Indexing error

[migu0]

I did a fresh install through Docker and and uploaded a PDF through the Files connector and the indexing errored. The same happened when connecting to S3.

Here's the error log:

Traceback (most recent call last):
  File "/usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py", line 789, in urlopen
    response = self._make_request(
               ^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py", line 536, in _make_request
    response = conn.getresponse()
               ^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/urllib3/connection.py", line 507, in getresponse
    httplib_response = super().getresponse()
                       ^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/http/client.py", line 1386, in getresponse
    response.begin()
  File "/usr/local/lib/python3.11/http/client.py", line 325, in begin
    version, status, reason = self._read_status()
                              ^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/http/client.py", line 294, in _read_status
    raise RemoteDisconnected("Remote end closed connection without"
http.client.RemoteDisconnected: Remote end closed connection without response

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/usr/local/lib/python3.11/site-packages/requests/adapters.py", line 589, in send
    resp = conn.urlopen(
           ^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py", line 843, in urlopen
    retries = retries.increment(
              ^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/urllib3/util/retry.py", line 474, in increment
    raise reraise(type(error), error, _stacktrace)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/urllib3/util/util.py", line 38, in reraise
    raise value.with_traceback(tb)
  File "/usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py", line 789, in urlopen
    response = self._make_request(
               ^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py", line 536, in _make_request
    response = conn.getresponse()
               ^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/urllib3/connection.py", line 507, in getresponse
    httplib_response = super().getresponse()
                       ^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/http/client.py", line 1386, in getresponse
    response.begin()
  File "/usr/local/lib/python3.11/http/client.py", line 325, in begin
    version, status, reason = self._read_status()
                              ^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/http/client.py", line 294, in _read_status
    raise RemoteDisconnected("Remote end closed connection without"
urllib3.exceptions.ProtocolError: ('Connection aborted.', RemoteDisconnected('Remote end closed connection without response'))

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/app/onyx/natural_language_processing/search_nlp_models.py", line 138, in _make_model_server_request
    response = final_make_request_func()
               ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/decorator.py", line 232, in fun
    return caller(func, *(extras + args), **kw)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/retry/api.py", line 73, in retry_decorator
    return __retry_internal(partial(f, *args, **kwargs), exceptions, tries, delay, max_delay, backoff, jitter,
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/retry/api.py", line 33, in __retry_internal
    return f()
           ^^^
  File "/usr/local/lib/python3.11/site-packages/decorator.py", line 232, in fun
    return caller(func, *(extras + args), **kw)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/retry/api.py", line 73, in retry_decorator
    return __retry_internal(partial(f, *args, **kwargs), exceptions, tries, delay, max_delay, backoff, jitter,
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/retry/api.py", line 33, in __retry_internal
    return f()
           ^^^
  File "/app/onyx/natural_language_processing/search_nlp_models.py", line 110, in _make_request
    response = requests.post(
               ^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/requests/api.py", line 115, in post
    return request("post", url, data=data, json=json, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/requests/api.py", line 59, in request
    return session.request(method=method, url=url, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/requests/sessions.py", line 589, in request
    resp = self.send(prep, **send_kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/requests/sessions.py", line 703, in send
    r = adapter.send(request, **kwargs)
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/requests/adapters.py", line 604, in send
    raise ConnectionError(err, request=request)
requests.exceptions.ConnectionError: ('Connection aborted.', RemoteDisconnected('Remote end closed connection without response'))

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/app/onyx/background/indexing/run_indexing.py", line 358, in _run_indexing
    index_pipeline_result = indexing_pipeline(
                            ^^^^^^^^^^^^^^^^^^
  File "/app/onyx/indexing/indexing_pipeline.py", line 167, in index_doc_batch_with_handler
    index_pipeline_result = index_doc_batch(
                            ^^^^^^^^^^^^^^^^
  File "/app/onyx/utils/timing.py", line 31, in wrapped_func
    result = func(*args, **kwargs)
             ^^^^^^^^^^^^^^^^^^^^^
  File "/app/onyx/indexing/indexing_pipeline.py", line 387, in index_doc_batch
    chunks_with_embeddings = embedder.embed_chunks(chunks) if chunks else []
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/onyx/utils/timing.py", line 31, in wrapped_func
    result = func(*args, **kwargs)
             ^^^^^^^^^^^^^^^^^^^^^
  File "/app/onyx/indexing/embedder.py", line 134, in embed_chunks
    embeddings = self.embedding_model.encode(
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/onyx/natural_language_processing/search_nlp_models.py", line 228, in encode
    return self._batch_encode_texts(
           ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/onyx/natural_language_processing/search_nlp_models.py", line 187, in _batch_encode_texts
    response = self._make_model_server_request(embed_request)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/onyx/natural_language_processing/search_nlp_models.py", line 150, in _make_model_server_request
    raise HTTPError(f"Request failed: {str(e)}") from e
httpx.HTTPError: Request failed: ('Connection aborted.', RemoteDisconnected('Remote end closed connection without response'))

[rkuo-danswer]

Hi Miguel ... it looks like the model server for your installation isn't responding. I would try to verify the container is actually running per the logs and also if it's receving any requestes.

[migu0]

Thank you. When I type something under "General", the local Ollama server definitely responds (running on my localhost, not through Docker).

However, when I want to index, I cannot see any activity on the Ollama server on localhost. What do I need to do get indexing working? Please note, no data is allowed to leave the machine, so I didn't enter an OpenAI key.

Here are the Ollama settings

Thank you

[rkuo-danswer]

You would want to run "docker container ls" from the command line to check which containers are active and running, including the model server. See if you can get the output from that?

[migu0]

Here's the output. I run ollama directly from my Terminal (not inside Docker) using ollama serve. I can successfully set up the connector to ollama and I set it communicating with it.

I was going to showcase your product to some banks and government institutions in Europe that need an on premise RAG this Wednesday but I don't think I can get it up and running by then.