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.
151 lines
3.3 KiB
Plaintext
151 lines
3.3 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "ce0f17b9",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Weaviate Hybrid Search\n",
|
|
"\n",
|
|
">[Weaviate](https://weaviate.io/developers/weaviate) is an open source vector database.\n",
|
|
"\n",
|
|
">[Hybrid search](https://weaviate.io/blog/hybrid-search-explained) is a technique that combines multiple search algorithms to improve the accuracy and relevance of search results. It uses the best features of both keyword-based search algorithms with vector search techniques.\n",
|
|
"\n",
|
|
">The `Hybrid search in Weaviate` uses sparse and dense vectors to represent the meaning and context of search queries and documents.\n",
|
|
"\n",
|
|
"This notebook shows how to use `Weaviate hybrid search` as a LangChain retriever."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "bba863a2-977c-4add-b5f4-bfc33a80eae5",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"#!pip install weaviate-client"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"id": "c10dd962",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import weaviate\n",
|
|
"import os\n",
|
|
"\n",
|
|
"WEAVIATE_URL = \"...\"\n",
|
|
"client = weaviate.Client(\n",
|
|
" url=WEAVIATE_URL,\n",
|
|
")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"id": "f47a2bfe",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.retrievers.weaviate_hybrid_search import WeaviateHybridSearchRetriever\n",
|
|
"from langchain.schema import Document"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"id": "f2eff08e",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"retriever = WeaviateHybridSearchRetriever(client, index_name=\"LangChain\", text_key=\"text\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"id": "cd8a7b17",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"docs = [Document(page_content=\"foo\")]"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"id": "3c5970db",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"['3f79d151-fb84-44cf-85e0-8682bfe145e0']"
|
|
]
|
|
},
|
|
"execution_count": 5,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"retriever.add_documents(docs)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"id": "bf7dbb98",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"[Document(page_content='foo', metadata={})]"
|
|
]
|
|
},
|
|
"execution_count": 6,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"retriever.get_relevant_documents(\"foo\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "b2bc87c1",
|
|
"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
|
|
}
|