在 Bigtable 中通过查找 K 最近邻来执行相似度向量搜索

from google.cloud import bigtable
from google.cloud.bigtable import column_family

client = bigtable.Client(project=PROJECT_ID, admin=True)
instance = client.instance(INSTANCE_ID)
table = instance.table(TABLE_ID)
column_families = {"docs":column_family.MaxVersionsGCRule(2), "search_phrase":column_family.MaxVersionsGCRule(2)}

if not table.exists():
  table.create(column_families=column_families)
else:
  print("Table already exists")

from typing import List, Optional
from vertexai.language_models import TextEmbeddingInput, TextEmbeddingModel
from vertexai.generative_models import GenerativeModel

#defines which LLM that we should use to generate the text
model = GenerativeModel("gemini-1.5-pro-001")

#First, use generative AI to create a list of 10 chunks for phrases
#This can be replaced with a static list of text items or your own data

chunks = []
for i in range(10):
  response = model.generate_content(
      "Generate a paragraph between 10 and 20 words that is about about either
      Bigtable or Generative AI"
)
chunks.append(response.text)
print(response.text)
#create embeddings for the chunks of text
def embed_text(
  texts: List[str] = chunks,
  task: str = "RETRIEVAL_DOCUMENT",
  model_name: str = "text-embedding-004",
  dimensionality: Optional[int] = 128,
) -> List[List[float]]:
  """Embeds texts with a pre-trained, foundational model."""
  model = TextEmbeddingModel.from_pretrained(model_name)
  inputs = [TextEmbeddingInput(text, task) for text in texts]
  kwargs = dict(output_dimensionality=dimensionality) if dimensionality else {}
  embeddings = model.get_embeddings(inputs, **kwargs)
  return [embedding.values for embedding in embeddings]

embeddings = embed_text()
print("embeddings created for text phrases")

import struct
def floats_to_bytes(float_list):
  """
  Convert a list of floats to a bytes object, where each float is represented
  by 4 big-endian bytes.

  Parameters:
  float_list (list of float): The list of floats to be converted.

  Returns:
  bytes: The resulting bytes object with concatenated 4-byte big-endian
  representations of the floats.
  """
  byte_array = bytearray()

  for value in float_list:
      packed_value = struct.pack('>f', value)
      byte_array.extend(packed_value)

  # Convert bytearray to bytes
  return bytes(byte_array)

from google.cloud.bigtable.data  import RowMutationEntry
from google.cloud.bigtable.data  import SetCell

mutations = []
embeddings = embed_text()
for i, embedding in enumerate(embeddings):
  print(embedding)

  #convert each embedding into a byte object
  vector = floats_to_bytes(embedding)

  #set the row key which will be used to pull the range of documents (ex. doc type or user id)
  row_key = f"doc_{i}"

  row = table.direct_row(row_key)

  #set the column for the embedding based on the byte object format of the embedding
  row.set_cell("docs","embedding",vector)
  #store the text associated with vector in the same key
  row.set_cell("docs","text",chunks[i])
  mutations.append(row)

#write the rows to Bigtable
table.mutate_rows(mutations)

from google.cloud.bigtable.data import BigtableDataClientAsync

#first embed the search phrase
search_embedding = embed_text(texts=["Apache HBase"])

query = """
      select _key, docs['text'] as description
      FROM knn_intro
      ORDER BY COSINE_DISTANCE(TO_VECTOR32(docs['embedding']), {search_embedding})
      LIMIT 1;
      """

async def execute_query():
  async with BigtableDataClientAsync(project=PROJECT_ID) as client:
    local_query = query
    async for row in await client.execute_query(query.format(search_embedding=search_embedding[0]), INSTANCE_ID):
      return(row["_key"],row["description"])

await execute_query()