mirror of
https://github.com/qdrant/fastembed.git
synced 2026-08-01 15:40:55 -05:00
81bab0cd1d
* Update version from 0.2.0 (yanked) to 0.2.1 * Update text embedding to include prefix for passages and queries * Update supported models to use the latest API * * fix(text_embedding_base.py): remove unnecessary prefix from texts in embed method * feat(text_embedding_base.py): update query_embed method to updated instruction for the v1.5 model * Remove comparison, since the ranking is identical even with varying embedding * Refactor text embedding query handling
242 lines
11 KiB
Plaintext
242 lines
11 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"%load_ext autoreload\n",
|
|
"%autoreload 2"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"metadata": {},
|
|
"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>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",
|
|
" </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",
|
|
" </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",
|
|
" </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",
|
|
" </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",
|
|
" </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",
|
|
" </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",
|
|
" </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",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>8</th>\n",
|
|
" <td>intfloat/multilingual-e5-large</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",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>9</th>\n",
|
|
" <td>sentence-transformers/paraphrase-multilingual-mpnet-base-v2</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",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>10</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",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>11</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",
|
|
" </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 intfloat/multilingual-e5-large 1024 \n",
|
|
"9 sentence-transformers/paraphrase-multilingual-mpnet-base-v2 768 \n",
|
|
"10 jinaai/jina-embeddings-v2-base-en 768 \n",
|
|
"11 jinaai/jina-embeddings-v2-small-en 512 \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 Multilingual model, e5-large. Recommend using this model for non-English languages \n",
|
|
"9 Sentence-transformers model for tasks like clustering or semantic search \n",
|
|
"10 English embedding model supporting 8192 sequence length \n",
|
|
"11 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 2.24 \n",
|
|
"9 1.11 \n",
|
|
"10 0.55 \n",
|
|
"11 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 {'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-multilingual-e5-large.tar.gz', 'hf': 'qdrant/multilingual-e5-large-onnx'} \n",
|
|
"9 {'hf': 'xenova/paraphrase-multilingual-mpnet-base-v2'} \n",
|
|
"10 {'hf': 'xenova/jina-embeddings-v2-base-en'} \n",
|
|
"11 {'hf': 'xenova/jina-embeddings-v2-small-en'} "
|
|
]
|
|
},
|
|
"execution_count": 4,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"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())"
|
|
]
|
|
}
|
|
],
|
|
"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": "3.11.5"
|
|
},
|
|
"orig_nbformat": 4
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 2
|
|
}
|