Leveraging archon locally with ollama and supbase(selfhosted)

Archon
1

so i have been playing around with this and hit a wall. I finally just straight up asked Sonnet 3.7 to tshoot for me.

my scenario is: I am running 2 distinct ollama instances. one for text embedding and one for main LLM "stuff’ on the main ollama i am using qwen2.5:7b. supabase is vanilla.

what Windsurf + Sonnet 3.7 told me kind of lined up with what my experience is. and its similar to others. when i try to use Ollama i get this error in the docker container logs.

openai.AuthenticationError: Error code: 401 - {‘error’: {‘message’: 'Incorrect API key provided: no-llm-a***********ided. You can find your API key at https://platform.openai.com/account/api-keys.', ‘type’: ‘invalid_request_error’, ‘param’: None, ‘code’: ‘invalid_api_key’}}
During task with name ‘advisor_with_examples’ and id ‘4fac2f08-825a-b456-91ae-9ad2600f7535’

i get this error even when i try and set all the api keys to hard coded ollama keys.

not sure if this helps but this is what i see. and again i am trying to 100% self host and this problem seems to only exist when i try to do it this way.

below is the full traceback 10.20.20.167 is my home server where “primary” ollama is running :

INFO:httpx:HTTP Request: GET [http://10.20.20.167](http://10.20.20.167):8000/rest/v1/site_pages?select=id&limit=1 "HTTP/1.1 200 OK"
INFO:httpx:HTTP Request: GET [http://10.20.20.167](http://10.20.20.167):8000/rest/v1/site_pages?select=%2A "HTTP/1.1 200 OK"
INFO:httpx:HTTP Request: GET [http://10.20.20.167](http://10.20.20.167):8000/rest/v1/site_pages?select=url&metadata-%3E%3Esource=eq.pydantic_ai_docs "HTTP/1.1 200 OK"
INFO:httpx:HTTP Request: POST [http://10.20.20.167](http://10.20.20.167):11434/chat/completions "HTTP/1.1 404 Not Found"
2025-04-14 02:00:03.606 Uncaught app execution
Traceback (most recent call last):
  File "/usr/local/lib/python3.12/site-packages/streamlit/runtime/scriptrunner/exec_code.py", line 88, in exec_func_with_error_handling
    result = func()
             ^^^^^^
  File "/usr/local/lib/python3.12/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 579, in code_to_exec
    exec(code, module.__dict__)
  File "/app/streamlit_ui.py", line 114, in <module>
    asyncio.run(main())
  File "/usr/local/lib/python3.12/asyncio/runners.py", line 195, in run
    return runner.run(main)
           ^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/asyncio/runners.py", line 118, in run
    return self._loop.run_until_complete(task)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/asyncio/base_events.py", line 691, in run_until_complete
    return future.result()
           ^^^^^^^^^^^^^^^
  File "/app/streamlit_ui.py", line 93, in main
    await chat_tab()
  File "/app/streamlit_pages/chat.py", line 81, in chat_tab
    async for chunk in run_agent_with_streaming(user_input):
  File "/app/streamlit_pages/chat.py", line 30, in run_agent_with_streaming
    async for msg in agentic_flow.astream(
  File "/usr/local/lib/python3.12/site-packages/langgraph/pregel/__init__.py", line 2007, in astream
    async for _ in runner.atick(
  File "/usr/local/lib/python3.12/site-packages/langgraph/pregel/runner.py", line 527, in atick
    _panic_or_proceed(
  File "/usr/local/lib/python3.12/site-packages/langgraph/pregel/runner.py", line 619, in _panic_or_proceed
    raise exc
  File "/usr/local/lib/python3.12/site-packages/langgraph/pregel/retry.py", line 128, in arun_with_retry
    return await task.proc.ainvoke(task.input, config)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/site-packages/langgraph/utils/runnable.py", line 532, in ainvoke
    input = await step.ainvoke(input, config, **kwargs)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/site-packages/langgraph/utils/runnable.py", line 320, in ainvoke
    ret = await asyncio.create_task(coro, context=context)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/archon/archon_graph.py", line 105, in define_scope_with_reasoner
    result = await reasoner.run(prompt)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/site-packages/pydantic_ai/agent.py", line 340, in run
    end_result, _ = await graph.run(
                    ^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/site-packages/pydantic_graph/graph.py", line 187, in run
    next_node = await self.next(next_node, history, state=state, deps=deps, infer_name=False)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/site-packages/pydantic_graph/graph.py", line 263, in next
    next_node = await node.run(ctx)
                ^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/site-packages/pydantic_ai/_agent_graph.py", line 254, in run
    model_response, request_usage = await agent_model.request(ctx.state.message_history, model_settings)
                                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/site-packages/pydantic_ai/models/openai.py", line 167, in request
    response = await self._completions_create(messages, False, cast(OpenAIModelSettings, model_settings or {}))
<truncated 40 lines>
    await chat_tab()
  File "/app/streamlit_pages/chat.py", line 81, in chat_tab
    async for chunk in run_agent_with_streaming(user_input):
  File "/app/streamlit_pages/chat.py", line 36, in run_agent_with_streaming
    async for msg in agentic_flow.astream(
  File "/usr/local/lib/python3.12/site-packages/langgraph/pregel/__init__.py", line 2007, in astream
    async for _ in runner.atick(
  File "/usr/local/lib/python3.12/site-packages/langgraph/pregel/runner.py", line 527, in atick
    _panic_or_proceed(
  File "/usr/local/lib/python3.12/site-packages/langgraph/pregel/runner.py", line 619, in _panic_or_proceed
    raise exc
  File "/usr/local/lib/python3.12/site-packages/langgraph/pregel/retry.py", line 128, in arun_with_retry
    return await task.proc.ainvoke(task.input, config)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/site-packages/langgraph/utils/runnable.py", line 532, in ainvoke
    input = await step.ainvoke(input, config, **kwargs)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/site-packages/langgraph/utils/runnable.py", line 320, in ainvoke
    ret = await asyncio.create_task(coro, context=context)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/archon/archon_graph.py", line 140, in advisor_with_examples
    result = await advisor_agent.run(state['latest_user_message'], deps=deps)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/site-packages/pydantic_ai/agent.py", line 340, in run
    end_result, _ = await graph.run(
                    ^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/site-packages/pydantic_graph/graph.py", line 187, in run
    next_node = await self.next(next_node, history, state=state, deps=deps, infer_name=False)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/site-packages/pydantic_graph/graph.py", line 263, in next
    next_node = await node.run(ctx)
                ^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/site-packages/pydantic_ai/_agent_graph.py", line 254, in run
    model_response, request_usage = await agent_model.request(ctx.state.message_history, model_settings)
                                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/site-packages/pydantic_ai/models/openai.py", line 167, in request
    response = await self._completions_create(messages, False, cast(OpenAIModelSettings, model_settings or {}))
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/site-packages/pydantic_ai/models/openai.py", line 203, in _completions_create
    return await self.client.chat.completions.create(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/site-packages/openai/resources/chat/completions.py", line 1720, in create
    return await self._post(
           ^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/site-packages/openai/_base_client.py", line 1849, in post
    return await self.request(cast_to, opts, stream=stream, stream_cls=stream_cls)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/site-packages/openai/_base_client.py", line 1543, in request
    return await self._request(
           ^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/site-packages/openai/_base_client.py", line 1644, in _request
    raise self._make_status_error_from_response(err.response) from None
openai.AuthenticationError: Error code: 401 - {'error': {'message': 'Incorrect API key provided: no-llm-a***********ided. You can find your API key at [https://platform.openai.com/account/api-keys.',](https://platform.openai.com/account/api-keys.',) 'type': 'invalid_request_error', 'param': None, 'code': 'invalid_api_key'}}
During task with name 'advisor_with_examples' and id '4fac2f08-825a-b456-91ae-9ad2600f7535'
1 Like
2

Thanks for sharing this issue! Certainly is trying to hit OpenAI instead of Ollama. Could you share what your environment setup looks like in the environment tab?

3

for you? anything

archon snipping1
archon snipping11209×1212 61.7 KB

this is my current env setup. i don’t have any api keys configured in any of my ollama containers. i haven’t tried setting anything yet. for the .env file in the folder from the git clone is blank as well.

4

archon snipping2
archon snipping21207×726 30 KB

second half

5

Thanks for this! A couple others have reported a similar issue so this is something I’m going to look into asap and see if I can reproduce (I haven’t been able to yet).

6

Having the same issue! Using ollama for everything but in the logs it’s looking like it’s trying to use openai

/venv/lib/python3.13/site-packages/openai/_base_client.py", line 1644, in _request
    raise self._make_status_error_from_response(err.response) from None
openai.AuthenticationError: Error code: 401 - {'error': {'message': 'Incorrect API key provided: no-llm-a***********ided. You can find your API key at https://platform.openai.com/account/api-keys.', 'type': 'invalid_request_error', 'param': None, 'code': 'invalid_api_key'}}
During task with name 'advisor_with_examples' and id '24fb7801-c49a-25f0-de2a-7143ffb14a02'