feat: Add embedding manager (#570)

This commit is contained in:
Taranjeet Singh
2023-09-11 23:43:53 -07:00
committed by GitHub
parent ba208f5b48
commit 2bd6881361
16 changed files with 311 additions and 73 deletions

View File

@@ -22,14 +22,17 @@ class BaseChunker(JSONSerializable):
documents = []
ids = []
idMap = {}
datas = loader.load_data(src)
data_result = loader.load_data(src)
data_records = data_result["data"]
doc_id = data_result["doc_id"]
metadatas = []
for data in datas:
for data in data_records:
content = data["content"]
meta_data = data["meta_data"]
# add data type to meta data to allow query using data type
meta_data["data_type"] = self.data_type.value
meta_data["doc_id"] = doc_id
url = meta_data["url"]
chunks = self.get_chunks(content)
@@ -45,6 +48,7 @@ class BaseChunker(JSONSerializable):
"documents": documents,
"ids": ids,
"metadatas": metadatas,
"doc_id": doc_id,
}
def get_chunks(self, content):