I am in python 3.11 venv with the latest open-webui.
When using either llamacpp or ollama as the embedding backend, I get the following error. it doesn't matter what model or settings I use.
I can clearly see the GPUs start to get used and logs in llamacpp show its sending data, so it maybe its an incompatibility with the embedding model?
ERROR [open_webui.apps.webui.routers.files] 400: 'NoneType' object is not iterable
Traceback (most recent call last):
File "/home/llm/open-webui/venv-3.11/lib64/python3.11/site-packages/open_webui/apps/retrieval/main.py", line 1028, in process_file
raise e
File "/home/llm/open-webui/venv-3.11/lib64/python3.11/site-packages/open_webui/apps/retrieval/main.py", line 1002, in process_file
result = save_docs_to_vector_db(
^^^^^^^^^^^^^^^^^^^^^^^
File "/home/llm/open-webui/venv-3.11/lib64/python3.11/site-packages/open_webui/apps/retrieval/main.py", line 876, in save_docs_to_vector_db
raise e
File "/home/llm/open-webui/venv-3.11/lib64/python3.11/site-packages/open_webui/apps/retrieval/main.py", line 854, in save_docs_to_vector_db
embeddings = embedding_function(
^^^^^^^^^^^^^^^^^^^
File "/home/llm/open-webui/venv-3.11/lib64/python3.11/site-packages/open_webui/apps/retrieval/utils.py", line 267, in <lambda>
return lambda query: generate_multiple(query, func)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/llm/open-webui/venv-3.11/lib64/python3.11/site-packages/open_webui/apps/retrieval/utils.py", line 262, in generate_multiple
embeddings.extend(func(query[i : i + embedding_batch_size]))
TypeError: 'NoneType' object is not iterable
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/llm/open-webui/venv-3.11/lib64/python3.11/site-packages/open_webui/apps/webui/routers/files.py", line 71, in upload_file
process_file(ProcessFileForm(file_id=id))
File "/home/llm/open-webui/venv-3.11/lib64/python3.11/site-packages/open_webui/apps/retrieval/main.py", line 1037, in process_file
raise HTTPException(
fastapi.exceptions.HTTPException: 400: 'NoneType' object is not iterable
Originally created by @frenzybiscuit on GitHub (Dec 19, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/7956
I am in python 3.11 venv with the latest open-webui.
When using either llamacpp or ollama as the embedding backend, I get the following error. it doesn't matter what model or settings I use.
I can clearly see the GPUs start to get used and logs in llamacpp show its sending data, so it maybe its an incompatibility with the embedding model?
```
ERROR [open_webui.apps.webui.routers.files] 400: 'NoneType' object is not iterable
Traceback (most recent call last):
File "/home/llm/open-webui/venv-3.11/lib64/python3.11/site-packages/open_webui/apps/retrieval/main.py", line 1028, in process_file
raise e
File "/home/llm/open-webui/venv-3.11/lib64/python3.11/site-packages/open_webui/apps/retrieval/main.py", line 1002, in process_file
result = save_docs_to_vector_db(
^^^^^^^^^^^^^^^^^^^^^^^
File "/home/llm/open-webui/venv-3.11/lib64/python3.11/site-packages/open_webui/apps/retrieval/main.py", line 876, in save_docs_to_vector_db
raise e
File "/home/llm/open-webui/venv-3.11/lib64/python3.11/site-packages/open_webui/apps/retrieval/main.py", line 854, in save_docs_to_vector_db
embeddings = embedding_function(
^^^^^^^^^^^^^^^^^^^
File "/home/llm/open-webui/venv-3.11/lib64/python3.11/site-packages/open_webui/apps/retrieval/utils.py", line 267, in <lambda>
return lambda query: generate_multiple(query, func)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/llm/open-webui/venv-3.11/lib64/python3.11/site-packages/open_webui/apps/retrieval/utils.py", line 262, in generate_multiple
embeddings.extend(func(query[i : i + embedding_batch_size]))
TypeError: 'NoneType' object is not iterable
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/llm/open-webui/venv-3.11/lib64/python3.11/site-packages/open_webui/apps/webui/routers/files.py", line 71, in upload_file
process_file(ProcessFileForm(file_id=id))
File "/home/llm/open-webui/venv-3.11/lib64/python3.11/site-packages/open_webui/apps/retrieval/main.py", line 1037, in process_file
raise HTTPException(
fastapi.exceptions.HTTPException: 400: 'NoneType' object is not iterable
```
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @frenzybiscuit on GitHub (Dec 19, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/7956
I am in python 3.11 venv with the latest open-webui.
When using either llamacpp or ollama as the embedding backend, I get the following error. it doesn't matter what model or settings I use.
I can clearly see the GPUs start to get used and logs in llamacpp show its sending data, so it maybe its an incompatibility with the embedding model?