AttributeError: 'TimesFm' object has no attribute 'forecast_with_covariates'

[algomaschine]

Guys, I've installed a latest experimental version of TimesFm, here're are the conda specs:

name: tfm2

channels:

• conda-forge
• defaults
• anaconda
  dependencies:
• jupyterlab
• pip
• python=3.10
• pip:
  • datasetsforecast
  • fire
  • git+https://github.com/awslabs/gluon-ts.git
  • huggingface_hub[cli]
  • neuralforecast
  • orjson
  • statsforecast
  • utilsforecast
  • git+https://github.com/amazon-science/chronos-forecasting.git
  • praxis
  • paxml
  • jax[cpu]==0.4.26
  • einshape
  • python-dotenv
  • nixtla>=0.5.1
  • rich
  • scikit-learn

I create this conda under wsl (ubuntu). The creation is successful, the package timefm is also installed by pip correctly.
Then I run jupyter notebook from within virtual machine and open this file downloaded locally https://github.com/google-research/timesfm/blob/master/notebooks/covariates.ipynb, but apparently the latest version of package doesn't see some api functions to be implemented.

---

AttributeError Traceback (most recent call last)
Cell In[13], line 16
13 start_time = time.time()
14 # Forecast with covariates
15 # Output: new forecast, forecast by the xreg
---> 16 cov_forecast, ols_forecast = model.forecast_with_covariates(
17 inputs=example["inputs"],
18 dynamic_numerical_covariates={
19 "gen_forecast": example["gen_forecast"],
20 },
21 dynamic_categorical_covariates={
22 "week_day": example["week_day"],
23 },
24 static_numerical_covariates={},
25 static_categorical_covariates={
26 "country": example["country"]
27 },
28 freq=[0] * len(example["inputs"]),
29 xreg_mode="xreg + timesfm", # default
30 ridge=0.0,
31 force_on_cpu=False,
32 normalize_xreg_target_per_input=True, # default
33 )
34 print(
35 f"\rFinished batch {i} linear in {time.time() - start_time} seconds",
36 end="",
37 )
38 metrics["eval_mae_timesfm"].extend(
39 mae(raw_forecast[:, :horizon_len], example["outputs"])
40 )

AttributeError: 'TimesFm' object has no attribute 'forecast_with_covariates'