add(feat): Text Embeddings by Cloudflare Workers AI (#14220)

Add [Text Embeddings by Cloudflare Workers
AI](https://developers.cloudflare.com/workers-ai/models/text-embeddings/).
It's a new integration.
Trying to align it with its langchain-js version counterpart
[here](https://api.js.langchain.com/classes/embeddings_cloudflare_workersai.CloudflareWorkersAIEmbeddings.html).
- Dependencies: N/A
- Done `make format` `make lint` `make spell_check` `make
integration_tests` and all my changes was passed
This commit is contained in:
cxumol
2023-12-04 19:25:05 -08:00
committed by GitHub
parent c51001f01e
commit 0d47d15a9f
3 changed files with 272 additions and 0 deletions

View File

@@ -0,0 +1,125 @@
{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"id": "59428e05",
"metadata": {},
"source": [
"# Text Embeddings on Cloudflare Workers AI\n",
"\n",
"[Cloudflare AI document](https://developers.cloudflare.com/workers-ai/models/text-embeddings/) listed all text embeddings models available.\n",
"\n",
"Both Cloudflare account ID and API token are required. Find how to obtain them from [this document](https://developers.cloudflare.com/workers-ai/get-started/rest-api/).\n"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "92c5b61e",
"metadata": {},
"outputs": [],
"source": [
"from langchain.embeddings.cloudflare_workersai import CloudflareWorkersAIEmbeddings"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "f60023b8",
"metadata": {},
"outputs": [],
"source": [
"import getpass\n",
"\n",
"my_account_id = getpass.getpass(\"Enter your Cloudflare account ID:\\n\\n\")\n",
"my_api_token = getpass.getpass(\"Enter your Cloudflare API token:\\n\\n\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "062547b9",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(384, [-0.033627357333898544, 0.03982774540781975, 0.03559349477291107])"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"embeddings = CloudflareWorkersAIEmbeddings(\n",
" account_id=my_account_id,\n",
" api_token=my_api_token,\n",
" model_name=\"@cf/baai/bge-small-en-v1.5\",\n",
")\n",
"# single string embeddings\n",
"query_result = embeddings.embed_query(\"test\")\n",
"len(query_result), query_result[:3]"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "e1dcc4bd",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(3, 384)"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# string embeddings in batches\n",
"batch_query_result = embeddings.embed_documents([\"test1\", \"test2\", \"test3\"])\n",
"len(batch_query_result), len(batch_query_result[0])"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "52de8b88",
"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": "3.9.18"
},
"vscode": {
"interpreter": {
"hash": "7377c2ccc78bc62c2683122d48c8cd1fb85a53850a1b1fc29736ed39852c9885"
}
}
},
"nbformat": 4,
"nbformat_minor": 5
}