I am getting an error when trying to predict using the TextGenerationModel text-bison as demonstrated in the lab.
I tried switching the model to text-bison-002 and other model versions listed in the PaLM Model Garden here but nothing seemed to work.
import vertexai
vertexai.init(project=PROJECT_ID,
location=REGION,
credentials = credentials)
from vertexai.language_models import TextGenerationModel
generation_model = TextGenerationModel.from_pretrained("text-bison-001")
print(generation_model.predict(prompt=prompt).text)
---------------------------------------------------------------------------
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[14], line 1
----> 1 print(generation_model.predict(prompt=prompt).text)
File /usr/local/lib/python3.10/site-packages/vertexai/language_models/_language_models.py:263, in TextGenerationModel.predict(self, prompt, max_output_tokens, temperature, top_k, top_p)
241 def predict(
242 self,
243 prompt: str,
(...)
248 top_p: float = _DEFAULT_TOP_P,
249 ) -> "TextGenerationResponse":
250 """Gets model response for a single prompt.
251
252 Args:
(...)
260 A `TextGenerationResponse` object that contains the text produced by the model.
261 """
--> 263 return self._batch_predict(
264 prompts=[prompt],
265 max_output_tokens=max_output_tokens,
266 temperature=temperature,
267 top_k=top_k,
268 top_p=top_p,
269 )[0]
File /usr/local/lib/python3.10/site-packages/vertexai/language_models/_language_models.py:342, in TextGenerationModel._batch_predict(self, prompts, max_output_tokens, temperature, top_k, top_p)
309 """Gets model response for a single prompt.
310
311 Args:
(...)
319 A list of `TextGenerationResponse` objects that contain the texts produced by the model.
320 """
321 # instances = [{"content": str(prompt)} for prompt in prompts]
322 # prediction_parameters = {
323 # "temperature": temperature,
(...)
339 # for prediction in prediction_response.predictions
340 # ]
--> 342 prediction_response = self._dlai_custom_api(prompts[0], temperature, top_p, top_k, max_output_tokens)
344 return [
345 TextGenerationResponse(
346 text=prediction_response["text"],
347 _prediction_response=None
348 )
349 ]
File /usr/local/lib/python3.10/site-packages/vertexai/language_models/_language_models.py:299, in TextGenerationModel._dlai_custom_api(self, prompt, temperature, top_p, top_k, max_output_tokens)
294 headers = {
295 'Content-Type': 'application/json',
296 'Authorization': f'Bearer {API_KEY}'
297 }
298 response = requests.request("POST", url, headers=headers, data=json.dumps(payload))
--> 299 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)