refac: metadata handling in vectordb

This commit is contained in:
Timothy Jaeryang Baek
2025-07-31 17:45:06 +04:00
parent aa83ebae58
commit 6a17ba5b7a
5 changed files with 31 additions and 24 deletions
+4 -17
View File
@@ -1229,27 +1229,14 @@ def save_docs_to_vector_db(
{
**doc.metadata,
**(metadata if metadata else {}),
"embedding_config": json.dumps(
{
"engine": request.app.state.config.RAG_EMBEDDING_ENGINE,
"model": request.app.state.config.RAG_EMBEDDING_MODEL,
}
),
"embedding_config": {
"engine": request.app.state.config.RAG_EMBEDDING_ENGINE,
"model": request.app.state.config.RAG_EMBEDDING_MODEL,
},
}
for doc in docs
]
# ChromaDB does not like datetime formats
# for meta-data so convert them to string.
for metadata in metadatas:
for key, value in metadata.items():
if (
isinstance(value, datetime)
or isinstance(value, list)
or isinstance(value, dict)
):
metadata[key] = str(value)
try:
if VECTOR_DB_CLIENT.has_collection(collection_name=collection_name):
log.info(f"collection {collection_name} already exists")