Apache Cassandra 集成

pip install -qU langchain-community "cassio>=0.1.4"

import os
from getpass import getpass

from datasets import (
    load_dataset,
)
from langchain_community.document_loaders import PyPDFLoader
from langchain_core.documents import Document
from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough
from langchain_openai import ChatOpenAI, OpenAIEmbeddings
from langchain_text_splitters import RecursiveCharacterTextSplitter

if "OPENAI_API_KEY" not in os.environ:
    os.environ["OPENAI_API_KEY"] = getpass("OPENAI_API_KEY = ")

embe = OpenAIEmbeddings()

from langchain_community.vectorstores import Cassandra

from cassandra.cluster import Cluster

cluster = Cluster(["127.0.0.1"])
session = cluster.connect()

import cassio

CASSANDRA_KEYSPACE = input("CASSANDRA_KEYSPACE = ")

cassio.init(session=session, keyspace=CASSANDRA_KEYSPACE)

vstore = Cassandra(
    embedding=embe,
    table_name="cassandra_vector_demo",
    # session=None, keyspace=None  # Uncomment on older versions of LangChain
)

ASTRA_DB_ID = input("ASTRA_DB_ID = ")
ASTRA_DB_APPLICATION_TOKEN = getpass("ASTRA_DB_APPLICATION_TOKEN = ")

desired_keyspace = input("ASTRA_DB_KEYSPACE (optional, can be left empty) = ")
if desired_keyspace:
    ASTRA_DB_KEYSPACE = desired_keyspace
else:
    ASTRA_DB_KEYSPACE = None

import cassio

cassio.init(
    database_id=ASTRA_DB_ID,
    token=ASTRA_DB_APPLICATION_TOKEN,
    keyspace=ASTRA_DB_KEYSPACE,
)

vstore = Cassandra(
    embedding=embe,
    table_name="cassandra_vector_demo",
    # session=None, keyspace=None  # Uncomment on older versions of LangChain
)

philo_dataset = load_dataset("datastax/philosopher-quotes")["train"]

docs = []
for entry in philo_dataset:
    metadata = {"author": entry["author"]}
    doc = Document(page_content=entry["quote"], metadata=metadata)
    docs.append(doc)

inserted_ids = vstore.add_documents(docs)
print(f"\nInserted {len(inserted_ids)} documents.")

texts = ["I think, therefore I am.", "To the things themselves!"]
metadatas = [{"author": "descartes"}, {"author": "husserl"}]
ids = ["desc_01", "huss_xy"]

inserted_ids_2 = vstore.add_texts(texts=texts, metadatas=metadatas, ids=ids)
print(f"\nInserted {len(inserted_ids_2)} documents.")

results = vstore.similarity_search("Our life is what we make of it", k=3)
for res in results:
    print(f"* {res.page_content} [{res.metadata}]")

results_filtered = vstore.similarity_search(
    "Our life is what we make of it",
    k=3,
    filter={"author": "plato"},
)
for res in results_filtered:
    print(f"* {res.page_content} [{res.metadata}]")

results = vstore.similarity_search_with_score("Our life is what we make of it", k=3)
for res, score in results:
    print(f"* [SIM={score:3f}] {res.page_content} [{res.metadata}]")

results = vstore.max_marginal_relevance_search(
    "Our life is what we make of it",
    k=3,
    filter={"author": "aristotle"},
)
for res in results:
    print(f"* {res.page_content} [{res.metadata}]")

delete_1 = vstore.delete(inserted_ids[:3])
print(f"all_succeed={delete_1}")  # True, all documents deleted

delete_2 = vstore.delete(inserted_ids[2:5])
print(f"some_succeeds={delete_2}")  # True, though some IDs were gone already

!curl -L \
    "https://github.com/awesome-astra/datasets/blob/main/demo-resources/what-is-philosophy/what-is-philosophy.pdf?raw=true" \
    -o "what-is-philosophy.pdf"

pdf_loader = PyPDFLoader("what-is-philosophy.pdf")
splitter = RecursiveCharacterTextSplitter(chunk_size=512, chunk_overlap=64)
docs_from_pdf = pdf_loader.load_and_split(text_splitter=splitter)

print(f"Documents from PDF: {len(docs_from_pdf)}.")
inserted_ids_from_pdf = vstore.add_documents(docs_from_pdf)
print(f"Inserted {len(inserted_ids_from_pdf)} documents.")

retriever = vstore.as_retriever(search_kwargs={"k": 3})

philo_template = """
You are a philosopher that draws inspiration from great thinkers of the past
to craft well-thought answers to user questions. Use the provided context as the basis
for your answers and do not make up new reasoning paths - just mix-and-match what you are given.
Your answers must be concise and to the point, and refrain from answering about other topics than philosophy.

CONTEXT:
{context}

QUESTION: {question}

YOUR ANSWER:"""

philo_prompt = ChatPromptTemplate.from_template(philo_template)

llm = ChatOpenAI()

chain = (
    {"context": retriever, "question": RunnablePassthrough()}
    | philo_prompt
    | llm
    | StrOutputParser()
)

chain.invoke("How does Russel elaborate on Peirce's idea of the security blanket?")

cassio.config.resolve_session().execute(
    f"DROP TABLE {cassio.config.resolve_keyspace()}.cassandra_vector_demo;"
)