search

run-llama / llama_index

LlamaIndex is a data framework for your LLM applications
https://docs.llamaindex.ai
MIT License
37.06k stars 5.32k forks source link

segmentation fault when using HuggingFaceEmbedding #9949

Closed anamariaUIC closed 3 months ago

anamariaUIC commented 10 months ago

Question Validation

Question

Hi,

I have this code that I throwing me the error:"segmentation fault"

import os
import streamlit as st

os.environ["REPLICATE_API_TOKEN"] = "my_token"

from llama_index.llms import Replicate

llama2_7b_chat = "meta/llama-2-7b-chat:8e6975e5ed6174911a6ff3d60540dfd4844201974602551e10e9e87ab143d81e"
llm = Replicate(
    model=llama2_7b_chat,
    temperature=0.01,
    additional_kwargs={"top_p": 1, "max_new_tokens": 300},
)

from llama_index import VectorStoreIndex, SimpleDirectoryReader
from llama_index.embeddings import HuggingFaceEmbedding
from llama_index import ServiceContext

embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-small-en-v1.5")
service_context = ServiceContext.from_defaults(
    llm=llm, embed_model=embed_model
)

documents = SimpleDirectoryReader("data").load_data()
index = VectorStoreIndex.from_documents(
    documents, service_context=service_context
)

#index = VectorStoreIndex.from_documents(documents)

# Get the query engine
query_engine = index.as_query_engine(streaming=True)

# Create a Streamlit web app
#st.title("LLM Query Interface")
query = st.text_input("Enter your query:")
submit_button = st.button("Submit")

if submit_button:
    # Query the engine with the defined query
    response = query_engine.query(query)
    st.write("### Query Result:")
    st.write(response)

if I disable embed_model code runs without problems.

I run the script via:

streamlit run my_script.py

I run this on Mac, Catalina, I have at least 250GB available memory. Please advise.

Thanks

dosubot[bot] commented 10 months ago

🤖

Hello @anamariaUIC! I'm Dosu, a friendly bot here to assist you with your LlamaIndex issues while we wait for a human maintainer. I'm here to help you debug problems, answer questions, and guide you on your way to becoming a contributor. Let's tackle this together!

The "segmentation fault" error you're encountering is typically caused by a program trying to read or write an illegal memory location. In the context of your LlamaIndex code, it's possible that the error is related to the HuggingFaceEmbedding and how it interacts with your system's memory.

One potential issue could be the size of the model you're trying to load with HuggingFace's from_pretrained method. If the model is too large, it might be causing your program to exceed its allocated memory, leading to a segmentation fault.

Another potential issue could be the use of PyTorch's torch.device in the infer_torch_device function. If you're trying to use a GPU device that isn't available or properly configured, it could lead to a segmentation fault.

Unfortunately, without more information about your system setup, the specific model you're using, and the exact circumstances under which the error occurs, it's difficult to provide a more specific solution.

If you're able to provide more details, I'd be happy to help further. Otherwise, I'd recommend checking your system's memory usage and your PyTorch device configuration as potential starting points for troubleshooting.

As for the role of the HuggingFaceEmbedding in the LlamaIndex codebase, it is responsible for generating embeddings for given text inputs using HuggingFace's transformer models. The class has several methods for generating embeddings, including _embed, _get_query_embedding, _get_text_embedding, and _get_text_embeddings. It also has asynchronous versions of these methods.

I hope this helps! If you have any other questions or need further clarification, please don't hesitate to ask.

Source Code

Sources

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.

logan-markewich commented 10 months ago

Theres not really a way to reproduce this? 😅 I can run this locally without issues. Is there any more information you can provide?

logan-markewich commented 10 months ago

Do you have cuda installed? Is that conflicting with pytorch somehow?

anamariaUIC commented 10 months ago

Hi

Can you please send me a list of all libraries that I should have installed?

Also commands that will show you status of my machine/env…

Thanks Ana

Sent from Outlook for iOShttps://aka.ms/o0ukef

From: Logan @.> Sent: Tuesday, January 9, 2024 6:25:03 PM To: run-llama/llama_index @.> Cc: Sokovic, Ana Marija @.>; Mention @.> Subject: Re: [run-llama/llama_index] segmentation fault when using HuggingFaceEmbedding (Issue #9949)

Do you have cuda installed? Is that conflicting with pytorch somehow?

— Reply to this email directly, view it on GitHubhttps://github.com/run-llama/llama_index/issues/9949#issuecomment-1884001798, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AUHBH5G3MWBSOOPEEQGA6VDYNXNV7AVCNFSM6AAAAABBT5P3Y2VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTQOBUGAYDCNZZHA. You are receiving this because you were mentioned.Message ID: @.***>

logan-markewich commented 10 months ago

@anamariaUIC I think the bare minimum is just pip install -U llama-index "transformers[torch]"

For example, if I run in google colab, there is no issue with segmentation faults 🤔

anamariaUIC commented 10 months ago

I am using Python 3.9.7 for this.

Do you know how do I do traceback for this code?

On Jan 9, 2024, at 6:52 PM, Sokovic, Ana Marija @.**@.>> wrote:

Hi

Can you please send me a list of all libraries that I should have installed?

Also commands that will show you status of my machine/env…

Thanks Ana

Sent from Outlook for iOShttps://aka.ms/o0ukef

From: Logan @.**@.>> Sent: Tuesday, January 9, 2024 6:25:03 PM To: run-llama/llama_index @.**@.>> Cc: Sokovic, Ana Marija @.**@.>>; Mention @.**@.>> Subject: Re: [run-llama/llama_index] segmentation fault when using HuggingFaceEmbedding (Issue #9949)

Do you have cuda installed? Is that conflicting with pytorch somehow?

— Reply to this email directly, view it on GitHubhttps://github.com/run-llama/llama_index/issues/9949#issuecomment-1884001798, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AUHBH5G3MWBSOOPEEQGA6VDYNXNV7AVCNFSM6AAAAABBT5P3Y2VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTQOBUGAYDCNZZHA. You are receiving this because you were mentioned.Message ID: @.***>

anamariaUIC commented 10 months ago

Thanks I will try this. What is this supposed to do?

On Jan 9, 2024, at 8:11 PM, Logan @.**@.>> wrote:

@anamariaUIChttps://github.com/anamariaUIC I think the bare minimum is just pip install -U llama-index "transformers[torch]"

For example, if I run in google colab, there is no issue with segmentation faults 🤔

— Reply to this email directly, view it on GitHubhttps://github.com/run-llama/llama_index/issues/9949#issuecomment-1884078832, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AUHBH5GLDFMDKGH7OTK5OKLYNX2EBAVCNFSM6AAAAABBT5P3Y2VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTQOBUGA3TQOBTGI. You are receiving this because you were mentioned.Message ID: @.***>

anamariaUIC commented 10 months ago

Installation finished and I run it again:

Installing collected packages: networkx, llama-index Attempting uninstall: networkx Found existing installation: networkx 2.6.3 Uninstalling networkx-2.6.3: Successfully uninstalled networkx-2.6.3 Attempting uninstall: llama-index Found existing installation: llama-index 0.9.25.post1 Uninstalling llama-index-0.9.25.post1: Successfully uninstalled llama-index-0.9.25.post1 Successfully installed llama-index-0.9.28.post2 networkx-3.2.1 (base) @.*** llama_test % streamlit run replicate_lama2.py 2024-01-09 20:58:13.449 INFO numexpr.utils: Note: NumExpr detected 12 cores but "NUMEXPR_MAX_THREADS" not set, so enforcing safe limit of 8. 2024-01-09 20:58:13.449 INFO numexpr.utils: NumExpr defaulting to 8 threads.

You can now view your Streamlit app in your browser.

Local URL: http://localhost:8501 Network URL: http://10.0.0.81:8501http://10.0.0.81:8501/

zsh: segmentation fault streamlit run replicate_lama2.py (base) @.*** llama_test %

Here is my env:

(base) @.*** llama_test % pip list Package Version

accelerate 0.25.0 aiofiles 23.2.1 aiohttp 3.9.1 aiosignal 1.3.1 alabaster 0.7.12 altair 4.2.2 anaconda-client 1.9.0 anaconda-navigator 2.1.1 anaconda-project 0.10.1 annotated-types 0.6.0 anyio 4.2.0 appdirs 1.4.4 applaunchservices 0.2.1 appnope 0.1.2 appscript 1.1.2 argh 0.26.2 argon2-cffi 20.1.0 arrow 0.13.1 asn1crypto 1.4.0 astroid 2.6.6 astropy 4.3.1 async-generator 1.10 async-timeout 4.0.3 atomicwrites 1.4.0 attrs 21.2.0 autopep8 1.5.7 awscli 1.22.67 Babel 2.9.1 backcall 0.2.0 backports.functools-lru-cache 1.6.4 backports.shutil-get-terminal-size 1.0.0 backports.tempfile 1.0 backports.weakref 1.0.post1 beautifulsoup4 4.12.2 binaryornot 0.4.4 bitarray 2.3.0 bkcharts 0.2 black 19.10b0 bleach 4.0.0 blinker 1.7.0 bokeh 2.4.1 boto 2.49.0 botocore 1.24.12 Bottleneck 1.3.2 brotlipy 0.7.0 cached-property 1.5.2 cachetools 5.3.2 certifi 2021.10.8 cffi 1.14.6 chardet 4.0.0 charset-normalizer 2.0.4 click 8.1.7 cloudpickle 2.0.0 clyent 1.2.2 colorama 0.4.3 conda 4.10.3 conda-build 3.21.5 conda-content-trust 0+unknown conda-pack 0.6.0 conda-package-handling 1.7.3 conda-repo-cli 1.0.4 conda-token 0.3.0 conda-verify 3.4.2 contextlib2 0.6.0.post1 cookiecutter 1.7.2 cryptography 3.4.8 cycler 0.10.0 Cython 0.29.24 cytoolz 0.11.0 daal4py 2021.3.0 dask 2021.10.0 dataclasses-json 0.6.3 debugpy 1.4.1 decorator 5.1.0 defusedxml 0.7.1 Deprecated 1.2.14 diff-match-patch 20200713 distributed 2021.10.0 distro 1.9.0 docutils 0.15.2 docx2txt 0.8 entrypoints 0.3 et-xmlfile 1.1.0 exceptiongroup 1.2.0 fastapi 0.108.0 fastcache 1.1.0 ffmpy 0.3.1 filelock 3.3.1 flake8 3.9.2 Flask 1.1.2 fonttools 4.25.0 frozenlist 1.4.1 fsspec 2023.12.2 future 0.18.2 gevent 21.8.0 gitdb 4.0.11 GitPython 3.1.40 glob2 0.7 globus-cli 3.22.0 globus-sdk 3.33.0 gmpy2 2.0.8 gradio 4.13.0 gradio_client 0.8.0 greenlet 1.1.1 h11 0.14.0 h5py 3.2.1 HeapDict 1.0.1 html5lib 1.1 httpcore 1.0.2 httpx 0.26.0 huggingface-hub 0.20.1 idna 3.2 imagecodecs 2021.8.26 imageio 2.9.0 imagesize 1.2.0 importlib-metadata 4.8.1 importlib-resources 6.1.1 inflection 0.5.1 iniconfig 1.1.1 intervaltree 3.1.0 ipykernel 6.4.1 ipython 7.29.0 ipython-genutils 0.2.0 ipywidgets 7.6.5 isort 5.9.3 itsdangerous 2.0.1 jdcal 1.4.1 jedi 0.18.0 Jinja2 2.11.3 jinja2-time 0.2.0 jmespath 1.0.1 joblib 1.1.0 json5 0.9.6 jsonpatch 1.33 jsonpointer 2.4 jsonschema 3.2.0 jupyter 1.0.0 jupyter-client 6.1.12 jupyter-console 6.4.0 jupyter-core 4.8.1 jupyter-server 1.4.1 jupyterlab 3.2.1 jupyterlab-pygments 0.1.2 jupyterlab-server 2.8.2 jupyterlab-widgets 1.0.0 keyring 23.1.0 kiwisolver 1.3.1 langchain 0.0.354 langchain-community 0.0.8 langchain-core 0.1.5 langsmith 0.0.77 lazy-object-proxy 1.6.0 libarchive-c 2.9 llama-index 0.9.28.post2 llvmlite 0.37.0 locket 0.2.1 lxml 4.6.3 markdown-it-py 3.0.0 MarkupSafe 2.0.1 marshmallow 3.20.1 matplotlib 3.4.3 matplotlib-inline 0.1.2 mccabe 0.6.1 mdurl 0.1.2 mistune 0.8.4 mkl-fft 1.3.1 mkl-random 1.2.2 mkl-service 2.4.0 mock 4.0.3 more-itertools 8.10.0 mpmath 1.2.1 msgpack 1.0.2 multidict 6.0.4 multipledispatch 0.6.0 munkres 1.1.4 mypy-extensions 0.4.3 navigator-updater 0.2.1 nbclassic 0.2.6 nbclient 0.5.3 nbconvert 6.1.0 nbformat 5.1.3 nest-asyncio 1.5.8 networkx 3.2.1 nltk 3.8.1 nose 1.3.7 notebook 6.4.5 numba 0.54.1 numexpr 2.7.3 numpy 1.20.3 numpydoc 1.1.0 olefile 0.46 openai 1.6.1 openpyxl 3.0.9 orjson 3.9.10 packaging 23.2 pandas 1.3.4 pandocfilters 1.4.3 parso 0.8.2 partd 1.2.0 path 16.0.0 pathlib 1.0.1 pathlib2 2.3.6 pathspec 0.7.0 patsy 0.5.2 pep8 1.7.1 pexpect 4.8.0 pickleshare 0.7.5 Pillow 8.4.0 pip 21.2.4 pkginfo 1.7.1 pluggy 0.13.1 ply 3.11 poyo 0.5.0 prometheus-client 0.11.0 prompt-toolkit 3.0.20 protobuf 3.20.3 psutil 5.8.0 ptyprocess 0.7.0 py 1.10.0 pyarrow 14.0.2 pyasn1 0.4.8 pycodestyle 2.7.0 pycosat 0.6.3 pycparser 2.20 pycurl 7.44.1 pydantic 2.5.3 pydantic_core 2.14.6 pydeck 0.8.1b0 pydocstyle 6.1.1 pydub 0.25.1 pyerfa 2.0.0 pyflakes 2.3.1 Pygments 2.17.2 PyJWT 2.1.0 pylint 2.9.6 pyls-spyder 0.4.0 Pympler 1.0.1 pyodbc 4.0.0-unsupported pyOpenSSL 21.0.0 pyparsing 3.0.4 pypdf 3.17.4 PyQt5 5.15.10 PyQt5-Qt5 5.15.12 PyQt5-sip 12.13.0 PyQtWebEngine 5.12 PyQtWebEngine-Qt5 5.15.12 pyrsistent 0.18.0 PySocks 1.7.1 pytest 6.2.4 python-dateutil 2.8.2 python-lsp-black 1.0.0 python-lsp-jsonrpc 1.0.0 python-lsp-server 1.2.4 python-multipart 0.0.6 python-slugify 5.0.2 pytz 2021.3 PyWavelets 1.1.1 PyYAML 5.4.1 pyzmq 22.2.1 QDarkStyle 3.0.2 qstylizer 0.1.10 QtAwesome 1.0.2 qtconsole 5.1.1 QtPy 1.10.0 regex 2023.12.25 replicate 0.22.0 requests 2.31.0 rich 13.7.0 rope 0.19.0 rsa 4.7.2 Rtree 0.9.7 ruamel.yaml 0.18.5 ruamel.yaml.clib 0.2.8 ruamel-yaml-conda 0.15.100 s3transfer 0.5.2 safetensors 0.4.1 scikit-image 0.18.3 scikit-learn 0.24.2 scikit-learn-intelex 2021.20210714.100439 scipy 1.7.1 seaborn 0.11.2 semantic-version 2.10.0 semver 3.0.2 Send2Trash 1.8.0 setuptools 58.0.4 shellingham 1.5.4 simplegeneric 0.8.1 singledispatch 3.7.0 sip 4.19.13 six 1.16.0 smmap 5.0.1 sniffio 1.2.0 snowballstemmer 2.1.0 sodapy 2.1.1 sortedcollections 2.1.0 sortedcontainers 2.4.0 soupsieve 2.2.1 Sphinx 4.2.0 sphinxcontrib-applehelp 1.0.2 sphinxcontrib-devhelp 1.0.2 sphinxcontrib-htmlhelp 2.0.0 sphinxcontrib-jsmath 1.0.1 sphinxcontrib-qthelp 1.0.3 sphinxcontrib-serializinghtml 1.1.5 sphinxcontrib-websupport 1.2.4 spyder 5.1.5 spyder-kernels 2.1.3 SQLAlchemy 2.0.25 starlette 0.32.0.post1 statsmodels 0.12.2 streamlit 1.12.0 sympy 1.9 tables 3.6.1 TBB 0.2 tblib 1.7.0 tenacity 8.2.3 terminado 0.9.4 testpath 0.5.0 text-unidecode 1.3 textdistance 4.2.1 threadpoolctl 2.2.0 three-merge 0.1.1 tifffile 2021.7.2 tiktoken 0.5.2 tinycss 0.4 tokenizers 0.15.0 toml 0.10.2 tomlkit 0.12.0 toolz 0.11.1 torch 2.1.2 tornado 6.1 tqdm 4.62.3 traitlets 5.1.0 transformers 4.36.2 typed-ast 1.4.3 typer 0.9.0 typing_extensions 4.9.0 typing-inspect 0.9.0 tzlocal 5.2 ujson 4.0.2 unicodecsv 0.14.1 Unidecode 1.2.0 urllib3 1.26.7 uvicorn 0.25.0 validators 0.22.0 watchdog 2.1.3 wcwidth 0.2.5 webencodings 0.5.1 websockets 11.0.3 Werkzeug 2.0.2 wheel 0.37.0 whichcraft 0.6.1 widgetsnbextension 3.5.1 wrapt 1.12.1 wurlitzer 2.1.1 xlrd 2.0.1 XlsxWriter 3.0.1 xlwings 0.24.9 xlwt 1.3.0 xmltodict 0.12.0 yapf 0.31.0 yarl 1.9.4 zict 2.0.0 zipp 3.6.0 zope.event 4.5.0 zope.interface 5.4.0 (base) @.*** llama_test %

On Jan 9, 2024, at 8:12 PM, Sokovic, Ana Marija @.**@.>> wrote:

Thanks I will try this. What is this supposed to do?

On Jan 9, 2024, at 8:11 PM, Logan @.**@.>> wrote:

@anamariaUIChttps://github.com/anamariaUIC I think the bare minimum is just pip install -U llama-index "transformers[torch]"

For example, if I run in google colab, there is no issue with segmentation faults 🤔

— Reply to this email directly, view it on GitHubhttps://github.com/run-llama/llama_index/issues/9949#issuecomment-1884078832, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AUHBH5GLDFMDKGH7OTK5OKLYNX2EBAVCNFSM6AAAAABBT5P3Y2VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTQOBUGA3TQOBTGI. You are receiving this because you were mentioned.Message ID: @.***>

anamariaUIC commented 10 months ago

Hello,

I would like to circle back on this ticket: While running this code in attachment via:

s treamlit run replicate_lama2.py

I am getting errors in attach. Can you please advise how to go about this? Now sure why it says: “No docs available” When all documents are in folder “data” which is in the same folder where replicate_lama2.py script is as attach shows.

Please advise, Best, Ana @. @.

On Jan 9, 2024, at 9:01 PM, Sokovic, Ana Marija @.**@.>> wrote:

Installation finished and I run it again:

Installing collected packages: networkx, llama-index Attempting uninstall: networkx Found existing installation: networkx 2.6.3 Uninstalling networkx-2.6.3: Successfully uninstalled networkx-2.6.3 Attempting uninstall: llama-index Found existing installation: llama-index 0.9.25.post1 Uninstalling llama-index-0.9.25.post1: Successfully uninstalled llama-index-0.9.25.post1 Successfully installed llama-index-0.9.28.post2 networkx-3.2.1 (base) @.*** llama_test % streamlit run replicate_lama2.py 2024-01-09 20:58:13.449 INFO numexpr.utils: Note: NumExpr detected 12 cores but "NUMEXPR_MAX_THREADS" not set, so enforcing safe limit of 8. 2024-01-09 20:58:13.449 INFO numexpr.utils: NumExpr defaulting to 8 threads.

You can now view your Streamlit app in your browser.

Local URL: http://localhost:8501http://localhost:8501/ Network URL: http://10.0.0.81:8501http://10.0.0.81:8501/

zsh: segmentation fault streamlit run replicate_lama2.py (base) @.*** llama_test %

Here is my env:

(base) @.*** llama_test % pip list Package Version

accelerate 0.25.0 aiofiles 23.2.1 aiohttp 3.9.1 aiosignal 1.3.1 alabaster 0.7.12 altair 4.2.2 anaconda-client 1.9.0 anaconda-navigator 2.1.1 anaconda-project 0.10.1 annotated-types 0.6.0 anyio 4.2.0 appdirs 1.4.4 applaunchservices 0.2.1 appnope 0.1.2 appscript 1.1.2 argh 0.26.2 argon2-cffi 20.1.0 arrow 0.13.1 asn1crypto 1.4.0 astroid 2.6.6 astropy 4.3.1 async-generator 1.10 async-timeout 4.0.3 atomicwrites 1.4.0 attrs 21.2.0 autopep8 1.5.7 awscli 1.22.67 Babel 2.9.1 backcall 0.2.0 backports.functools-lru-cache 1.6.4 backports.shutil-get-terminal-size 1.0.0 backports.tempfile 1.0 backports.weakref 1.0.post1 beautifulsoup4 4.12.2 binaryornot 0.4.4 bitarray 2.3.0 bkcharts 0.2 black 19.10b0 bleach 4.0.0 blinker 1.7.0 bokeh 2.4.1 boto 2.49.0 botocore 1.24.12 Bottleneck 1.3.2 brotlipy 0.7.0 cached-property 1.5.2 cachetools 5.3.2 certifi 2021.10.8 cffi 1.14.6 chardet 4.0.0 charset-normalizer 2.0.4 click 8.1.7 cloudpickle 2.0.0 clyent 1.2.2 colorama 0.4.3 conda 4.10.3 conda-build 3.21.5 conda-content-trust 0+unknown conda-pack 0.6.0 conda-package-handling 1.7.3 conda-repo-cli 1.0.4 conda-token 0.3.0 conda-verify 3.4.2 contextlib2 0.6.0.post1 cookiecutter 1.7.2 cryptography 3.4.8 cycler 0.10.0 Cython 0.29.24 cytoolz 0.11.0 daal4py 2021.3.0 dask 2021.10.0 dataclasses-json 0.6.3 debugpy 1.4.1 decorator 5.1.0 defusedxml 0.7.1 Deprecated 1.2.14 diff-match-patch 20200713 distributed 2021.10.0 distro 1.9.0 docutils 0.15.2 docx2txt 0.8 entrypoints 0.3 et-xmlfile 1.1.0 exceptiongroup 1.2.0 fastapi 0.108.0 fastcache 1.1.0 ffmpy 0.3.1 filelock 3.3.1 flake8 3.9.2 Flask 1.1.2 fonttools 4.25.0 frozenlist 1.4.1 fsspec 2023.12.2 future 0.18.2 gevent 21.8.0 gitdb 4.0.11 GitPython 3.1.40 glob2 0.7 globus-cli 3.22.0 globus-sdk 3.33.0 gmpy2 2.0.8 gradio 4.13.0 gradio_client 0.8.0 greenlet 1.1.1 h11 0.14.0 h5py 3.2.1 HeapDict 1.0.1 html5lib 1.1 httpcore 1.0.2 httpx 0.26.0 huggingface-hub 0.20.1 idna 3.2 imagecodecs 2021.8.26 imageio 2.9.0 imagesize 1.2.0 importlib-metadata 4.8.1 importlib-resources 6.1.1 inflection 0.5.1 iniconfig 1.1.1 intervaltree 3.1.0 ipykernel 6.4.1 ipython 7.29.0 ipython-genutils 0.2.0 ipywidgets 7.6.5 isort 5.9.3 itsdangerous 2.0.1 jdcal 1.4.1 jedi 0.18.0 Jinja2 2.11.3 jinja2-time 0.2.0 jmespath 1.0.1 joblib 1.1.0 json5 0.9.6 jsonpatch 1.33 jsonpointer 2.4 jsonschema 3.2.0 jupyter 1.0.0 jupyter-client 6.1.12 jupyter-console 6.4.0 jupyter-core 4.8.1 jupyter-server 1.4.1 jupyterlab 3.2.1 jupyterlab-pygments 0.1.2 jupyterlab-server 2.8.2 jupyterlab-widgets 1.0.0 keyring 23.1.0 kiwisolver 1.3.1 langchain 0.0.354 langchain-community 0.0.8 langchain-core 0.1.5 langsmith 0.0.77 lazy-object-proxy 1.6.0 libarchive-c 2.9 llama-index 0.9.28.post2 llvmlite 0.37.0 locket 0.2.1 lxml 4.6.3 markdown-it-py 3.0.0 MarkupSafe 2.0.1 marshmallow 3.20.1 matplotlib 3.4.3 matplotlib-inline 0.1.2 mccabe 0.6.1 mdurl 0.1.2 mistune 0.8.4 mkl-fft 1.3.1 mkl-random 1.2.2 mkl-service 2.4.0 mock 4.0.3 more-itertools 8.10.0 mpmath 1.2.1 msgpack 1.0.2 multidict 6.0.4 multipledispatch 0.6.0 munkres 1.1.4 mypy-extensions 0.4.3 navigator-updater 0.2.1 nbclassic 0.2.6 nbclient 0.5.3 nbconvert 6.1.0 nbformat 5.1.3 nest-asyncio 1.5.8 networkx 3.2.1 nltk 3.8.1 nose 1.3.7 notebook 6.4.5 numba 0.54.1 numexpr 2.7.3 numpy 1.20.3 numpydoc 1.1.0 olefile 0.46 openai 1.6.1 openpyxl 3.0.9 orjson 3.9.10 packaging 23.2 pandas 1.3.4 pandocfilters 1.4.3 parso 0.8.2 partd 1.2.0 path 16.0.0 pathlib 1.0.1 pathlib2 2.3.6 pathspec 0.7.0 patsy 0.5.2 pep8 1.7.1 pexpect 4.8.0 pickleshare 0.7.5 Pillow 8.4.0 pip 21.2.4 pkginfo 1.7.1 pluggy 0.13.1 ply 3.11 poyo 0.5.0 prometheus-client 0.11.0 prompt-toolkit 3.0.20 protobuf 3.20.3 psutil 5.8.0 ptyprocess 0.7.0 py 1.10.0 pyarrow 14.0.2 pyasn1 0.4.8 pycodestyle 2.7.0 pycosat 0.6.3 pycparser 2.20 pycurl 7.44.1 pydantic 2.5.3 pydantic_core 2.14.6 pydeck 0.8.1b0 pydocstyle 6.1.1 pydub 0.25.1 pyerfa 2.0.0 pyflakes 2.3.1 Pygments 2.17.2 PyJWT 2.1.0 pylint 2.9.6 pyls-spyder 0.4.0 Pympler 1.0.1 pyodbc 4.0.0-unsupported pyOpenSSL 21.0.0 pyparsing 3.0.4 pypdf 3.17.4 PyQt5 5.15.10 PyQt5-Qt5 5.15.12 PyQt5-sip 12.13.0 PyQtWebEngine 5.12 PyQtWebEngine-Qt5 5.15.12 pyrsistent 0.18.0 PySocks 1.7.1 pytest 6.2.4 python-dateutil 2.8.2 python-lsp-black 1.0.0 python-lsp-jsonrpc 1.0.0 python-lsp-server 1.2.4 python-multipart 0.0.6 python-slugify 5.0.2 pytz 2021.3 PyWavelets 1.1.1 PyYAML 5.4.1 pyzmq 22.2.1 QDarkStyle 3.0.2 qstylizer 0.1.10 QtAwesome 1.0.2 qtconsole 5.1.1 QtPy 1.10.0 regex 2023.12.25 replicate 0.22.0 requests 2.31.0 rich 13.7.0 rope 0.19.0 rsa 4.7.2 Rtree 0.9.7 ruamel.yaml 0.18.5 ruamel.yaml.clib 0.2.8 ruamel-yaml-conda 0.15.100 s3transfer 0.5.2 safetensors 0.4.1 scikit-image 0.18.3 scikit-learn 0.24.2 scikit-learn-intelex 2021.20210714.100439 scipy 1.7.1 seaborn 0.11.2 semantic-version 2.10.0 semver 3.0.2 Send2Trash 1.8.0 setuptools 58.0.4 shellingham 1.5.4 simplegeneric 0.8.1 singledispatch 3.7.0 sip 4.19.13 six 1.16.0 smmap 5.0.1 sniffio 1.2.0 snowballstemmer 2.1.0 sodapy 2.1.1 sortedcollections 2.1.0 sortedcontainers 2.4.0 soupsieve 2.2.1 Sphinx 4.2.0 sphinxcontrib-applehelp 1.0.2 sphinxcontrib-devhelp 1.0.2 sphinxcontrib-htmlhelp 2.0.0 sphinxcontrib-jsmath 1.0.1 sphinxcontrib-qthelp 1.0.3 sphinxcontrib-serializinghtml 1.1.5 sphinxcontrib-websupport 1.2.4 spyder 5.1.5 spyder-kernels 2.1.3 SQLAlchemy 2.0.25 starlette 0.32.0.post1 statsmodels 0.12.2 streamlit 1.12.0 sympy 1.9 tables 3.6.1 TBB 0.2 tblib 1.7.0 tenacity 8.2.3 terminado 0.9.4 testpath 0.5.0 text-unidecode 1.3 textdistance 4.2.1 threadpoolctl 2.2.0 three-merge 0.1.1 tifffile 2021.7.2 tiktoken 0.5.2 tinycss 0.4 tokenizers 0.15.0 toml 0.10.2 tomlkit 0.12.0 toolz 0.11.1 torch 2.1.2 tornado 6.1 tqdm 4.62.3 traitlets 5.1.0 transformers 4.36.2 typed-ast 1.4.3 typer 0.9.0 typing_extensions 4.9.0 typing-inspect 0.9.0 tzlocal 5.2 ujson 4.0.2 unicodecsv 0.14.1 Unidecode 1.2.0 urllib3 1.26.7 uvicorn 0.25.0 validators 0.22.0 watchdog 2.1.3 wcwidth 0.2.5 webencodings 0.5.1 websockets 11.0.3 Werkzeug 2.0.2 wheel 0.37.0 whichcraft 0.6.1 widgetsnbextension 3.5.1 wrapt 1.12.1 wurlitzer 2.1.1 xlrd 2.0.1 XlsxWriter 3.0.1 xlwings 0.24.9 xlwt 1.3.0 xmltodict 0.12.0 yapf 0.31.0 yarl 1.9.4 zict 2.0.0 zipp 3.6.0 zope.event 4.5.0 zope.interface 5.4.0 (base) @.*** llama_test %

On Jan 9, 2024, at 8:12 PM, Sokovic, Ana Marija @.**@.>> wrote:

Thanks I will try this. What is this supposed to do?

On Jan 9, 2024, at 8:11 PM, Logan @.**@.>> wrote:

@anamariaUIChttps://github.com/anamariaUIC I think the bare minimum is just pip install -U llama-index "transformers[torch]"

For example, if I run in google colab, there is no issue with segmentation faults 🤔

— Reply to this email directly, view it on GitHubhttps://github.com/run-llama/llama_index/issues/9949#issuecomment-1884078832, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AUHBH5GLDFMDKGH7OTK5OKLYNX2EBAVCNFSM6AAAAABBT5P3Y2VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTQOBUGA3TQOBTGI. You are receiving this because you were mentioned.Message ID: @.***>

dosubot[bot] commented 7 months ago

Hi, @anamariaUIC

I'm helping the LlamaIndex team manage their backlog and am marking this issue as stale. The issue you reported describes a segmentation fault error when using the HuggingFaceEmbedding in a Python script, specifically when running the script via Streamlit on a Mac with at least 250GB of available memory. Disabling the embed_model resolves the issue. There were discussions around potential causes of the error, including issues related to the size of the model and PyTorch's torch.device. Additional inquiries were made about reproducing the issue, CUDA installation conflicting with PyTorch, and the request for a list of required libraries and commands to check the machine's environment.

Could you please confirm if this issue is still relevant to the latest version of the LlamaIndex repository? If it is, kindly let the LlamaIndex team know by commenting on the issue. Otherwise, feel free to close the issue yourself, or it will be automatically closed in 7 days. Thank you!

anamariaUIC commented 7 months ago

Input file is here:

On Apr 17, 2024, at 11:45 AM, Sokovic, Ana Marija @.**@.>> wrote:

Hello,

We updated drivers to 535 version see attached and privateGPT chat bot opens up. The issue is now that quering a very simple question from a file (attached here) really gives poor results. Please see attached. I would like to to subtract these two numbers.

Next I’m askign it explicitely to subtract those two numbers and than I see Segmentation error. Please see attached.

This was installed like this:

salloc --job-name "InteractiveJob" --cpus-per-task 4 --mem-per-cpu 50gb --time 01:00:10 -p batch_gpu --gres=gpu:1

rm -rf .local .cache /scratch/network/$USER/privateGPT /scratch/network/$USER/tmp mkdir /scratch/network/$USER/tmp export TMPDIR=/scratch/network/$USER/tmp module load Python/3.11.3-GCCcore-12.3.0 pip install --user poetry module load git module load CUDA export PATH=$PATH:/home/$USER/.local/bin export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/home/$USER/.local/lib cd /scratch/network/$USER git clone https://github.com/imartinez/privateGPT.git cd privateGPT/ export PYTHONPATH=$PYTHONPATH:$PWD poetry install --extras "ui llms-llama-cpp embeddings-huggingface vector-stores-qdrant" poetry run python scripts/setup CMAKE_ARGS='-DLLAMA_CUBLAS=on' poetry run pip install --force-reinstall --no-cache-dir llama-cpp-python PGPT_PROFILES=local make run

to run

cd /scratch/network/$USER/privateGPT ./run_gpt.sh

<Screen Shot 2024-04-17 at 11.44.15 AM.png> This was installed with the default LLM model for privateGPT (last week) Please advise,

Thanks Ana <Screen Shot 2024-04-17 at 11.29.58 AM.png> <Screen Shot 2024-04-17 at 11.38.18 AM.png>

On Apr 17, 2024, at 11:21 AM, dosubot[bot] @.**@.>> wrote:

CAUTION: External Sender

Hi, @anamariaUIChttps://github.com/anamariaUIC

I'm helping the LlamaIndex team manage their backlog and am marking this issue as stale. The issue you reported describes a segmentation fault error when using the HuggingFaceEmbedding in a Python script, specifically when running the script via Streamlit on a Mac with at least 250GB of available memory. Disabling the embed_model resolves the issue. There were discussions around potential causes of the error, including issues related to the size of the model and PyTorch's torch.device. Additional inquiries were made about reproducing the issue, CUDA installation conflicting with PyTorch, and the request for a list of required libraries and commands to check the machine's environment.

Could you please confirm if this issue is still relevant to the latest version of the LlamaIndex repository? If it is, kindly let the LlamaIndex team know by commenting on the issue. Otherwise, feel free to close the issue yourself, or it will be automatically closed in 7 days. Thank you!

— Reply to this email directly, view it on GitHubhttps://github.com/run-llama/llama_index/issues/9949#issuecomment-2061701200, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AUHBH5AIZFYUBXAY5BEXJ7LY52OO3AVCNFSM6AAAAABBT5P3Y2VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDANRRG4YDCMRQGA. You are receiving this because you were mentioned.Message ID: @.***>

This email originated from outside the University of Illinois System. Use caution when replying, clicking links, or opening attachments. DO NOT reply to any requests asking you to reply from a personal account or SMS.

anamariaUIC commented 7 months ago

Hello,

Can you please get back to me about this?

Thanks Ana

On Apr 17, 2024, at 11:45 AM, Sokovic, Ana Marija @.**@.>> wrote:

Hello,

We updated drivers to 535 version see attached and privateGPT chat bot opens up. The issue is now that quering a very simple question from a file (attached here) really gives poor results. Please see attached. I would like to to subtract these two numbers.

Next I’m askign it explicitely to subtract those two numbers and than I see Segmentation error. Please see attached.

This was installed like this:

salloc --job-name "InteractiveJob" --cpus-per-task 4 --mem-per-cpu 50gb --time 01:00:10 -p batch_gpu --gres=gpu:1

rm -rf .local .cache /scratch/network/$USER/privateGPT /scratch/network/$USER/tmp mkdir /scratch/network/$USER/tmp export TMPDIR=/scratch/network/$USER/tmp module load Python/3.11.3-GCCcore-12.3.0 pip install --user poetry module load git module load CUDA export PATH=$PATH:/home/$USER/.local/bin export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/home/$USER/.local/lib cd /scratch/network/$USER git clone https://github.com/imartinez/privateGPT.git cd privateGPT/ export PYTHONPATH=$PYTHONPATH:$PWD poetry install --extras "ui llms-llama-cpp embeddings-huggingface vector-stores-qdrant" poetry run python scripts/setup CMAKE_ARGS='-DLLAMA_CUBLAS=on' poetry run pip install --force-reinstall --no-cache-dir llama-cpp-python PGPT_PROFILES=local make run

to run

cd /scratch/network/$USER/privateGPT ./run_gpt.sh

<Screen Shot 2024-04-17 at 11.44.15 AM.png> This was installed with the default LLM model for privateGPT (last week) Please advise,

Thanks Ana <Screen Shot 2024-04-17 at 11.29.58 AM.png> <Screen Shot 2024-04-17 at 11.38.18 AM.png>

On Apr 17, 2024, at 11:21 AM, dosubot[bot] @.**@.>> wrote:

CAUTION: External Sender

Hi, @anamariaUIChttps://github.com/anamariaUIC

I'm helping the LlamaIndex team manage their backlog and am marking this issue as stale. The issue you reported describes a segmentation fault error when using the HuggingFaceEmbedding in a Python script, specifically when running the script via Streamlit on a Mac with at least 250GB of available memory. Disabling the embed_model resolves the issue. There were discussions around potential causes of the error, including issues related to the size of the model and PyTorch's torch.device. Additional inquiries were made about reproducing the issue, CUDA installation conflicting with PyTorch, and the request for a list of required libraries and commands to check the machine's environment.

Could you please confirm if this issue is still relevant to the latest version of the LlamaIndex repository? If it is, kindly let the LlamaIndex team know by commenting on the issue. Otherwise, feel free to close the issue yourself, or it will be automatically closed in 7 days. Thank you!

— Reply to this email directly, view it on GitHubhttps://github.com/run-llama/llama_index/issues/9949#issuecomment-2061701200, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AUHBH5AIZFYUBXAY5BEXJ7LY52OO3AVCNFSM6AAAAABBT5P3Y2VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDANRRG4YDCMRQGA. You are receiving this because you were mentioned.Message ID: @.***>

This email originated from outside the University of Illinois System. Use caution when replying, clicking links, or opening attachments. DO NOT reply to any requests asking you to reply from a personal account or SMS.

dosubot[bot] commented 7 months ago

To address the issues you're encountering with privateGPT, including poor performance and a segmentation fault when querying simple questions from a file, consider the following steps:

  1. Memory and Resources: Ensure your system has enough memory and resources. Segmentation faults often occur due to memory overuse.

  2. Driver Compatibility: Confirm that the updated drivers (version 535) are compatible with your system and the version of privateGPT you're using.

  3. Request and Response Management: Investigate how requests and responses are managed, especially regarding data handling from attached files. Mismanagement can lead to performance issues and crashes.

  4. Configuration Parameters: Review and adjust configuration parameters like max_tokens, temperature, top_k, top_p, and repetition_penalty for optimal settings.

  5. Debugging: Use logging and debugging tools to trace the execution flow and pinpoint where the segmentation fault occurs.

  6. Dependencies: Ensure all dependencies are up to date and correctly installed. Issues with libraries like requests and sseclient-py can cause unexpected behavior.

  7. Simplified Scenario Testing: Run a simplified version of the operation without file attachments to determine if the problem is related to file handling.

  8. System Logs: Check system logs and error messages for clues about the cause of the segmentation fault.

  9. Fallback Configuration: If the issue persists, consider reverting to a previous stable driver update or privateGPT version while investigating.

For handling PDF files, privateGPT utilizes the PDFNougatOCR class for OCR technology to extract text. If your issue involves PDF file handling, reviewing this class and its methods might provide insights.

These steps are tailored to help troubleshoot and potentially resolve the issues you've described. If you need further assistance, please provide more specific details such as error messages, logs, or scenarios leading to the problems.

Sources

#### About Dosu This response is meant to be useful and save you time. It is **not meant to be a precise solution**, but rather a starting point for your own research. Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant. If you want to continue the conversation, start your reply with @dosu-bot.
anamariaUIC commented 7 months ago

Hello,

Can you please send me a response from an actual developer. I provided so many details in my previous message that this generic response is refering to.

Thanks Ana

On Apr 19, 2024, at 10:08 AM, dosubot[bot] @.**@.>> wrote:

CAUTION: External Sender

To address the issues you're encountering with privateGPT, including poor performance and a segmentation fault when querying simple questions from a file, consider the following steps:

  1. Memory and Resources: Ensure your system has enough memory and resources. Segmentation faults often occur due to memory overuse.

  2. Driver Compatibility: Confirm that the updated drivers (version 535) are compatible with your system and the version of privateGPT you're using.

  3. Request and Response Management: Investigate how requests and responses are managed, especially regarding data handling from attached files. Mismanagement can lead to performance issues and crashes.

  4. Configuration Parameters: Review and adjust configuration parameters like max_tokens, temperature, top_k, top_p, and repetition_penalty for optimal settings.

  5. Debugging: Use logging and debugging tools to trace the execution flow and pinpoint where the segmentation fault occurs.

  6. Dependencies: Ensure all dependencies are up to date and correctly installed. Issues with libraries like requests and sseclient-py can cause unexpected behavior.

  7. Simplified Scenario Testing: Run a simplified version of the operation without file attachments to determine if the problem is related to file handling.

  8. System Logs: Check system logs and error messages for clues about the cause of the segmentation fault.

  9. Fallback Configuration: If the issue persists, consider reverting to a previous stable driver update or privateGPT version while investigating.

For handling PDF files, privateGPT utilizes the PDFNougatOCR class for OCR technology to extract text. If your issue involves PDF file handling, reviewing this class and its methods might provide insights.

These steps are tailored to help troubleshoot and potentially resolve the issues you've described. If you need further assistance, please provide more specific details such as error messages, logs, or scenarios leading to the problems.

Sources

About Dosu

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bothttps://github.com/dosu-bot.

— Reply to this email directly, view it on GitHubhttps://github.com/run-llama/llama_index/issues/9949#issuecomment-2066775204, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AUHBH5G4TWDO5GXJLQS4VXTY6EXOVAVCNFSM6AAAAABBT5P3Y2VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDANRWG43TKMRQGQ. You are receiving this because you were mentioned.Message ID: @.***>

This email originated from outside the University of Illinois System. Use caution when replying, clicking links, or opening attachments. DO NOT reply to any requests asking you to reply from a personal account or SMS.

dosubot[bot] commented 7 months ago

@logan-markewich could you help with this? Ana is seeking assistance from a developer for a specific issue related to privateGPT, including poor performance and a segmentation fault when querying simple questions from a file.

#### About Dosu This response is meant to be useful and save you time. It is **not meant to be a precise solution**, but rather a starting point for your own research. Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant. If you want to continue the conversation, start your reply with @dosu-bot.
anamariaUIC commented 7 months ago

Hello,

Can you please help me with this issue?

Thanks Ana

On Apr 19, 2024, at 12:36 PM, dosubot[bot] @.**@.>> wrote:

CAUTION: External Sender

@logan-markewichhttps://github.com/logan-markewich could you help with this? Ana is seeking assistance from a developer for a specific issue related to privateGPT, including poor performance and a segmentation fault when querying simple questions from a file.

About Dosu

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bothttps://github.com/dosu-bot.

— Reply to this email directly, view it on GitHubhttps://github.com/run-llama/llama_index/issues/9949#issuecomment-2067012888, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AUHBH5EWAIGUKZ3X7DSWTMLY6FI2ZAVCNFSM6AAAAABBT5P3Y2VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDANRXGAYTEOBYHA. You are receiving this because you were mentioned.Message ID: @.***>

This email originated from outside the University of Illinois System. Use caution when replying, clicking links, or opening attachments. DO NOT reply to any requests asking you to reply from a personal account or SMS.

dosubot[bot] commented 7 months ago

@logan-markewich could you please assist Ana with the specific issue she's encountering related to privateGPT, including poor performance and a segmentation fault when querying simple questions from a file? Ana is looking for guidance from a developer on this matter. Thank you.

#### Details **About Dosu** This response is meant to be useful and save you time. It is **not meant to be a precise solution**, but rather a starting point for your own research. Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

To continue the conversation, mention @dosu.

anamariaUIC commented 6 months ago

Hello,

Can you please help me with this segmentation error?

Thanks Ana

On Apr 22, 2024, at 3:22 PM, dosubot[bot] @.**@.>> wrote:

CAUTION: External Sender

@logan-markewichhttps://github.com/logan-markewich could you please assist Ana with the specific issue she's encountering related to privateGPT, including poor performance and a segmentation fault when querying simple questions from a file? Ana is looking for guidance from a developer on this matter. Thank you.

Details

About Dosu This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

To continue the conversation, mention @dosuhttps://github.com/dosu.

— Reply to this email directly, view it on GitHubhttps://github.com/run-llama/llama_index/issues/9949#issuecomment-2070886393, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AUHBH5EEREVDCMSKVKJPM23Y6VWQZAVCNFSM6AAAAABBT5P3Y2VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDANZQHA4DMMZZGM. You are receiving this because you were mentioned.Message ID: @.***>

This email originated from outside the University of Illinois System. Use caution when replying, clicking links, or opening attachments. DO NOT reply to any requests asking you to reply from a personal account or SMS.

dosubot[bot] commented 6 months ago

@logan-markewich could you please assist Ana with the specific issue she's encountering related to privateGPT, including poor performance and a segmentation fault when querying simple questions from a file? Ana is looking for guidance from a developer on this matter. Thank you.

#### Details **About Dosu** This response is meant to be useful and save you time. It is **not meant to be a precise solution**, but rather a starting point for your own research. Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

To continue the conversation, mention @dosu.

anamariaUIC commented 6 months ago

some aditional info:

when I use data.txt documnt to query I get my answers without issues.

When I use Balance_sheet.txt I’m getting: Segmentation fault @.*** (core dumped)

On May 13, 2024, at 10:53 AM, dosubot[bot] @.**@.>> wrote:

CAUTION: External Sender

@logan-markewichhttps://github.com/logan-markewich could you please assist Ana with the specific issue she's encountering related to privateGPT, including poor performance and a segmentation fault when querying simple questions from a file? Ana is looking for guidance from a developer on this matter. Thank you.

Details

About Dosu This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

To continue the conversation, mention @dosuhttps://github.com/dosu.

— Reply to this email directly, view it on GitHubhttps://github.com/run-llama/llama_index/issues/9949#issuecomment-2108080966, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AUHBH5CV4XFT2YF2TTHSHN3ZCDOWPAVCNFSM6AAAAABBT5P3Y2VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDCMBYGA4DAOJWGY. You are receiving this because you were mentioned.Message ID: @.***>

This email originated from outside the University of Illinois System. Use caution when replying, clicking links, or opening attachments. DO NOT reply to any requests asking you to reply from a personal account or SMS.

Accessing Extreme and SABER Computing Resources

  1. Account Setup Before accessing Extreme or SABER, ensure you have an active account. If you don't have an account, please register following the provided guidelines.

  2. Logging In For Windows Users:

    • Use an SSH client to connect.
    • Enter the following command: ssh @. or ssh @. - Replace netid with your UIC NetID.
    • Replace login-node with the appropriate node name (e.g., login-1, login-2). For Linux/MacOS Users:
    • Open the terminal application.
    • Use the same SSH command as above.

  3. Authentication Process

    • Username and Password: Enter your UIC NetID and ACCC common password. - DUO 2-Factor Authentication (2FA):
    • After entering your password, you'll be prompted for a 2FA method.
    • Choose either a phone call, text message, or a Duo Mobile App notification. - For setting up 2FA, visit the provided DUO setup link.

  4. Accessing Compute Nodes

    • Extreme:
    • CPU Nodes: Use login-1 or login-2. - GPU Nodes: Use login-3.
    • SABER:
    • Currently offers CPU only nodes: login-1 and login-2. - GPU nodes are planned for future availability.

  5. SSH Commands for Unix, Linux, macOS Ensure SSH is installed on your system. Run the following commands in your terminal:

    • For Extreme: $ ssh -X login-*.extreme.acer.uic.edu -l netid
    • For SABER: $ ssh -X @.****..acer.uic.edu - Replace netid with your UIC NetID.
    • Replace login-* with the desired login node.
    • Replace with either extreme or saber.

  6. Composition Analysis of Balance Sheet :-

Company Name Volkswagen AG Common Sized Balance Sheet

2020 2021 2022 2020(%) 2021(%) 2022(%) Assets: Current Assets: Cash and MS 55071 62255 66378 11.08 11.78 11.75 Accounts Receivable Net 82816 82807 89758 16.66 15.67 15.89 Inventory 43283 43725 52274 8.71 8.27 9.26 Other Current Assets 13774 11560 15899 2.77 2.19 2.82 Total Current Assets 194944 200347 224309 39.22 37.90 39.72

Long Term Assets:

Prop,Plant and Equip 63884 63695 63890 12.85 12.05 11.31 Other Intangible Assets 67968 77689 83241 13.67 14.70 14.74 Other Long Term Assets 170318 186878 193332 34.26 35.35 34.23 Total Long Term Assets 302170 328262 340463 60.78 62.10 60.28 Total Assets 497114 528609 564772 100.00 100.00 100.00 Liabilities:

Current Liabilities

Other Payable 23017 24238 29474 4.63 4.59 5.22 Short Term Debt 88648 78584 83448 17.83 14.87 14.78 Other Current Liabilities 53745 61571 70070 10.81 11.65 12.41 Total Current Liabilities 165410 164393 182992 33.27 31.10 32.40

Long Term Liabilities Long Term Debt 114809 131618 121737 23.10 24.90 21.56 Other Long Term Liabilites 88112 86444 81716 17.72 16.35 14.47

Total Long Term Liabi 202921 218062 203453 40.82 41.25 36.02 Total Liabilities 368331 382455 386445 74.09 72.35 68.42 Shareholders Equity

Subscribed Capital 1283 1283 1283 0.26 0.24 0.23 Retained Earnings 100772 117342 137267 20.27 22.20 24.30 Other Equity 26728 27529 39777 5.38 5.21 7.04

Total Shareholder's Equity 128783 146154 178327 25.91 27.65 31.58

dosubot[bot] commented 6 months ago

@logan-markewich could you please assist Ana with the specific issue she's encountering related to privateGPT, including poor performance and a segmentation fault when querying simple questions from a file? Ana is looking for guidance from a developer on this matter. Thank you.

#### Details **Sources** - [llama-index-integrations/readers/llama-index-readers-gpt-repo/llama_index/readers/gpt_repo/base.py](https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/readers/llama-index-readers-gpt-repo/llama_index/readers/gpt_repo/base.py) - [llama-index-integrations/readers/llama-index-readers-semanticscholar/tests/test.py](https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/readers/llama-index-readers-semanticscholar/tests/test.py) - [llama-index-core/llama_index/core/langchain_helpers/memory_wrapper.py](https://github.com/run-llama/llama_index/blob/main/llama-index-core/llama_index/core/langchain_helpers/memory_wrapper.py)
**About Dosu** This response is meant to be useful and save you time. It is **not meant to be a precise solution**, but rather a starting point for your own research. Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

To continue the conversation, mention @dosu.