46 lines
1.7 KiB
Python
46 lines
1.7 KiB
Python
from langchain.vectorstores import Weaviate
|
|
from langchain_weaviate.vectorstores import WeaviateVectorStore
|
|
|
|
import weaviate
|
|
from weaviate.classes.init import Auth
|
|
from weaviate.config import AdditionalConfig, Timeout
|
|
from app.embedding import WeaviateCustomEmbeddings
|
|
import os
|
|
|
|
internal_url = "vector-store-01jse60hep6416b15n1nsj6ch8.cheetah.svc.cluster.local"
|
|
external_url = "183.111.96.67"
|
|
# http_host = os.getenv("WEAVIATE_HTTP_HOST", "183.111.96.67")
|
|
http_host = os.getenv("WEAVIATE_HTTP_HOST", external_url)
|
|
# grpc_host = os.getenv("WEAVIATE_GRPC_HOST", "183.111.96.67")
|
|
grpc_host = os.getenv("WEAVIATE_GRPC_HOST", external_url)
|
|
weaviate_api_key = os.getenv("WEAVIATE_API_KEY", "01jse60hwsf37za5kmnkzzcwa9")
|
|
|
|
def get_retriever():
|
|
client = weaviate.connect_to_custom(
|
|
http_host=http_host, # Hostname for the HTTP API connection
|
|
http_port=31008, # Default is 80, WCD uses 443
|
|
http_secure=False, # Whether to use https (secure) for the HTTP API connection
|
|
grpc_host=grpc_host, # Hostname for the gRPC API connection
|
|
grpc_port=30311, # Default is 50051, WCD uses 443
|
|
grpc_secure=False, # Whether to use a secure channel for the gRPC API connection
|
|
auth_credentials=Auth.api_key(weaviate_api_key), # API key for authentication
|
|
)
|
|
|
|
embedding = WeaviateCustomEmbeddings()
|
|
|
|
vectorstore = WeaviateVectorStore(
|
|
client=client,
|
|
index_name="Loca",
|
|
text_key="page_content",
|
|
embedding=embedding,
|
|
attributes=["source", "page_content"]
|
|
)
|
|
|
|
retriever = vectorstore.as_retriever(
|
|
search_kwargs={
|
|
"k": 5
|
|
}
|
|
)
|
|
|
|
return retriever
|