forked from Archives/langchain
You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
121 lines
2.7 KiB
Plaintext
121 lines
2.7 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"id": "ed47bb62",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Sentence Transformers Embeddings\n",
|
|
"\n",
|
|
"Let's generate embeddings using the [SentenceTransformers](https://www.sbert.net/) integration. SentenceTransformers is a python package that can generate text and image embeddings, originating from [Sentence-BERT](https://arxiv.org/abs/1908.10084)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"id": "06c9f47d",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"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 sentence_transformers > /dev/null"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 8,
|
|
"id": "861521a9",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.embeddings import SentenceTransformerEmbeddings "
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 9,
|
|
"id": "ff9be586",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"embeddings = SentenceTransformerEmbeddings(model=\"all-MiniLM-L6-v2\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 10,
|
|
"id": "d0a98ae9",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"text = \"This is a test document.\""
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 11,
|
|
"id": "5d6c682b",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"query_result = embeddings.embed_query(text)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 12,
|
|
"id": "bb5e74c0",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"doc_result = embeddings.embed_documents([text, \"This is not a test document.\"])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "aaad49f8",
|
|
"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": "3.11.2"
|
|
},
|
|
"vscode": {
|
|
"interpreter": {
|
|
"hash": "7377c2ccc78bc62c2683122d48c8cd1fb85a53850a1b1fc29736ed39852c9885"
|
|
}
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|