A little issue httpx.ConnectError: [Errno 111] Connection refused

[Nocturna22]

Hello,

EDIT:
Found the error.

I first started Open Notebook and much much later ollama. Thats the Problem.
Maby a clearer Errormessage would be helpful. Like:

Ollama isnt running. Please stop Open Notebook, launch ollama and restart Open Notebook.

(Or somethink like that.)

I really think there is huuuuge potential in this Project and i really like to help you as far as i can 😊

---

I just found out, that ollama wasnt started... 🤦 (so the below isnt up to date. Scroll at the bottom
to find the new error i got)

if i choose to upload a file, i get this error:
RuntimeError: API request failed: 500 - {"detail":"Error creating source: All connection attempts failed"}

File "/app/pages/stream_app/source.py", line 115, in add_source
    sources_service.create_source(
File "/app/api/sources_service.py", line 128, in create_source
    source_data = api_client.create_source(
                  ^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/api/client.py", line 311, in create_source
    return self._make_request("POST", "/api/sources", json=data)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/api/client.py", line 49, in _make_request
    raise RuntimeError(

Whats stange about it: if i close the Notebook and reopen it. The File is there.

I installed Open Notebook like this:

docker-compose down
docker-compose pull
docker-compose up -d

docker-compose.yaml:

services:
  surrealdb:
    image: surrealdb/surrealdb:v2
    ports:
      - "8000:8000"
    volumes:
      - surreal_data:/mydata
    command: start --user root --pass root rocksdb:/mydata/mydatabase.db
    pull_policy: always
    user: root

  open_notebook:
    image: lfnovo/open_notebook:latest
    ports:
      - "8080:8502"
    environment:
        - OLLAMA_BASE_URL=http://host.docker.internal:11434
        - OLLAMA_API_BASE=http://host.docker.internal:11434
        - SURREAL_ADDRESS=surrealdb
        - SURREAL_PORT=8000
        - SURREAL_USER=root
        - SURREAL_PASS=root
        - SURREAL_NAMESPACE=open_notebook
        - SURREAL_DATABASE=open_notebook
    depends_on:
      - surrealdb
    pull_policy: always
    volumes:
      - notebook_data:/app/data

volumes:
  surreal_data:
  notebook_data:

If i then want to chat with it, i get this error:

httpx.ConnectError: [Errno 111] Connection refused

File "/app/.venv/lib/python3.12/site-packages/streamlit/runtime/scriptrunner/exec_code.py", line 128, in exec_func_with_error_handling
    result = func()
             ^^^^^^
File "/app/.venv/lib/python3.12/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 667, in code_to_exec
    _mpa_v1(self._main_script_path)
File "/app/.venv/lib/python3.12/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 165, in _mpa_v1
    page.run()
File "/app/.venv/lib/python3.12/site-packages/streamlit/navigation/page.py", line 300, in run
    exec(code, module.__dict__)  # noqa: S102
    ^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/pages/2_📒_Notebooks.py", line 118, in <module>
    notebook_page(current_notebook)
File "/app/pages/2_📒_Notebooks.py", line 94, in notebook_page
    chat_sidebar(current_notebook=current_notebook, current_session=current_session)
File "/app/pages/stream_app/chat.py", line 216, in chat_sidebar
    response = execute_chat(
               ^^^^^^^^^^^^^
File "/app/pages/stream_app/chat.py", line 61, in execute_chat
    result = chat_graph.invoke(
             ^^^^^^^^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/langgraph/pregel/__init__.py", line 2844, in invoke
    for chunk in self.stream(
                 ^^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/langgraph/pregel/__init__.py", line 2534, in stream
    for _ in runner.tick(
             ^^^^^^^^^^^^
File "/app/open_notebook/graphs/chat.py", line 36, in call_model_with_messages
    ai_message = model.invoke(payload)
                 ^^^^^^^^^^^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/langchain_core/language_models/chat_models.py", line 378, in invoke
    self.generate_prompt(
File "/app/.venv/lib/python3.12/site-packages/langchain_core/language_models/chat_models.py", line 963, in generate_prompt
    return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/langchain_core/language_models/chat_models.py", line 782, in generate
    self._generate_with_cache(
File "/app/.venv/lib/python3.12/site-packages/langchain_core/language_models/chat_models.py", line 1028, in _generate_with_cache
    result = self._generate(
             ^^^^^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/langchain_ollama/chat_models.py", line 800, in _generate
    final_chunk = self._chat_stream_with_aggregation(
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/langchain_ollama/chat_models.py", line 735, in _chat_stream_with_aggregation
    for chunk in self._iterate_over_stream(messages, stop, **kwargs):
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/langchain_ollama/chat_models.py", line 822, in _iterate_over_stream
    for stream_resp in self._create_chat_stream(messages, stop, **kwargs):
                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/langchain_ollama/chat_models.py", line 721, in _create_chat_stream
    yield from self._client.chat(**chat_params)
File "/app/.venv/lib/python3.12/site-packages/ollama/_client.py", line 165, in inner
    with self._client.stream(*args, **kwargs) as r:
         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/contextlib.py", line 137, in __enter__
    return next(self.gen)
           ^^^^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/httpx/_client.py", line 868, in stream
    response = self.send(
               ^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/httpx/_client.py", line 914, in send
    response = self._send_handling_auth(
               ^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/httpx/_client.py", line 942, in _send_handling_auth
    response = self._send_handling_redirects(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/httpx/_client.py", line 979, in _send_handling_redirects
    response = self._send_single_request(request)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/httpx/_client.py", line 1014, in _send_single_request
    response = transport.handle_request(request)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/httpx/_transports/default.py", line 249, in handle_request
    with map_httpcore_exceptions():
         ^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/contextlib.py", line 158, in __exit__
    self.gen.throw(value)
File "/app/.venv/lib/python3.12/site-packages/httpx/_transports/default.py", line 118, in map_httpcore_exceptions
    raise mapped_exc(message) from exc

---

new error i got, processing a png :

ConnectionError: Failed to connect to API: timed out

File "/app/pages/stream_app/source.py", line 115, in add_source
    sources_service.create_source(
File "/app/api/sources_service.py", line 128, in create_source
    source_data = api_client.create_source(
                  ^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/api/client.py", line 311, in create_source
    return self._make_request("POST", "/api/sources", json=data)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/api/client.py", line 44, in _make_request
    raise ConnectionError(f"Failed to connect to API: {str(e)}")

i dont know why i cant connect to the API and get a timeout 🤔

[lfnovo]

It could be that your ollama is listening on localhost, but not on 0.0.0.0 (required for network access which is what docker would use).

TL;DR you need to set OLLAMA_HOST=0.0.0.0 in the host machine so that Ollama knows to listen to all network addresses.

Here is my ollama service file for reference:

[Unit]
Description=Ollama Service
After=network-online.target

[Service]
ExecStart=/usr/local/bin/ollama serve
User=ollama
Group=ollama
Restart=always
RestartSec=3
Environment="PATH=/home/lfnovo/.local/share/pnpm:/home/lfnovo/.cargo/bin:/usr/local/cuda-12.6/bin:/home/lfnovo/.pyenv/shims:/home/lfnovo/.local/bin:/home/lfnovo/.pyenv/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin"
Environment="OLLAMA_HOST=0.0.0.0"

[Install]
WantedBy=default.target

Let me know if that works.