Closed ghost closed 1 year ago
I am also getting this exact same error with GPTSimpleVectorIndex despite it working fine up until yesterday. Win10, Python 311, llama-index-0.5.17
We recently changed the way we save/load vector stores from disk - sorry about that
@mfelat out of curiosity, is it expensive to rebuild the vector index?
no not expensive, but the interesting part is, it works on my mac without an error. how can I reindex the file?
Rebuild the index from the existing set of documents e.g. create a new index
Rebuild the index from the existing set of documents e.g. create a new index
fixed the issue by downgrading the llama_index to 0.4.40. not sure if this is the best way, if I reindex with the latest version would it be better?
I just spent about $250 indexing a library of legal documents. How can I migrate?
修改了后,感觉效果不行了
Is there still a need to rebuild the index to fix this issue? I would prefer to wait until there is a clear resolution.
as a workaround, I downgraded the llama_index to 0.4.40, but if the newer version of indexing provides better quality, I could reindex. I'd appreciate any feedback on that.
I downgraded like you suggested and that works, thanks!
Got an unusual warning from openai:
UserWarning: You are trying to use a chat model. This way of initializing it is no longer supported. Instead, please use: from langchain.chat_models import ChatOpenAI
from langchain.chat_models import ChatOpenAI
this is for indexing I think, right? so we probably need to reindex as I'm using gpt-3.5-turbo for completinons
from langchain.chat_models import ChatOpenAI
this is for indexing I think, right? so we probably need to reindex as I'm using gpt-3.5-turbo for completinons
That was for querying only, using GPT3.5. I indexed the documents using the default (ADA2) weeks ago. I haven't tried reindexing yet.
same, would be cool if we could get a hint on how to migrate the index files.
I experienced this issue as well, after upgrading to the latest version. A migration tool would be ideal, to avoid the cost of recreating indexes. I was also wondering, will there be any similar problems with the upcoming 0.6 version?
Hi, @mfelat! I'm here to help the LlamaIndex team manage their backlog and I wanted to let you know that we are marking this issue as stale.
Based on my understanding, the issue titled "Getting type = vector_store_dict[TYPE_KEY] KeyError: 'type' error only on streamlit cloud" is about an error that occurs when running an app on Streamlit Cloud. Users have reported a KeyError related to the 'type' key in the vector_store_dict. Some users have found a workaround by downgrading the llama_index package, but there is a discussion about the need to reindex with the latest version for better quality. Additionally, there are requests for a migration tool to avoid recreating indexes and concerns about potential problems with the upcoming 0.6 version.
Before we proceed, we would like to confirm if this issue is still relevant to the latest version of the LlamaIndex repository. If it is, please let us know by commenting on this issue. Otherwise, feel free to close the issue yourself or it will be automatically closed in 7 days.
Thank you for your understanding and we appreciate your contribution to the LlamaIndex project!
hello, I'm getting this error with my app only when I run it on streamlit cloud and couldn't resolve it, what might be causing it?
Collecting usage statistics. To deactivate, set browser.gatherUsageStats to False.
2023-04-17 23:08:01.114 Uncaught app exception
Traceback (most recent call last):
File "/home/appuser/venv/lib/python3.9/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 565, in _run_script
exec(code, module.dict) File "/app/chat6529/6529GPT.py", line 99, in
st.session_state.response_text, st.session_state.similarity_score = process_question(query) File "/app/chat6529/6529GPT.py", line 54, in process_question
index = GPTSimpleVectorIndex.load_from_disk(input_index) File "/home/appuser/venv/lib/python3.9/site-packages/llama_index/indices/base.py", line 364, in load_from_disk
return cls.load_from_string(file_contents, **kwargs) File "/home/appuser/venv/lib/python3.9/site-packages/llama_index/indices/base.py", line 340, in load_from_string
return cls.load_from_dict(result_dict, **kwargs) File "/home/appuser/venv/lib/python3.9/site-packages/llama_index/indices/vector_store/base.py", line 260, in load_from_dict
vector_store = load_vector_store_from_dict( File "/home/appuser/venv/lib/python3.9/site-packages/llama_index/vector_stores/registry.py", line 52, in load_vector_store_from_dict
type = vector_store_dict[TYPE_KEY] KeyError: 'type'