尼罗河向量存储（多租户 PostgreSQL）

%pip install llama-index-vector-stores-nile
%pip install /Users/gwen/workspaces/llama_index/llama-index-integrations/vector_stores/llama-index-vector-stores-nile/dist/llama_index_vector_stores_nile-0.1.1.tar.gz

!pip install llama-index

import logging

from llama_index.core import SimpleDirectoryReader, StorageContext
from llama_index.core import VectorStoreIndex
from llama_index.core.vector_stores import (
    MetadataFilter,
    MetadataFilters,
    FilterOperator,
)
from llama_index.vector_stores.nile import NileVectorStore, IndexType

%env NILEDB_SERVICE_URL=postgresql://username:password@us-west-2.db.thenile.dev:5432/niledb

# Get the service url by reading local .env file with NILE_SERVICE_URL variable
import os

NILEDB_SERVICE_URL = os.environ["NILEDB_SERVICE_URL"]

# OR set it explicitly
# NILE_SERVICE_URL = "postgresql://nile:password@db.thenile.dev:5432/nile"

vector_store = NileVectorStore(
    service_url=NILEDB_SERVICE_URL,
    table_name="documents",
    tenant_aware=True,
    num_dimensions=1536,
)

%env OPENAI_API_KEY=sk-...

# Uncomment and set it explicitly if you prefer not to use .env
# os.environ["OPENAI_API_KEY"] = "sk-..."

!mkdir -p data
!wget "https://raw.githubusercontent.com/niledatabase/niledatabase/main/examples/ai/sales_insight/data/transcripts/nexiv-solutions__0_transcript.txt" -O "data/nexiv-solutions__0_transcript.txt"
!wget "https://raw.githubusercontent.com/niledatabase/niledatabase/main/examples/ai/sales_insight/data/transcripts/modamart__0_transcript.txt" -O "data/modamart__0_transcript.txt"

reader = SimpleDirectoryReader(
    input_files=["data/nexiv-solutions__0_transcript.txt"]
)
documents_nexiv = reader.load_data()

reader = SimpleDirectoryReader(input_files=["data/modamart__0_transcript.txt"])
documents_modamart = reader.load_data()

tenant_id_nexiv = str(vector_store.create_tenant("nexiv-solutions"))
tenant_id_modamart = str(vector_store.create_tenant("modamart"))

# Add the tenant id to the metadata
for i, doc in enumerate(documents_nexiv, start=1):
    doc.metadata["tenant_id"] = tenant_id_nexiv
    doc.metadata[
        "category"
    ] = "IT"  # We will use this to apply additional filters in a later example
    doc.id_ = f"nexiv_doc_id_{i}"  # We are also setting a custom id, this is optional but can be useful

for i, doc in enumerate(documents_modamart, start=1):
    doc.metadata["tenant_id"] = tenant_id_modamart
    doc.metadata["category"] = "Retail"
    doc.id_ = f"modamart_doc_id_{i}"

storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex.from_documents(
    documents_nexiv + documents_modamart,
    storage_context=storage_context,
    show_progress=True,
)

/Users/gwen/.pyenv/versions/3.10.15/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html
  from .autonotebook import tqdm as notebook_tqdm
Parsing nodes: 100%|██████████| 2/2 [00:00<00:00, 1129.32it/s]
Generating embeddings: 100%|██████████| 2/2 [00:00<00:00,  4.58it/s]

nexiv_query_engine = index.as_query_engine(
    similarity_top_k=3,
    vector_store_kwargs={
        "tenant_id": str(tenant_id_nexiv),
    },
)

print(nexiv_query_engine.query("What were the customer pain points?"))

The customer pain points were related to managing customer data using multiple platforms, leading to data discrepancies, time-consuming reconciliation efforts, and decreased productivity.

modamart_query_engine = index.as_query_engine(
    similarity_top_k=3,
    vector_store_kwargs={
        "tenant_id": str(tenant_id_modamart),
    },
)

print(modamart_query_engine.query("What were the customer pain points?"))

The customer's pain points were concerns about the quality and value of the winter jackets, skepticism towards reviews, worries about sizing and fit when ordering clothes online, and the desire for a warm but lightweight jacket.

index = VectorStoreIndex.from_vector_store(vector_store=vector_store)
query_engine = index.as_query_engine(
    vector_store_kwargs={
        "tenant_id": str(tenant_id_modamart),
    },
)
response = query_engine.query("What action items do we need to follow up on?")

print(response)

The action items to follow up on include sending the customer detailed testimonials about the lightweight and warm qualities of the jackets, providing the customer with a sizing guide, and emailing the customer a 10% discount on their first purchase.

try:
    vector_store.create_index(index_type=IndexType.PGVECTOR_IVFFLAT, nlists=10)
except Exception as e:
    # This will throw an error if the index already exists, which may be expected
    print(e)

nexiv_query_engine = index.as_query_engine(
    similarity_top_k=3,
    vector_store_kwargs={
        "tenant_id": str(tenant_id_nexiv),
        "ivfflat_probes": 10,
    },
)

print(
    nexiv_query_engine.query("What action items do we need to follow up on?")
)

vector_store.drop_index()

Index documents_embedding_idx already exists

try:
    vector_store.create_index(
        index_type=IndexType.PGVECTOR_HNSW, m=16, ef_construction=64
    )
except Exception as e:
    # This will throw an error if the index already exists, which may be expected
    print(e)

nexiv_query_engine = index.as_query_engine(
    similarity_top_k=3,
    vector_store_kwargs={
        "tenant_id": str(tenant_id_nexiv),
        "hnsw_ef": 10,
    },
)

print(nexiv_query_engine.query("Did we mention any pricing?"))

vector_store.drop_index()

filters = MetadataFilters(
    filters=[
        MetadataFilter(
            key="category", operator=FilterOperator.EQ, value="Retail"
        ),
    ]
)

nexiv_query_engine_filtered = index.as_query_engine(
    similarity_top_k=3,
    filters=filters,
    vector_store_kwargs={"tenant_id": str(tenant_id_nexiv)},
)
print(
    "test query on nexiv with filter on category = Retail (should return empty): ",
    nexiv_query_engine_filtered.query("What were the customer pain points?"),
)

test query on nexiv with filter on category = Retail (should return empty):  Empty Response

ref_doc_id = "nexiv_doc_id_1"
vector_store.delete(ref_doc_id, tenant_id=tenant_id_nexiv)

# Query the data again
print(
    "test query on nexiv after deletion (should return empty): ",
    nexiv_query_engine.query("What were the customer pain points?"),
)

test query on nexiv after deletion (should return empty):  Empty Response