David Riccitelli

For the time being, switching to orjson brought a great advantage. The profiling now shows that the SPARQL queries are slowing down the initial indexing. The queries are being cached...

Thanks @jcrist, yes I started adding the schema as an improvement I am testing out on the languagemodel (along with reactive rxpy) and so far the profiler looks promising :-)...

And now that I added some multiproc, we're back at that :-) 

@jcrist is there a way to ignore a typed value when the type is unknown? Right now I get this error: ``` msgspec.ValidationError: Invalid value 'globecoordinate' - at `$.claims[...][0].mainsnak.datavalue.type` ```...

I ended up defining it. So far so good ...

This is how I set the Document Cache and a custom `DocumentLoader` for JSONLD11 (Titanium): ``` private final static JsonLdOptions JSONLD_OPTIONS_VALUE = new JsonLdOptions(); static { // This set a...

Reopening after fixing the issues. Local tests succeed. We need to check here too.

We're checking the Python 3.10 test.

@logan-markewich we fixed the tests. Please let us know if you need more actions from our side. Cheers.

@logan-markewich I fixed the `metadata` issue, we're now sending it with the request. As per the entity ID please see my comment [here](https://github.com/run-llama/llama_index/pull/13028#discussion_r1604470790).