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.
134 lines
3.3 KiB
Plaintext
134 lines
3.3 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# DeepInfra\n",
|
|
"\n",
|
|
"[DeepInfra](https://deepinfra.com/?utm_source=langchain) is a serverless inference as a service that provides access to a [variety of LLMs](https://deepinfra.com/models?utm_source=langchain) and [embeddings models](https://deepinfra.com/models?type=embeddings&utm_source=langchain). This notebook goes over how to use LangChain with DeepInfra for text embeddings."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdin",
|
|
"output_type": "stream",
|
|
"text": [
|
|
" ········\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"# sign up for an account: https://deepinfra.com/login?utm_source=langchain\n",
|
|
"\n",
|
|
"from getpass import getpass\n",
|
|
"\n",
|
|
"DEEPINFRA_API_TOKEN = getpass()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import os\n",
|
|
"\n",
|
|
"os.environ[\"DEEPINFRA_API_TOKEN\"] = DEEPINFRA_API_TOKEN"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.embeddings import DeepInfraEmbeddings"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"embeddings = DeepInfraEmbeddings(\n",
|
|
" model_id=\"sentence-transformers/clip-ViT-B-32\",\n",
|
|
" query_instruction=\"\",\n",
|
|
" embed_instruction=\"\",\n",
|
|
")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"docs = [\"Dog is not a cat\",\n",
|
|
" \"Beta is the second letter of Greek alphabet\"]\n",
|
|
"document_result = embeddings.embed_documents(docs)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"query = \"What is the first letter of Greek alphabet\"\n",
|
|
"query_result = embeddings.embed_query(query)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Cosine similarity between \"Dog is not a cat\" and query: 0.7489097144129355\n",
|
|
"Cosine similarity between \"Beta is the second letter of Greek alphabet\" and query: 0.9519380640702013\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"import numpy as np\n",
|
|
"\n",
|
|
"query_numpy = np.array(query_result)\n",
|
|
"for doc_res, doc in zip(document_result, docs):\n",
|
|
" document_numpy = np.array(doc_res)\n",
|
|
" similarity = np.dot(query_numpy, document_numpy) / (np.linalg.norm(query_numpy)*np.linalg.norm(document_numpy))\n",
|
|
" print(f\"Cosine similarity between \\\"{doc}\\\" and query: {similarity}\")"
|
|
]
|
|
}
|
|
],
|
|
"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": "3.10.10"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 4
|
|
}
|