Find answers from the community

Updated 2 years ago

Getting the following when querying

Getting the following when querying Opensearch

Plain Text

None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used.

Token indices sequence length is longer than the specified maximum sequence length for this model (3324 > 1024). Running this sequence through the model will result in indexing errors

1 comment

wwalid

Here's what triggered it:

I first initialize the index by:

Plain Text

documents = SimpleDirectoryReader('./hcaa/static').load_data()
GPTOpensearchIndex(documents=documents, client=self.opensearch_client)

Then I later re instantiate the GPTOpensearchIndex object to query

Plain Text

from llama_index.data_structs.data_structs import OpensearchIndexDict

index = GPTOpensearchIndex(client=self.opensearch_client, index_struct=OpensearchIndexDict())
response = index.query(q)

Add a reply