When running cell 13:
response = deployed_model.predict(PROMPT)
I get the following error:
---------------------------------------------------------------------------
JSONDecodeError Traceback (most recent call last)
File /usr/local/lib/python3.10/site-packages/requests/models.py:971, in Response.json(self, **kwargs)
970 try:
--> 971 return complexjson.loads(self.text, **kwargs)
972 except JSONDecodeError as e:
973 # Catch JSON-related errors and raise as requests.JSONDecodeError
974 # This aliases json.JSONDecodeError and simplejson.JSONDecodeError
File /usr/local/lib/python3.10/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 /usr/local/lib/python3.10/json/decoder.py:340, in JSONDecoder.decode(self, s, _w)
339 if end != len(s):
--> 340 raise JSONDecodeError("Extra data", s, end)
341 return obj
JSONDecodeError: Extra data: line 1 column 5 (char 4)
During handling of the above exception, another exception occurred:
JSONDecodeError Traceback (most recent call last)
Cell In[13], line 3
1 ### depending on the latency of your prompt
2 ### it can take some time to load
----> 3 response = deployed_model.predict(PROMPT)
File /usr/local/lib/python3.10/site-packages/vertexai/language_models/_language_models.py:426, in TextGenerationModel.predict(self, prompt, max_output_tokens, temperature, top_k, top_p)
404 def predict(
405 self,
406 prompt: str,
(...)
411 top_p: float = _DEFAULT_TOP_P,
412 ) -> "MultiCandidateTextGenerationResponse":
413 """Gets model response for a single prompt.
414
415 Args:
(...)
423 A `TextGenerationResponse` object that contains the text produced by the model.
424 """
--> 426 return self._batch_predict(
427 prompts=[prompt],
428 max_output_tokens=max_output_tokens,
429 temperature=temperature,
430 top_k=top_k,
431 top_p=top_p,
432 )
File /usr/local/lib/python3.10/site-packages/vertexai/language_models/_language_models.py:516, in TextGenerationModel._batch_predict(self, prompts, max_output_tokens, temperature, top_k, top_p)
483 """Gets model response for a single prompt.
484
485 Args:
(...)
493 A list of `TextGenerationResponse` objects that contain the texts produced by the model.
494 """
495 # instances = [{"content": str(prompt)} for prompt in prompts]
496 # prediction_parameters = {
497 # "temperature": temperature,
(...)
513 # for prediction in prediction_response.predictions
514 # ]
--> 516 json_prediction_response = self._dlai_custom_api(prompts[0], temperature, top_p, top_k, max_output_tokens)
517 prediction_response = _build_dict_to_prediction(json_prediction_response["prediction_response"][0])
518 # return [
519 # TextGenerationResponse(
520 # text=prediction_response["text"],
521 # _prediction_response=prediction_response[""],
522 # )
523 # ]
File /usr/local/lib/python3.10/site-packages/vertexai/language_models/_language_models.py:461, in TextGenerationModel._dlai_custom_api(self, prompt, temperature, top_p, top_k, max_output_tokens)
456 headers = {
457 'Content-Type': 'application/json',
458 'Authorization': f'Bearer {API_KEY}'
459 }
460 response = requests.request("POST", url, headers=headers, data=json.dumps(payload))
--> 461 return response.json()
File /usr/local/lib/python3.10/site-packages/requests/models.py:975, in Response.json(self, **kwargs)
971 return complexjson.loads(self.text, **kwargs)
972 except JSONDecodeError as e:
973 # Catch JSON-related errors and raise as requests.JSONDecodeError
974 # This aliases json.JSONDecodeError and simplejson.JSONDecodeError
--> 975 raise RequestsJSONDecodeError(e.msg, e.doc, e.pos)
JSONDecodeError: Extra data: line 1 column 5 (char 4)