feature:url,csv embedding

This commit is contained in:
chenketing
2023-05-11 23:48:56 +08:00
parent ed855df01d
commit d42a9f3bd1
7 changed files with 86 additions and 108 deletions

View File

@@ -0,0 +1,13 @@
from pilot.source_embedding.csv_embedding import CSVEmbedding
# path = "/Users/chenketing/Downloads/share_ireserve双写数据异常2.xlsx"
path = "/Users/chenketing/Downloads/vectors.csv"
model_name = "/Users/chenketing/Desktop/project/all-MiniLM-L6-v2"
vector_store_path = "/pilot/source_embedding/"
pdf_embedding = CSVEmbedding(file_path=path, model_name=model_name, vector_store_config={"vector_store_name": "url", "vector_store_path": "vector_store_path"})
pdf_embedding.source_embedding()
print("success")

View File

@@ -0,0 +1,10 @@
from pilot.source_embedding.url_embedding import URLEmbedding
path = "https://www.understandingwar.org/backgrounder/russian-offensive-campaign-assessment-february-8-2023"
model_name = "/Users/chenketing/Desktop/project/all-MiniLM-L6-v2"
vector_store_path = "/pilot/source_embedding/"
pdf_embedding = URLEmbedding(file_path=path, model_name=model_name, vector_store_config={"vector_store_name": "url", "vector_store_path": "vector_store_path"})
pdf_embedding.source_embedding()
print("success")