Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}} encountered when running langchain program with Azure AI

Peter 0

I encountered below NotFoundError when running langchain tutorial program (code: model.invoke(messages). Please help and advise, thanks.

NotFoundError: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}

LangChain tutorial program:


import os
os.environ["AZURE_OPENAI_API_KEY"] = "d957dxxxxxxxxxxxxxxxxxxxxxxxxx18438ba99f4b7"
os.environ["AZURE_OPENAI_ENDPOINT"] = "https://xxxxxxxxxx.cognitiveservices.azure.com/"
os.environ["AZURE_OPENAI_DEPLOYMENT"] = "Microsoft.CognitiveServicesAllInOne-20240775798778"
os.environ["AZURE_OPENAI_API_VERSION"] = "2021-04-30"

from langchain_openai import AzureChatOpenAI

model = AzureChatOpenAI(
    azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
    azure_deployment=os.environ["AZURE_OPENAI_DEPLOYMENT"],
    openai_api_version=os.environ["AZURE_OPENAI_API_VERSION"]
)

from langchain_core.messages import HumanMessage, SystemMessage
messages = [
    SystemMessage(content="Translate the following from English into Italian"),
    HumanMessage(content="hi!"),
]
model.invoke(messages)

santoshkc 8,690 Reputation points Microsoft Vendor

2024-09-24T16:57:55.7266667+00:00

Hi @Peter,

Following up to see if the below answer was helpful. If this answers your query, do click Accept Answer and Yes for was this answer helpful. And, if you have any further query do let us know.

Thank you.
santoshkc 8,690 Reputation points Microsoft Vendor

2024-09-25T18:01:55.7833333+00:00

Hi @Peter,

Did you got any chance to check the below response?

1 answer

santoshkc 8,690 Microsoft Vendor

Hi @Peter,

Thank you for reaching out to Microsoft Q&A forum!

I tried to repro the issue with the given code below and able to run the program:

import os
from langchain_openai import AzureChatOpenAI
from langchain_core.messages import HumanMessage, SystemMessage

# Set your Azure OpenAI credentials in environment variables
os.environ["AZURE_OPENAI_API_KEY"] = "<KEY>"
os.environ["AZURE_OPENAI_ENDPOINT"] = "https://<ENDPOINT>.openai.azure.com/" # Ensure this is correct
os.environ["AZURE_OPENAI_DEPLOYMENT"] = "gpt-4o-mini" # Use your actual deployment name
os.environ["AZURE_OPENAI_API_VERSION"] = "2023-05-15" # Check if this version is supported

# Initialize the AzureChatOpenAI model
model = AzureChatOpenAI(
    azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
    azure_deployment=os.environ["AZURE_OPENAI_DEPLOYMENT"],
    openai_api_version=os.environ["AZURE_OPENAI_API_VERSION"]
)

# Create system and human messages
messages = [
    SystemMessage(content="Translate the following from English into Italian"),
    HumanMessage(content="hi!")
]
response = model.invoke(messages)

# Print the translation
print("Translation:", response)

Output:
User's image

Hope this helps. Do let us know if you any further queries.

If this answers your query, do click Accept Answer and Yes for was this answer helpful.

Peter 0 Reputation points

2024-09-26T13:03:49.4733333+00:00

I still got 404 error, may I know where to locate deployment name? now I got the deployment name is quite lengthy (Microsoft.CognitiveServicesAllInOne-202409XXXXXXXX) and I just queried if my deployment name is correct, thanks.
santoshkc 8,690 Reputation points Microsoft Vendor

2024-09-26T15:17:45.2866667+00:00
Hi @Peter,

To locate the deployment name for Azure OpenAI, follow these steps:

Go to the Azure portal.

Navigate to your Azure OpenAI resource.

In the left-hand menu, select Deployments.

Open the deployed model and you will see the deployment name listed here, which is required for API calls.

As per the below screenshot, provide the deployment name in your code as: os.environ["AZURE_OPENAI_DEPLOYMENT"] = "test_model"

Ensure you are using the correct and complete deployment name in your API requests. The lengthy name you mentioned (e.g., "Microsoft.CognitiveServicesAllInOne-202409XXXXXXXX") might not be the actual deployment name; it should be something shorter and user-defined during setup. Double-check the exact deployment name in the Deployments section of your resource.

I hope this helps. Thank you.

Could you please take a moment to retake the survey on the above response? Your feedback is greatly appreciated.

Peter 0

Thanks, already put the correct deployment name in there. However, still found error 404, please find my program codes and error codes pasted below for your kind review and advice. Thanks a lot!

program codes: Screenshot 2024-09-27 at 12.46.11 PM

error codes:

---------------------------------------------------------------------------
NotFoundError                             Traceback (most recent call last)
Cell In[19], line 8
      1 #codes from email on 27/Sep/2024
      2 
      3 # Create system and human messages
      4 messages = [
      5     SystemMessage(content="Translate the following from English into Italian"),
      6     HumanMessage(content="hi!")
      7 ]
----> 8 response = model.invoke(messages)
     10 # Print the translation
     11 print("Translation:", response)

File /Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/langchain_core/language_models/chat_models.py:284, in BaseChatModel.invoke(self, input, config, stop, **kwargs)
    273 def invoke(
    274     self,
    275     input: LanguageModelInput,
   (...)
    279     **kwargs: Any,
    280 ) -> BaseMessage:
    281     config = ensure_config(config)
    282     return cast(
    283         ChatGeneration,
--> 284         self.generate_prompt(
    285             [self._convert_input(input)],
    286             stop=stop,
    287             callbacks=config.get("callbacks"),
    288             tags=config.get("tags"),
    289             metadata=config.get("metadata"),
    290             run_name=config.get("run_name"),
    291             run_id=config.pop("run_id", None),
    292             **kwargs,
    293         ).generations[0][0],
    294     ).message

File /Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/langchain_core/language_models/chat_models.py:784, in BaseChatModel.generate_prompt(self, prompts, stop, callbacks, **kwargs)
    776 def generate_prompt(
    777     self,
    778     prompts: list[PromptValue],
   (...)
    781     **kwargs: Any,
    782 ) -> LLMResult:
    783     prompt_messages = [p.to_messages() for p in prompts]
--> 784     return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)

File /Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/langchain_core/language_models/chat_models.py:641, in BaseChatModel.generate(self, messages, stop, callbacks, tags, metadata, run_name, run_id, **kwargs)
    639         if run_managers:
    640             run_managers[i].on_llm_error(e, response=LLMResult(generations=[]))
--> 641         raise e
    642 flattened_outputs = [
    643     LLMResult(generations=[res.generations], llm_output=res.llm_output)  # type: ignore[list-item]
    644     for res in results
    645 ]
    646 llm_output = self._combine_llm_outputs([res.llm_output for res in results])

File /Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/langchain_core/language_models/chat_models.py:631, in BaseChatModel.generate(self, messages, stop, callbacks, tags, metadata, run_name, run_id, **kwargs)
    628 for i, m in enumerate(messages):
    629     try:
    630         results.append(
--> 631             self._generate_with_cache(
    632                 m,
    633                 stop=stop,
    634                 run_manager=run_managers[i] if run_managers else None,
    635                 **kwargs,
    636             )
    637         )
    638     except BaseException as e:
    639         if run_managers:

File /Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/langchain_core/language_models/chat_models.py:853, in BaseChatModel._generate_with_cache(self, messages, stop, run_manager, **kwargs)
    851 else:
    852     if inspect.signature(self._generate).parameters.get("run_manager"):
--> 853         result = self._generate(
    854             messages, stop=stop, run_manager=run_manager, **kwargs
    855         )
    856     else:
    857         result = self._generate(messages, stop=stop, **kwargs)

File /Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/langchain_openai/chat_models/base.py:670, in BaseChatOpenAI._generate(self, messages, stop, run_manager, **kwargs)
    668     generation_info = {"headers": dict(raw_response.headers)}
    669 else:
--> 670     response = self.client.create(**payload)
    671 return self._create_chat_result(response, generation_info)

File /Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/openai/_utils/_utils.py:274, in required_args.<locals>.inner.<locals>.wrapper(*args, **kwargs)
    272             msg = f"Missing required argument: {quote(missing[0])}"
    273     raise TypeError(msg)
--> 274 return func(*args, **kwargs)

File /Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/openai/resources/chat/completions.py:704, in Completions.create(self, messages, model, frequency_penalty, function_call, functions, logit_bias, logprobs, max_completion_tokens, max_tokens, n, parallel_tool_calls, presence_penalty, response_format, seed, service_tier, stop, stream, stream_options, temperature, tool_choice, tools, top_logprobs, top_p, user, extra_headers, extra_query, extra_body, timeout)
    668 @required_args(["messages", "model"], ["messages", "model", "stream"])
    669 def create(
    670     self,
   (...)
    701     timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
    702 ) -> ChatCompletion | Stream[ChatCompletionChunk]:
    703     validate_response_format(response_format)
--> 704     return self._post(
    705         "/chat/completions",
    706         body=maybe_transform(
    707             {
    708                 "messages": messages,
    709                 "model": model,
    710                 "frequency_penalty": frequency_penalty,
    711                 "function_call": function_call,
    712                 "functions": functions,
    713                 "logit_bias": logit_bias,
    714                 "logprobs": logprobs,
    715                 "max_completion_tokens": max_completion_tokens,
    716                 "max_tokens": max_tokens,
    717                 "n": n,
    718                 "parallel_tool_calls": parallel_tool_calls,
    719                 "presence_penalty": presence_penalty,
    720                 "response_format": response_format,
    721                 "seed": seed,
    722                 "service_tier": service_tier,
    723                 "stop": stop,
    724                 "stream": stream,
    725                 "stream_options": stream_options,
    726                 "temperature": temperature,
    727                 "tool_choice": tool_choice,
    728                 "tools": tools,
    729                 "top_logprobs": top_logprobs,
    730                 "top_p": top_p,
    731                 "user": user,
    732             },
    733             completion_create_params.CompletionCreateParams,
    734         ),
    735         options=make_request_options(
    736             extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
    737         ),
    738         cast_to=ChatCompletion,
    739         stream=stream or False,
    740         stream_cls=Stream[ChatCompletionChunk],
    741     )

File /Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/openai/_base_client.py:1268, in SyncAPIClient.post(self, path, cast_to, body, options, files, stream, stream_cls)
   1254 def post(
   1255     self,
   1256     path: str,
   (...)
   1263     stream_cls: type[_StreamT] | None = None,
   1264 ) -> ResponseT | _StreamT:
   1265     opts = FinalRequestOptions.construct(
   1266         method="post", url=path, json_data=body, files=to_httpx_files(files), **options
   1267     )
-> 1268     return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))

File /Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/openai/_base_client.py:945, in SyncAPIClient.request(self, cast_to, options, remaining_retries, stream, stream_cls)
    942 else:
    943     retries_taken = 0
--> 945 return self._request(
    946     cast_to=cast_to,
    947     options=options,
    948     stream=stream,
    949     stream_cls=stream_cls,
    950     retries_taken=retries_taken,
    951 )

File /Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/openai/_base_client.py:1049, in SyncAPIClient._request(self, cast_to, options, retries_taken, stream, stream_cls)
   1046         err.response.read()
   1048     log.debug("Re-raising status error")
-> 1049     raise self._make_status_error_from_response(err.response) from None
   1051 return self._process_response(
   1052     cast_to=cast_to,
   1053     options=options,
   (...)
   1057     retries_taken=retries_taken,
   1058 )

NotFoundError: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}

santoshkc 8,690 Reputation points Microsoft Vendor

2024-09-27T14:43:27.9966667+00:00

Hi @Peter,

Can you please try using the version as 2023-05-15. Follow this format

os.environ["AZURE_OPENAI_API_VERSION"] = "2023-05-15"and let us know, how it is working. Also, if Langchain is not installed, try to install.
santoshkc 8,690 Reputation points Microsoft Vendor

2024-09-30T09:58:36.4766667+00:00

Hi @Peter,

We haven’t heard from you on the last response and was just checking back to see if you have a resolution yet. Otherwise, will respond with more details and we will try to help.

Thank you.

Could you please take a moment to retake the survey on the above response? Your feedback is greatly appreciated.
Peter 0 Reputation points

2024-10-02T10:41:10.0933333+00:00

Dear all, thanks for the support. error 404 issues resolved. I went to the Get-Start tutorial, deployed "GPT-35-turbo", and then copied all related data from the "deployment" section and pasted them into the python program, and no 404 error code existed anymore.
santoshkc 8,690 Reputation points Microsoft Vendor

2024-10-03T11:36:00.2666667+00:00

Hi @Peter,

Glad to know that your issue has been resolved. And thanks for sharing the information, which might be beneficial to other community members reading this thread.
Thank you.

Could you please take a moment to retake the survey on my earlier response? Your feedback is greatly appreciated.

Share via

Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}} encountered when running langchain program with Azure AI

1 answer

Your answer