mirror of
https://github.com/hwchase17/langchain
synced 2024-11-08 07:10:35 +00:00
39 lines
1.3 KiB
Python
39 lines
1.3 KiB
Python
|
### Ingest code - you may need to run this the first time
|
||
|
|
import os
|
||
|
|
|
||
|
|
from langchain.document_loaders import WebBaseLoader
|
||
|
|
from langchain.embeddings import OpenAIEmbeddings
|
||
|
|
from langchain.text_splitter import RecursiveCharacterTextSplitter
|
||
|
|
from langchain.vectorstores import MomentoVectorIndex
|
||
|
|
from momento import (
|
||
|
|
CredentialProvider,
|
||
|
|
PreviewVectorIndexClient,
|
||
|
|
VectorIndexConfigurations,
|
||
|
|
)
|
||
|
|
|
||
|
|
|
||
|
|
def load(API_KEY_ENV_VAR_NAME: str, index_name: str) -> None:
|
||
|
|
if os.environ.get(API_KEY_ENV_VAR_NAME, None) is None:
|
||
|
|
raise Exception(f"Missing `{API_KEY_ENV_VAR_NAME}` environment variable.")
|
||
|
|
|
||
|
|
# Load
|
||
|
|
loader = WebBaseLoader("https://lilianweng.github.io/posts/2023-06-23-agent/")
|
||
|
|
data = loader.load()
|
||
|
|
|
||
|
|
# Split
|
||
|
|
text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)
|
||
|
|
all_splits = text_splitter.split_documents(data)
|
||
|
|
|
||
|
|
# Add to vectorDB
|
||
|
|
MomentoVectorIndex.from_documents(
|
||
|
|
all_splits,
|
||
|
|
embedding=OpenAIEmbeddings(),
|
||
|
|
client=PreviewVectorIndexClient(
|
||
|
|
configuration=VectorIndexConfigurations.Default.latest(),
|
||
|
|
credential_provider=CredentialProvider.from_environment_variable(
|
||
|
|
API_KEY_ENV_VAR_NAME
|
||
|
|
),
|
||
|
|
),
|
||
|
|
index_name=index_name,
|
||
|
|
)
|