Getting OpenAI API Key error after changing to Huggingface model - Rasa Open Source - Rasa Community Forum

Getting OpenAI API Key error after changing to Huggingface model

post by sleepingcat4 on Apr 23, 2024

I have changed the default OpenAI model to Microsoft Phi-2 model from Huggingface. I followed the default tutorial: LLM Providers

please note: I have already installed huggingfacehub and set huggingface token as an environment variable. set HUGGINGFACEHUB_API_TOKEN=<token>

and made relevant changes to config.yaml file. For reference below config.yaml file:

recipe: default.v1
language: en
pipeline:
- name: LLMCommandGenerator
  llm:
    type: "huggingface_hub"
    repo_id: "microsoft/phi-2"
    task: "text-generation"

policies:
- name: FlowPolicy
#  - name: EnterpriseSearchPolicy
#  - name: RulePolicy
assistant_id: 20240424-061357-all-patch

I’m receiving the following error:

Traceback (most recent call last):
  File "E:\Computer Science\CALM\venv\lib\site-packages\rasa\engine\graph.py", line 526, in __call__
    output = self._fn(self._component, **run_kwargs)
  File "E:\Computer Science\CALM\venv\lib\site-packages\rasa\dialogue_understanding\generator\llm_command_generator.py", line 213, in train
    self.flow_retrieval.populate(flows.user_flows, domain)
  File "E:\Computer Science\CALM\venv\lib\site-packages\rasa\dialogue_understanding\generator\flow_retrieval.py", line 181, in populate
    embeddings = self._create_embedder(self.config)
  File "E:\Computer Science\CALM\venv\lib\site-packages\rasa\dialogue_understanding\generator\flow_retrieval.py", line 153, in _create_embedder
    return embedder_factory(
  File "E:\Computer Science\CALM\venv\lib\site-packages\rasa\shared\utils\llm.py", line 245, in embedder_factory
    return embeddings_cls(**parameters)
  File "E:\Computer Science\CALM\venv\lib\site-packages\pydantic\v1\main.py", line 341, in __init__
    raise validation_error
pydantic.v1.error_wrappers.ValidationError: 1 validation error for OpenAIEmbeddings
__root__
  Did not find openai_api_key, please add an environment variable `OPENAI_API_KEY` which contains it, or pass  `openai_api_key` as a named parameter. (type=value_error)

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "C:\Program Files\Python38\lib\runpy.py", line 194, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "C:\Program Files\Python38\lib\runpy.py", line 87, in _run_code
    exec(code, run_globals)
  File "E:\Computer Science\CALM\venv\Scripts\rasa.exe\__main__.py", line 8, in <module>
  File "E:\Computer Science\CALM\venv\lib\site-packages\rasa\__main__.py", line 133, in main
    cmdline_arguments.func(cmdline_arguments)
  File "E:\Computer Science\CALM\venv\lib\site-packages\rasa\cli\train.py", line 61, in <lambda>
    train_parser.set_defaults(func=lambda args: run_training(args, can_exit=True))
  File "E:\Computer Science\CALM\venv\lib\site-packages\rasa\cli\train.py", line 104, in run_training
    training_result = train_all(
  File "E:\Computer Science\CALM\venv\lib\site-packages\rasa\api.py", line 105, in train
    return asyncio.run(
  File "C:\Program Files\Python38\lib\asyncio\runners.py", line 44, in run
    return loop.run_until_complete(main)
  File "C:\Program Files\Python38\lib\asyncio\base_events.py", line 616, in run_until_complete
    return future.result()
  File "E:\Computer Science\CALM\venv\lib\site-packages\rasa\model_training.py", line 246, in train
    return await _train_graph(
  File "E:\Computer Science\CALM\venv\lib\site-packages\rasa\model_training.py", line 336, in _train_graph
    await trainer.train(
  File "E:\Computer Science\CALM\venv\lib\site-packages\rasa\engine\training\graph_trainer.py", line 106, in train
    await graph_runner.run(inputs={PLACEHOLDER_IMPORTER: importer})
  File "E:\Computer Science\CALM\venv\lib\site-packages\rasa\engine\runner\dask.py", line 103, in run
    dask_result = await execute_dask_graph(run_graph, run_targets)
  File "E:\Computer Science\CALM\venv\lib\site-packages\rasa\engine\runner\dask.py", line 254, in execute_dask_graph
    await fire_task()
  File "E:\Computer Science\CALM\venv\lib\site-packages\rasa\engine\runner\dask.py", line 246, in fire_task
    task_result = await _execute_task(dsk[key], data)
  File "E:\Computer Science\CALM\venv\lib\site-packages\rasa\engine\runner\dask.py", line 176, in _execute_task
    return await func(*awaited_args)
  File "E:\Computer Science\CALM\venv\lib\site-packages\rasa\engine\graph.py", line 533, in __call__
    raise GraphComponentException(
rasa.engine.exceptions.GraphComponentException: Error running graph component for node train_LLMCommandGenerator0.

Can someone help me to solve this issue?

post by abboudtest on May 8, 2024

using huggingface as LLM provider doesn’t work for me

post by vss on Jun 20, 2024

Did anyone get it working?