You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Bug Summary:
I'm getting an exception while trying to index ( Add ) documents to the workspace collection
Steps to Reproduce:
I think the main problem is that I added a document before and somehow it didn't finish to the end or something so now I'm unable to add the same document again because a chunk of the collection already exists
Expected Behavior:
There should be some handling for large documents ( 2000 pages ) by introducing some kind of queue for the indexing instead of the document not being visible until it's fully indexed ( Which might take up to a few hours in my case )
Actual Behavior:
The document is not appearing until it's fully indexed so I'm not really sure what is the status of the document now
Environment
Open WebUI Version: 0.35
Operating System: Windows [ Client not host ]
Browser (if applicable): Chromium 126.0.6478.71
Reproduction Details
Confirmation:
I have read and followed all the instructions provided in the README.md.
I am on the latest version of both Open WebUI and Ollama.
I have included the browser console logs.
I have included the Docker container logs.
Logs and Screenshots
Browser Console Logs:
Nothing is getting logged on the browser, the request is timing out due to taking so long from the server side
Docker Container Logs:
metadata={'source': '/app/backend/data/uploads/RSS-D15', 'page': 128, 'start_index': 41})] 2cc3c148b3126225d91ab1a587ffb8aaf528aad7bc4def43f5c43c394e6f772
ERROR:apps.rag.main:Collection 2cc3c148b3126225d91ab1a587ffb8aaf528aad7bc4def43f5c43c394e6f772 already exists
Traceback (most recent call last):
File "/app/backend/apps/rag/main.py", line 938, in store_docs_in_vector_db
collection = CHROMA_CLIENT.create_collection(name=collection_name)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/chromadb/api/client.py", line 198, in create_collection
return self._server.create_collection(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/chromadb/telemetry/opentelemetry/__init__.py", line 143, in wrapper
return f(*args, **kwargs)
^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/chromadb/api/segment.py", line 173, in create_collection
coll, created = self._sysdb.create_collection(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/chromadb/telemetry/opentelemetry/__init__.py", line 143, in wrapper
return f(*args, **kwargs)
^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/chromadb/db/mixins/sysdb.py", line 220, in create_collection
raise UniqueConstraintError(f"Collection {name} already exists")
chromadb.db.base.UniqueConstraintError: Collection 2cc3c148b3126225d91ab1a587ffb8aaf528aad7bc4def43f5c43c394e6f772 already exists
Installation Method
Docker
Additional Information
Basically the main problem is assuming that a document indexing could be done instantly, I have documents up to 4000 pages that I would like to index and the only way to do that is by adding some kind of queue with jobs for the indexing and showing the document as ( under processing )
The text was updated successfully, but these errors were encountered:
Bug Report
Description
Bug Summary:
I'm getting an exception while trying to index ( Add ) documents to the workspace collection
Steps to Reproduce:
I think the main problem is that I added a document before and somehow it didn't finish to the end or something so now I'm unable to add the same document again because a chunk of the collection already exists
Expected Behavior:
There should be some handling for large documents ( 2000 pages ) by introducing some kind of queue for the indexing instead of the document not being visible until it's fully indexed ( Which might take up to a few hours in my case )
Actual Behavior:
The document is not appearing until it's fully indexed so I'm not really sure what is the status of the document now
Environment
Open WebUI Version: 0.35
Operating System: Windows [ Client not host ]
Browser (if applicable): Chromium 126.0.6478.71
Reproduction Details
Confirmation:
Logs and Screenshots
Browser Console Logs:
Nothing is getting logged on the browser, the request is timing out due to taking so long from the server side
Docker Container Logs:
Installation Method
Docker
Additional Information
Basically the main problem is assuming that a document indexing could be done instantly, I have documents up to 4000 pages that I would like to index and the only way to do that is by adding some kind of queue with jobs for the indexing and showing the document as ( under processing )
The text was updated successfully, but these errors were encountered: