Problem with assignment 4

I am having a problem running the function: check_if_faq_or_product in the graded assignment: C1M4_assignment.

`When I try to run a query, here is the error I get:
InvalidRequestError Traceback (most recent call last)
Cell In[13], line 8
1 queries = [‘What is your return policy?’,
2 ‘Give me three examples of blue T-shirts you have available.’,
3 ‘How can I contact the user support?’,
4 ‘Do you have blue Dresses?’,
5 ‘Create a look suitable for a wedding party happening during dawn.’]
7 for query in queries:
----> 8 response = check_if_faq_or_product(query)
9 label = response
10 print(f"Query: {query} Label: {label}")

Cell In[12], line 40, in check_if_faq_or_product(query)
37 kwargs = generate_params_dict(prompt, temperature = 0.4, max_tokens = 1)
39 # Call generate_with_single_input with **kwargs
—> 40 response = generate_with_single_input(**kwargs)
41 # Get the label by accessing the ‘content’ key of the response dictionary
43 label = response[‘content’]

File ~/work/utils.py:213, in generate_with_single_input(prompt, role, top_p, temperature, max_tokens, model, together_api_key, **kwargs)
211 together_api_key = os.environ[‘TOGETHER_API_KEY’]
212 client = Together(api_key=together_api_key)
→ 213 json_dict = client.chat.completions.create(**payload).model_dump()
214 json_dict[‘choices’][-1][‘message’][‘role’] = json_dict[‘choices’][-1][‘message’][‘role’].name.lower()
215 try:

File /usr/local/lib/python3.12/site-packages/together/resources/chat/completions.py:141, in ChatCompletions.create(self, messages, model, max_tokens, stop, temperature, top_p, top_k, repetition_penalty, presence_penalty, frequency_penalty, min_p, logit_bias, seed, stream, logprobs, echo, n, safety_model, response_format, tools, tool_choice, **kwargs)
112 requestor = api_requestor.APIRequestor(
113 client=self._client,
114 )
116 parameter_payload = ChatCompletionRequest(
117 model=model,
118 messages=messages,
(…) 138 **kwargs,
139 ).model_dump(exclude_none=True)
→ 141 response, _, _ = requestor.request(
142 options=TogetherRequest(
143 method=“POST”,
144 url=“chat/completions”,
145 params=parameter_payload,
146 ),
147 stream=stream,
148 )
150 if stream:
151 # must be an iterator
152 assert not isinstance(response, TogetherResponse)

File /usr/local/lib/python3.12/site-packages/together/abstract/api_requestor.py:249, in APIRequestor.request(self, options, stream, remaining_retries, request_timeout)
231 def request(
232 self,
233 options: TogetherRequest,
(…) 240 str | None,
241 ]:
242 result = self.request_raw(
243 options=options,
244 remaining_retries=remaining_retries or self.retries,
245 stream=stream,
246 request_timeout=request_timeout,
247 )
→ 249 resp, got_stream = self._interpret_response(result, stream)
250 return resp, got_stream, self.api_key

File /usr/local/lib/python3.12/site-packages/together/abstract/api_requestor.py:650, in APIRequestor._interpret_response(self, result, stream)
647 else:
648 content = result.content.decode(“utf-8”)
649 return (
→ 650 self._interpret_response_line(
651 content,
652 result.status_code,
653 result.headers,
654 stream=False,
655 ),
656 False,
657 )

File /usr/local/lib/python3.12/site-packages/together/abstract/api_requestor.py:748, in APIRequestor._interpret_response_line(self, rbody, rcode, rheaders, stream)
746 # Handle streaming errors
747 if not 200 <= rcode < 300:
→ 748 raise self.handle_error_response(resp, rcode, stream_error=stream)
749 return resp

InvalidRequestError: Error code: 400 - {“message”: “Unable to access non-serverless model meta-llama/Llama-3.2-3B-Instruct-Turbo. Please visit Together AI | The AI Native Cloud to create and start a new dedicated endpoint for the model.”, “type_”: “invalid_request_error”, “code”: “model_not_available”}`

This happens despite restoring to original version.

hi @Anjan1970

this issue has been reported to staff on weekend, so wait for their response once their weekday start in USA, to give an update on this issue.

Regards

Dr. Deepti

hi @Anjan1970

Recent staff update

together.ai has deprecated a lot of models in the past days resulting in concurrent issues with labs of RAG courses.

Lab assignment 3 to 5 and all ungraded labs are updated now.

You need to Restore original version, to get the updated notebook.

I also would recommend to first delete the old file, and restore original version, so any cache issue is not encountered when running codes again.

Courses, labs are created with multiple channels, so labs gets affected when any changes.made at one end and can take multiple attempts to resolve issue.

Let us know if you still continue to have issue

Regards

Dr. Deepti