mirror of
https://github.com/hwchase17/langchain
synced 2024-10-31 15:20:26 +00:00
234 lines
5.7 KiB
Plaintext
234 lines
5.7 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"id": "683953b3",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Pinecone\n",
|
|
"\n",
|
|
">[Pinecone](https://docs.pinecone.io/docs/overview) is a vector database with broad functionality.\n",
|
|
"\n",
|
|
"This notebook shows how to use functionality related to the `Pinecone` vector database.\n",
|
|
"\n",
|
|
"To use Pinecone, you must have an API key. \n",
|
|
"Here are the [installation instructions](https://docs.pinecone.io/docs/quickstart)."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "b4c41cad-08ef-4f72-a545-2151e4598efe",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"!pip install pinecone-client openai tiktoken"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "c1e38361-c1fe-4ac6-86e9-c90ebaf7ae87",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import os\n",
|
|
"import getpass\n",
|
|
"\n",
|
|
"PINECONE_API_KEY = getpass.getpass(\"Pinecone API Key:\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "02a536e0-d603-4d79-b18b-1ed562977b40",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"PINECONE_ENV = getpass.getpass(\"Pinecone Environment:\")"
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"id": "320af802-9271-46ee-948f-d2453933d44b",
|
|
"metadata": {},
|
|
"source": [
|
|
"We want to use `OpenAIEmbeddings` so we have to get the OpenAI API Key."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "ffea66e4-bc23-46a9-9580-b348dfe7b7a7",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "aac9563e",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"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": null,
|
|
"id": "a3c3999a",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.document_loaders import TextLoader\n",
|
|
"\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=PINECONE_API_KEY, # find at app.pinecone.io\n",
|
|
" environment=PINECONE_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",
|
|
"# if you already have an index, you can load it like this\n",
|
|
"# docsearch = Pinecone.from_existing_index(index_name, embeddings)\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)"
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"id": "86a4b96b",
|
|
"metadata": {},
|
|
"source": [
|
|
"### Adding More Text to an Existing Index\n",
|
|
"\n",
|
|
"More text can embedded and upserted to an existing Pinecone index using the `add_texts` function\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "38a7a60e",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"index = pinecone.Index(\"langchain-demo\")\n",
|
|
"vectorstore = Pinecone(index, embeddings.embed_query, \"text\")\n",
|
|
"\n",
|
|
"vectorstore.add_texts(\"More text!\")"
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"id": "d46d1452",
|
|
"metadata": {},
|
|
"source": [
|
|
"### Maximal Marginal Relevance Searches\n",
|
|
"\n",
|
|
"In addition to using similarity search in the retriever object, you can also use `mmr` as retriever.\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "a359ed74",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"retriever = docsearch.as_retriever(search_type=\"mmr\")\n",
|
|
"matched_docs = retriever.get_relevant_documents(query)\n",
|
|
"for i, d in enumerate(matched_docs):\n",
|
|
" print(f\"\\n## Document {i}\\n\")\n",
|
|
" print(d.page_content)"
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"id": "7c477287",
|
|
"metadata": {},
|
|
"source": [
|
|
"Or use `max_marginal_relevance_search` directly:"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "9ca82740",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"found_docs = docsearch.max_marginal_relevance_search(query, k=2, fetch_k=10)\n",
|
|
"for i, doc in enumerate(found_docs):\n",
|
|
" print(f\"{i + 1}.\", doc.page_content, \"\\n\")"
|
|
]
|
|
}
|
|
],
|
|
"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": "3.10.6"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|