Apache Cassandra、Python、およびOllamaを使用してRAGアプリを構築する

ollama pull nomic-embed-text

cassandra

CREATE KEYSPACE IF NOT EXISTS embeddings

   WITH REPLICATION = { 'class' : 'SimpleStrategy', 'replication_factor' : '1' };

​

USE embeddings;

​

CREATE TABLE IF NOT EXISTS embeddings.document_vectors (

  record_id timeuuid,

  id uuid,

  content_chunk text,

  content_vector VECTOR <FLOAT, 768>,

  created_at timestamp,

  PRIMARY KEY (id, created_at)

)

WITH CLUSTERING ORDER BY (created_at DESC);

​

CREATE INDEX IF NOT EXISTS edv_ann_index

  ON embeddings.document_vectors(content_vector) USING 'sai';

sudo apt install python3-virtualenv && python3 -m venv myvenv

source /media/setia/Data/Tutorials/cassandra-ollama-app/myvenv/bin/activate

pip install cassandra-driver

pip install requests

from cassandra.cluster import Cluster

from cassandra.query import PreparedStatement, BoundStatement

import uuid

import datetime

import requests

​

cluster = Cluster(['127.0.0.1'],port=9042)

session = cluster.connect()

​

def generate_embedding(text):

    embedding_url = 'http://localhost:11434/api/embed'

    body = {

        "model": "nomic-embed-text",

        "input": text

    }

​

    response = requests.post(embedding_url, json = body)

    return response.json()['embeddings'][0] 

​

def insert_chunk(content, vector):

    id = uuid.uuid4()

    content_chunk = content

    content_vector = vector

    created_at = datetime.datetime.now()

    insert_query = """

        INSERT INTO embeddings.document_vectors (record_id, id, content_chunk, content_vector, created_at)

        VALUES (now(), ?, ?, ?, ?)

        """

    prepared_stmt = session.prepare(insert_query)

    session.execute(prepared_stmt, [

        id, 

        content_chunk, 

        content_vector, 

        created_at

    ])

​

def insert_sample_data_in_cassandra():

  sentences = [

    "The aroma of freshly baked bread wafted through the quaint bakery nestled in the cobblestone streets of Paris, making Varun feel like time stood still.",

    "Sipping a spicy masala chai in a bustling tea stall in Mumbai, Varun felt he was tasting the very soul of the city.",

    "The sushi in a small Tokyo diner was so fresh, it felt like Varun was on a culinary journey to the sea itself.",

    "Under the starry desert sky in Morocco, Varun enjoyed a lamb tagine that tasted like a dream cooked slowly over a fire.",

    "The cozy Italian trattoria served the creamiest risotto, perfectly capturing the heart of Tuscany on a plate, which Varun savored with delight.",

    "Enjoying fish tacos on a sunny beach in Mexico, with the waves crashing nearby, made the flavors unforgettable for Varun.",

    "The crispy waffles drizzled with syrup at a Belgian café were worth every minute of waiting, as Varun indulged in the decadent treat.",

    "A bowl of warm pho in a roadside eatery in Hanoi felt like comfort wrapped in a broth of herbs and spices, giving Varun a sense of warmth.",

    "Sampling chocolate truffles in a Swiss chocolate shop, Varun found himself in a moment of pure bliss amidst snow-capped mountains.",

    "The street food stalls in Bangkok served fiery pad Thai that left Varun with a tangy memory of the city’s vibrant energy."

    ]

  for sentence in sentences:

     vector = generate_embedding(sentence)

     insert_chunk(sentence, vector)

​

insert_sample_data_in_cassandra()

​

​

​

python app.py

SELECT content_chunk FROM embeddings.document_vectors;

def query_rag(text):

     text_embeddings = generate_embedding(text)

     select_query = """

        SELECT content_chunk,similarity_cosine(content_vector, ?) FROM embeddings.document_vectors

        ORDER BY content_vector ANN OF ?

        LIMIT 3

        """

     prepared_stmt = session.prepare(select_query)

     result_rows = session.execute(prepared_stmt, [

            text_embeddings,

            text_embeddings 

        ])

     for row in result_rows:

         print(row[0], row[1])

​

​

query_rag('Tell about my Bangkok experiences')

#insert_sample_data_in_cassandra()