mirror of
https://github.com/hwchase17/langchain
synced 2024-10-29 17:07:25 +00:00
fdba711d28
Updated `integrations/embeddings`: fixed titles; added links, descriptions Updated `integrations/providers`.
100 lines
2.3 KiB
Plaintext
100 lines
2.3 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "719619d3",
|
|
"metadata": {},
|
|
"source": [
|
|
"# BGE on Hugging Face\n",
|
|
"\n",
|
|
">[BGE models on the HuggingFace](https://huggingface.co/BAAI/bge-large-en) are [the best open-source embedding models](https://huggingface.co/spaces/mteb/leaderboard).\n",
|
|
">BGE model is created by the [Beijing Academy of Artificial Intelligence (BAAI)](https://www.baai.ac.cn/english.html). `BAAI` is a private non-profit organization engaged in AI research and development.\n",
|
|
"\n",
|
|
"This notebook shows how to use `BGE Embeddings` through `Hugging Face`"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "f7a54279",
|
|
"metadata": {
|
|
"scrolled": true
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"#!pip install sentence_transformers"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "9e1d5b6b",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.embeddings import HuggingFaceBgeEmbeddings\n",
|
|
"\n",
|
|
"model_name = \"BAAI/bge-small-en\"\n",
|
|
"model_kwargs = {'device': 'cpu'}\n",
|
|
"encode_kwargs = {'normalize_embeddings': False}\n",
|
|
"hf = HuggingFaceBgeEmbeddings(\n",
|
|
" model_name=model_name,\n",
|
|
" model_kwargs=model_kwargs,\n",
|
|
" encode_kwargs=encode_kwargs\n",
|
|
")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"id": "e59d1a89",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"384"
|
|
]
|
|
},
|
|
"execution_count": 5,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"embedding = hf.embed_query(\"hi this is harrison\")\n",
|
|
"len(embedding)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "e596315f",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
}
|
|
],
|
|
"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": "3.10.12"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|