forked from Archives/langchain
106 lines
2.4 KiB
Plaintext
106 lines
2.4 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "683953b3",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Pinecone\n",
|
|
"\n",
|
|
"This notebook shows how to use functionality related to the Pinecone 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 Pinecone\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": "6e104aee",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import pinecone \n",
|
|
"\n",
|
|
"# initialize pinecone\n",
|
|
"pinecone.init(\n",
|
|
" api_key=\"YOUR_API_KEY\", # find at app.pinecone.io\n",
|
|
" environment=\"YOUR_ENV\" # next to api key in console\n",
|
|
")\n",
|
|
"\n",
|
|
"index_name = \"langchain-demo\"\n",
|
|
"\n",
|
|
"docsearch = Pinecone.from_documents(docs, embeddings, index_name=index_name)\n",
|
|
"\n",
|
|
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
|
|
"docs = docsearch.similarity_search(query)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "9c608226",
|
|
"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
|
|
}
|