running into issues using the langchain on text-davinci-003 model

[mmoya91]

I'm trying to use the text-davinci-003 model using the following config.cfg

[nlp]
lang = "en"
pipeline = ["llm"]

[components]

[components.llm]
factory = "llm"

[components.llm.task]
@llm_tasks = "spacy.TextCat.v3"
labels = ["COMPLIMENT", "INSULT"]

[components.llm.model]
@llm_models = "langchain.AzureOpenAI.v1"
name = "text-davinci-003"

but I'm running into

  File "/Users/mariamoya/mlplatform/lib/document_classifier/src/document_classifier/test-spacy-llm.py", line 5, in <module>
    doc = nlp("You look gorgeous!")
          ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/mariamoya/.pyenv/versions/3.11.3/envs/document_classifier/lib/python3.11/site-packages/spacy/language.py", line 1047, in __call__
    error_handler(name, proc, [doc], e)
  File "/Users/mariamoya/.pyenv/versions/3.11.3/envs/document_classifier/lib/python3.11/site-packages/spacy/util.py", line 1724, in raise_error
    raise e
  File "/Users/mariamoya/.pyenv/versions/3.11.3/envs/document_classifier/lib/python3.11/site-packages/spacy/language.py", line 1042, in __call__
    doc = proc(doc, **component_cfg.get(name, {}))  # type: ignore[call-arg]
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/mariamoya/.pyenv/versions/3.11.3/envs/document_classifier/lib/python3.11/site-packages/spacy_llm/pipeline/llm.py", line 156, in __call__
    docs = self._process_docs([doc])
           ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/mariamoya/.pyenv/versions/3.11.3/envs/document_classifier/lib/python3.11/site-packages/spacy_llm/pipeline/llm.py", line 210, in _process_docs
    responses_iters = tee(self._model(prompts_iters[0]), n_iters)
                          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/mariamoya/.pyenv/versions/3.11.3/envs/document_classifier/lib/python3.11/site-packages/spacy_llm/models/langchain/model.py", line 45, in __call__
    return self.query(self._langchain_model, prompts)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/mariamoya/.pyenv/versions/3.11.3/envs/document_classifier/lib/python3.11/site-packages/spacy_llm/models/langchain/model.py", line 56, in query_langchain
    return [model(pr) for pr in prompts]
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/mariamoya/.pyenv/versions/3.11.3/envs/document_classifier/lib/python3.11/site-packages/spacy_llm/models/langchain/model.py", line 56, in <listcomp>
    return [model(pr) for pr in prompts]
            ^^^^^^^^^
  File "/Users/mariamoya/.pyenv/versions/3.11.3/envs/document_classifier/lib/python3.11/site-packages/langchain/llms/base.py", line 786, in __call__
    self.generate(
  File "/Users/mariamoya/.pyenv/versions/3.11.3/envs/document_classifier/lib/python3.11/site-packages/langchain/llms/base.py", line 582, in generate
    output = self._generate_helper(
             ^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/mariamoya/.pyenv/versions/3.11.3/envs/document_classifier/lib/python3.11/site-packages/langchain/llms/base.py", line 488, in _generate_helper
    raise e
  File "/Users/mariamoya/.pyenv/versions/3.11.3/envs/document_classifier/lib/python3.11/site-packages/langchain/llms/base.py", line 475, in _generate_helper
    self._generate(
  File "/Users/mariamoya/.pyenv/versions/3.11.3/envs/document_classifier/lib/python3.11/site-packages/langchain/llms/openai.py", line 399, in _generate
    response = completion_with_retry(
               ^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/mariamoya/.pyenv/versions/3.11.3/envs/document_classifier/lib/python3.11/site-packages/langchain/llms/openai.py", line 115, in completion_with_retry
    return _completion_with_retry(**kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/mariamoya/.pyenv/versions/3.11.3/envs/document_classifier/lib/python3.11/site-packages/tenacity/__init__.py", line 289, in wrapped_f
    return self(f, *args, **kw)
           ^^^^^^^^^^^^^^^^^^^^
  File "/Users/mariamoya/.pyenv/versions/3.11.3/envs/document_classifier/lib/python3.11/site-packages/tenacity/__init__.py", line 379, in __call__
    do = self.iter(retry_state=retry_state)
         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/mariamoya/.pyenv/versions/3.11.3/envs/document_classifier/lib/python3.11/site-packages/tenacity/__init__.py", line 314, in iter
    return fut.result()
           ^^^^^^^^^^^^
  File "/Users/mariamoya/.pyenv/versions/3.11.3/lib/python3.11/concurrent/futures/_base.py", line 449, in result
    return self.__get_result()
           ^^^^^^^^^^^^^^^^^^^
  File "/Users/mariamoya/.pyenv/versions/3.11.3/lib/python3.11/concurrent/futures/_base.py", line 401, in __get_result
    raise self._exception
  File "/Users/mariamoya/.pyenv/versions/3.11.3/envs/document_classifier/lib/python3.11/site-packages/tenacity/__init__.py", line 382, in __call__
    result = fn(*args, **kwargs)
             ^^^^^^^^^^^^^^^^^^^
  File "/Users/mariamoya/.pyenv/versions/3.11.3/envs/document_classifier/lib/python3.11/site-packages/langchain/llms/openai.py", line 113, in _completion_with_retry
    return llm.client.create(**kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/mariamoya/.pyenv/versions/3.11.3/envs/document_classifier/lib/python3.11/site-packages/openai/api_resources/completion.py", line 25, in create
    return super().create(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/mariamoya/.pyenv/versions/3.11.3/envs/document_classifier/lib/python3.11/site-packages/openai/api_resources/abstract/engine_api_resource.py", line 155, in create
    response, _, api_key = requestor.request(
                           ^^^^^^^^^^^^^^^^^^
  File "/Users/mariamoya/.pyenv/versions/3.11.3/envs/document_classifier/lib/python3.11/site-packages/openai/api_requestor.py", line 299, in request
    resp, got_stream = self._interpret_response(result, stream)
                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/mariamoya/.pyenv/versions/3.11.3/envs/document_classifier/lib/python3.11/site-packages/openai/api_requestor.py", line 710, in _interpret_response
    self._interpret_response_line(
  File "/Users/mariamoya/.pyenv/versions/3.11.3/envs/document_classifier/lib/python3.11/site-packages/openai/api_requestor.py", line 775, in _interpret_response_line
    raise self.handle_error_response(
openai.error.InvalidRequestError: Resource not found

was wondering if anyone would happen to know what I might be missing?

[rmitsch]

Hi @mmoya91! It's possible this is related to the known LangChain/Azure integration issues. Looking into it.

Can you connect to Azure OpenAI using your credentials with langchain directly? See here for a guide. Just to ensure that your auth details/setup works.

[rmitsch]

See #311 (comment): I suspect you aren't providing the full configuration required to run langchain with Azure OpenAI. Have a look at the example I linked - if you still encounter issues, please update this thread. Otherwise I'll close this issue in a few days.

[rmitsch]

Note: v0.6.0 is out and has native support for Azure OpenAI.

[mmoya91]

perfect, thank you for the update @rmitsch!