Hi ,
I get the below error in Lesson 3 when I try to get response
response = response_agent.invoke(
{“messages”: [{“role”: “user”, “content”: “Jim is my friend”}]},
config=config
)
ERROR:
InternalServerError: 500 error
During task with name ‘agent’ and id ‘ecdbd979-d488-e527-a648-58b2ac6616b1’
Kindly hlep
Try after sometime probably after 24-48 hour if the error still occurs, let us know here. Make sure when you try again clear your browsing and cache history.
you are charging every month and out of which it wont work for 2 days , its been already 2 days , this is rdiculous, and looks like the subscription will be over by the time your service is up and i have to pay again
Didnt expect this from deeplearning.ai
internal server error is not dependent completely on deeplearning.ai only, any courses involves multiple interfaces if you understand AI technicalities and this error could be from multiple dependencies used while creating a lab.
@Lesly can you please look into this issue if the issue is from our side or developer dependencies.
I had the same error in “long-term-agentic-memory-with-langgraph”, so i moved to this course, and now here I face the same error,
thank you for reporting this, I will bring this issue to be highly prioritized in addressing your concern.
just be sure can mention the lab name, so that I can check if I am also encountering the same error.
long-term-agentic-memory-with-langgraph –>lesson_3
I get error in fine-tuning-and-reinforcement-learning-for-llms-intro-to-post-training - Module 1 →graded lab–M1_G1_Inspecting_Finetuned_vs_Base_Model - i will raise tisone in teh relevant Topic
can you share the link as I cannot find lab name you mentioned in the course you mentioned
response = response_agent.invoke(
{“messages”: [{“role”: “user”, “content”: “Jim is my friend”}]},
config=config
)
agree I got the same error, I think the agent using the model, seems to have deprecated causing this issue. @skr687 thank you for notifying.
Posting the complete error here so staff can notice it
InternalServerError Traceback (most recent call last)
Cell In[35], line 1
----> 1 response = response_agent.invoke(
2 {"messages": [{"role": "user", "content": "Jim is my friend"}]},
3 config=config
4 )
File /usr/local/lib/python3.11/site-packages/langgraph/pregel/__init__.py:2069, in Pregel.invoke(self, input, config, stream_mode, output_keys, interrupt_before, interrupt_after, debug, **kwargs)
2067 else:
2068 chunks = []
-> 2069 for chunk in self.stream(
2070 input,
2071 config,
2072 stream_mode=stream_mode,
2073 output_keys=output_keys,
2074 interrupt_before=interrupt_before,
2075 interrupt_after=interrupt_after,
2076 debug=debug,
2077 **kwargs,
2078 ):
2079 if stream_mode == "values":
2080 latest = chunk
File /usr/local/lib/python3.11/site-packages/langgraph/pregel/__init__.py:1724, in Pregel.stream(self, input, config, stream_mode, output_keys, interrupt_before, interrupt_after, debug, subgraphs)
1718 # Similarly to Bulk Synchronous Parallel / Pregel model
1719 # computation proceeds in steps, while there are channel updates.
1720 # Channel updates from step N are only visible in step N+1
1721 # channels are guaranteed to be immutable for the duration of the step,
1722 # with channel updates applied only at the transition between steps.
1723 while loop.tick(input_keys=self.input_channels):
-> 1724 for _ in runner.tick(
1725 loop.tasks.values(),
1726 timeout=self.step_timeout,
1727 retry_policy=self.retry_policy,
1728 get_waiter=get_waiter,
1729 ):
1730 # emit output
1731 yield from output()
1732 # emit output
File /usr/local/lib/python3.11/site-packages/langgraph/pregel/runner.py:230, in PregelRunner.tick(self, tasks, reraise, timeout, retry_policy, get_waiter)
228 t = tasks[0]
229 try:
--> 230 run_with_retry(
231 t,
232 retry_policy,
233 configurable={
234 CONFIG_KEY_SEND: partial(writer, t),
235 CONFIG_KEY_CALL: partial(call, t),
236 },
237 )
238 self.commit(t, None)
239 except Exception as exc:
File /usr/local/lib/python3.11/site-packages/langgraph/pregel/retry.py:40, in run_with_retry(task, retry_policy, configurable)
38 task.writes.clear()
39 # run the task
---> 40 return task.proc.invoke(task.input, config)
41 except ParentCommand as exc:
42 ns: str = config[CONF][CONFIG_KEY_CHECKPOINT_NS]
File /usr/local/lib/python3.11/site-packages/langgraph/utils/runnable.py:506, in RunnableSeq.invoke(self, input, config, **kwargs)
502 config = patch_config(
503 config, callbacks=run_manager.get_child(f"seq:step:{i + 1}")
504 )
505 if i == 0:
--> 506 input = step.invoke(input, config, **kwargs)
507 else:
508 input = step.invoke(input, config)
File /usr/local/lib/python3.11/site-packages/langgraph/utils/runnable.py:262, in RunnableCallable.invoke(self, input, config, **kwargs)
260 context = copy_context()
261 context.run(_set_config_context, child_config)
--> 262 ret = context.run(self.func, *args, **kwargs)
263 except BaseException as e:
264 run_manager.on_chain_error(e)
File /usr/local/lib/python3.11/site-packages/langgraph/prebuilt/chat_agent_executor.py:639, in create_react_agent.<locals>.call_model(state, config)
637 def call_model(state: AgentState, config: RunnableConfig) -> AgentState:
638 _validate_chat_history(state["messages"])
--> 639 response = cast(AIMessage, model_runnable.invoke(state, config))
640 # add agent name to the AIMessage
641 response.name = name
File /usr/local/lib/python3.11/site-packages/langchain_core/runnables/base.py:3024, in RunnableSequence.invoke(self, input, config, **kwargs)
3022 input = context.run(step.invoke, input, config, **kwargs)
3023 else:
-> 3024 input = context.run(step.invoke, input, config)
3025 # finish the root run
3026 except BaseException as e:
File /usr/local/lib/python3.11/site-packages/langchain_core/runnables/base.py:5360, in RunnableBindingBase.invoke(self, input, config, **kwargs)
5354 def invoke(
5355 self,
5356 input: Input,
5357 config: Optional[RunnableConfig] = None,
5358 **kwargs: Optional[Any],
5359 ) -> Output:
-> 5360 return self.bound.invoke(
5361 input,
5362 self._merge_configs(config),
5363 **{**self.kwargs, **kwargs},
5364 )
File /usr/local/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 /usr/local/lib/python3.11/site-packages/langchain_core/language_models/chat_models.py:860, in BaseChatModel.generate_prompt(self, prompts, stop, callbacks, **kwargs)
852 def generate_prompt(
853 self,
854 prompts: list[PromptValue],
(...)
857 **kwargs: Any,
858 ) -> LLMResult:
859 prompt_messages = [p.to_messages() for p in prompts]
--> 860 return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)
File /usr/local/lib/python3.11/site-packages/langchain_core/language_models/chat_models.py:690, in BaseChatModel.generate(self, messages, stop, callbacks, tags, metadata, run_name, run_id, **kwargs)
687 for i, m in enumerate(messages):
688 try:
689 results.append(
--> 690 self._generate_with_cache(
691 m,
692 stop=stop,
693 run_manager=run_managers[i] if run_managers else None,
694 **kwargs,
695 )
696 )
697 except BaseException as e:
698 if run_managers:
File /usr/local/lib/python3.11/site-packages/langchain_core/language_models/chat_models.py:925, in BaseChatModel._generate_with_cache(self, messages, stop, run_manager, **kwargs)
923 else:
924 if inspect.signature(self._generate).parameters.get("run_manager"):
--> 925 result = self._generate(
926 messages, stop=stop, run_manager=run_manager, **kwargs
927 )
928 else:
929 result = self._generate(messages, stop=stop, **kwargs)
File /usr/local/lib/python3.11/site-packages/langchain_anthropic/chat_models.py:814, in ChatAnthropic._generate(self, messages, stop, run_manager, **kwargs)
812 return generate_from_stream(stream_iter)
813 payload = self._get_request_payload(messages, stop=stop, **kwargs)
--> 814 data = self._client.messages.create(**payload)
815 return self._format_output(data, **kwargs)
File /usr/local/lib/python3.11/site-packages/anthropic/_utils/_utils.py:275, in required_args.<locals>.inner.<locals>.wrapper(*args, **kwargs)
273 msg = f"Missing required argument: {quote(missing[0])}"
274 raise TypeError(msg)
--> 275 return func(*args, **kwargs)
File /usr/local/lib/python3.11/site-packages/anthropic/resources/messages/messages.py:904, in Messages.create(self, max_tokens, messages, model, metadata, stop_sequences, stream, system, temperature, tool_choice, tools, top_k, top_p, extra_headers, extra_query, extra_body, timeout)
897 if model in DEPRECATED_MODELS:
898 warnings.warn(
899 f"The model '{model}' is deprecated and will reach end-of-life on {DEPRECATED_MODELS[model]}.\nPlease migrate to a newer model. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.",
900 DeprecationWarning,
901 stacklevel=3,
902 )
--> 904 return self._post(
905 "/v1/messages",
906 body=maybe_transform(
907 {
908 "max_tokens": max_tokens,
909 "messages": messages,
910 "model": model,
911 "metadata": metadata,
912 "stop_sequences": stop_sequences,
913 "stream": stream,
914 "system": system,
915 "temperature": temperature,
916 "tool_choice": tool_choice,
917 "tools": tools,
918 "top_k": top_k,
919 "top_p": top_p,
920 },
921 message_create_params.MessageCreateParams,
922 ),
923 options=make_request_options(
924 extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
925 ),
926 cast_to=Message,
927 stream=stream or False,
928 stream_cls=Stream[RawMessageStreamEvent],
929 )
File /usr/local/lib/python3.11/site-packages/anthropic/_base_client.py:1289, in SyncAPIClient.post(self, path, cast_to, body, options, files, stream, stream_cls)
1275 def post(
1276 self,
1277 path: str,
(...)
1284 stream_cls: type[_StreamT] | None = None,
1285 ) -> ResponseT | _StreamT:
1286 opts = FinalRequestOptions.construct(
1287 method="post", url=path, json_data=body, files=to_httpx_files(files), **options
1288 )
-> 1289 return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
File /usr/local/lib/python3.11/site-packages/anthropic/_base_client.py:966, in SyncAPIClient.request(self, cast_to, options, remaining_retries, stream, stream_cls)
963 else:
964 retries_taken = 0
--> 966 return self._request(
967 cast_to=cast_to,
968 options=options,
969 stream=stream,
970 stream_cls=stream_cls,
971 retries_taken=retries_taken,
972 )
File /usr/local/lib/python3.11/site-packages/anthropic/_base_client.py:1055, in SyncAPIClient._request(self, cast_to, options, retries_taken, stream, stream_cls)
1053 if remaining_retries > 0 and self._should_retry(err.response):
1054 err.response.close()
-> 1055 return self._retry_request(
1056 input_options,
1057 cast_to,
1058 retries_taken=retries_taken,
1059 response_headers=err.response.headers,
1060 stream=stream,
1061 stream_cls=stream_cls,
1062 )
1064 # If the response is streamed then we need to explicitly read the response
1065 # to completion before attempting to access the response text.
1066 if not err.response.is_closed:
File /usr/local/lib/python3.11/site-packages/anthropic/_base_client.py:1104, in SyncAPIClient._retry_request(self, options, cast_to, retries_taken, response_headers, stream, stream_cls)
1100 # In a synchronous context we are blocking the entire thread. Up to the library user to run the client in a
1101 # different thread if necessary.
1102 time.sleep(timeout)
-> 1104 return self._request(
1105 options=options,
1106 cast_to=cast_to,
1107 retries_taken=retries_taken + 1,
1108 stream=stream,
1109 stream_cls=stream_cls,
1110 )
File /usr/local/lib/python3.11/site-packages/anthropic/_base_client.py:1055, in SyncAPIClient._request(self, cast_to, options, retries_taken, stream, stream_cls)
1053 if remaining_retries > 0 and self._should_retry(err.response):
1054 err.response.close()
-> 1055 return self._retry_request(
1056 input_options,
1057 cast_to,
1058 retries_taken=retries_taken,
1059 response_headers=err.response.headers,
1060 stream=stream,
1061 stream_cls=stream_cls,
1062 )
1064 # If the response is streamed then we need to explicitly read the response
1065 # to completion before attempting to access the response text.
1066 if not err.response.is_closed:
File /usr/local/lib/python3.11/site-packages/anthropic/_base_client.py:1104, in SyncAPIClient._retry_request(self, options, cast_to, retries_taken, response_headers, stream, stream_cls)
1100 # In a synchronous context we are blocking the entire thread. Up to the library user to run the client in a
1101 # different thread if necessary.
1102 time.sleep(timeout)
-> 1104 return self._request(
1105 options=options,
1106 cast_to=cast_to,
1107 retries_taken=retries_taken + 1,
1108 stream=stream,
1109 stream_cls=stream_cls,
1110 )
File /usr/local/lib/python3.11/site-packages/anthropic/_base_client.py:1070, in SyncAPIClient._request(self, cast_to, options, retries_taken, stream, stream_cls)
1067 err.response.read()
1069 log.debug("Re-raising status error")
-> 1070 raise self._make_status_error_from_response(err.response) from None
1072 return self._process_response(
1073 cast_to=cast_to,
1074 options=options,
(...)
1078 retries_taken=retries_taken,
1079 )
InternalServerError: 500 error
During task with name 'agent' and id 'bcf99c01-b3a8-ee28-b94f-0f582f2ed84c'
I have escalated your issue at multiple place. I understand the inconvenience. Please wait for the staff to respond on this thread.
Thank you for reporting @skr687 !
I just tested it and got the same InternalServerError 
Doing some research, just found out some issues (github issues i1, i2) related to Anthropic<>LangGraph.
According to the LangGraph documentation, we might need some more upgrades (from langchain_anthropic import ChatAnthropic, model sonnet-4-5-…) for our notebooks. I’ll share this with the engineering team.
Notice, this issue is affecting to Lesson 3 and Lesson 5 were we use the sonnet model, however in Lesson 4 we use ‘openai’ and that issue is not happening.
For curiosity, I tested using ‘openai’ model in Lesson 3, and it worked.
For your peace of mind, this issue has been reported to our team (as a bug/upgrade) for review and resolution. The changes will be reflected in the notebooks soon.
you mentioned you got this error at two places or courses, can you please let lesly know which is another place you got the error.
no, other lab there was no error, it was a graded a lab and i didnt code a missing part, the None response I was getting, I was assuming theLLM is not returning anything, ignore that
Why is fixing this issue taking this long??
read the staff response
ok thanks will use openai:gpt-4o
