There is a validation error

[chunyuma]

Hello,

While I ran the following code:

import sketch
import pandas as pd
sales_data = pd.read_csv("https://gist.githubusercontent.com/bluecoconut/9ce2135aafb5c6ab2dc1d60ac595646e/raw/c93c3500a1f7fae469cba716f09358cfddea6343/sales_demo_with_pii_and_all_states.csv")
sales_data.sketch.ask("What columns might have PII information in them?")

I got the the error below:

File /usr/local/anaconda3/envs/mypersonal_env/lib/python3.10/site-packages/pydantic/main.py:159, in BaseModel.__init__(__pydantic_self__, **data)
    157 # `__tracebackhide__` tells pytest and some other tools to omit this function from tracebacks
    158 __tracebackhide__ = True
--> 159 __pydantic_self__.__pydantic_validator__.validate_python(data, self_instance=__pydantic_self__)

ValidationError: 1 validation error for Parameters
stop
  Field required [type=missing, input_value={}, input_type=dict]
    For further information visit https://errors.pydantic.dev/2.2/v/missing

Could you please help me figure out the reason? Thanks!

[bluecoconut]

Yup! this is now fixed. Was caused by pydantic update having stricter rules. This is now fixed! Sorry about this.

[priyamshah112]

---

ValidationError Traceback (most recent call last)
Cell In[5], line 1
----> 1 df.sketch.ask("Is there any PII information in this dataset?")

File ~/anaconda3/envs/ttd/lib/python3.10/site-packages/sketch/pandas_extension.py:330, in SketchHelper.ask(self, question, call_display)
329 def ask(self, question, call_display=True):
--> 330 result = call_prompt_on_dataframe(self._obj, ask_from_parts, question=question)
331 if not call_display:
332 return result

File ~/anaconda3/envs/ttd/lib/python3.10/site-packages/sketch/pandas_extension.py:180, in call_prompt_on_dataframe(df, prompt, **kwargs)
177 text_to_copy = f"SKETCH ERROR - see print logs for full error"
178 else:
179 # using local version
--> 180 text_to_copy = prompt(**prompt_kwargs)
181 return text_to_copy

File ~/anaconda3/envs/ttd/lib/python3.10/site-packages/lambdaprompt/prompt.py:109, in Prompt.call(self, *args, **kwargs)
107 response = None
108 try:
--> 109 response = resolve(self.execute(*args, **kwargs))
110 except Exception:
111 response = f"{traceback.format_exc()}"

File ~/anaconda3/envs/ttd/lib/python3.10/site-packages/lambdaprompt/prompt.py:99, in Prompt.execute(self, *args, **kwargs)
95 if not isinstance(self, AsyncPrompt) and inspect.iscoroutinefunction(
96 self.function
97 ):
98 return resolve(self.function(*args, **kwargs))
---> 99 return self.function(*args, **kwargs)

File ~/anaconda3/envs/ttd/lib/python3.10/site-packages/sketch/pandas_extension.py:264, in ask_from_parts(dfname, column_names, data_types, extras, question, index_col_name)
260 description = get_description_from_parts(
261 column_names, data_types, extras, index_col_name
262 )
263 description = pd.json_normalize(description).to_csv(index=False)
--> 264 return ask_prompt(dfname=dfname, data_description=description, question=question)

File ~/anaconda3/envs/ttd/lib/python3.10/site-packages/lambdaprompt/prompt.py:109, in Prompt.call(self, *args, **kwargs)
107 response = None
108 try:
--> 109 response = resolve(self.execute(*args, **kwargs))
110 except Exception:
111 response = f"{traceback.format_exc()}"

File ~/anaconda3/envs/ttd/lib/python3.10/site-packages/lambdaprompt/prompt.py:98, in Prompt.execute(self, *args, **kwargs)
94 def execute(self, *args, **kwargs):
95 if not isinstance(self, AsyncPrompt) and inspect.iscoroutinefunction(
96 self.function
97 ):
---> 98 return resolve(self.function(*args, **kwargs))
99 return self.function(*args, **kwargs)

File ~/anaconda3/envs/ttd/lib/python3.10/site-packages/lambdaprompt/prompt.py:21, in resolve(obj)
19 def resolve(obj):
20 if inspect.isawaitable(obj):
---> 21 obj = asyncio.run(obj)
22 return obj

File ~/.local/lib/python3.10/site-packages/nest_asyncio.py:31, in _patch_asyncio..run(main, debug)
29 task = asyncio.ensure_future(main)
30 try:
---> 31 return loop.run_until_complete(task)
32 finally:
33 if not task.done():

File ~/.local/lib/python3.10/site-packages/nest_asyncio.py:99, in _patch_loop..run_until_complete(self, future)
96 if not f.done():
97 raise RuntimeError(
98 'Event loop stopped before Future completed.')
---> 99 return f.result()

File ~/anaconda3/envs/ttd/lib/python3.10/asyncio/futures.py:201, in Future.result(self)
199 self.__log_traceback = False
200 if self._exception is not None:
--> 201 raise self._exception.with_traceback(self._exception_tb)
202 return self._result

File ~/anaconda3/envs/ttd/lib/python3.10/asyncio/tasks.py:232, in Task.__step(failed resolving arguments)
228 try:
229 if exc is None:
230 # We use the send method directly, because coroutines
231 # don't have __iter__ and __next__ methods.
--> 232 result = coro.send(None)
233 else:
234 result = coro.throw(exc)

File ~/anaconda3/envs/ttd/lib/python3.10/site-packages/lambdaprompt/prompt.py:176, in Completion.init..function(*prompt_args, **prompt_kwargs)
174 async def function(*prompt_args, **prompt_kwargs):
175 prompt = self.get_prompt(*prompt_args, **prompt_kwargs)
--> 176 backend = self.backend or get_backend('completion')
177 return await backend(prompt, **self.kwargs)

File ~/anaconda3/envs/ttd/lib/python3.10/site-packages/lambdaprompt/backends.py:32, in get_backend(method)
30 backend_env = os.environ.get("LAMBDAPROMPT_BACKEND", None)
31 if backend_env:
---> 32 set_backend(backend_env)
33 if method in backends:
34 return backends[method]

File ~/anaconda3/envs/ttd/lib/python3.10/site-packages/lambdaprompt/backends.py:15, in set_backend(backend_name)
13 backends['completion'] = MPT7BInstructCompletion()
14 elif backend_name == 'StarCoder':
---> 15 backends['completion'] = StarCoderCompletion()
16 elif backend_name == 'StarCoderGGML':
17 backends['completion'] = StarCoderGGMLQuantizedCompletion()

File ~/anaconda3/envs/ttd/lib/python3.10/site-packages/lambdaprompt/backends.py:305, in StarCoderCompletion.init(self, hf_access_token, **kwargs)
303 if not hf_access_token:
304 raise Exception("No HuggingFace access token found (envvar HF_ACCESS_TOKEN))")
--> 305 super().init("bigcode/starcoder", use_auth_token=hf_access_token, load_config=False, **kwargs)

File ~/anaconda3/envs/ttd/lib/python3.10/site-packages/lambdaprompt/backends.py:226, in HuggingFaceBackend.init(self, model_name, torch_dtype, trust_remote_code, use_auth_token, use_device_map, load_config, **param_override)
224 from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer
225 torch_dtype = torch_dtype or torch.bfloat16
--> 226 super().init(**param_override)
227 init_kwargs = {
228 "torch_dtype": torch_dtype,
229 "trust_remote_code": trust_remote_code,
230 "use_auth_token": use_auth_token,
231 }
232 if load_config:

File ~/anaconda3/envs/ttd/lib/python3.10/site-packages/lambdaprompt/backends.py:46, in Backend.init(self, **param_override)
45 def init(self, **param_override):
---> 46 self.param_override = self.Parameters(**param_override)

File ~/anaconda3/envs/ttd/lib/python3.10/site-packages/pydantic/main.py:171, in BaseModel.init(self, **data)
169 # __tracebackhide__ tells pytest and some other tools to omit this function from tracebacks
170 tracebackhide = True
--> 171 self.pydantic_validator.validate_python(data, self_instance=self)

ValidationError: 1 validation error for Parameters
stop
Field required [type=missing, input_value={}, input_type=dict]
For further information visit https://errors.pydantic.dev/2.6/v/missing

I am still facing the issue with StarCoder. Can you tell me if the fix is specific to some library version or code line?

[priyamshah112]

For temporary fix, I have added line 220 of backends.py
class HuggingFaceBackend(Backend):
class Parameters(Backend.Parameters):
temperature: float = 0.01
max_new_tokens: int = 500
use_cache: bool = True
do_sample: bool = True
top_p: float = 0.92
top_k: int = 0
repetition_penalty: float = 1.1
stop: Optional[Union[str, List[str]]] = None #code_change: Assigned None

[gilgamesh7]

Hi team, thank you for the great work !
Unfortunately, this is still happening , are you able to help ?
I have put in more details in #36

Thank you team !