Find answers from the community

Updated 3 months ago

super grateful for any help..!

super grateful for any help..!
L
t
31 comments
@thomoliverz do you have any google readers installed? Maybe double check you have the latest

pip install -U llama-index-readers-google llama-index-readers-gcs
but do i need a google reader @Logan M ? i am trying to use airtable reader
I'm not sure if you do or not, but that line of code wouldn't get triggered unless you had it installed πŸ‘€
thanks @Logan M - reinstalled/ updated both of those.

tried again (see screenshot)

got the attached txt file

Have I installed something wrong? I redid everything & just did llama-index-core.. but maybe I need more for airtable?
Attachment
Screenshot_2024-04-16_at_13.19.42.png
seems to be related to ElasticsearchReader ? Somehow?

I'm not really able to replicate though
Are you using a venv? I would start fresh

In a new terminal
Plain Text
# uninstall anything global related to llama-index
pip freeze | grep llama-index | pip uninstall -y 

# make a new env
python -m venv venv
source venv/bin/activate

# install
pip install llama-index-readers-airtable ...
thanks @Logan M .... how bizarre is this..? Still happening for me when I do it in replit. I just tried in VS code & worked.


in replit I totally created new environment, installed 2 llama-index & llama-index-readers-airtable & still get the same error

I would be surprised if it was a replit issue as I have been using replit for llama index for the past yr..!
trying some new stuff & will report back
ok i tried my thing & still didn't work...

do you think it could be a replit issue @Logan M ?
Feels like it could be a replit issue πŸ€” I haven't used replit much at all tbh haha
omg - me again - still facing this incredibly weird issue

as soon as I add the line:

from llama_index.readers.airtable import AirtableReader

it seems to mess up my code when I run it

But now the error is different - see attached

It now says... ModuleNotFoundError: No module named 'openai.openai_object'

does this give u more info on the likely package issue @Logan M ?
Hey @thomoliverz -- That error seems to mean you installed some older openai client? Try pip install -U openai πŸ€”
Still get the same error - am totally lost
what does pip show openai give?
this is an issue with litellm πŸ˜…
What version of llama-index are you using? Seems like a fairly old version. You might have to actually downgrade the openai package
I'm not sure which version of openai that will work with though, might have to iterate a bit
Well I had all my code written with the airtable reader probably like 3-4 months ago (maybe a bit more)

now I'm redoing it so I upgraded to the new llama index

is there something i can do to get round the litellm issue..?
im happy to go from scratch

i just need to load the airtable data in and every time i try to do that by downloading the airtable reader it all goes wrong..
but maybe to use the airtable reader i need to be using an older version of something else..?
From your tracebacks, it seems like you are using llama_index==0.9.X instead of llama_index==0.10.X πŸ‘€
Does that seem right?
I see llama_index/llm_predictor/__init__.py for example, which is not a path in v0.10.X (it would be llama_index/core/llm_predictor/__init__.py)
Possibly but I upgraded llama index when k started tweaking again a few days ago. And right now I have tried starting from scratch, downloading most up to date llama index as well as the airtable reader and then get the issue …
Can you reproduce in a google colab?
If not, then it feels related to your env setup πŸ€”
I finally managed to resolve this... @Logan M

I freezed all the requirements I was using in VS & those in Replit & found - as you suggested - that VS was using OpenAI 1.20 vs 1.25. So I then installed the right one in Replit & still didn't work...

So then I just copied over requirements exactly from VS to Replit & still didn't work (because Replit automatically updates packages when you run your script.

So then had to default lock all the right packages.

So, working in Replit (which means I can deploy). But still don't know what the issue was. See requirements attached in a sec.
Replit
aiohttp==3.9.5
aiosignal==1.3.1
annotated-types==0.6.0
anyio==4.3.0
async-timeout==4.0.3
attrs==23.2.0
beautifulsoup4==4.12.3
certifi==2024.2.2
charset-normalizer==3.3.2
click==8.1.7
dataclasses-json==0.6.5
Deprecated==1.2.14
dirtyjson==1.0.8
distro==1.9.0
exceptiongroup==1.2.1
frozenlist==1.4.1
fsspec==2024.3.1
gpt-index==0.8.42
greenlet==3.0.3
h11==0.14.0
httpcore==1.0.5
httpx==0.27.0
idna==3.7
inflection==0.5.1
joblib==1.4.2
jsonpatch==1.33
jsonpointer==2.4
langchain==0.1.17
langchain-community==0.0.36
langchain-core==0.1.50
langchain-text-splitters==0.0.1
langsmith==0.1.54
llama-index==0.10.34
llama-index-agent-openai==0.2.3
llama-index-cli==0.1.12
llama-index-core==0.10.34
llama-index-embeddings-openai==0.1.9
llama-index-indices-managed-llama-cloud==0.1.6
llama-index-legacy==0.9.48
llama-index-llms-openai==0.1.16
llama-index-multi-modal-llms-openai==0.1.5
llama-index-program-openai==0.1.6
llama-index-question-gen-openai==0.1.3
llama-index-readers-airtable==0.1.3
llama-index-readers-file==0.1.20
llama-index-readers-llama-parse==0.1.4
llama-parse==0.4.2
llamaindex-py-client==0.1.19
marshmallow==3.21.2
multidict==6.0.5
mypy-extensions==1.0.0
nest-asyncio==1.6.0
networkx==3.3
nltk==3.8.1
numpy==1.26.4
openai==1.25.2
orjson==3.10.3
packaging==23.2
pandas==2.2.2
pillow==10.3.0
pyairtable==2.3.3
pydantic==2.7.1
pydantic_core==2.18.2
pypdf==4.2.0
python-dateutil==2.9.0.post0
python-dotenv==1.0.1
pytz==2024.1
PyYAML==6.0.1
regex==2024.4.28
requests==2.31.0
six==1.16.0
sniffio==1.3.1
soupsieve==2.5
SQLAlchemy==2.0.30
striprtf==0.0.26
tenacity==8.2.3
tiktoken==0.6.0
tqdm==4.66.4
typing-inspect==0.9.0
typing_extensions==4.11.0
tzdata==2024.1
urllib3==1.26.18
wrapt==1.16.0
yarl==1.9.4
Add a reply
Sign up and join the conversation on Discord