Using AI feature (local model and online) leading to errors

[amru39]

Describe the bug :


Using the AI feature leading to errors with both local and online models.

To Reproduce :


Running AI chat leads to errors as shown below.

Local Ollama with LLAMA3:8b

File "/home/rahul/Downloads/QualCoder/src/qualcoder/ai_async_worker.py", line 108, in run
result = self.fn(*self.args, **self.kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/src/qualcoder/ai_llm.py", line 728, in _retrieve_similar_data
descriptions = self.generate_code_descriptions(code_name, code_memo)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/src/qualcoder/ai_llm.py", line 703, in generate_code_descriptions
res = self.large_llm.invoke(code_descriptions_prompt, response_format={"type": "json_object"}, config=config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/langchain_core/language_models/chat_models.py", line 393, in invoke
self.generate_prompt(

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/langchain_core/language_models/chat_models.py", line 1019, in generate_prompt
return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/langchain_core/language_models/chat_models.py", line 837, in generate
self._generate_with_cache(

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/langchain_core/language_models/chat_models.py", line 1085, in _generate_with_cache
result = self._generate(
^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/langchain_openai/chat_models/base.py", line 1142, in _generate
return generate_from_stream(stream_iter)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/langchain_core/language_models/chat_models.py", line 168, in generate_from_stream
generation = next(stream, None)
^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/langchain_openai/chat_models/base.py", line 1096, in _stream
with context_manager as response:

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/openai/lib/streaming/chat/_completions.py", line 150, in enter
raw_stream = self.__api_request()
^^^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/openai/_utils/_utils.py", line 286, in wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/openai/resources/chat/completions/completions.py", line 1147, in create
return self._post(
^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/openai/_base_client.py", line 1259, in post
return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/openai/_base_client.py", line 1047, in request
raise self._make_status_error_from_response(err.response) from None

AI Error:
NotFoundError:

OpenAI API:

File "/home/rahul/Downloads/QualCoder/src/qualcoder/ai_async_worker.py", line 108, in run
result = self.fn(*self.args, **self.kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/src/qualcoder/ai_llm.py", line 728, in _retrieve_similar_data
descriptions = self.generate_code_descriptions(code_name, code_memo)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/src/qualcoder/ai_llm.py", line 703, in generate_code_descriptions
res = self.large_llm.invoke(code_descriptions_prompt, response_format={"type": "json_object"}, config=config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/langchain_core/language_models/chat_models.py", line 393, in invoke
self.generate_prompt(

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/langchain_core/language_models/chat_models.py", line 1019, in generate_prompt
return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/langchain_core/language_models/chat_models.py", line 837, in generate
self._generate_with_cache(

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/langchain_core/language_models/chat_models.py", line 1085, in _generate_with_cache
result = self._generate(
^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/langchain_openai/chat_models/base.py", line 1142, in _generate
return generate_from_stream(stream_iter)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/langchain_core/language_models/chat_models.py", line 168, in generate_from_stream
generation = next(stream, None)
^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/langchain_openai/chat_models/base.py", line 1096, in _stream
with context_manager as response:

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/openai/lib/streaming/chat/_completions.py", line 150, in enter
raw_stream = self.__api_request()
^^^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/openai/_utils/_utils.py", line 286, in wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/openai/resources/chat/completions/completions.py", line 1147, in create
return self._post(
^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/openai/_base_client.py", line 1259, in post
return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/openai/_base_client.py", line 1047, in request
raise self._make_status_error_from_response(err.response) from None

AI Error:
RateLimitError:

Expected behavior :


Error should not occur.

Screenshots :

Desktop (please complete the following information):

• OS: LinuxMint
• Version 22.2 Cinnamon

Additional context :


Using QualCoder 3.7.

[amru39]

For local model using following in config.ini

[ai_model_Ollama local AI]
desc = Ollama is an open source server that lets you run LLMs locally on
your computer. To use it in QualCoder, you must have Ollama set up and
running first. Use the Advanced AI Options below to select between your
locally installed models.
access_info_url = https://ollama.com
large_model = llama3:8b
large_model_context_window = 8092
fast_model = llama3:8b
fast_model_context_window = 8092
api_base = http://localhost:11434/
api_key = ollama

[kaixxx]

These are two different issues:

• Ollama: It seems that Ollama reported an "NotFoundError" back. Look at the log file in ~.qualcoder if you find a more detailed error report. Your config looks right. Maybe the model (llama3:8b) is not properly installed? Try it first outside QualCoder.

• OpenAI: A "RateLimitError" usually means that you don't have enough paid credits in your account at OpenAI.

[amru39]

Thanks for the immediate response.

1. The model is working outside of QualCoder. Maybe I will try with another local model and see if it works.
2. I will check my OpenAI credits.

[amru39]

Here is the error from the logs:

2025/09/05 16:43:20 ERROR qualcoder.settings.ai_update_avaliable_models Error getting AI model list: NotFoundError: 404 page not found
2025/09/05 16:43:39 DEBUG qualcoder.ai_llm.generate_code_descriptions AI generate_code_descriptions

2025/09/05 16:43:39 DEBUG qualcoder.ai_llm.generate_code_descriptions Prompt:
[SystemMessage(content='You are assisting a team of qualitative social researchers.', additional_kwargs={}, response_metadata={}), HumanMessage(content='We are searching for empirical data that fits a code named "What should be considered when looking for venues?" with the following code memo: "". \nYour task: Give back a list of up to 10 reformulated variants of the code, using synonyms or directly related concepts. Also consider the memo, if available. Try to give a variety of diverse reformulations. Use simple language.Always answer in the following language: "English". Do not use numbers or bullet points. Do not explain anything or repeat the code name, just give back the list of variants. Return the list as a valid JSON object in the following form:\n{'descriptions': ['first description', 'second description', Ellipsis]}', additional_kwargs={}, response_metadata={})]
2025/09/05 16:43:39 ERROR qualcoder.ai_llm._ai_async_error Uncaught exception: AI Error:
NotFoundError:
File "/home/rahul/Downloads/QualCoder/src/qualcoder/ai_async_worker.py", line 108, in run
result = self.fn(*self.args, **self.kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/src/qualcoder/ai_llm.py", line 728, in _retrieve_similar_data
descriptions = self.generate_code_descriptions(code_name, code_memo)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/src/qualcoder/ai_llm.py", line 703, in generate_code_descriptions
res = self.large_llm.invoke(code_descriptions_prompt, response_format={"type": "json_object"}, config=config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/langchain_core/language_models/chat_models.py", line 393, in invoke
self.generate_prompt(

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/langchain_core/language_models/chat_models.py", line 1019, in generate_prompt
return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/langchain_core/language_models/chat_models.py", line 837, in generate
self._generate_with_cache(

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/langchain_core/language_models/chat_models.py", line 1085, in _generate_with_cache
result = self._generate(
^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/langchain_openai/chat_models/base.py", line 1142, in _generate
return generate_from_stream(stream_iter)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/langchain_core/language_models/chat_models.py", line 168, in generate_from_stream
generation = next(stream, None)
^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/langchain_openai/chat_models/base.py", line 1096, in _stream
with context_manager as response:

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/openai/lib/streaming/chat/_completions.py", line 150, in enter
raw_stream = self.__api_request()
^^^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/openai/_utils/_utils.py", line 286, in wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/openai/resources/chat/completions/completions.py", line 1147, in create
return self._post(
^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/openai/_base_client.py", line 1259, in post
return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/openai/_base_client.py", line 1047, in request
raise self._make_status_error_from_response(err.response) from None

[kaixxx]

Thank you. It seems that your api_base is incomplete. Change it to:
api_base = http://localhost:11434/v1

Background: QualCoder uses the OpenAI-compatible API, which Ollama exposes under the v1 path.

(I must give ChatGPT credit for finding this error.)

[amru39]

After changing the api_base still running into the issue:

From QualCoder:

File "/home/rahul/Downloads/QualCoder/src/qualcoder/ai_async_worker.py", line 108, in run
result = self.fn(*self.args, **self.kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/src/qualcoder/ai_llm.py", line 588, in _ai_async_stream
for chunk in llm.stream(messages):

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/langchain_core/language_models/chat_models.py", line 520, in stream
for chunk in self._stream(input_messages, stop=stop, **kwargs):

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/langchain_openai/chat_models/base.py", line 1093, in _stream
response = self.client.create(**payload)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/openai/_utils/_utils.py", line 286, in wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/openai/resources/chat/completions/completions.py", line 1147, in create
return self._post(
^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/openai/_base_client.py", line 1259, in post
return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/openai/_base_client.py", line 1000, in request
raise APITimeoutError(request=request) from err

AI Error:
APITimeoutError:

From log:
2025/09/07 13:24:10 DEBUG qualcoder.ai_llm.generate_code_descriptions Prompt:
[SystemMessage(content='You are assisting a team of qualitative social researchers.', additional_kwargs={}, response_metadata={}), HumanMessage(content='We are searching for empirical data that fits a code named "What should be considered when looking for venues?" with the following code memo: "". \nYour task: Give back a list of up to 10 reformulated variants of the code, using synonyms or directly related concepts. Also consider the memo, if available. Try to give a variety of diverse reformulations. Use simple language.Always answer in the following language: "English". Do not use numbers or bullet points. Do not explain anything or repeat the code name, just give back the list of variants. Return the list as a valid JSON object in the following form:\n{'descriptions': ['first description', 'second description', Ellipsis]}', additional_kwargs={}, response_metadata={})]
2025/09/07 13:25:32 DEBUG qualcoder.ai_llm.generate_code_descriptions {"descriptions": ["Aspects to consider when selecting event locations", "Factors influencing venue choice", "Key considerations when booking a space", "Things to keep in mind for successful events", "Important criteria for finding the right setting", "Choosing the ideal location", "Pivotal decisions for venues selected", "What to think about when selecting a site", "Relevant information for making informed choices", "Essential elements for venue selection"]}
2025/09/07 13:25:36 DEBUG qualcoder.ai_llm._retrieve_similar_data First 10 chunks of retrieved data:
[Document(id='7649b69f-f0b2-4d67-8e94-add6ee0f6d96', metadata={'id': 3, 'name': 'Best Practices for Holding In-Person Meetings and Events.docx', 'start_index': 2862, 'score': np.float32(18.903095)}, page_content='An announcement will be made before the meeting/event as to the location and attendees will be invited to use it at any time. Periodic reminders will be provided.\n\nDuring discussion or question/answer periods, facilitators must allow time for attendees to process information and provide opportunities for people who have not spoken to speak.\n\nAlternative forms of providing thoughts, questions, and feedback are encouraged.'), Document(id='5dcd1659-533c-40d3-bf88-e27c85fbf2f4', metadata={'id': 3, 'name': 'Best Practices for Holding In-Person Meetings and Events.docx', 'start_index': 798, 'score': np.float32(18.791847)}, page_content='Text columns must be avoided and there must be ample white space around text blocks.\n\nBraille copies will be made available upon request.\n\nVolunteers\n\nVolunteers should assist with moving seating (if movable) to provide additional space.\n\nPresentations\n\nBlind and low vision individuals will be prioritized in being closer to presentations.\n\nSpeakers will provide an image description of themselves when first speaking.\n\nSpeakers will identify themselves each time they talk.'), Document(id='36e0d901-de6b-4162-922c-6ce044c6a1ac', metadata={'id': 1, 'name': 'Best Practices for Choosing an Accessible Location.docx', 'start_index': 0, 'score': np.float32(18.78954)}, page_content='Best Practices for Choosing an Accessible Location\n\nPhysical locations must be wheelchair accessible with accessible bathrooms.\n\nException is wheelchair accessible outdoor locations without bathrooms.\n\nSuch locations must be advertised as not having bathrooms on-site and nearest bathroom options must be identified to attendees and upon request.\n\nAccessible includes the entrance and surrounding sidewalks.\n\nEntrance cannot have only steps and sidewalks must have a curb cut.'), Document(id='e207c8a0-7bac-470f-a78d-03dc623e97d2', metadata={'id': 1, 'name': 'Best Practices for Choosing an Accessible Location.docx', 'start_index': 409, 'score': np.float32(18.706995)}, page_content='Entrance cannot have only steps and sidewalks must have a curb cut.\n\nForcing disabled individuals to enter through a separate entrance is unacceptable.\n\nPhysical locations with steps, stairs, and ramps must have railings.\n\nPhysical locations must have seating.\n\nIf standing room only or outdoors, a small amount of temporary seating must be provided.\n\nSeating must have backs and at least half must have arms. Some seating without arms must be provided.'), Document(id='0c1ab9d8-12e3-4652-af01-fbf96743258e', metadata={'id': 1, 'name': 'Best Practices for Choosing an Accessible Location.docx', 'start_index': 1266, 'score': np.float32(18.658052)}, page_content='PPT will plan to provide rides to physical locations upon request. This option must be advertised.\n\nLighting must be sufficient to enable individuals with low vision to see steps and other obstacles.\n\nPhysical and virtual locations must have space/capacity for ASL or language interpretation as well as captioning (either web-based or projector-based).'), Document(id='66c30c07-b4d5-4f7c-add8-63563190bfd4', metadata={'id': 3, 'name': 'Best Practices for Holding In-Person Meetings and Events.docx', 'start_index': 2114, 'score': np.float32(18.644344)}, page_content='For events that expect widespread public attendance, ASL and Spanish interpretation will be provided regardless of request.\n\nOther language interpretation will be provided upon request.\n\nDeaf Interpreters are prioritized for ASL interpretation.\n\nSeating and space must be reserved that enables individuals to see both the interpreter and the speakers.\n\nLive Captioning\n\nFor meetings and events, live captioning (CART) will be provided on request.'), Document(id='044bf48a-636e-4588-a77c-9751fbbf9f07', metadata={'id': 3, 'name': 'Best Practices for Holding In-Person Meetings and Events.docx', 'start_index': 4451, 'score': np.float32(18.624914)}, page_content='Service animals must be allowed at all meetings and events.\n\nIf the presence of a service animal impacts another person’s ability to attend (ex: allergies or past trauma), PPT will work with the individual and the individual with the service animal to develop a plan to ensure both can continue attending.\n\nOutdoor events will have a clearly marked toileting space for service animals.\n\nIndoor events will have designated outdoor toileting space for service animals.'), Document(id='39874a0d-1d06-4d92-beea-faa944c97196', metadata={'id': 3, 'name': 'Best Practices for Holding In-Person Meetings and Events.docx', 'start_index': 4116, 'score': np.float32(18.624699)}, page_content='Foods with common allergens will be placed away from foods without allergens.\n\nServing utensils must be used for only one food item each to prevent cross-contamination.\n\nWhen providing food, vegan and allergy-free options must be provided.\n\nA volunteer must be present at food and beverage tables to help anyone who needs assistance.\n\nService animals must be allowed at all meetings and events.'), Document(id='38e40720-688e-4bf5-a355-44030352a62f', metadata={'id': 3, 'name': 'Best Practices for Holding In-Person Meetings and Events.docx', 'start_index': 3207, 'score': np.float32(18.606857)}, page_content='Alternative forms of providing thoughts, questions, and feedback are encouraged.\n\nAttendees must be allowed to speak slowly, pause, or communicate in their preferred communication style.\n\nOther Needs\n\nPaths to event spaces, restrooms, and exits must be clearly marked.\n\nSpeakers will provide their pronouns when they first speak.\n\nMeeting attendees will be given a name card on which to write their name and pronouns.\n\nMeetings and events must be scent-free.'), Document(id='a4985a7f-9a7f-4fa4-bd34-e84502be133f', metadata={'id': 3, 'name': 'Best Practices for Holding In-Person Meetings and Events.docx', 'start_index': 3626, 'score': np.float32(18.597708)}, page_content='Meetings and events must be scent-free.\n\nScent-free means that attendees do not wear any chemicals or fragrances. \n\nFood and Water\n\nAll events and meetings must have access to free water for all attendees.\n\nPlastic straws must be available upon request.\n\nEvents and meetings that are scheduled during a common meal time must have, at minimum, snacks for attendees.\n\nAny food will include a description of ingredients, with highlighted common allergens: nuts, shellfish, gluten, and dairy.')]
2025/09/07 13:27:07 ERROR qualcoder.ai_llm._ai_async_error Uncaught exception: AI Error:
APITimeoutError:
File "/home/rahul/Downloads/QualCoder/src/qualcoder/ai_async_worker.py", line 108, in run
result = self.fn(*self.args, **self.kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/src/qualcoder/ai_llm.py", line 588, in _ai_async_stream
for chunk in llm.stream(messages):

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/langchain_core/language_models/chat_models.py", line 520, in stream
for chunk in self._stream(input_messages, stop=stop, **kwargs):

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/langchain_openai/chat_models/base.py", line 1093, in _stream
response = self.client.create(**payload)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/openai/_utils/_utils.py", line 286, in wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/openai/resources/chat/completions/completions.py", line 1147, in create
return self._post(
^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/openai/_base_client.py", line 1259, in post
return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/rahul/Downloads/QualCoder/env/lib/python3.12/site-packages/openai/_base_client.py", line 1000, in request
raise APITimeoutError(request=request) from err

---

Checked with deepseek-r1:8b, which is also leading to same issue. I have API credits in OpenAI as well.

[kaixxx]

Your log file shows that the communication with the AI is working now. But at some point the server is not responding in time, and you run into a timeout error.

• You can increase the ai_timeout value in config. ini.
• If you are using OpenAI or any other online AI server, check if your internet connection is stable.
• If you are using Ollama locally, your Ollama server might simply need a longer ai_timeout to respond. But there might also be another reason why Ollama is not responding Check the Ollama log files (if available).