Redis®*: ベクトル検索とRAG

FT.CREATE chunksIndex
  ON HASH
  PREFIX 1 chunk:
  SCHEMA
    content TEXT
    documentId TAG
    publishedAt NUMERIC
    embedding VECTOR HNSW 6
      TYPE FLOAT32
      DIM 1536
      DISTANCE_METRIC COSINE

FT.SEARCH chunksIndex "*=>[KNN 5 @embedding $queryVector AS score]"
  PARAMS 2 queryVector "<rawBytes>"
  SORTBY score
  RETURN 2 content score
  DIALECT 2

FT.SEARCH chunksIndex "(@documentId:{doc42} @publishedAt:[1735689600 +inf])=>[KNN 5 @embedding $queryVector AS score]"
  PARAMS 2 queryVector "<rawBytes>"
  SORTBY score
  DIALECT 2

import { createClient, SCHEMA_FIELD_TYPE, SCHEMA_VECTOR_FIELD_ALGORITHM } from 'redis';

const client = createClient({ url: process.env.STACKHERO_REDIS_URL_TLS });
await client.connect();

const DIMENSIONS = 1536;
const toBytes = embedding => Buffer.from(new Float32Array(embedding).buffer);

// 1. 起動時に一度だけインデックスを作成
try {
  await client.ft.create(
    'chunksIndex',
    {
      content: SCHEMA_FIELD_TYPE.TEXT,
      documentId: SCHEMA_FIELD_TYPE.TAG,
      embedding: {
        type: SCHEMA_FIELD_TYPE.VECTOR,
        ALGORITHM: SCHEMA_VECTOR_FIELD_ALGORITHM.HNSW,
        TYPE: 'FLOAT32',
        DIM: DIMENSIONS,
        DISTANCE_METRIC: 'COSINE'
      }
    },
    { ON: 'HASH', PREFIX: 'chunk:' }
  );
}
catch (error) {
  if (!error.message.includes('Index already exists')) {
    throw error;
  }
}

// 2. チャンクをインデックス化（embeddingはモデルプロバイダーから取得）
async function indexChunk({ id, documentId, content, embedding }) {
  await client.hSet(`chunk:${id}`, {
    content,
    documentId,
    embedding: toBytes(embedding)
  });
}

// 3. 質問に最も近いチャンクを、特定ドキュメントに限定して取得
async function retrieve({ questionEmbedding, documentId, count = 5 }) {
  const results = await client.ft.search(
    'chunksIndex',
    `(@documentId:{${documentId}})=>[KNN ${count} @embedding $queryVector AS score]`,
    {
      PARAMS: { queryVector: toBytes(questionEmbedding) },
      SORTBY: 'score',
      RETURN: [ 'content', 'score' ],
      DIALECT: 2
    }
  );

  return results.documents.map(({ value }) => value.content);
}

// 4. モデルへのコンテキストとして渡す
const context = await retrieve({ questionEmbedding, documentId: 'doc42' });
const prompt = `Answer using only this context:\n\n${context.join('\n\n')}\n\nQuestion: ${question}`;

import os
import numpy as np
import redis
from redis.commands.search.field import TextField, TagField, VectorField
from redis.commands.search.index_definition import IndexDefinition, IndexType
from redis.commands.search.query import Query

DIMENSIONS = 1536

r = redis.from_url(os.environ['STACKHERO_REDIS_URL_TLS'])

# 起動時に一度だけインデックスを作成
try:
    r.ft('chunksIndex').create_index(
        (
            TextField('content'),
            TagField('documentId'),
            VectorField(
                'embedding',
                'HNSW',
                {'TYPE': 'FLOAT32', 'DIM': DIMENSIONS, 'DISTANCE_METRIC': 'COSINE'},
            ),
        ),
        definition=IndexDefinition(prefix=['chunk:'], index_type=IndexType.HASH),
    )
except redis.ResponseError as error:
    if 'Index already exists' not in str(error):
        raise


def index_chunk(chunk_id, document_id, content, embedding):
    r.hset(
        f'chunk:{chunk_id}',
        mapping={
            'content': content,
            'documentId': document_id,
            'embedding': np.array(embedding, dtype=np.float32).tobytes(),
        },
    )


def retrieve(question_embedding, document_id, count=5):
    query = (
        Query(f'(@documentId:{{{document_id}}})=>[KNN {count} @embedding $queryVector AS score]')
        .sort_by('score')
        .return_fields('content', 'score')
        .dialect(2)
    )
    results = r.ft('chunksIndex').search(
        query,
        query_params={'queryVector': np.array(question_embedding, dtype=np.float32).tobytes()},
    )
    return [document.content for document in results.docs]