Hi, is there a way to use a postgres vector store (pgvector) as a docstore? All the data is actually already there.

Specifically, what I want to do, is use the data we already store in pgvector to build a QueryFusionRetriever, with a vector_retriever and a bm25retriever. In theory, I should be able to perform bm25 retrieval in the postgres database, but the bm25retriever can only be initilised with a docstore.

I also found out this sparse vector_store_query_mode, but I believe thats only for hybrid text search, so not what I am looking for.

Any ideas on how can I achieve this?

Hi everyone. I think I found a bug and would like to know if someone has had this issue before. I am building an IngestionPipeline, and I want to paralellize the ingestion process. One of the Transformation steps is embedding the nodes. However, it seems like the baseEmbeddings class does not support it. The error message:

File ".../Python/3.11/lib/python/site-packages/IPython/core/interactiveshell.py", line 3551, in run_code
await eval(code_obj, self.user_global_ns, self.user_ns)
File "/var/folders/_0/jky_78wd6pl1z86rd3_9gntm0000gq/T/ipykernel_87921/4016904397.py", line 2, in <module>
nodes = await pipeline.arun(documents=data, num_workers=3)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/homebrew/lib/python3.11/site-packages/llama_index/ingestion/pipeline.py", line 369, in arun
File "/opt/homebrew/lib/python3.11/site-packages/llama_index/ingestion/pipeline.py", line 110, in arun_transformations
hash = get_transformation_hash(nodes, transform)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/homebrew/lib/python3.11/site-packages/llama_index/embeddings/base.py", line 345, in acall
TypeError: BaseEmbedding.aget_text_embedding_batch() got an unexpected keyword argument 'num_workers'