extractor.acreate_schema() raises ApiError: status_code: 500, body: Internal Server Error

[n400peanuts]

Describe the bug

By running the notebook demo_pydantic_model.ipynb I encountered an ApiError when I run:

schema_response = await extractor.acreate_schema("Resume Schema", data_schema=Resume)

that is, when I try to enforce a Pydantic model previously created.

This is the full traceback (which gives also some info about how I was running the code):

`

JSONDecodeError Traceback (most recent call last)
File ~/opt/anaconda3/envs/py312/lib/python3.12/site-packages/llama_cloud/resources/extraction/client.py:468, in AsyncExtractionClient.create_schema(self, name, project_id, data_schema)
467 try:
--> 468 _response_json = _response.json()
469 except JSONDecodeError:

File ~/opt/anaconda3/envs/py312/lib/python3.12/site-packages/httpx/_models.py:764, in Response.json(self, **kwargs)
763 def json(self, **kwargs: typing.Any) -> typing.Any:
--> 764 return jsonlib.loads(self.content, **kwargs)

File ~/opt/anaconda3/envs/py312/lib/python3.12/json/init.py:346, in loads(s, cls, object_hook, parse_float, parse_int, parse_constant, object_pairs_hook, **kw)
343 if (cls is None and object_hook is None and
344 parse_int is None and parse_float is None and
345 parse_constant is None and object_pairs_hook is None and not kw):
--> 346 return _default_decoder.decode(s)
347 if cls is None:

File ~/opt/anaconda3/envs/py312/lib/python3.12/json/decoder.py:337, in JSONDecoder.decode(self, s, _w)
333 """Return the Python representation of s (a str instance
334 containing a JSON document).
335
336 """
--> 337 obj, end = self.raw_decode(s, idx=_w(s, 0).end())
338 end = _w(s, end).end()

File ~/opt/anaconda3/envs/py312/lib/python3.12/json/decoder.py:355, in JSONDecoder.raw_decode(self, s, idx)
354 except StopIteration as err:
--> 355 raise JSONDecodeError("Expecting value", s, err.value) from None
356 return obj, end

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

During handling of the above exception, another exception occurred:

ApiError Traceback (most recent call last)
Cell In[5], line 1
----> 1 schema_response = await extractor.acreate_schema("Resume Schema", data_schema=Resume)

File ~/opt/anaconda3/envs/py312/lib/python3.12/site-packages/llama_extract/base.py:261, in LlamaExtract.acreate_schema(self, name, data_schema, project_id)
256 else:
257 raise ValueError(
258 "data_schema must be either a dictionary or a Pydantic model"
259 )
--> 261 response = await self._async_client.extraction.create_schema(
262 name=name, data_schema=json_schema, project_id=project_id
263 )
264 return response

File ~/opt/anaconda3/envs/py312/lib/python3.12/site-packages/llama_cloud/resources/extraction/client.py:470, in AsyncExtractionClient.create_schema(self, name, project_id, data_schema)
468 _response_json = _response.json()
469 except JSONDecodeError:
--> 470 raise ApiError(status_code=_response.status_code, body=_response.text)
471 raise ApiError(status_code=_response.status_code, body=_response_json)

ApiError: status_code: 500, body: Internal Server Error
`

Files
The files are within the repository already as this was a demo notebook

Client:
Please remove untested options:

• API

[Yuvraj-Takey]

I'm also encountering the same error when executing examples/demo_json_schema.ipynb.
ApiError: status_code: 500, body: Internal Server Error

However, I found a workaround: using the update_schema method will internally replace the old schema and return the new one schema. Here is the code sample
extraction_schema = await extractor.aupdate_schema(extraction_schema.id, data_schema=userSchema)

(@n400peanuts You can replace userSchema with your data as Resume)

[KannamSridharKumar]

@Yuvraj-Takey

To be able to run the code you have suggested, we already need to have extraction_schema.id.
But, we are getting the error when we run the extraction_schema first time.

Can you pls share your full code?

Thanks,

[KannamSridharKumar]

@Yuvraj-Takey thanks, i just figured it out.
We first create the default schema, which is working fine. Then update it.

extraction_schema = await extractor.ainfer_schema("Test Schema", fpaths)

extraction_schema = await extractor.aupdate_schema(extraction_schema.id, data_schema=data_schema)

[samarth777]

@Yuvraj-Takey thanks, i just figured it out. We first create the default schema, which is working fine. Then update it.

extraction_schema = await extractor.ainfer_schema("Test Schema", fpaths)

extraction_schema = await extractor.aupdate_schema(extraction_schema.id, data_schema=data_schema)

what is fpaths? how to create the default schema that works?