forked from Archives/langchain
164 lines
4.0 KiB
Plaintext
164 lines
4.0 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "683953b3",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Weaviate\n",
|
|
"\n",
|
|
"This notebook shows how to use functionality related to the Weaviate vector database."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"id": "aac9563e",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
|
|
"from langchain.text_splitter import CharacterTextSplitter\n",
|
|
"from langchain.vectorstores import Weaviate\n",
|
|
"from langchain.document_loaders import TextLoader"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"id": "a3c3999a",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.document_loaders import TextLoader\n",
|
|
"loader = TextLoader('../../state_of_the_union.txt')\n",
|
|
"documents = loader.load()\n",
|
|
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
|
|
"docs = text_splitter.split_documents(documents)\n",
|
|
"\n",
|
|
"embeddings = OpenAIEmbeddings()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "5888dcc7",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import weaviate\n",
|
|
"import os\n",
|
|
"\n",
|
|
"WEAVIATE_URL = \"\"\n",
|
|
"client = weaviate.Client(\n",
|
|
" url=WEAVIATE_URL,\n",
|
|
" additional_headers={\n",
|
|
" 'X-OpenAI-Api-Key': os.environ[\"OPENAI_API_KEY\"]\n",
|
|
" }\n",
|
|
")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "f004e8ee",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"client.schema.delete_all()\n",
|
|
"client.schema.get()\n",
|
|
"schema = {\n",
|
|
" \"classes\": [\n",
|
|
" {\n",
|
|
" \"class\": \"Paragraph\",\n",
|
|
" \"description\": \"A written paragraph\",\n",
|
|
" \"vectorizer\": \"text2vec-openai\",\n",
|
|
" \"moduleConfig\": {\n",
|
|
" \"text2vec-openai\": {\n",
|
|
" \"model\": \"babbage\",\n",
|
|
" \"type\": \"text\"\n",
|
|
" }\n",
|
|
" },\n",
|
|
" \"properties\": [\n",
|
|
" {\n",
|
|
" \"dataType\": [\"text\"],\n",
|
|
" \"description\": \"The content of the paragraph\",\n",
|
|
" \"moduleConfig\": {\n",
|
|
" \"text2vec-openai\": {\n",
|
|
" \"skip\": False,\n",
|
|
" \"vectorizePropertyName\": False\n",
|
|
" }\n",
|
|
" },\n",
|
|
" \"name\": \"content\",\n",
|
|
" },\n",
|
|
" ],\n",
|
|
" },\n",
|
|
" ]\n",
|
|
"}\n",
|
|
"\n",
|
|
"client.schema.create(schema)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "ef6d5d04",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"vectorstore = Weaviate(client, \"Paragraph\", \"content\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "06e8c1ed",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
|
|
"docs = vectorstore.similarity_search(query)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "38b86be6",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"print(docs[0].page_content)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "a359ed74",
|
|
"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"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|