Anyone had experience using

ttheta

Anyone had experience using VectorIndexAutoRetriever and getting it to work? I have the syntax correct, I think, but when I try to run the query_engine I get an opaque error I'm not sure how to debug.

for item in collection_names:
retriever = VectorIndexAutoRetriever(
            index=vector_store_indicies[item], 
            vector_store_info=index_infos['vector_index'][item],
            prompt_template_str = retriever_prompt_strings[item],
            similarity_top_k=num_k,
            max_top_k=5
        )
response_synthesizer = TreeSummarize(summary_template=qa_prompt_templates[item])
query_engine = RetrieverQueryEngine(
            retriever=retriever,
            response_synthesizer=response_synthesizer,
            node_postprocessors = [metadata_replace]
        )

That code appears to be valid, but when the interpreter gets to the following, it chokes:
`
response = query_engine.query(
f"{query_str}",
)
-> in pydantic.main.BaseModel.parse_obj:522
TypeError: 'NoneType' object is not iterable
│ ❱ 63 │ │ │ response = query_engine.query( │
│ 64 │ │ │ │ f"{query_str}", │
│ 65 │ │ │ │ )

2 comments

ttheta

│ C:\anaconda3\envs\kedro_workbench_venv\lib\site-packages\llama_index\query_engine\retriever_quer │
│ y_engine.py:172 in _query │
│ │
│ C:\anaconda3\envs\kedro_workbench_venv\lib\site-packages\llama_index\query_engine\retriever_quer │
│ y_engine.py:120 in retrieve │
│ │
│ C:\anaconda3\envs\kedro_workbench_venv\lib\site-packages\llama_index\indices\base_retriever.py:2 │
│ 2 in retrieve │
│ │
│ C:\anaconda3\envs\kedro_workbench_venv\lib\site-packages\llama_index\indices\vector_store\retrie │
│ vers\auto_retriever\auto_retriever.py:99 in _retrieve │
│ │
│ C:\anaconda3\envs\kedro_workbench_venv\lib\site-packages\llama_index\indices\vector_store\retrie │
│ vers\auto_retriever\output_parser.py:13 in parse │
│ │
│ in pydantic.main.BaseModel.parse_obj:525 │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
ValidationError: 1 validation error for VectorStoreQuerySpec
root
VectorStoreQuerySpec expected dict not NoneType (type=type_error)

WWhiteFang_Jr

Could be Pydantic issue, Try downgrading pydantic with pip install pydantic==1.10.12 version once.

See if it works

Add a reply

Find answers from the community

Anyone had experience using