I am new to AOSS. I have a serverless vector opensearch collection. I am trying to use langchain to add embeddings to the db
My code -
def opensearchvector(docs, embedding_function, opensearch_url, awsauth, index_name):
return OpenSearchVectorSearch.from_documents(
docs,
embedding_function,
opensearch_url=opensearch_url,
http_auth=awsauth,
use_ssl=True,
verify_certs=True,
http_compress = True,
connection_class=RequestsHttpConnection,
index_name = index_name,
engine="faiss"
)
This worked for me a few days ago, but recently it has started giving me the illegal_document_exception -
('1 document(s) failed to index.', [{'index': {'_index': 'json-test-index', '_id': 'cec36b7c-7140-45cb-aaa0-ddede89ed5af', 'status': 400, 'error': {'type': 'illegal_argument_exception', 'reason': 'Document ID is not supported in create/index operation request'}
.
I am not adding any indexes to my documents but still i get this error