forked from Archives/langchain
166 lines
3.3 KiB
Plaintext
166 lines
3.3 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "eb1c0ea9",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Aleph Alpha\n",
|
|
"\n",
|
|
"There are two possible ways to use Aleph Alpha's semantic embeddings. If you have texts with a dissimilar structure (e.g. a Document and a Query) you would want to use asymmetric embeddings. Conversely, for texts with comparable structures, symmetric embeddings are the suggested approach."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "9ecc84f9",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Asymmetric"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"id": "8a920a89",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.embeddings import AlephAlphaAsymmetricSemanticEmbedding"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"id": "f2d04da3",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"document = \"This is a content of the document\"\n",
|
|
"query = \"What is the contnt of the document?\""
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "e6ecde96",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"embeddings = AlephAlphaAsymmetricSemanticEmbedding()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "90e68411",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"doc_result = embeddings.embed_documents([document])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "55903233",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"query_result = embeddings.embed_query(query)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "b8c00aab",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Symmetric"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "eabb763a",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.embeddings import AlephAlphaSymmetricSemanticEmbedding"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"id": "0ad799f7",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"text = \"This is a test text\""
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "af86dc10",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"embeddings = AlephAlphaSymmetricSemanticEmbedding()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "d292536f",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"doc_result = embeddings.embed_documents([text])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "c704a7cf",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"query_result = embeddings.embed_query(text)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "33492471",
|
|
"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": "3.9.1"
|
|
},
|
|
"vscode": {
|
|
"interpreter": {
|
|
"hash": "7377c2ccc78bc62c2683122d48c8cd1fb85a53850a1b1fc29736ed39852c9885"
|
|
}
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|