            cache_dir=str(self._cache_dir),
+            cache_dir=str(self.cache_dir),
            documents=documents,
            batch_size=batch_size,
            parallel=parallel,
@@ -230,7 +222,9 @@ class OnnxTextEmbedding(TextEmbeddingBase, OnnxModel[np.ndarray]):
        return onnx_input

    @classmethod
-    def _post_process_onnx_output(cls, output: Tuple[np.ndarray, np.ndarray]) -> Iterable[np.ndarray]:
+    def _post_process_onnx_output(
+        cls, output: Tuple[np.ndarray, np.ndarray]
+    ) -> Iterable[np.ndarray]:
        embeddings, _ = output
        return normalize(embeddings[:, 0]).astype(np.float32)

@@ -55,7 +55,7 @@ class TextEmbedding(TextEmbeddingBase):

        for EMBEDDING_MODEL_TYPE in self.EMBEDDINGS_REGISTRY:
            supported_models = EMBEDDING_MODEL_TYPE.list_supported_models()
-            if any(model_name == model["model"] for model in supported_models):
+            if any(model_name.lower() == model["model"].lower() for model in supported_models):
                self.model = EMBEDDING_MODEL_TYPE(model_name, cache_dir, threads, **kwargs)
                return

@@ -6,7 +6,13 @@ from fastembed.common.model_management import ModelManagement


 class TextEmbeddingBase(ModelManagement):
-    def __init__(self, model_name: str, cache_dir: Optional[str] = None, threads: Optional[int] = None, **kwargs):
+    def __init__(
+        self,
+        model_name: str,
+        cache_dir: Optional[str] = None,
+        threads: Optional[int] = None,
+        **kwargs,
+    ):
        self.model_name = model_name
        self.cache_dir = cache_dir
        self.threads = threads
@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 1.7.1 and should not be changed by hand.
+# This file is automatically @generated by Poetry 1.8.2 and should not be changed by hand.

 [[package]]
 name = "anyio"
@@ -639,29 +639,29 @@ devel = ["colorama", "json-spec", "jsonschema", "pylint", "pytest", "pytest-benc

 [[package]]
 name = "filelock"
-version = "3.13.1"
+version = "3.13.3"
 description = "A platform independent file lock."
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "filelock-3.13.1-py3-none-any.whl", hash = "sha256:57dbda9b35157b05fb3e58ee91448612eb674172fab98ee235ccb0b5bee19a1c"},
-    {file = "filelock-3.13.1.tar.gz", hash = "sha256:521f5f56c50f8426f5e03ad3b281b490a87ef15bc6c526f168290f0c7148d44e"},
+    {file = "filelock-3.13.3-py3-none-any.whl", hash = "sha256:5ffa845303983e7a0b7ae17636509bc97997d58afeafa72fb141a17b152284cb"},
+    {file = "filelock-3.13.3.tar.gz", hash = "sha256:a79895a25bbefdf55d1a2a0a80968f7dbb28edcd6d4234a0afb3f37ecde4b546"},
 ]

 [package.extras]
-docs = ["furo (>=2023.9.10)", "sphinx (>=7.2.6)", "sphinx-autodoc-typehints (>=1.24)"]
-testing = ["covdefaults (>=2.3)", "coverage (>=7.3.2)", "diff-cover (>=8)", "pytest (>=7.4.3)", "pytest-cov (>=4.1)", "pytest-mock (>=3.12)", "pytest-timeout (>=2.2)"]
+docs = ["furo (>=2023.9.10)", "sphinx (>=7.2.6)", "sphinx-autodoc-typehints (>=1.25.2)"]
+testing = ["covdefaults (>=2.3)", "coverage (>=7.3.2)", "diff-cover (>=8.0.1)", "pytest (>=7.4.3)", "pytest-cov (>=4.1)", "pytest-mock (>=3.12)", "pytest-timeout (>=2.2)"]
 typing = ["typing-extensions (>=4.8)"]

 [[package]]
 name = "flatbuffers"
-version = "24.3.7"
+version = "24.3.25"
 description = "The FlatBuffers serialization format for Python"
 optional = false
 python-versions = "*"
 files = [
-    {file = "flatbuffers-24.3.7-py2.py3-none-any.whl", hash = "sha256:80c4f5dcad0ee76b7e349671a0d657f2fbba927a0244f88dd3f5ed6a3694e1fc"},
-    {file = "flatbuffers-24.3.7.tar.gz", hash = "sha256:0895c22b9a6019ff2f4de2e5e2f7cd15914043e6e7033a94c0c6369422690f22"},
+    {file = "flatbuffers-24.3.25-py2.py3-none-any.whl", hash = "sha256:8dbdec58f935f3765e4f7f3cf635ac3a77f83568138d6a2311f524ec96364812"},
+    {file = "flatbuffers-24.3.25.tar.gz", hash = "sha256:de2ec5b203f21441716617f38443e0a8ebf3d25bf0d9c0bb0ce68fa00ad546a4"},
 ]

 [[package]]
@@ -677,13 +677,13 @@ files = [

 [[package]]
 name = "fsspec"
-version = "2024.2.0"
+version = "2024.3.1"
 description = "File-system specification"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "fsspec-2024.2.0-py3-none-any.whl", hash = "sha256:817f969556fa5916bc682e02ca2045f96ff7f586d45110fcb76022063ad2c7d8"},
-    {file = "fsspec-2024.2.0.tar.gz", hash = "sha256:b6ad1a679f760dda52b1168c859d01b7b80648ea6f7f7c7f5a8a91dc3f3ecb84"},
+    {file = "fsspec-2024.3.1-py3-none-any.whl", hash = "sha256:918d18d41bf73f0e2b261824baeb1b124bcf771767e3a26425cd7dec3332f512"},
+    {file = "fsspec-2024.3.1.tar.gz", hash = "sha256:f39780e282d7d117ffb42bb96992f8a90795e4d0fb0f661a70ca39fe9c43ded9"},
 ]

 [package.extras]
@@ -771,13 +771,13 @@ files = [

 [[package]]
 name = "httpcore"
-version = "1.0.4"
+version = "1.0.5"
 description = "A minimal low-level HTTP client."
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "httpcore-1.0.4-py3-none-any.whl", hash = "sha256:ac418c1db41bade2ad53ae2f3834a3a0f5ae76b56cf5aa497d2d033384fc7d73"},
-    {file = "httpcore-1.0.4.tar.gz", hash = "sha256:cb2839ccfcba0d2d3c1131d3c3e26dfc327326fbe7a5dc0dbfe9f6c9151bb022"},
+    {file = "httpcore-1.0.5-py3-none-any.whl", hash = "sha256:421f18bac248b25d310f3cacd198d55b8e6125c107797b609ff9b7a6ba7991b5"},
+    {file = "httpcore-1.0.5.tar.gz", hash = "sha256:34a38e2f9291467ee3b44e89dd52615370e152954ba21721378a87b2960f7a61"},
 ]

 [package.dependencies]
@@ -788,7 +788,7 @@ h11 = ">=0.13,<0.15"
 asyncio = ["anyio (>=4.0,<5.0)"]
 http2 = ["h2 (>=3,<5)"]
 socks = ["socksio (==1.*)"]
-trio = ["trio (>=0.22.0,<0.25.0)"]
+trio = ["trio (>=0.22.0,<0.26.0)"]

 [[package]]
 name = "httpx"
@@ -876,24 +876,24 @@ license = ["ukkonen"]

 [[package]]
 name = "idna"
-version = "3.6"
+version = "3.7"
 description = "Internationalized Domain Names in Applications (IDNA)"
 optional = false
 python-versions = ">=3.5"
 files = [
-    {file = "idna-3.6-py3-none-any.whl", hash = "sha256:c05567e9c24a6b9faaa835c4821bad0590fbb9d5779e7caa6e1cc4978e7eb24f"},
-    {file = "idna-3.6.tar.gz", hash = "sha256:9ecdbbd083b06798ae1e86adcbfe8ab1479cf864e4ee30fe4e46a003d12491ca"},
+    {file = "idna-3.7-py3-none-any.whl", hash = "sha256:82fee1fc78add43492d3a1898bfa6d8a904cc97d8427f683ed8e798d07761aa0"},
+    {file = "idna-3.7.tar.gz", hash = "sha256:028ff3aadf0609c1fd278d8ea3089299412a7a8b9bd005dd08b9f8285bcb5cfc"},
 ]

 [[package]]
 name = "importlib-metadata"
-version = "7.0.2"
+version = "7.1.0"
 description = "Read metadata from Python packages"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "importlib_metadata-7.0.2-py3-none-any.whl", hash = "sha256:f4bc4c0c070c490abf4ce96d715f68e95923320370efb66143df00199bb6c100"},
-    {file = "importlib_metadata-7.0.2.tar.gz", hash = "sha256:198f568f3230878cb1b44fbd7975f87906c22336dba2e4a7f05278c281fbd792"},
+    {file = "importlib_metadata-7.1.0-py3-none-any.whl", hash = "sha256:30962b96c0c223483ed6cc7280e7f0199feb01a0e40cfae4d4450fc6fab1f570"},
+    {file = "importlib_metadata-7.1.0.tar.gz", hash = "sha256:b78938b926ee8d5f020fc4772d487045805a55ddbad2ecf21c6d60938dc7fcd2"},
 ]

 [package.dependencies]
@@ -902,17 +902,17 @@ zipp = ">=0.5"
 [package.extras]
 docs = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"]
 perf = ["ipython"]
-testing = ["flufl.flake8", "importlib-resources (>=1.3)", "packaging", "pyfakefs", "pytest (>=6)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-mypy", "pytest-perf (>=0.9.2)", "pytest-ruff (>=0.2.1)"]
+testing = ["flufl.flake8", "importlib-resources (>=1.3)", "jaraco.test (>=5.4)", "packaging", "pyfakefs", "pytest (>=6)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-mypy", "pytest-perf (>=0.9.2)", "pytest-ruff (>=0.2.1)"]

 [[package]]
 name = "importlib-resources"
-version = "6.3.0"
+version = "6.4.0"
 description = "Read resources from Python packages"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "importlib_resources-6.3.0-py3-none-any.whl", hash = "sha256:783407aa1cd05550e3aa123e8f7cfaebee35ffa9cb0242919e2d1e4172222705"},
-    {file = "importlib_resources-6.3.0.tar.gz", hash = "sha256:166072a97e86917a9025876f34286f549b9caf1d10b35a1b372bffa1600c6569"},
+    {file = "importlib_resources-6.4.0-py3-none-any.whl", hash = "sha256:50d10f043df931902d4194ea07ec57960f66a80449ff867bfe782b4c486ba78c"},
+    {file = "importlib_resources-6.4.0.tar.gz", hash = "sha256:cdb2b453b8046ca4e3798eb1d84f3cce1446a0e8e7b5ef4efb600f19fc398145"},
 ]

 [package.dependencies]
@@ -920,7 +920,7 @@ zipp = {version = ">=3.1.0", markers = "python_version < \"3.10\""}

 [package.extras]
 docs = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (<7.2.5)", "sphinx (>=3.5)", "sphinx-lint"]
-testing = ["jaraco.collections", "pytest (>=6)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-mypy", "pytest-ruff (>=0.2.1)", "zipp (>=3.17)"]
+testing = ["jaraco.test (>=5.4)", "pytest (>=6)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-mypy", "pytest-ruff (>=0.2.1)", "zipp (>=3.17)"]

 [[package]]
 name = "iniconfig"
@@ -935,13 +935,13 @@ files = [

 [[package]]
 name = "ipykernel"
-version = "6.29.3"
+version = "6.29.4"
 description = "IPython Kernel for Jupyter"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "ipykernel-6.29.3-py3-none-any.whl", hash = "sha256:5aa086a4175b0229d4eca211e181fb473ea78ffd9869af36ba7694c947302a21"},
-    {file = "ipykernel-6.29.3.tar.gz", hash = "sha256:e14c250d1f9ea3989490225cc1a542781b095a18a19447fcf2b5eaf7d0ac5bd2"},
+    {file = "ipykernel-6.29.4-py3-none-any.whl", hash = "sha256:1181e653d95c6808039c509ef8e67c4126b3b3af7781496c7cbfb5ed938a27da"},
+    {file = "ipykernel-6.29.4.tar.gz", hash = "sha256:3d44070060f9475ac2092b760123fadf105d2e2493c24848b6691a7c4f42af5c"},
 ]

 [package.dependencies]
@@ -1057,18 +1057,15 @@ i18n = ["Babel (>=2.7)"]

 [[package]]
 name = "json5"
-version = "0.9.22"
+version = "0.9.24"
 description = "A Python implementation of the JSON5 data format."
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "json5-0.9.22-py3-none-any.whl", hash = "sha256:6621007c70897652f8b5d03885f732771c48d1925591ad989aa80c7e0e5ad32f"},
-    {file = "json5-0.9.22.tar.gz", hash = "sha256:b729bde7650b2196a35903a597d2b704b8fdf8648bfb67368cfb79f1174a17bd"},
+    {file = "json5-0.9.24-py3-none-any.whl", hash = "sha256:4ca101fd5c7cb47960c055ef8f4d0e31e15a7c6c48c3b6f1473fc83b6c462a13"},
+    {file = "json5-0.9.24.tar.gz", hash = "sha256:0c638399421da959a20952782800e5c1a78c14e08e1dc9738fa10d8ec14d58c8"},
 ]

-[package.extras]
-dev = ["hypothesis"]
-
 [[package]]
 name = "jsonpointer"
 version = "2.4"
@@ -1171,13 +1168,13 @@ test = ["ipykernel", "pre-commit", "pytest (<8)", "pytest-cov", "pytest-timeout"

 [[package]]
 name = "jupyter-events"
-version = "0.9.1"
+version = "0.10.0"
 description = "Jupyter Event System library"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "jupyter_events-0.9.1-py3-none-any.whl", hash = "sha256:e51f43d2c25c2ddf02d7f7a5045f71fc1d5cb5ad04ef6db20da961c077654b9b"},
-    {file = "jupyter_events-0.9.1.tar.gz", hash = "sha256:a52e86f59eb317ee71ff2d7500c94b963b8a24f0b7a1517e2e653e24258e15c7"},
+    {file = "jupyter_events-0.10.0-py3-none-any.whl", hash = "sha256:4b72130875e59d57716d327ea70d3ebc3af1944d3717e5a498b8a06c6c159960"},
+    {file = "jupyter_events-0.10.0.tar.gz", hash = "sha256:670b8229d3cc882ec782144ed22e0d29e1c2d639263f92ca8383e66682845e22"},
 ]

 [package.dependencies]
@@ -1266,13 +1263,13 @@ test = ["jupyter-server (>=2.0.0)", "pytest (>=7.0)", "pytest-jupyter[server] (>

 [[package]]
 name = "jupyterlab"
-version = "4.1.4"
+version = "4.1.5"
 description = "JupyterLab computational environment"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "jupyterlab-4.1.4-py3-none-any.whl", hash = "sha256:f92c3f2b12b88efcf767205f49be9b2f86b85544f9c4f342bb5e9904a16cf931"},
-    {file = "jupyterlab-4.1.4.tar.gz", hash = "sha256:e03c82c124ad8a0892e498b9dde79c50868b2c267819aca3f55ce47c57ebeb1d"},
+    {file = "jupyterlab-4.1.5-py3-none-any.whl", hash = "sha256:3bc843382a25e1ab7bc31d9e39295a9f0463626692b7995597709c0ab236ab2c"},
+    {file = "jupyterlab-4.1.5.tar.gz", hash = "sha256:c9ad75290cb10bfaff3624bf3fbb852319b4cce4c456613f8ebbaa98d03524db"},
 ]

 [package.dependencies]
@@ -1355,13 +1352,13 @@ dev = ["Sphinx (==7.2.5)", "colorama (==0.4.5)", "colorama (==0.4.6)", "exceptio

 [[package]]
 name = "markdown"
-version = "3.5.2"
+version = "3.6"
 description = "Python implementation of John Gruber's Markdown."
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "Markdown-3.5.2-py3-none-any.whl", hash = "sha256:d43323865d89fc0cb9b20c75fc8ad313af307cc087e84b657d9eec768eddeadd"},
-    {file = "Markdown-3.5.2.tar.gz", hash = "sha256:e1ac7b3dc550ee80e602e71c1d168002f062e49f1b11e26a36264dafd4df2ef8"},
+    {file = "Markdown-3.6-py3-none-any.whl", hash = "sha256:48f276f4d8cfb8ce6527c8f79e2ee29708508bf4d40aa410fbc3b4ee832c850f"},
+    {file = "Markdown-3.6.tar.gz", hash = "sha256:ed4f41f6daecbeeb96e576ce414c41d2d876daa9a16cb35fa8ed8c2ddfad0224"},
 ]

 [package.dependencies]
@@ -1525,13 +1522,13 @@ mkdocs = ">=1.1"

 [[package]]
 name = "mkdocs-material"
-version = "9.5.13"
+version = "9.5.15"
 description = "Documentation that simply works"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "mkdocs_material-9.5.13-py3-none-any.whl", hash = "sha256:5cbe17fee4e3b4980c8420a04cc762d8dc052ef1e10532abd4fce88e5ea9ce6a"},
-    {file = "mkdocs_material-9.5.13.tar.gz", hash = "sha256:d8e4caae576312a88fd2609b81cf43d233cdbe36860d67a68702b018b425bd87"},
+    {file = "mkdocs_material-9.5.15-py3-none-any.whl", hash = "sha256:e5c96dec3d19491de49ca643fc1dbb92b278e43cdb816c775bc47db77d9b62fb"},
+    {file = "mkdocs_material-9.5.15.tar.gz", hash = "sha256:39f03cca45e82bf54eb7456b5a18bd252eabfdd67f237a229471484a0a4d4635"},
 ]

 [package.dependencies]
@@ -1649,13 +1646,13 @@ test = ["flaky", "ipykernel (>=6.19.3)", "ipython", "ipywidgets", "nbconvert (>=

 [[package]]
 name = "nbconvert"
-version = "7.16.2"
+version = "7.16.3"
 description = "Converting Jupyter Notebooks (.ipynb files) to other formats.  Output formats include asciidoc, html, latex, markdown, pdf, py, rst, script.  nbconvert can be used both as a Python library (`import nbconvert`) or as a command line tool (invoked as `jupyter nbconvert ...`)."
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "nbconvert-7.16.2-py3-none-any.whl", hash = "sha256:0c01c23981a8de0220255706822c40b751438e32467d6a686e26be08ba784382"},
-    {file = "nbconvert-7.16.2.tar.gz", hash = "sha256:8310edd41e1c43947e4ecf16614c61469ebc024898eb808cce0999860fc9fb16"},
+    {file = "nbconvert-7.16.3-py3-none-any.whl", hash = "sha256:ddeff14beeeedf3dd0bc506623e41e4507e551736de59df69a91f86700292b3b"},
+    {file = "nbconvert-7.16.3.tar.gz", hash = "sha256:a6733b78ce3d47c3f85e504998495b07e6ea9cf9bf6ec1c98dda63ec6ad19142"},
 ]

 [package.dependencies]
@@ -1682,18 +1679,18 @@ docs = ["ipykernel", "ipython", "myst-parser", "nbsphinx (>=0.2.12)", "pydata-sp
 qtpdf = ["nbconvert[qtpng]"]
 qtpng = ["pyqtwebengine (>=5.15)"]
 serve = ["tornado (>=6.1)"]
-test = ["flaky", "ipykernel", "ipywidgets (>=7.5)", "pytest"]
+test = ["flaky", "ipykernel", "ipywidgets (>=7.5)", "pytest (>=7)"]
 webpdf = ["playwright"]

 [[package]]
 name = "nbformat"
-version = "5.10.2"
+version = "5.10.3"
 description = "The Jupyter Notebook format"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "nbformat-5.10.2-py3-none-any.whl", hash = "sha256:7381189a0d537586b3f18bae5dbad347d7dd0a7cf0276b09cdcd5c24d38edd99"},
-    {file = "nbformat-5.10.2.tar.gz", hash = "sha256:c535b20a0d4310167bf4d12ad31eccfb0dc61e6392d6f8c570ab5b45a06a49a3"},
+    {file = "nbformat-5.10.3-py3-none-any.whl", hash = "sha256:d9476ca28676799af85385f409b49d95e199951477a159a576ef2a675151e5e8"},
+    {file = "nbformat-5.10.3.tar.gz", hash = "sha256:60ed5e910ef7c6264b87d644f276b1b49e24011930deef54605188ddeb211685"},
 ]

 [package.dependencies]
@@ -1733,13 +1730,13 @@ setuptools = "*"

 [[package]]
 name = "notebook"
-version = "7.1.1"
+version = "7.1.2"
 description = "Jupyter Notebook - A web-based notebook environment for interactive computing"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "notebook-7.1.1-py3-none-any.whl", hash = "sha256:197d8e0595acabf4005851c8716e952a81b405f7aefb648067a761fbde267ce7"},
-    {file = "notebook-7.1.1.tar.gz", hash = "sha256:818e7420fa21f402e726afb9f02df7f3c10f294c02e383ed19852866c316108b"},
+    {file = "notebook-7.1.2-py3-none-any.whl", hash = "sha256:fc6c24b9aef18d0cd57157c9c47e95833b9b0bdc599652639acf0bdb61dc7d5f"},
+    {file = "notebook-7.1.2.tar.gz", hash = "sha256:efc2c80043909e0faa17fce9e9b37c059c03af0ec99a4d4db84cb21d9d2e936a"},
 ]

 [package.dependencies]
@@ -1855,40 +1852,46 @@ files = [

 [[package]]
 name = "onnx"
-version = "1.15.0"
+version = "1.16.0"
 description = "Open Neural Network Exchange"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "onnx-1.15.0-cp310-cp310-macosx_10_12_universal2.whl", hash = "sha256:51cacb6aafba308aaf462252ced562111f6991cdc7bc57a6c554c3519453a8ff"},
-    {file = "onnx-1.15.0-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:0aee26b6f7f7da7e840de75ad9195a77a147d0662c94eaa6483be13ba468ffc1"},
-    {file = "onnx-1.15.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:baf6ef6c93b3b843edb97a8d5b3d229a1301984f3f8dee859c29634d2083e6f9"},
-    {file = "onnx-1.15.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:96ed899fe6000edc05bb2828863d3841cfddd5a7cf04c1a771f112e94de75d9f"},
-    {file = "onnx-1.15.0-cp310-cp310-win32.whl", hash = "sha256:f1ad3d77fc2f4b4296f0ac2c8cadd8c1dcf765fc586b737462d3a0fe8f7c696a"},
-    {file = "onnx-1.15.0-cp310-cp310-win_amd64.whl", hash = "sha256:ca4ebc4f47109bfb12c8c9e83dd99ec5c9f07d2e5f05976356c6ccdce3552010"},
-    {file = "onnx-1.15.0-cp311-cp311-macosx_10_12_universal2.whl", hash = "sha256:233ffdb5ca8cc2d960b10965a763910c0830b64b450376da59207f454701f343"},
-    {file = "onnx-1.15.0-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:51fa79c9ea9af033638ec51f9177b8e76c55fad65bb83ea96ee88fafade18ee7"},
-    {file = "onnx-1.15.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f277d4861729f5253a51fa41ce91bfec1c4574ee41b5637056b43500917295ce"},
-    {file = "onnx-1.15.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d8a7c94d2ebead8f739fdb70d1ce5a71726f4e17b3e5b8ad64455ea1b2801a85"},
-    {file = "onnx-1.15.0-cp311-cp311-win32.whl", hash = "sha256:17dcfb86a8c6bdc3971443c29b023dd9c90ff1d15d8baecee0747a6b7f74e650"},
-    {file = "onnx-1.15.0-cp311-cp311-win_amd64.whl", hash = "sha256:60a3e28747e305cd2e766e6a53a0a6d952cf9e72005ec6023ce5e07666676a4e"},
-    {file = "onnx-1.15.0-cp38-cp38-macosx_10_12_universal2.whl", hash = "sha256:6b5c798d9e0907eaf319e3d3e7c89a2ed9a854bcb83da5fefb6d4c12d5e90721"},
-    {file = "onnx-1.15.0-cp38-cp38-macosx_10_12_x86_64.whl", hash = "sha256:a4f774ff50092fe19bd8f46b2c9b27b1d30fbd700c22abde48a478142d464322"},
-    {file = "onnx-1.15.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b2b0e7f3938f2d994c34616bfb8b4b1cebbc4a0398483344fe5e9f2fe95175e6"},
-    {file = "onnx-1.15.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:49cebebd0020a4b12c1dd0909d426631212ef28606d7e4d49463d36abe7639ad"},
-    {file = "onnx-1.15.0-cp38-cp38-win32.whl", hash = "sha256:1fdf8a3ff75abc2b32c83bf27fb7c18d6b976c9c537263fadd82b9560fe186fa"},
-    {file = "onnx-1.15.0-cp38-cp38-win_amd64.whl", hash = "sha256:763e55c26e8de3a2dce008d55ae81b27fa8fb4acbb01a29b9f3c01f200c4d676"},
-    {file = "onnx-1.15.0-cp39-cp39-macosx_10_12_universal2.whl", hash = "sha256:b2d5e802837629fc9c86f19448d19dd04d206578328bce202aeb3d4bedab43c4"},
-    {file = "onnx-1.15.0-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:9a9cfbb5e5d5d88f89d0dfc9df5fb858899db874e1d5ed21e76c481f3cafc90d"},
-    {file = "onnx-1.15.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3f472bbe5cb670a0a4a4db08f41fde69b187a009d0cb628f964840d3f83524e9"},
-    {file = "onnx-1.15.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2bf2de9bef64792e5b8080c678023ac7d2b9e05d79a3e17e92cf6a4a624831d2"},
-    {file = "onnx-1.15.0-cp39-cp39-win32.whl", hash = "sha256:ef4d9eb44b111e69e4534f3233fc2c13d1e26920d24ae4359d513bd54694bc6d"},
-    {file = "onnx-1.15.0-cp39-cp39-win_amd64.whl", hash = "sha256:95d7a3e2d79d371e272e39ae3f7547e0b116d0c7f774a4004e97febe6c93507f"},
-    {file = "onnx-1.15.0.tar.gz", hash = "sha256:b18461a7d38f286618ca2a6e78062a2a9c634ce498e631e708a8041b00094825"},
+    {file = "onnx-1.16.0-cp310-cp310-macosx_10_15_universal2.whl", hash = "sha256:9eadbdce25b19d6216f426d6d99b8bc877a65ed92cbef9707751c6669190ba4f"},
+    {file = "onnx-1.16.0-cp310-cp310-macosx_10_15_x86_64.whl", hash = "sha256:034ae21a2aaa2e9c14119a840d2926d213c27aad29e5e3edaa30145a745048e1"},
+    {file = "onnx-1.16.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ec22a43d74eb1f2303373e2fbe7fbcaa45fb225f4eb146edfed1356ada7a9aea"},
+    {file = "onnx-1.16.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:298f28a2b5ac09145fa958513d3d1e6b349ccf86a877dbdcccad57713fe360b3"},
+    {file = "onnx-1.16.0-cp310-cp310-win32.whl", hash = "sha256:66300197b52beca08bc6262d43c103289c5d45fde43fb51922ed1eb83658cf0c"},
+    {file = "onnx-1.16.0-cp310-cp310-win_amd64.whl", hash = "sha256:ae0029f5e47bf70a1a62e7f88c80bca4ef39b844a89910039184221775df5e43"},
+    {file = "onnx-1.16.0-cp311-cp311-macosx_10_15_universal2.whl", hash = "sha256:f51179d4af3372b4f3800c558d204b592c61e4b4a18b8f61e0eea7f46211221a"},
+    {file = "onnx-1.16.0-cp311-cp311-macosx_10_15_x86_64.whl", hash = "sha256:5202559070afec5144332db216c20f2fff8323cf7f6512b0ca11b215eacc5bf3"},
+    {file = "onnx-1.16.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:77579e7c15b4df39d29465b216639a5f9b74026bdd9e4b6306cd19a32dcfe67c"},
+    {file = "onnx-1.16.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0e60ca76ac24b65c25860d0f2d2cdd96d6320d062a01dd8ce87c5743603789b8"},
+    {file = "onnx-1.16.0-cp311-cp311-win32.whl", hash = "sha256:81b4ee01bc554e8a2b11ac6439882508a5377a1c6b452acd69a1eebb83571117"},
+    {file = "onnx-1.16.0-cp311-cp311-win_amd64.whl", hash = "sha256:7449241e70b847b9c3eb8dae622df8c1b456d11032a9d7e26e0ee8a698d5bf86"},
+    {file = "onnx-1.16.0-cp312-cp312-macosx_10_15_universal2.whl", hash = "sha256:03a627488b1a9975d95d6a55582af3e14c7f3bb87444725b999935ddd271d352"},
+    {file = "onnx-1.16.0-cp312-cp312-macosx_10_15_x86_64.whl", hash = "sha256:c392faeabd9283ee344ccb4b067d1fea9dfc614fa1f0de7c47589efd79e15e78"},
+    {file = "onnx-1.16.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0efeb46985de08f0efe758cb54ad3457e821a05c2eaf5ba2ccb8cd1602c08084"},
+    {file = "onnx-1.16.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ddf14a3d32234f23e44abb73a755cb96a423fac7f004e8f046f36b10214151ee"},
+    {file = "onnx-1.16.0-cp312-cp312-win32.whl", hash = "sha256:62a2e27ae8ba5fc9b4a2620301446a517b5ffaaf8566611de7a7c2160f5bcf4c"},
+    {file = "onnx-1.16.0-cp312-cp312-win_amd64.whl", hash = "sha256:3e0860fea94efde777e81a6f68f65761ed5e5f3adea2e050d7fbe373a9ae05b3"},
+    {file = "onnx-1.16.0-cp38-cp38-macosx_10_15_universal2.whl", hash = "sha256:70a90649318f3470985439ea078277c9fb2a2e6e2fd7c8f3f2b279402ad6c7e6"},
+    {file = "onnx-1.16.0-cp38-cp38-macosx_10_15_x86_64.whl", hash = "sha256:71839546b7f93be4fa807995b182ab4b4414c9dbf049fee11eaaced16fcf8df2"},
+    {file = "onnx-1.16.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7665217c45a61eb44718c8e9349d2ad004efa0cb9fbc4be5c6d5e18b9fe12b52"},
+    {file = "onnx-1.16.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e5752bbbd5717304a7643643dba383a2fb31e8eb0682f4e7b7d141206328a73b"},
+    {file = "onnx-1.16.0-cp38-cp38-win32.whl", hash = "sha256:257858cbcb2055284f09fa2ae2b1cfd64f5850367da388d6e7e7b05920a40c90"},
+    {file = "onnx-1.16.0-cp38-cp38-win_amd64.whl", hash = "sha256:209fe84995a28038e29ae8369edd35f33e0ef1ebc3bddbf6584629823469deb1"},
+    {file = "onnx-1.16.0-cp39-cp39-macosx_10_15_universal2.whl", hash = "sha256:8cf3e518b1b1b960be542e7c62bed4e5219e04c85d540817b7027029537dec92"},
+    {file = "onnx-1.16.0-cp39-cp39-macosx_10_15_x86_64.whl", hash = "sha256:30f02beaf081c7d9fa3a8c566a912fc4408e28fc33b1452d58f890851691d364"},
+    {file = "onnx-1.16.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7fb29a9a692b522deef1f6b8f2145da62c0c43ea1ed5b4c0f66f827fdc28847d"},
+    {file = "onnx-1.16.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7755cbd5f4e47952e37276ea5978a46fc8346684392315902b5ed4a719d87d06"},
+    {file = "onnx-1.16.0-cp39-cp39-win32.whl", hash = "sha256:7532343dc5b8b5e7c3e3efa441a3100552f7600155c4db9120acd7574f64ffbf"},
+    {file = "onnx-1.16.0-cp39-cp39-win_amd64.whl", hash = "sha256:d7886c05aa6d583ec42f6287678923c1e343afc4350e49d5b36a0023772ffa22"},
+    {file = "onnx-1.16.0.tar.gz", hash = "sha256:237c6987c6c59d9f44b6136f5819af79574f8d96a760a1fa843bede11f3822f7"},
 ]

 [package.dependencies]
-numpy = "*"
+numpy = ">=1.20"
 protobuf = ">=3.20.2"

 [package.extras]
@@ -2032,79 +2035,80 @@ files = [

 [[package]]
 name = "pillow"
-version = "10.2.0"
+version = "10.3.0"
 description = "Python Imaging Library (Fork)"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "pillow-10.2.0-cp310-cp310-macosx_10_10_x86_64.whl", hash = "sha256:7823bdd049099efa16e4246bdf15e5a13dbb18a51b68fa06d6c1d4d8b99a796e"},
-    {file = "pillow-10.2.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:83b2021f2ade7d1ed556bc50a399127d7fb245e725aa0113ebd05cfe88aaf588"},
-    {file = "pillow-10.2.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6fad5ff2f13d69b7e74ce5b4ecd12cc0ec530fcee76356cac6742785ff71c452"},
-    {file = "pillow-10.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:da2b52b37dad6d9ec64e653637a096905b258d2fc2b984c41ae7d08b938a67e4"},
-    {file = "pillow-10.2.0-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:47c0995fc4e7f79b5cfcab1fc437ff2890b770440f7696a3ba065ee0fd496563"},
-    {file = "pillow-10.2.0-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:322bdf3c9b556e9ffb18f93462e5f749d3444ce081290352c6070d014c93feb2"},
-    {file = "pillow-10.2.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:51f1a1bffc50e2e9492e87d8e09a17c5eea8409cda8d3f277eb6edc82813c17c"},
-    {file = "pillow-10.2.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:69ffdd6120a4737710a9eee73e1d2e37db89b620f702754b8f6e62594471dee0"},
-    {file = "pillow-10.2.0-cp310-cp310-win32.whl", hash = "sha256:c6dafac9e0f2b3c78df97e79af707cdc5ef8e88208d686a4847bab8266870023"},
-    {file = "pillow-10.2.0-cp310-cp310-win_amd64.whl", hash = "sha256:aebb6044806f2e16ecc07b2a2637ee1ef67a11840a66752751714a0d924adf72"},
-    {file = "pillow-10.2.0-cp310-cp310-win_arm64.whl", hash = "sha256:7049e301399273a0136ff39b84c3678e314f2158f50f517bc50285fb5ec847ad"},
-    {file = "pillow-10.2.0-cp311-cp311-macosx_10_10_x86_64.whl", hash = "sha256:35bb52c37f256f662abdfa49d2dfa6ce5d93281d323a9af377a120e89a9eafb5"},
-    {file = "pillow-10.2.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:9c23f307202661071d94b5e384e1e1dc7dfb972a28a2310e4ee16103e66ddb67"},
-    {file = "pillow-10.2.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:773efe0603db30c281521a7c0214cad7836c03b8ccff897beae9b47c0b657d61"},
-    {file = "pillow-10.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:11fa2e5984b949b0dd6d7a94d967743d87c577ff0b83392f17cb3990d0d2fd6e"},
-    {file = "pillow-10.2.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:716d30ed977be8b37d3ef185fecb9e5a1d62d110dfbdcd1e2a122ab46fddb03f"},
-    {file = "pillow-10.2.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:a086c2af425c5f62a65e12fbf385f7c9fcb8f107d0849dba5839461a129cf311"},
-    {file = "pillow-10.2.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:c8de2789052ed501dd829e9cae8d3dcce7acb4777ea4a479c14521c942d395b1"},
-    {file = "pillow-10.2.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:609448742444d9290fd687940ac0b57fb35e6fd92bdb65386e08e99af60bf757"},
-    {file = "pillow-10.2.0-cp311-cp311-win32.whl", hash = "sha256:823ef7a27cf86df6597fa0671066c1b596f69eba53efa3d1e1cb8b30f3533068"},
-    {file = "pillow-10.2.0-cp311-cp311-win_amd64.whl", hash = "sha256:1da3b2703afd040cf65ec97efea81cfba59cdbed9c11d8efc5ab09df9509fc56"},
-    {file = "pillow-10.2.0-cp311-cp311-win_arm64.whl", hash = "sha256:edca80cbfb2b68d7b56930b84a0e45ae1694aeba0541f798e908a49d66b837f1"},
-    {file = "pillow-10.2.0-cp312-cp312-macosx_10_10_x86_64.whl", hash = "sha256:1b5e1b74d1bd1b78bc3477528919414874748dd363e6272efd5abf7654e68bef"},
-    {file = "pillow-10.2.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:0eae2073305f451d8ecacb5474997c08569fb4eb4ac231ffa4ad7d342fdc25ac"},
-    {file = "pillow-10.2.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b7c2286c23cd350b80d2fc9d424fc797575fb16f854b831d16fd47ceec078f2c"},
-    {file = "pillow-10.2.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1e23412b5c41e58cec602f1135c57dfcf15482013ce6e5f093a86db69646a5aa"},
-    {file = "pillow-10.2.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:52a50aa3fb3acb9cf7213573ef55d31d6eca37f5709c69e6858fe3bc04a5c2a2"},
-    {file = "pillow-10.2.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:127cee571038f252a552760076407f9cff79761c3d436a12af6000cd182a9d04"},
-    {file = "pillow-10.2.0-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:8d12251f02d69d8310b046e82572ed486685c38f02176bd08baf216746eb947f"},
-    {file = "pillow-10.2.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:54f1852cd531aa981bc0965b7d609f5f6cc8ce8c41b1139f6ed6b3c54ab82bfb"},
-    {file = "pillow-10.2.0-cp312-cp312-win32.whl", hash = "sha256:257d8788df5ca62c980314053197f4d46eefedf4e6175bc9412f14412ec4ea2f"},
-    {file = "pillow-10.2.0-cp312-cp312-win_amd64.whl", hash = "sha256:154e939c5f0053a383de4fd3d3da48d9427a7e985f58af8e94d0b3c9fcfcf4f9"},
-    {file = "pillow-10.2.0-cp312-cp312-win_arm64.whl", hash = "sha256:f379abd2f1e3dddb2b61bc67977a6b5a0a3f7485538bcc6f39ec76163891ee48"},
-    {file = "pillow-10.2.0-cp38-cp38-macosx_10_10_x86_64.whl", hash = "sha256:8373c6c251f7ef8bda6675dd6d2b3a0fcc31edf1201266b5cf608b62a37407f9"},
-    {file = "pillow-10.2.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:870ea1ada0899fd0b79643990809323b389d4d1d46c192f97342eeb6ee0b8483"},
-    {file = "pillow-10.2.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b4b6b1e20608493548b1f32bce8cca185bf0480983890403d3b8753e44077129"},
-    {file = "pillow-10.2.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3031709084b6e7852d00479fd1d310b07d0ba82765f973b543c8af5061cf990e"},
-    {file = "pillow-10.2.0-cp38-cp38-manylinux_2_28_aarch64.whl", hash = "sha256:3ff074fc97dd4e80543a3e91f69d58889baf2002b6be64347ea8cf5533188213"},
-    {file = "pillow-10.2.0-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:cb4c38abeef13c61d6916f264d4845fab99d7b711be96c326b84df9e3e0ff62d"},
-    {file = "pillow-10.2.0-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:b1b3020d90c2d8e1dae29cf3ce54f8094f7938460fb5ce8bc5c01450b01fbaf6"},
-    {file = "pillow-10.2.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:170aeb00224ab3dc54230c797f8404507240dd868cf52066f66a41b33169bdbe"},
-    {file = "pillow-10.2.0-cp38-cp38-win32.whl", hash = "sha256:c4225f5220f46b2fde568c74fca27ae9771536c2e29d7c04f4fb62c83275ac4e"},
-    {file = "pillow-10.2.0-cp38-cp38-win_amd64.whl", hash = "sha256:0689b5a8c5288bc0504d9fcee48f61a6a586b9b98514d7d29b840143d6734f39"},
-    {file = "pillow-10.2.0-cp39-cp39-macosx_10_10_x86_64.whl", hash = "sha256:b792a349405fbc0163190fde0dc7b3fef3c9268292586cf5645598b48e63dc67"},
-    {file = "pillow-10.2.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:c570f24be1e468e3f0ce7ef56a89a60f0e05b30a3669a459e419c6eac2c35364"},
-    {file = "pillow-10.2.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d8ecd059fdaf60c1963c58ceb8997b32e9dc1b911f5da5307aab614f1ce5c2fb"},
-    {file = "pillow-10.2.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c365fd1703040de1ec284b176d6af5abe21b427cb3a5ff68e0759e1e313a5e7e"},
-    {file = "pillow-10.2.0-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:70c61d4c475835a19b3a5aa42492409878bbca7438554a1f89d20d58a7c75c01"},
-    {file = "pillow-10.2.0-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:b6f491cdf80ae540738859d9766783e3b3c8e5bd37f5dfa0b76abdecc5081f13"},
-    {file = "pillow-10.2.0-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:9d189550615b4948f45252d7f005e53c2040cea1af5b60d6f79491a6e147eef7"},
-    {file = "pillow-10.2.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:49d9ba1ed0ef3e061088cd1e7538a0759aab559e2e0a80a36f9fd9d8c0c21591"},
-    {file = "pillow-10.2.0-cp39-cp39-win32.whl", hash = "sha256:babf5acfede515f176833ed6028754cbcd0d206f7f614ea3447d67c33be12516"},
-    {file = "pillow-10.2.0-cp39-cp39-win_amd64.whl", hash = "sha256:0304004f8067386b477d20a518b50f3fa658a28d44e4116970abfcd94fac34a8"},
-    {file = "pillow-10.2.0-cp39-cp39-win_arm64.whl", hash = "sha256:0fb3e7fc88a14eacd303e90481ad983fd5b69c761e9e6ef94c983f91025da869"},
-    {file = "pillow-10.2.0-pp310-pypy310_pp73-macosx_10_10_x86_64.whl", hash = "sha256:322209c642aabdd6207517e9739c704dc9f9db943015535783239022002f054a"},
-    {file = "pillow-10.2.0-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3eedd52442c0a5ff4f887fab0c1c0bb164d8635b32c894bc1faf4c618dd89df2"},
-    {file = "pillow-10.2.0-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cb28c753fd5eb3dd859b4ee95de66cc62af91bcff5db5f2571d32a520baf1f04"},
-    {file = "pillow-10.2.0-pp310-pypy310_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:33870dc4653c5017bf4c8873e5488d8f8d5f8935e2f1fb9a2208c47cdd66efd2"},
-    {file = "pillow-10.2.0-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:3c31822339516fb3c82d03f30e22b1d038da87ef27b6a78c9549888f8ceda39a"},
-    {file = "pillow-10.2.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:a2b56ba36e05f973d450582fb015594aaa78834fefe8dfb8fcd79b93e64ba4c6"},
-    {file = "pillow-10.2.0-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:d8e6aeb9201e655354b3ad049cb77d19813ad4ece0df1249d3c793de3774f8c7"},
-    {file = "pillow-10.2.0-pp39-pypy39_pp73-macosx_10_10_x86_64.whl", hash = "sha256:2247178effb34a77c11c0e8ac355c7a741ceca0a732b27bf11e747bbc950722f"},
-    {file = "pillow-10.2.0-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:15587643b9e5eb26c48e49a7b33659790d28f190fc514a322d55da2fb5c2950e"},
-    {file = "pillow-10.2.0-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:753cd8f2086b2b80180d9b3010dd4ed147efc167c90d3bf593fe2af21265e5a5"},
-    {file = "pillow-10.2.0-pp39-pypy39_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:7c8f97e8e7a9009bcacbe3766a36175056c12f9a44e6e6f2d5caad06dcfbf03b"},
-    {file = "pillow-10.2.0-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:d1b35bcd6c5543b9cb547dee3150c93008f8dd0f1fef78fc0cd2b141c5baf58a"},
-    {file = "pillow-10.2.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:fe4c15f6c9285dc54ce6553a3ce908ed37c8f3825b5a51a15c91442bb955b868"},
-    {file = "pillow-10.2.0.tar.gz", hash = "sha256:e87f0b2c78157e12d7686b27d63c070fd65d994e8ddae6f328e0dcf4a0cd007e"},
+    {file = "pillow-10.3.0-cp310-cp310-macosx_10_10_x86_64.whl", hash = "sha256:90b9e29824800e90c84e4022dd5cc16eb2d9605ee13f05d47641eb183cd73d45"},
+    {file = "pillow-10.3.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:a2c405445c79c3f5a124573a051062300936b0281fee57637e706453e452746c"},
+    {file = "pillow-10.3.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:78618cdbccaa74d3f88d0ad6cb8ac3007f1a6fa5c6f19af64b55ca170bfa1edf"},
+    {file = "pillow-10.3.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:261ddb7ca91fcf71757979534fb4c128448b5b4c55cb6152d280312062f69599"},
+    {file = "pillow-10.3.0-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:ce49c67f4ea0609933d01c0731b34b8695a7a748d6c8d186f95e7d085d2fe475"},
+    {file = "pillow-10.3.0-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:b14f16f94cbc61215115b9b1236f9c18403c15dd3c52cf629072afa9d54c1cbf"},
+    {file = "pillow-10.3.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:d33891be6df59d93df4d846640f0e46f1a807339f09e79a8040bc887bdcd7ed3"},
+    {file = "pillow-10.3.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:b50811d664d392f02f7761621303eba9d1b056fb1868c8cdf4231279645c25f5"},
+    {file = "pillow-10.3.0-cp310-cp310-win32.whl", hash = "sha256:ca2870d5d10d8726a27396d3ca4cf7976cec0f3cb706debe88e3a5bd4610f7d2"},
+    {file = "pillow-10.3.0-cp310-cp310-win_amd64.whl", hash = "sha256:f0d0591a0aeaefdaf9a5e545e7485f89910c977087e7de2b6c388aec32011e9f"},
+    {file = "pillow-10.3.0-cp310-cp310-win_arm64.whl", hash = "sha256:ccce24b7ad89adb5a1e34a6ba96ac2530046763912806ad4c247356a8f33a67b"},
+    {file = "pillow-10.3.0-cp311-cp311-macosx_10_10_x86_64.whl", hash = "sha256:5f77cf66e96ae734717d341c145c5949c63180842a545c47a0ce7ae52ca83795"},
+    {file = "pillow-10.3.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:e4b878386c4bf293578b48fc570b84ecfe477d3b77ba39a6e87150af77f40c57"},
+    {file = "pillow-10.3.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fdcbb4068117dfd9ce0138d068ac512843c52295ed996ae6dd1faf537b6dbc27"},
+    {file = "pillow-10.3.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9797a6c8fe16f25749b371c02e2ade0efb51155e767a971c61734b1bf6293994"},
+    {file = "pillow-10.3.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:9e91179a242bbc99be65e139e30690e081fe6cb91a8e77faf4c409653de39451"},
+    {file = "pillow-10.3.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:1b87bd9d81d179bd8ab871603bd80d8645729939f90b71e62914e816a76fc6bd"},
+    {file = "pillow-10.3.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:81d09caa7b27ef4e61cb7d8fbf1714f5aec1c6b6c5270ee53504981e6e9121ad"},
+    {file = "pillow-10.3.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:048ad577748b9fa4a99a0548c64f2cb8d672d5bf2e643a739ac8faff1164238c"},
+    {file = "pillow-10.3.0-cp311-cp311-win32.whl", hash = "sha256:7161ec49ef0800947dc5570f86568a7bb36fa97dd09e9827dc02b718c5643f09"},
+    {file = "pillow-10.3.0-cp311-cp311-win_amd64.whl", hash = "sha256:8eb0908e954d093b02a543dc963984d6e99ad2b5e36503d8a0aaf040505f747d"},
+    {file = "pillow-10.3.0-cp311-cp311-win_arm64.whl", hash = "sha256:4e6f7d1c414191c1199f8996d3f2282b9ebea0945693fb67392c75a3a320941f"},
+    {file = "pillow-10.3.0-cp312-cp312-macosx_10_10_x86_64.whl", hash = "sha256:e46f38133e5a060d46bd630faa4d9fa0202377495df1f068a8299fd78c84de84"},
+    {file = "pillow-10.3.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:50b8eae8f7334ec826d6eeffaeeb00e36b5e24aa0b9df322c247539714c6df19"},
+    {file = "pillow-10.3.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9d3bea1c75f8c53ee4d505c3e67d8c158ad4df0d83170605b50b64025917f338"},
+    {file = "pillow-10.3.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:19aeb96d43902f0a783946a0a87dbdad5c84c936025b8419da0a0cd7724356b1"},
+    {file = "pillow-10.3.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:74d28c17412d9caa1066f7a31df8403ec23d5268ba46cd0ad2c50fb82ae40462"},
+    {file = "pillow-10.3.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:ff61bfd9253c3915e6d41c651d5f962da23eda633cf02262990094a18a55371a"},
+    {file = "pillow-10.3.0-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:d886f5d353333b4771d21267c7ecc75b710f1a73d72d03ca06df49b09015a9ef"},
+    {file = "pillow-10.3.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:4b5ec25d8b17217d635f8935dbc1b9aa5907962fae29dff220f2659487891cd3"},
+    {file = "pillow-10.3.0-cp312-cp312-win32.whl", hash = "sha256:51243f1ed5161b9945011a7360e997729776f6e5d7005ba0c6879267d4c5139d"},
+    {file = "pillow-10.3.0-cp312-cp312-win_amd64.whl", hash = "sha256:412444afb8c4c7a6cc11a47dade32982439925537e483be7c0ae0cf96c4f6a0b"},
+    {file = "pillow-10.3.0-cp312-cp312-win_arm64.whl", hash = "sha256:798232c92e7665fe82ac085f9d8e8ca98826f8e27859d9a96b41d519ecd2e49a"},
+    {file = "pillow-10.3.0-cp38-cp38-macosx_10_10_x86_64.whl", hash = "sha256:4eaa22f0d22b1a7e93ff0a596d57fdede2e550aecffb5a1ef1106aaece48e96b"},
+    {file = "pillow-10.3.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:cd5e14fbf22a87321b24c88669aad3a51ec052eb145315b3da3b7e3cc105b9a2"},
+    {file = "pillow-10.3.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1530e8f3a4b965eb6a7785cf17a426c779333eb62c9a7d1bbcf3ffd5bf77a4aa"},
+    {file = "pillow-10.3.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5d512aafa1d32efa014fa041d38868fda85028e3f930a96f85d49c7d8ddc0383"},
+    {file = "pillow-10.3.0-cp38-cp38-manylinux_2_28_aarch64.whl", hash = "sha256:339894035d0ede518b16073bdc2feef4c991ee991a29774b33e515f1d308e08d"},
+    {file = "pillow-10.3.0-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:aa7e402ce11f0885305bfb6afb3434b3cd8f53b563ac065452d9d5654c7b86fd"},
+    {file = "pillow-10.3.0-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:0ea2a783a2bdf2a561808fe4a7a12e9aa3799b701ba305de596bc48b8bdfce9d"},
+    {file = "pillow-10.3.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:c78e1b00a87ce43bb37642c0812315b411e856a905d58d597750eb79802aaaa3"},
+    {file = "pillow-10.3.0-cp38-cp38-win32.whl", hash = "sha256:72d622d262e463dfb7595202d229f5f3ab4b852289a1cd09650362db23b9eb0b"},
+    {file = "pillow-10.3.0-cp38-cp38-win_amd64.whl", hash = "sha256:2034f6759a722da3a3dbd91a81148cf884e91d1b747992ca288ab88c1de15999"},
+    {file = "pillow-10.3.0-cp39-cp39-macosx_10_10_x86_64.whl", hash = "sha256:2ed854e716a89b1afcedea551cd85f2eb2a807613752ab997b9974aaa0d56936"},
+    {file = "pillow-10.3.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:dc1a390a82755a8c26c9964d457d4c9cbec5405896cba94cf51f36ea0d855002"},
+    {file = "pillow-10.3.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4203efca580f0dd6f882ca211f923168548f7ba334c189e9eab1178ab840bf60"},
+    {file = "pillow-10.3.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3102045a10945173d38336f6e71a8dc71bcaeed55c3123ad4af82c52807b9375"},
+    {file = "pillow-10.3.0-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:6fb1b30043271ec92dc65f6d9f0b7a830c210b8a96423074b15c7bc999975f57"},
+    {file = "pillow-10.3.0-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:1dfc94946bc60ea375cc39cff0b8da6c7e5f8fcdc1d946beb8da5c216156ddd8"},
+    {file = "pillow-10.3.0-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:b09b86b27a064c9624d0a6c54da01c1beaf5b6cadfa609cf63789b1d08a797b9"},
+    {file = "pillow-10.3.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:d3b2348a78bc939b4fed6552abfd2e7988e0f81443ef3911a4b8498ca084f6eb"},
+    {file = "pillow-10.3.0-cp39-cp39-win32.whl", hash = "sha256:45ebc7b45406febf07fef35d856f0293a92e7417ae7933207e90bf9090b70572"},
+    {file = "pillow-10.3.0-cp39-cp39-win_amd64.whl", hash = "sha256:0ba26351b137ca4e0db0342d5d00d2e355eb29372c05afd544ebf47c0956ffeb"},
+    {file = "pillow-10.3.0-cp39-cp39-win_arm64.whl", hash = "sha256:50fd3f6b26e3441ae07b7c979309638b72abc1a25da31a81a7fbd9495713ef4f"},
+    {file = "pillow-10.3.0-pp310-pypy310_pp73-macosx_10_10_x86_64.whl", hash = "sha256:6b02471b72526ab8a18c39cb7967b72d194ec53c1fd0a70b050565a0f366d355"},
+    {file = "pillow-10.3.0-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:8ab74c06ffdab957d7670c2a5a6e1a70181cd10b727cd788c4dd9005b6a8acd9"},
+    {file = "pillow-10.3.0-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:048eeade4c33fdf7e08da40ef402e748df113fd0b4584e32c4af74fe78baaeb2"},
+    {file = "pillow-10.3.0-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9e2ec1e921fd07c7cda7962bad283acc2f2a9ccc1b971ee4b216b75fad6f0463"},
+    {file = "pillow-10.3.0-pp310-pypy310_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:4c8e73e99da7db1b4cad7f8d682cf6abad7844da39834c288fbfa394a47bbced"},
+    {file = "pillow-10.3.0-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:16563993329b79513f59142a6b02055e10514c1a8e86dca8b48a893e33cf91e3"},
+    {file = "pillow-10.3.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:dd78700f5788ae180b5ee8902c6aea5a5726bac7c364b202b4b3e3ba2d293170"},
+    {file = "pillow-10.3.0-pp39-pypy39_pp73-macosx_10_10_x86_64.whl", hash = "sha256:aff76a55a8aa8364d25400a210a65ff59d0168e0b4285ba6bf2bd83cf675ba32"},
+    {file = "pillow-10.3.0-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:b7bc2176354defba3edc2b9a777744462da2f8e921fbaf61e52acb95bafa9828"},
+    {file = "pillow-10.3.0-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:793b4e24db2e8742ca6423d3fde8396db336698c55cd34b660663ee9e45ed37f"},
+    {file = "pillow-10.3.0-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d93480005693d247f8346bc8ee28c72a2191bdf1f6b5db469c096c0c867ac015"},
+    {file = "pillow-10.3.0-pp39-pypy39_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:c83341b89884e2b2e55886e8fbbf37c3fa5efd6c8907124aeb72f285ae5696e5"},
+    {file = "pillow-10.3.0-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:1a1d1915db1a4fdb2754b9de292642a39a7fb28f1736699527bb649484fb966a"},
+    {file = "pillow-10.3.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:a0eaa93d054751ee9964afa21c06247779b90440ca41d184aeb5d410f20ff591"},
+    {file = "pillow-10.3.0.tar.gz", hash = "sha256:9d2455fbf44c914840c793e89aa82d0e1763a14253a000743719ae5946814b2d"},
 ]

 [package.extras]
@@ -2158,13 +2162,13 @@ testing = ["pytest", "pytest-benchmark"]

 [[package]]
 name = "pre-commit"
-version = "3.6.2"
+version = "3.7.0"
 description = "A framework for managing and maintaining multi-language pre-commit hooks."
 optional = false
 python-versions = ">=3.9"
 files = [
-    {file = "pre_commit-3.6.2-py2.py3-none-any.whl", hash = "sha256:ba637c2d7a670c10daedc059f5c49b5bd0aadbccfcd7ec15592cf9665117532c"},
-    {file = "pre_commit-3.6.2.tar.gz", hash = "sha256:c3ef34f463045c88658c5b99f38c1e297abdcc0ff13f98d3370055fbbfabc67e"},
+    {file = "pre_commit-3.7.0-py2.py3-none-any.whl", hash = "sha256:5eae9e10c2b5ac51577c3452ec0a490455c45a0533f7960f993a0d01e59decab"},
+    {file = "pre_commit-3.7.0.tar.gz", hash = "sha256:e209d61b8acdcf742404408531f0c37d49d2c734fd7cff2d6076083d191cb060"},
 ]

 [package.dependencies]
@@ -2204,22 +2208,22 @@ wcwidth = "*"

 [[package]]
 name = "protobuf"
-version = "4.25.3"
+version = "5.26.1"
 description = ""
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "protobuf-4.25.3-cp310-abi3-win32.whl", hash = "sha256:d4198877797a83cbfe9bffa3803602bbe1625dc30d8a097365dbc762e5790faa"},
-    {file = "protobuf-4.25.3-cp310-abi3-win_amd64.whl", hash = "sha256:209ba4cc916bab46f64e56b85b090607a676f66b473e6b762e6f1d9d591eb2e8"},
-    {file = "protobuf-4.25.3-cp37-abi3-macosx_10_9_universal2.whl", hash = "sha256:f1279ab38ecbfae7e456a108c5c0681e4956d5b1090027c1de0f934dfdb4b35c"},
-    {file = "protobuf-4.25.3-cp37-abi3-manylinux2014_aarch64.whl", hash = "sha256:e7cb0ae90dd83727f0c0718634ed56837bfeeee29a5f82a7514c03ee1364c019"},
-    {file = "protobuf-4.25.3-cp37-abi3-manylinux2014_x86_64.whl", hash = "sha256:7c8daa26095f82482307bc717364e7c13f4f1c99659be82890dcfc215194554d"},
-    {file = "protobuf-4.25.3-cp38-cp38-win32.whl", hash = "sha256:f4f118245c4a087776e0a8408be33cf09f6c547442c00395fbfb116fac2f8ac2"},
-    {file = "protobuf-4.25.3-cp38-cp38-win_amd64.whl", hash = "sha256:c053062984e61144385022e53678fbded7aea14ebb3e0305ae3592fb219ccfa4"},
-    {file = "protobuf-4.25.3-cp39-cp39-win32.whl", hash = "sha256:19b270aeaa0099f16d3ca02628546b8baefe2955bbe23224aaf856134eccf1e4"},
-    {file = "protobuf-4.25.3-cp39-cp39-win_amd64.whl", hash = "sha256:e3c97a1555fd6388f857770ff8b9703083de6bf1f9274a002a332d65fbb56c8c"},
-    {file = "protobuf-4.25.3-py3-none-any.whl", hash = "sha256:f0700d54bcf45424477e46a9f0944155b46fb0639d69728739c0e47bab83f2b9"},
-    {file = "protobuf-4.25.3.tar.gz", hash = "sha256:25b5d0b42fd000320bd7830b349e3b696435f3b329810427a6bcce6a5492cc5c"},
+    {file = "protobuf-5.26.1-cp310-abi3-win32.whl", hash = "sha256:3c388ea6ddfe735f8cf69e3f7dc7611e73107b60bdfcf5d0f024c3ccd3794e23"},
+    {file = "protobuf-5.26.1-cp310-abi3-win_amd64.whl", hash = "sha256:e6039957449cb918f331d32ffafa8eb9255769c96aa0560d9a5bf0b4e00a2a33"},
+    {file = "protobuf-5.26.1-cp37-abi3-macosx_10_9_universal2.whl", hash = "sha256:38aa5f535721d5bb99861166c445c4105c4e285c765fbb2ac10f116e32dcd46d"},
+    {file = "protobuf-5.26.1-cp37-abi3-manylinux2014_aarch64.whl", hash = "sha256:fbfe61e7ee8c1860855696e3ac6cfd1b01af5498facc6834fcc345c9684fb2ca"},
+    {file = "protobuf-5.26.1-cp37-abi3-manylinux2014_x86_64.whl", hash = "sha256:f7417703f841167e5a27d48be13389d52ad705ec09eade63dfc3180a959215d7"},
+    {file = "protobuf-5.26.1-cp38-cp38-win32.whl", hash = "sha256:d693d2504ca96750d92d9de8a103102dd648fda04540495535f0fec7577ed8fc"},
+    {file = "protobuf-5.26.1-cp38-cp38-win_amd64.whl", hash = "sha256:9b557c317ebe6836835ec4ef74ec3e994ad0894ea424314ad3552bc6e8835b4e"},
+    {file = "protobuf-5.26.1-cp39-cp39-win32.whl", hash = "sha256:b9ba3ca83c2e31219ffbeb9d76b63aad35a3eb1544170c55336993d7a18ae72c"},
+    {file = "protobuf-5.26.1-cp39-cp39-win_amd64.whl", hash = "sha256:7ee014c2c87582e101d6b54260af03b6596728505c79f17c8586e7523aaa8f8c"},
+    {file = "protobuf-5.26.1-py3-none-any.whl", hash = "sha256:da612f2720c0183417194eeaa2523215c4fcc1a1949772dc65f05047e08d5932"},
+    {file = "protobuf-5.26.1.tar.gz", hash = "sha256:8ca2a1d97c290ec7b16e4e5dff2e5ae150cc1582f55b5ab300d45cb0dfa90e51"},
 ]

 [[package]]
@@ -2438,6 +2442,7 @@ files = [
    {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:69b023b2b4daa7548bcfbd4aa3da05b3a74b772db9e23b982788168117739938"},
    {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:81e0b275a9ecc9c0c0c07b4b90ba548307583c125f54d5b6946cfee6360c733d"},
    {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ba336e390cd8e4d1739f42dfe9bb83a3cc2e80f567d8805e11b46f4a943f5515"},
+    {file = "PyYAML-6.0.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:326c013efe8048858a6d312ddd31d56e468118ad4cdeda36c719bf5bb6192290"},
    {file = "PyYAML-6.0.1-cp310-cp310-win32.whl", hash = "sha256:bd4af7373a854424dabd882decdc5579653d7868b8fb26dc7d0e99f823aa5924"},
    {file = "PyYAML-6.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:fd1592b3fdf65fff2ad0004b5e363300ef59ced41c2e6b3a99d4089fa8c5435d"},
    {file = "PyYAML-6.0.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:6965a7bc3cf88e5a1c3bd2e0b5c22f8d677dc88a455344035f03399034eb3007"},
@@ -2445,8 +2450,16 @@ files = [
    {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:42f8152b8dbc4fe7d96729ec2b99c7097d656dc1213a3229ca5383f973a5ed6d"},
    {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:062582fca9fabdd2c8b54a3ef1c978d786e0f6b3a1510e0ac93ef59e0ddae2bc"},
    {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d2b04aac4d386b172d5b9692e2d2da8de7bfb6c387fa4f801fbf6fb2e6ba4673"},
+    {file = "PyYAML-6.0.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:e7d73685e87afe9f3b36c799222440d6cf362062f78be1013661b00c5c6f678b"},
    {file = "PyYAML-6.0.1-cp311-cp311-win32.whl", hash = "sha256:1635fd110e8d85d55237ab316b5b011de701ea0f29d07611174a1b42f1444741"},
    {file = "PyYAML-6.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:bf07ee2fef7014951eeb99f56f39c9bb4af143d8aa3c21b1677805985307da34"},
+    {file = "PyYAML-6.0.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:855fb52b0dc35af121542a76b9a84f8d1cd886ea97c84703eaa6d88e37a2ad28"},
+    {file = "PyYAML-6.0.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:40df9b996c2b73138957fe23a16a4f0ba614f4c0efce1e9406a184b6d07fa3a9"},
+    {file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a08c6f0fe150303c1c6b71ebcd7213c2858041a7e01975da3a99aed1e7a378ef"},
+    {file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c22bec3fbe2524cde73d7ada88f6566758a8f7227bfbf93a408a9d86bcc12a0"},
+    {file = "PyYAML-6.0.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8d4e9c88387b0f5c7d5f281e55304de64cf7f9c0021a3525bd3b1c542da3b0e4"},
+    {file = "PyYAML-6.0.1-cp312-cp312-win32.whl", hash = "sha256:d483d2cdf104e7c9fa60c544d92981f12ad66a457afae824d146093b8c294c54"},
+    {file = "PyYAML-6.0.1-cp312-cp312-win_amd64.whl", hash = "sha256:0d3304d8c0adc42be59c5f8a4d9e3d7379e6955ad754aa9d6ab7a398b59dd1df"},
    {file = "PyYAML-6.0.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:50550eb667afee136e9a77d6dc71ae76a44df8b3e51e41b77f6de2932bfe0f47"},
    {file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1fe35611261b29bd1de0070f0b2f47cb6ff71fa6595c077e42bd0c419fa27b98"},
    {file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:704219a11b772aea0d8ecd7058d0082713c3562b4e271b849ad7dc4a5c90c13c"},
@@ -2463,6 +2476,7 @@ files = [
    {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a0cd17c15d3bb3fa06978b4e8958dcdc6e0174ccea823003a106c7d4d7899ac5"},
    {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:28c119d996beec18c05208a8bd78cbe4007878c6dd15091efb73a30e90539696"},
    {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7e07cbde391ba96ab58e532ff4803f79c4129397514e1413a7dc761ccd755735"},
+    {file = "PyYAML-6.0.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:49a183be227561de579b4a36efbb21b3eab9651dd81b1858589f796549873dd6"},
    {file = "PyYAML-6.0.1-cp38-cp38-win32.whl", hash = "sha256:184c5108a2aca3c5b3d3bf9395d50893a7ab82a38004c8f61c258d4428e80206"},
    {file = "PyYAML-6.0.1-cp38-cp38-win_amd64.whl", hash = "sha256:1e2722cc9fbb45d9b87631ac70924c11d3a401b2d7f410cc0e3bbf249f2dca62"},
    {file = "PyYAML-6.0.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:9eb6caa9a297fc2c2fb8862bc5370d0303ddba53ba97e71f08023b6cd73d16a8"},
@@ -2470,6 +2484,7 @@ files = [
    {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5773183b6446b2c99bb77e77595dd486303b4faab2b086e7b17bc6bef28865f6"},
    {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b786eecbdf8499b9ca1d697215862083bd6d2a99965554781d0d8d1ad31e13a0"},
    {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bc1bf2925a1ecd43da378f4db9e4f799775d6367bdb94671027b73b393a7c42c"},
+    {file = "PyYAML-6.0.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:04ac92ad1925b2cff1db0cfebffb6ffc43457495c9b3c39d3fcae417d7125dc5"},
    {file = "PyYAML-6.0.1-cp39-cp39-win32.whl", hash = "sha256:faca3bdcf85b2fc05d06ff3fbc1f83e1391b3e724afa3feba7d13eeab355484c"},
    {file = "PyYAML-6.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:510c9deebc5c0225e8c96813043e62b680ba2f9c50a08d3724c7f28a747d1486"},
    {file = "PyYAML-6.0.1.tar.gz", hash = "sha256:bfdf460b1736c775f2ba9f6a92bca30bc2095067b8a9d77876d1fad6cc3b4a43"},
@@ -2596,13 +2611,13 @@ cffi = {version = "*", markers = "implementation_name == \"pypy\""}

 [[package]]
 name = "referencing"
-version = "0.33.0"
+version = "0.34.0"
 description = "JSON Referencing + Python"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "referencing-0.33.0-py3-none-any.whl", hash = "sha256:39240f2ecc770258f28b642dd47fd74bc8b02484de54e1882b74b35ebd779bd5"},
-    {file = "referencing-0.33.0.tar.gz", hash = "sha256:c775fedf74bc0f9189c2a3be1c12fd03e8c23f4d371dce795df44e06c5b412f7"},
+    {file = "referencing-0.34.0-py3-none-any.whl", hash = "sha256:d53ae300ceddd3169f1ffa9caf2cb7b769e92657e4fafb23d34b93679116dfd4"},
+    {file = "referencing-0.34.0.tar.gz", hash = "sha256:5773bd84ef41799a5a8ca72dc34590c041eb01bf9aa02632b4a973fb0181a844"},
 ]

 [package.dependencies]
@@ -2867,28 +2882,28 @@ files = [

 [[package]]
 name = "ruff"
-version = "0.2.2"
+version = "0.3.4"
 description = "An extremely fast Python linter and code formatter, written in Rust."
 optional = false
 python-versions = ">=3.7"
 files = [
-    {file = "ruff-0.2.2-py3-none-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:0a9efb032855ffb3c21f6405751d5e147b0c6b631e3ca3f6b20f917572b97eb6"},
-    {file = "ruff-0.2.2-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:d450b7fbff85913f866a5384d8912710936e2b96da74541c82c1b458472ddb39"},
-    {file = "ruff-0.2.2-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ecd46e3106850a5c26aee114e562c329f9a1fbe9e4821b008c4404f64ff9ce73"},
-    {file = "ruff-0.2.2-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:5e22676a5b875bd72acd3d11d5fa9075d3a5f53b877fe7b4793e4673499318ba"},
-    {file = "ruff-0.2.2-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1695700d1e25a99d28f7a1636d85bafcc5030bba9d0578c0781ba1790dbcf51c"},
-    {file = "ruff-0.2.2-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:b0c232af3d0bd8f521806223723456ffebf8e323bd1e4e82b0befb20ba18388e"},
-    {file = "ruff-0.2.2-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f63d96494eeec2fc70d909393bcd76c69f35334cdbd9e20d089fb3f0640216ca"},
-    {file = "ruff-0.2.2-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:6a61ea0ff048e06de273b2e45bd72629f470f5da8f71daf09fe481278b175001"},
-    {file = "ruff-0.2.2-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5e1439c8f407e4f356470e54cdecdca1bd5439a0673792dbe34a2b0a551a2fe3"},
-    {file = "ruff-0.2.2-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:940de32dc8853eba0f67f7198b3e79bc6ba95c2edbfdfac2144c8235114d6726"},
-    {file = "ruff-0.2.2-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:0c126da55c38dd917621552ab430213bdb3273bb10ddb67bc4b761989210eb6e"},
-    {file = "ruff-0.2.2-py3-none-musllinux_1_2_i686.whl", hash = "sha256:3b65494f7e4bed2e74110dac1f0d17dc8e1f42faaa784e7c58a98e335ec83d7e"},
-    {file = "ruff-0.2.2-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:1ec49be4fe6ddac0503833f3ed8930528e26d1e60ad35c2446da372d16651ce9"},
-    {file = "ruff-0.2.2-py3-none-win32.whl", hash = "sha256:d920499b576f6c68295bc04e7b17b6544d9d05f196bb3aac4358792ef6f34325"},
-    {file = "ruff-0.2.2-py3-none-win_amd64.whl", hash = "sha256:cc9a91ae137d687f43a44c900e5d95e9617cb37d4c989e462980ba27039d239d"},
-    {file = "ruff-0.2.2-py3-none-win_arm64.whl", hash = "sha256:c9d15fc41e6054bfc7200478720570078f0b41c9ae4f010bcc16bd6f4d1aacdd"},
-    {file = "ruff-0.2.2.tar.gz", hash = "sha256:e62ed7f36b3068a30ba39193a14274cd706bc486fad521276458022f7bccb31d"},
+    {file = "ruff-0.3.4-py3-none-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:60c870a7d46efcbc8385d27ec07fe534ac32f3b251e4fc44b3cbfd9e09609ef4"},
+    {file = "ruff-0.3.4-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:6fc14fa742e1d8f24910e1fff0bd5e26d395b0e0e04cc1b15c7c5e5fe5b4af91"},
+    {file = "ruff-0.3.4-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d3ee7880f653cc03749a3bfea720cf2a192e4f884925b0cf7eecce82f0ce5854"},
+    {file = "ruff-0.3.4-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:cf133dd744f2470b347f602452a88e70dadfbe0fcfb5fd46e093d55da65f82f7"},
+    {file = "ruff-0.3.4-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3f3860057590e810c7ffea75669bdc6927bfd91e29b4baa9258fd48b540a4365"},
+    {file = "ruff-0.3.4-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:986f2377f7cf12efac1f515fc1a5b753c000ed1e0a6de96747cdf2da20a1b369"},
+    {file = "ruff-0.3.4-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c4fd98e85869603e65f554fdc5cddf0712e352fe6e61d29d5a6fe087ec82b76c"},
+    {file = "ruff-0.3.4-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:64abeed785dad51801b423fa51840b1764b35d6c461ea8caef9cf9e5e5ab34d9"},
+    {file = "ruff-0.3.4-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:df52972138318bc7546d92348a1ee58449bc3f9eaf0db278906eb511889c4b50"},
+    {file = "ruff-0.3.4-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:98e98300056445ba2cc27d0b325fd044dc17fcc38e4e4d2c7711585bd0a958ed"},
+    {file = "ruff-0.3.4-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:519cf6a0ebed244dce1dc8aecd3dc99add7a2ee15bb68cf19588bb5bf58e0488"},
+    {file = "ruff-0.3.4-py3-none-musllinux_1_2_i686.whl", hash = "sha256:bb0acfb921030d00070539c038cd24bb1df73a2981e9f55942514af8b17be94e"},
+    {file = "ruff-0.3.4-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:cf187a7e7098233d0d0c71175375c5162f880126c4c716fa28a8ac418dcf3378"},
+    {file = "ruff-0.3.4-py3-none-win32.whl", hash = "sha256:af27ac187c0a331e8ef91d84bf1c3c6a5dea97e912a7560ac0cef25c526a4102"},
+    {file = "ruff-0.3.4-py3-none-win_amd64.whl", hash = "sha256:de0d5069b165e5a32b3c6ffbb81c350b1e3d3483347196ffdf86dc0ef9e37dd6"},
+    {file = "ruff-0.3.4-py3-none-win_arm64.whl", hash = "sha256:6810563cc08ad0096b57c717bd78aeac888a1bfd38654d9113cb3dc4d3f74232"},
+    {file = "ruff-0.3.4.tar.gz", hash = "sha256:f0f4484c6541a99862b693e13a151435a279b271cff20e37101116a21e2a1ad1"},
 ]

 [[package]]
@@ -3234,13 +3249,13 @@ test = ["argcomplete (>=3.0.3)", "mypy (>=1.7.0)", "pre-commit", "pytest (>=7.0,

 [[package]]
 name = "types-python-dateutil"
-version = "2.8.19.20240311"
+version = "2.9.0.20240316"
 description = "Typing stubs for python-dateutil"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "types-python-dateutil-2.8.19.20240311.tar.gz", hash = "sha256:51178227bbd4cbec35dc9adffbf59d832f20e09842d7dcb8c73b169b8780b7cb"},
-    {file = "types_python_dateutil-2.8.19.20240311-py3-none-any.whl", hash = "sha256:ef813da0809aca76472ca88807addbeea98b19339aebe56159ae2f4b4f70857a"},
+    {file = "types-python-dateutil-2.9.0.20240316.tar.gz", hash = "sha256:5d2f2e240b86905e40944dd787db6da9263f0deabef1076ddaed797351ec0202"},
+    {file = "types_python_dateutil-2.9.0.20240316-py3-none-any.whl", hash = "sha256:6b8cb66d960771ce5ff974e9dd45e38facb81718cc1e208b10b1baccbfdbee3b"},
 ]

 [[package]]
@@ -3415,13 +3430,13 @@ dev = ["black (>=19.3b0)", "pytest (>=4.6.2)"]

 [[package]]
 name = "zipp"
-version = "3.18.0"
+version = "3.18.1"
 description = "Backport of pathlib-compatible object wrapper for zip files"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "zipp-3.18.0-py3-none-any.whl", hash = "sha256:c1bb803ed69d2cce2373152797064f7e79bc43f0a3748eb494096a867e0ebf79"},
-    {file = "zipp-3.18.0.tar.gz", hash = "sha256:df8d042b02765029a09b157efd8e820451045890acc30f8e37dd2f94a060221f"},
+    {file = "zipp-3.18.1-py3-none-any.whl", hash = "sha256:206f5a15f2af3dbaee80769fb7dc6f249695e940acca08dfb2a4769fe61e538b"},
+    {file = "zipp-3.18.1.tar.gz", hash = "sha256:2884ed22e7d8961de1c9a05142eb69a247f120291bc0206a00a7642f09b5b715"},
 ]

 [package.extras]
@@ -3431,4 +3446,4 @@ testing = ["big-O", "jaraco.functools", "jaraco.itertools", "more-itertools", "p
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.8.0,<3.13"
-content-hash = "791d690524cb9f690de5e42822ef6f7a5a3d1179e464eb2f36824a433406cf15"
+content-hash = "ace5b40bd629af8ec1a369f1cfb507db7bb6b18c1387357e0d029d9b50a66335"
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "fastembed"
-version = "0.2.3"
+version = "0.2.6"
 description = "Fast, light, accurate library built for retrieval embedding generation"
 authors = ["NirantK <nirant.bits@gmail.com>"]
 license = "Apache License"
@@ -15,7 +15,6 @@ python = ">=3.8.0,<3.13"
 onnx = "^1.15.0"
 onnxruntime = "^1.17.0"
 tqdm = "^4.66"
-requests = "^2.31"
 tokenizers = "^0.15.1"
 huggingface-hub = "^0.20"
 loguru = "^0.7.2"
@@ -26,7 +25,7 @@ numpy = [

 [tool.poetry.group.dev.dependencies]
 pytest = "^7.4.2"
-ruff = "^0.2.2"
+ruff = "^0.3.1"
 notebook = ">=7.0.2"
 pre-commit = {version = "^3.6.2", python = ">=3.9,<3.12" }

@@ -43,4 +42,4 @@ requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"

 [tool.ruff]
-line-length = 120
+line-length = 99
@@ -2,8 +2,24 @@ import pytest
 from fastembed.sparse.sparse_text_embedding import SparseTextEmbedding

 CANONICAL_COLUMN_VALUES = {
-    "prithvida/SPLADE_PP_en_v1": {
-        "indices": [2040, 2047, 2088, 2299, 2748, 3011, 3376, 3795, 4774, 5304, 5798, 6160, 7592, 7632, 8484],
+    "prithvida/Splade_PP_en_v1": {
+        "indices": [
+            2040,
+            2047,
+            2088,
+            2299,
+            2748,
+            3011,
+            3376,
+            3795,
+            4774,
+            5304,
+            5798,
+            6160,
+            7592,
+            7632,
+            8484,
+        ],
        "values": [
            0.4219532012939453,
            0.4320072531700134,
@@ -40,3 +56,43 @@ def test_batch_embedding():

        for i, value in enumerate(result.values):
            assert pytest.approx(value, abs=0.001) == expected_result["values"][i]
+
+
+def test_single_embedding():
+    docs_to_embed = docs
+
+    for model_name, expected_result in CANONICAL_COLUMN_VALUES.items():
+        print("evaluating", model_name)
+        model = SparseTextEmbedding(model_name=model_name)
+        result = next(iter(model.embed(docs_to_embed, batch_size=6)))
+        print(result.indices)
+
+        assert result.indices.tolist() == expected_result["indices"]
+
+        for i, value in enumerate(result.values):
+            assert pytest.approx(value, abs=0.001) == expected_result["values"][i]
+
+
+def test_parallel_processing():
+    import numpy as np
+
+    model = SparseTextEmbedding(
+        model_name="prithivida/Splade_PP_en_v1",
+    )
+    docs = ["hello world", "flag embedding"] * 30
+    sparse_embeddings_duo = list(model.embed(docs, batch_size=10, parallel=2))
+    sparse_embeddings_all = list(model.embed(docs, batch_size=10, parallel=0))
+    sparse_embeddings = list(model.embed(docs, batch_size=10, parallel=None))
+
+    assert len(sparse_embeddings) == len(sparse_embeddings_duo) == len(sparse_embeddings_all) == len(docs)
+
+    for sparse_embedding, sparse_embedding_duo, sparse_embedding_all in zip(
+        sparse_embeddings, sparse_embeddings_duo, sparse_embeddings_all
+    ):
+        assert (
+            sparse_embedding.indices.tolist()
+            == sparse_embedding_duo.indices.tolist()
+            == sparse_embedding_all.indices.tolist()
+        )
+        assert np.allclose(sparse_embedding.values, sparse_embedding_duo.values, atol=1e-3)
+        assert np.allclose(sparse_embedding.values, sparse_embedding_all.values, atol=1e-3)
@@ -8,6 +8,7 @@ from fastembed.text.text_embedding import TextEmbedding
 CANONICAL_VECTOR_VALUES = {
    "BAAI/bge-small-en": np.array([-0.0232, -0.0255, 0.0174, -0.0639, -0.0006]),
    "BAAI/bge-small-en-v1.5": np.array([0.01522374, -0.02271799, 0.00860278, -0.07424029, 0.00386434]),
+    "BAAI/bge-small-en-v1.5-quantized": np.array([0.01522374, -0.02271799, 0.00860278, -0.07424029, 0.00386434]),
    "BAAI/bge-small-zh-v1.5": np.array([-0.01023294, 0.07634465, 0.0691722, -0.04458365, -0.03160762]),
    "BAAI/bge-base-en": np.array([0.0115, 0.0372, 0.0295, 0.0121, 0.0346]),
    "BAAI/bge-base-en-v1.5": np.array([0.01129394, 0.05493144, 0.02615099, 0.00328772, 0.02996045]),
@@ -26,6 +27,10 @@ CANONICAL_VECTOR_VALUES = {
        [-1.6531514e-02, 8.5380634e-05, -1.8171231e-01, -3.9333291e-03, 1.2763254e-02]
    ),
    "thenlper/gte-large": np.array([-0.01920587, 0.00113156, -0.00708992, -0.00632304, -0.04025577]),
+    "mixedbread-ai/mxbai-embed-large-v1": np.array([0.02295546, 0.03196154, 0.016512, -0.04031524, -0.0219634]),
+    "nomic-ai/nomic-embed-text-v1.5-Q": np.array(
+        [-0.01554983, 0.0129992, -0.17909265, -0.01062993, 0.00512859]
+    ),
 }
Author	SHA1	Message	Date
Anush008	24dd472185	chore: updated model file path	2024-04-17 02:30:02 +05:30
Anush008	221b554228	test: nomic-ai/nomic-embed-text-v1.5-Q	2024-04-17 02:23:24 +05:30
Anush	fff693b46d	Merge branch 'removed-gcs' into QModels	2024-04-17 02:14:28 +05:30
Anush008	1dbef6b239	feat: Quantized models support	2024-04-17 02:13:58 +05:30
Anush	ff82bf7174	chore: Updated source onnx_embedding.py	2024-04-17 02:10:55 +05:30
Anush008	c0e457305a	refactor: removed GCS sources	2024-04-16 23:06:56 +05:30
Andrew Green	9bad44368e	Workaround for running on SLURM (#198 ) * Workaround for running on SLURM onnxruntime would usually get the number of threads from OMP_NUM_THREADS, but that isn't set on SLURM which handles the number of threads differently. This addition tries to figure out if we're running under SLURM, and if so sets the session options accordingly using SLURM environment variables instead. Tested working with latest versions of onnxruntime and fastembed on slurm 23.02.07 * onnxruntime requires number of threads be an integer Caused by me having mis-matched version from my machine and the slurm cluster :( * `os.getenv` returns None for unset environment variables, fix logic Instead of empty string, which I thought it did	2024-04-15 19:14:11 +05:30
dependabot[bot]andNirant	a5cab7a31a	build(deps): bump idna from 3.6 to 3.7 (#195 ) Bumps [idna](https://github.com/kjd/idna) from 3.6 to 3.7. - [Release notes](https://github.com/kjd/idna/releases) - [Changelog](https://github.com/kjd/idna/blob/master/HISTORY.rst) - [Commits](https://github.com/kjd/idna/compare/v3.6...v3.7) --- updated-dependencies: - dependency-name: idna dependency-type: indirect ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Nirant <NirantK@users.noreply.github.com>	2024-04-15 06:04:54 +05:30
Anush	e55c145924	chore: Exclude unused model repo files (#196 ) * chore: Exclude unused model files * fix: blob pattern	2024-04-12 20:15:02 +05:30
dependabot[bot]andNirant	ad02f60eea	build(deps-dev): bump pillow from 10.2.0 to 10.3.0 (#186 ) Bumps [pillow](https://github.com/python-pillow/Pillow) from 10.2.0 to 10.3.0. - [Release notes](https://github.com/python-pillow/Pillow/releases) - [Changelog](https://github.com/python-pillow/Pillow/blob/main/CHANGES.rst) - [Commits](https://github.com/python-pillow/Pillow/compare/10.2.0...10.3.0) --- updated-dependencies: - dependency-name: pillow dependency-type: direct:development ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Nirant <NirantK@users.noreply.github.com>	2024-04-08 16:21:32 +05:30
NirantandGeorge	2fcec07f1b	Add Python version to the ISSUE_TEMPLATE (#188 ) * Add Python version * Update .github/ISSUE_TEMPLATE/bug-report.yml Co-authored-by: George <george.panchuk@qdrant.tech> --------- Co-authored-by: George <george.panchuk@qdrant.tech>	2024-04-08 16:05:29 +05:30
George	f340a73a3e	refactoring: update binary quantization notebook (#180 )	2024-04-02 14:45:27 +05:30
Nirant	335f673f3a	Update bug-report.yml	2024-04-02 13:51:51 +05:30
Nirant	ee7ba0a536	Update bug-report.yml	2024-04-02 13:51:27 +05:30
George	912e95e5c8	fix: remove model archive if model extraction was not finished correctly (#179 )	2024-04-01 20:11:32 +02:00
Nirant	c09909773e	Add Execution Counts (#177 ) * Update notebooks * Update FastEmbed usage across docs * Refactor code for better readability and maintainability * Clean outputs * Change dataset * Add numbers inline in output * Remove inline outputs since I used :memory: * Fix syntax error in Hindi_Tamil_RAG_with_Navarasa7B.ipynb	2024-04-01 20:48:26 +05:30
Nirant	3d2254d215	Bump version to 0.2.6 in pyproject.toml (#175 )	2024-04-01 17:16:07 +05:30
GeorgeandNirant Kasliwal	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	d6f9ace425	Update size_in_GB for BAAI/bge-small-en-v1.5 model (#176 )	2024-04-01 16:40:45 +05:30
George Nirant Nirant Kasliwal	8b7b8476a5	fix: fix model sizes in supported models lists (#167 ) * fix: fix model sizes in supported models lists * fix: remove redundant comment * fix: fix test * fix: update supported models notebook * Consistentcy around quantization in supported_onnx_models --------- Co-authored-by: Nirant <NirantK@users.noreply.github.com> Co-authored-by: Nirant Kasliwal <nirant.bits@gmail.com>	2024-04-01 16:18:49 +05:30
George	ae35a96bcb	new: simplify imports (#171 ) * new: simplify imports * refactoring: update import	2024-04-01 12:58:26 +05:30
GeorgeandNirant	25671ec349	Update ruff (#172 ) * refactoring: reduce max line-length * new: update ruff --------- Co-authored-by: Nirant <NirantK@users.noreply.github.com>	2024-04-01 12:55:15 +05:30
George	ce98631b9a	Fix spladepp parallelism (#169 ) * fix: add get_worker_class implementation to spladepp * fix: add tests for parallel embed for spladepp	2024-04-01 10:22:24 +05:30
George	0a4ed42b58	fix: unify existing patterns, remove redundant (#168 )	2024-03-30 14:40:19 +05:30
NirantandAnush	e3d2e1dc44	Hybrid Search Tutorial (#165 ) * Re-organize docs * Rename notebooks * Move nbs * Working Sparse and Dense Search * Add RRF * Refactor code to improve performance and readability * Add ESCI label for the RRF results * Update docs/examples/Hybrid_Search.ipynb Co-authored-by: Anush <anushshetty90@gmail.com> * Update docs/examples/Hybrid_Search.ipynb Co-authored-by: Anush <anushshetty90@gmail.com> * Remove unnecessary code and update vector format --------- Co-authored-by: Anush <anushshetty90@gmail.com>	2024-03-29 21:10:14 +05:30
Nirant	62c21b0237	Add misspelled version of SPLADE++ model for English (#161 )	2024-03-22 21:06:03 +05:30
Anush	d791f38704	chore: case-insensitive model_management.py (#160 )	2024-03-22 21:02:31 +05:30
Nirant Kasliwal	c651b2b539	Update SPLADE notebook with new sections	2024-03-22 15:18:34 +05:30
Yuvraj WaleandNirant	bc1e23849b	feat: support mixedbread-ai/mxbai-embed-large-v1 (#158 ) * add: support mixedbread-ai/mxbai-embed-large-v1 * refactor: canonical vector * Update fastembed/text/onnx_embedding.py --------- Co-authored-by: Nirant <NirantK@users.noreply.github.com>	2024-03-22 06:23:54 +05:30
Nirant	4db4839995	[PyPi Publish] Bump version to 0.2.5 in pyproject.toml (#156 ) * Bump version to 0.2.5 in pyproject.toml * chore: case insensitive check (#157)	2024-03-20 19:11:44 +05:30
NirantandAnush	96a2a9097a	Fix model name typo + Add SPLADE notebook (#155 ) * Rename model + Add SPLADE notebook * Update docs/examples/SPLADE_with_FastEmbed.ipynb Co-authored-by: Anush <anushshetty90@gmail.com> * Update docs/examples/SPLADE_with_FastEmbed.ipynb Co-authored-by: Anush <anushshetty90@gmail.com> * Update docs/examples/SPLADE_with_FastEmbed.ipynb Co-authored-by: Anush <anushshetty90@gmail.com> * Update CANONICAL_COLUMN_VALUES in test_sparse_embeddings.py --------- Co-authored-by: Anush <anushshetty90@gmail.com>	2024-03-20 18:15:53 +05:30
NirantandKumar Shivendu	256b2265d5	Move CONTRIBUTING.md + Add Test for Adding New Models (#154 ) * Move CONTRIBUTING.md + Ad Test for Adding New Models * Update CONTRIBUTING.md Co-authored-by: Kumar Shivendu <kshivendu1@gmail.com> --------- Co-authored-by: Kumar Shivendu <kshivendu1@gmail.com>	2024-03-18 19:58:02 +05:30
NirantandKumar Shivendu	1e91c8d165	Fix Issue Template forms (#152 ) * Add CONTRIBUTING.md file with guidelines for contributing to FastEmbed * Add code linting and pre-commit info to CONTRIBUTING * Update CONTRIBUTING.md Co-authored-by: Kumar Shivendu <kshivendu1@gmail.com> * Add bug/new model issue template and move CONTRIBUTING.md * Re-organize issue templates --------- Co-authored-by: Kumar Shivendu <kshivendu1@gmail.com>	2024-03-14 15:11:23 +05:30
Nirant	a761f456b2	Add import statement for version debugging (#151 )	2024-03-14 15:02:15 +05:30
NirantandKumar Shivendu	287e19c494	Add CONTRIBUTING.md file with guidelines for contributing to FastEmbed (#150 ) * Add CONTRIBUTING.md file with guidelines for contributing to FastEmbed * Add code linting and pre-commit info to CONTRIBUTING * Update CONTRIBUTING.md Co-authored-by: Kumar Shivendu <kshivendu1@gmail.com> * Add bug/new model issue template and move CONTRIBUTING.md --------- Co-authored-by: Kumar Shivendu <kshivendu1@gmail.com>	2024-03-14 14:50:48 +05:30
Anush	6a94994038	Release v0.2.4 (#149 )	2024-03-13 23:56:01 +05:30
Andrey Vasnetsov	361f674e47	avoid changing output dimentionality for a single input (#148 )	2024-03-13 23:38:51 +05:30