Typesense is an open-source, in-memory search engine, that you can either self-host or run on Typesense Cloud.
Typesense focuses on performance by storing the entire index in RAM (with a backup on disk) and also focuses on providing an out-of-the-box developer experience by simplifying available options and setting good defaults.
It also lets you combine attribute-based filtering together with vector queries, to fetch the most relevant documents.
This notebook shows you how to use Typesense as your VectorStore.
Let's first install our dependencies:
%pip install --upgrade --quiet typesense openapi-schema-pydantic langchain-openai langchain-community tiktoken
We want to use OpenAIEmbeddings so we have to get the OpenAI API Key.
import getpass
import os
if "OPENAI_API_KEY" not in os.environ:
os.environ["OPENAI_API_KEY"] = getpass.getpass("OpenAI API Key:")
from langchain_community.document_loaders import TextLoader
from langchain_community.vectorstores import Typesense
from langchain_openai import OpenAIEmbeddings
from langchain_text_splitters import CharacterTextSplitter
Let's import our test dataset:
loader = TextLoader("../../how_to/state_of_the_union.txt")
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
docs = text_splitter.split_documents(documents)
embeddings = OpenAIEmbeddings()
docsearch = Typesense.from_documents(
docs,
embeddings,
typesense_client_params={
"host": "localhost",
"port": "8108",
"protocol": "http",
"typesense_api_key": "xyz",
"typesense_collection_name": "lang-chain",
},
)
query = "What did the president say about Ketanji Brown Jackson"
found_docs = docsearch.similarity_search(query)
print(found_docs[0].page_content)
Typesense, as all the other vector stores, is a LangChain Retriever, by using cosine similarity.
retriever = docsearch.as_retriever()
retriever
query = "What did the president say about Ketanji Brown Jackson"
retriever.invoke(query)[0]
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4