Closed akos-sch closed 2 weeks ago
I received a tip from a Google contact about a possible data store/ranking issue specific to the data I set up the data store with. I created a different data store with other data and managed to retrieve multiple documents. Seems like there weren't many relevant documents with the queries I tried. Therefore, I consider this issue closed.
The current implementation only supports the retrieval of the most relevant document for unstructured documents:
On top of this, this is hidden, as with unstructured data stores, the returned chunk type is always extractive segments:
With
0
forengine_data_type
for unstructured data stores and the default ofFalse
forget_extractive_answers
,chunk_type
will only take"extractive_segments"
.Field:
This field can not be set to anything else but
1
.Content spec setting:
engine_data_type=0
for the data store, and as said before by defaultget_extractive_answers
is set toFalse
.This means the content specification is set with 1 segment count.
There is an option to set
max_documents
. However, when I tested different values, I always got one document as a response.Code snippet used:
I use version
"1.0.3"
oflangchain-google-community
.Could you fix this?