本指南将使用 Fleet Context 下载 LlamaIndex 文档的嵌入，并在其之上构建混合的稠密/稀疏向量检索引擎。

前置条件

!pip install llama-index
!pip install --upgrade fleet-context

import os
import openai

os.environ["OPENAI_API_KEY"] = "sk-..." # add your API key here!
openai.api_key = os.environ["OPENAI_API_KEY"]

从 Fleet Context 下载嵌入

我们将使用 Fleet Context 下载 LlamaIndex 全部文档的嵌入（~12k 个块，~100mb 内容）。只要把库名作为参数传入，你就能下载排名前 1220 个库中任意一个的嵌入。支持的完整库清单可在这里页面底部查看。

之所以这样做，是因为 Fleet 构建了一条嵌入流水线，保留了许多重要信息，能让检索与生成效果更好——包括在页面中的位置（用于重排）、块类型（class/function/attribute 等）、所属的上级章节等等。更多内容可以在他们的 Github 页面上阅读。

from context import download_embeddings

df = download_embeddings("llamaindex")

输出：

终端窗口

    100%|██████████| 83.7M/83.7M [00:03<00:00, 27.4MiB/s]
                                         id  \
    0  e268e2a1-9193-4e7b-bb9b-7a4cb88fc735
    1  e495514b-1378-4696-aaf9-44af948de1a1
    2  e804f616-7db0-4455-9a06-49dd275f3139
    3  eb85c854-78f1-4116-ae08-53b2a2a9fa41
    4  edfc116e-cf58-4118-bad4-c4bc0ca1495e

# Show some examples of the metadata
df["metadata"][0]
display(Markdown(f"{df['metadata'][8000]['text']}"))

输出：

终端窗口

classmethod from_dict(data: Dict[str, Any], kwargs: Any) → Self classmethod from_json(data_str: str, kwargs: Any) → Self classmethod from_orm(obj: Any) → Model json(, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False, encoder: Optional[Callable[[Any], Any]] = None, models_as_dict: bool = True*, dumps_kwargs: Any) → unicode Generate a JSON representation of the model, include and exclude arguments as per dict().

为 LlamaIndex 中的混合检索创建 Pinecone 索引

我们要创建一个 Pinecone 索引，并把向量 upsert 进去，从而用稀疏向量与稠密向量做混合检索。继续之前请确保你已有 Pinecone 账号。

import logging
import sys

logging.basicConfig(stream=sys.stdout, level=logging.INFO)
logging.getLogger().handlers = []
logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))

import pinecone

api_key = "..."  # Add your Pinecone API key here
pinecone.init(
    api_key=api_key, environment="us-east-1-aws"
)  # Add your db region here

# Fleet Context uses the text-embedding-ada-002 model from OpenAI with 1536 dimensions.

# NOTE: Pinecone requires dotproduct similarity for hybrid search
pinecone.create_index(
    "quickstart-fleet-context",
    dimension=1536,
    metric="dotproduct",
    pod_type="p1",
)

pinecone.describe_index(
    "quickstart-fleet-context"
)  # Make sure you create an index in pinecone

from llama_index.vector_stores.pinecone import PineconeVectorStore

pinecone_index = pinecone.Index("quickstart-fleet-context")
vector_store = PineconeVectorStore(pinecone_index, add_sparse_vector=True)

批量把向量 upsert 进 Pinecone

Pinecone 建议每次 upsert 100 个向量。我们会在稍微调整数据格式之后照此执行。

import random
import itertools

def chunks(iterable, batch_size=100):
    """A helper function to break an iterable into chunks of size batch_size."""
    it = iter(iterable)
    chunk = tuple(itertools.islice(it, batch_size))
    while chunk:
        yield chunk
        chunk = tuple(itertools.islice(it, batch_size))

# generator that generates many (id, vector, metadata, sparse_values) pairs
data_generator = map(
    lambda row: {
        "id": row[1]["id"],
        "values": row[1]["values"],
        "metadata": row[1]["metadata"],
        "sparse_values": row[1]["sparse_values"],
    },
    df.iterrows(),
)

# Upsert data with 1000 vectors per upsert request
for ids_vectors_chunk in chunks(data_generator, batch_size=100):
    print(f"Upserting {len(ids_vectors_chunk)} vectors...")
    pinecone_index.upsert(vectors=ids_vectors_chunk)

在 LlamaIndex 中构建 Pinecone 向量库

最后，我们通过 LlamaIndex 构建 Pinecone 向量库并查询它以获得结果。

from llama_index.core import VectorStoreIndex
from IPython.display import Markdown, display

index = VectorStoreIndex.from_vector_store(vector_store=vector_store)

查询你的索引！

query_engine = index.as_query_engine(
    vector_store_query_mode="hybrid", similarity_top_k=8
)
response = query_engine.query("How do I use llama_index SimpleDirectoryReader")

display(Markdown(f"<b>{response}</b>"))

输出：

终端窗口

<b>To use the SimpleDirectoryReader in llama_index, you need to import it from the llama_index library. Once imported, you can create an instance of the SimpleDirectoryReader class by providing the directory path as an argument. Then, you can use the `load_data()` method on the SimpleDirectoryReader instance to load the documents from the specified directory.</b>