如果你在 Colab 中打开这个 Notebook，可能需要先安装 LlamaIndex 🦙。

%pip install llama-index-vector-stores-mongodb

!pip install llama-index

# Provide URI to constructor, or use environment variable
import pymongo
from llama_index.vector_stores.mongodb import MongoDBAtlasVectorSearch
from llama_index.core import VectorStoreIndex
from llama_index.core import StorageContext
from llama_index.core import SimpleDirectoryReader

下载数据

!mkdir -p 'data/10k/'
!wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/examples/data/10k/uber_2021.pdf' -O 'data/10k/uber_2021.pdf'

# mongo_uri = os.environ["MONGO_URI"]
mongo_uri = (
    "mongodb+srv://<username>:<password>@<host>?retryWrites=true&w=majority"
)
mongodb_client = pymongo.MongoClient(mongo_uri)
async_mongodb_client = pymongo.AsyncMongoClient(mongo_uri)

store = MongoDBAtlasVectorSearch(
    mongodb_client=mongodb_client, async_mongodb_client=async_mongodb_client
)
store.create_vector_search_index(
    dimensions=1536, path="embedding", similarity="cosine"
)
storage_context = StorageContext.from_defaults(vector_store=store)
uber_docs = SimpleDirectoryReader(
    input_files=["./data/10k/uber_2021.pdf"]
).load_data()
index = VectorStoreIndex.from_documents(
    uber_docs, storage_context=storage_context
)

response = index.as_query_engine().query("What was Uber's revenue?")
display(Markdown(f"<b>{response}</b>"))

Uber 2021 年的收入为 174.55 亿美元。

from llama_index.core import Response

# Initial size

print(store._collection.count_documents({}))
# Get a ref_doc_id
typed_response = (
    response if isinstance(response, Response) else response.get_response()
)
ref_doc_id = typed_response.source_nodes[0].node.ref_doc_id
print(store._collection.count_documents({"metadata.ref_doc_id": ref_doc_id}))
# Test store delete
if ref_doc_id:
    store.delete(ref_doc_id)
    print(store._collection.count_documents({}))

4454
1
4453

注意：对于 MongoDB Atlas，你必须创建一个 Atlas Search Index。

MongoDB 文档 | 创建 Atlas 向量搜索索引