turbopuffer 集成

pip install -qU langchain-turbopuffer

import getpass
import os

if not os.getenv("TURBOPUFFER_API_KEY"):
    os.environ["TURBOPUFFER_API_KEY"] = getpass.getpass("Enter your turbopuffer API key: ")

os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")
os.environ["LANGSMITH_TRACING"] = "true"

from langchain_openai import OpenAIEmbeddings
from turbopuffer import Turbopuffer

tpuf = Turbopuffer(region="gcp-us-central1")
ns = tpuf.namespace("langchain-test")

embeddings = OpenAIEmbeddings(model="text-embedding-3-small")

from langchain_turbopuffer import TurbopufferVectorStore

vector_store = TurbopufferVectorStore(embedding=embeddings, namespace=ns)

from uuid import uuid4

from langchain_core.documents import Document

document_1 = Document(
    page_content="I had chocolate chip pancakes and scrambled eggs for breakfast this morning.",
    metadata={"source": "tweet"},
)

document_2 = Document(
    page_content="The weather forecast for tomorrow is cloudy and overcast, with a high of 62 degrees.",
    metadata={"source": "news"},
)

document_3 = Document(
    page_content="Building an exciting new project with LangChain - come check it out!",
    metadata={"source": "tweet"},
)

document_4 = Document(
    page_content="Robbers broke into the city bank and stole $1 million in cash.",
    metadata={"source": "news"},
)

document_5 = Document(
    page_content="Wow! That was an amazing movie. I can't wait to see it again.",
    metadata={"source": "tweet"},
)

document_6 = Document(
    page_content="Is the new iPhone worth the price? Read this review to find out.",
    metadata={"source": "website"},
)

document_7 = Document(
    page_content="The top 10 soccer players in the world right now.",
    metadata={"source": "website"},
)

document_8 = Document(
    page_content="LangGraph is the best framework for building stateful, agentic applications!",
    metadata={"source": "tweet"},
)

document_9 = Document(
    page_content="The stock market is down 500 points today due to fears of a recession.",
    metadata={"source": "news"},
)

document_10 = Document(
    page_content="I have a bad feeling I am going to get deleted :(",
    metadata={"source": "tweet"},
)

documents = [
    document_1,
    document_2,
    document_3,
    document_4,
    document_5,
    document_6,
    document_7,
    document_8,
    document_9,
    document_10,
]
uuids = [str(uuid4()) for _ in range(len(documents))]
vector_store.add_documents(documents=documents, ids=uuids)

vector_store.delete(ids=[uuids[-1]])

results = vector_store.similarity_search(
    "LangChain provides abstractions to make working with LLMs easy",
    k=2,
    filters=("source", "Eq", "tweet"),
)
for res in results:
    print(f"* {res.page_content} [{res.metadata}]")

results = vector_store.similarity_search_with_score(
    "Will it be hot tomorrow?", k=1, filters=("source", "Eq", "news")
)
for res, score in results:
    print(f"* [SIM={score:3f}] {res.page_content} [{res.metadata}]")

retriever = vector_store.as_retriever(
    search_type="similarity_score_threshold",
    search_kwargs={"k": 1, "score_threshold": 0.4},
)
retriever.invoke("Stealing from the bank is a crime")

results = vector_store.similarity_search(
    "interesting articles",
    k=2,
    filters=("source", "Eq", "website"),
)