Streamlit JSONDecodeError: Expecting value: line 1 column 1 (char 0)

Dear @DmitryKey , it is a pleasure to follow your guides and go through the examples. Thank you for providing such interesting tools.

Concerning “Neural Search with BERT and Solr” everything seems to go alright including indexing and searching on the solr server, however, once I start streamlit the following errors occur when I search. Do you have any idea about what it may be?

JSONDecodeError: Expecting value: line 1 column 1 (char 0)
Traceback:

File "/home/n/documents/my_jina_app/baas/env/lib/python3.6/site-packages/streamlit/script_runner.py", line 337, in _run_script
    exec(code, module.__dict__)
File "/home/n/documents/my_jina_app/baas/bert-solr-search/src/search_demo_solr.py", line 122, in <module>
    docs, query_time, numfound = sc.query("vector", query)
File "src/client/solr_client.py", line 102, in query
    resp = resp.json()
File "/home/n/documents/my_jina_app/baas/env/lib/python3.6/site-packages/requests/models.py", line 898, in json
    return complexjson.loads(self.text, **kwargs)
File "/home/n/anaconda3/lib/python3.6/json/__init__.py", line 354, in loads
    return _default_decoder.decode(s)
File "/home/n/anaconda3/lib/python3.6/json/decoder.py", line 339, in decode
    obj, end = self.raw_decode(s, idx=_w(s, 0).end())
File "/home/n/anaconda3/lib/python3.6/json/decoder.py", line 357, in raw_decode
    raise JSONDecodeError("Expecting value", s, err.value) from None

Thank you for your consideration.

[xeisberg]

Thank you for the assistance @DmitryKey.

So in the end the problem was the src/search_demo_solr.py file on line 122 : docs,query_time, numfound = sc.query("vector", query) where one needs to replace “vector” with the core name in your solr index which may be determined by the amount of files that one indexes(in my case it became vector_10 for 10 files.

Edit: spelling

[DmitryKey]

thanks for checking that!

How many dimensions do your vectors have? In my case I use 768 dim vectors, so the only way to query them is to use HTTP POST, because the character length of the query exceeds HTTP GET.

Btw, would you be open for a quick zoom call to show your vector search setup? It might be a little faster to figure things out. Ok, if not: we can also continue discussing here!