forked from Archives/langchain
5f356b9993
<!-- Fixed a simple typo on https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/vectorstore.html where the word "use" was missing. #### Who can review? Tag maintainers/contributors who might be interested: <!-- For a quicker response, figure out the right person to tag with @ @hwchase17 - project lead Tracing / Callbacks - @agola11 Async - @agola11 DataLoaders - @eyurtsev Models - @hwchase17 - @agola11 Agents / Tools / Toolkits - @vowelparrot VectorStores / Retrievers / Memory - @dev2049 -->
213 lines
4.8 KiB
Plaintext
213 lines
4.8 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "fc0db1bc",
|
|
"metadata": {},
|
|
"source": [
|
|
"# VectorStore\n",
|
|
"\n",
|
|
"The index - and therefore the retriever - that LangChain has the most support for is the `VectorStoreRetriever`. As the name suggests, this retriever is backed heavily by a VectorStore.\n",
|
|
"\n",
|
|
"Once you construct a VectorStore, its very easy to construct a retriever. Let's walk through an example."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"id": "5831703b",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.document_loaders import TextLoader\n",
|
|
"loader = TextLoader('../../../state_of_the_union.txt')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 9,
|
|
"id": "9fbcc58f",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Exiting: Cleaning up .chroma directory\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"from langchain.text_splitter import CharacterTextSplitter\n",
|
|
"from langchain.vectorstores import FAISS\n",
|
|
"from langchain.embeddings import OpenAIEmbeddings\n",
|
|
"\n",
|
|
"documents = loader.load()\n",
|
|
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
|
|
"texts = text_splitter.split_documents(documents)\n",
|
|
"embeddings = OpenAIEmbeddings()\n",
|
|
"db = FAISS.from_documents(texts, embeddings)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 10,
|
|
"id": "0cbfb1af",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"retriever = db.as_retriever()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 11,
|
|
"id": "fc12700b",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"docs = retriever.get_relevant_documents(\"what did he say about ketanji brown jackson\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "79b783de",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Maximum Marginal Relevance Retrieval\n",
|
|
"By default, the vectorstore retriever uses similarity search. If the underlying vectorstore support maximum marginal relevance search, you can specify that as the search type."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 12,
|
|
"id": "44c7303e",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"retriever = db.as_retriever(search_type=\"mmr\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 13,
|
|
"id": "d16ceec6",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"docs = retriever.get_relevant_documents(\"what did he say abotu ketanji brown jackson\")"
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"id": "2d958271",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Similarity Score Threshold Retrieval\n",
|
|
"\n",
|
|
"You can also use a retrieval method that sets a similarity score threshold and only returns documents with a score above that threshold"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"id": "d4272ad8",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"retriever = db.as_retriever(search_type=\"similarity_score_threshold\", search_kwargs={\"score_threshold\": .5})"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"id": "438e761d",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"docs = retriever.get_relevant_documents(\"what did he say abotu ketanji brown jackson\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "c23b7698",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Specifying top k\n",
|
|
"You can also specify search kwargs like `k` to use when doing retrieval."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 14,
|
|
"id": "b5f44cdf",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"retriever = db.as_retriever(search_kwargs={\"k\": 1})"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 15,
|
|
"id": "56b6a545",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"docs = retriever.get_relevant_documents(\"what did he say abotu ketanji brown jackson\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 16,
|
|
"id": "b5416858",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"1"
|
|
]
|
|
},
|
|
"execution_count": 16,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"len(docs)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "9a658023",
|
|
"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": "3.10.6"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|