The community members are experiencing an issue with index.as_query_engine() in runner.aevaluate_queries, which seems to be related to the Faiss vector store. The error message indicates that the dimensions of the Faiss store do not match the dimensions of the model used to query it. The community members suggest that the issue is caused by not using the same embedding model to query the index as was used to create it. To resolve the issue, the community members recommend ensuring that the same embedding model is used for both indexing and querying.
result = func(*args, kwargs) File "/Users/ilpinto/dev/lightspeed-rag-content/.conda/lib/python3.10/site-packages/llama_index/core/indices/vector_store/retrievers/retriever.py", line 101, in _retrieve return self._get_nodes_with_embeddings(query_bundle) File "/Users/ilpinto/dev/lightspeed-rag-content/.conda/lib/python3.10/site-packages/llama_index/core/indices/vector_store/retrievers/retriever.py", line 177, in _get_nodes_with_embeddings query_result = self._vector_store.query(query, self._kwargs) File "/Users/ilpinto/dev/lightspeed-rag-content/.conda/lib/python3.10/site-packages/llama_index/vector_stores/faiss/base.py", line 182, in query dists, indices = self._faiss_index.search( File "/Users/ilpinto/dev/lightspeed-rag-content/.conda/lib/python3.10/site-packages/faiss/class_wrappers.py", line 329, in replacement_search assert d == self.d AssertionError
The dimensions come from the embedding model -- the error meant that you aren't using the same embedding model to query that you used to build the index
