Error when running the indexing example about ragatouille

[VidyasagarDudekula]

Hi for now I have a workaround solution, please try to add this:

if __name__ == '__main__':
    main() #your main code

my code:-

from ragatouille import RAGPretrainedModel
import requests
def run():
    RAG = RAGPretrainedModel.from_pretrained("colbert-ir/colbertv2.0")
    def get_wikipedia_page(title: str):
        """
        Retrieve the full text content of a Wikipedia page.

        :param title: str - Title of the Wikipedia page.
        :return: str - Full text content of the page as raw string.
        """
        # Wikipedia API endpoint
        URL = "https://en.wikipedia.org/w/api.php"

        # Parameters for the API request
        params = {
            "action": "query",
            "format": "json",
            "titles": title,
            "prop": "extracts",
            "explaintext": True,
        }
        # Custom User-Agent header to comply with Wikipedia's best practices
        headers = {"User-Agent": "RAGatouille_tutorial/0.0.1 ([email protected])"}

        response = requests.get(URL, params=params, headers=headers)
        data = response.json()

        # Extracting page content
        page = next(iter(data["query"]["pages"].values()))
        return page["extract"] if "extract" in page else None
    full_document = get_wikipedia_page("Hayao_Miyazaki")
    RAG.index(
        collection=[full_document],
        index_name="Miyazaki-1234",
        max_document_length=180,
        split_documents=True,
    )
    results = RAG.search(query="What animation studio did Miyazaki found?", k=3)
    print(results)
if __name__ == '__main__':
    run()

[excubo-jg]

Reinstalling the environment solved the issue

[bclavie]

Hey! Thank you for flagging, this is helping track down what's causing a stream of new problems.

This being a multiprocessing error, I believe it could be related to the recent changes around multiprocessing in upstream ColBERT. Tagging @Anmol6 who's leading the work on this -- that might have to be tweaked or reverted as it seems to have caused a lot of unexpected issues.

@excubo-jg, would you be able to try with the previous version of ColBERT to check if it works fine? pip uninstall colbert-ai && pip install colbert-ai==0.2.16.

[excubo-jg]

@bclavie I tried but this did not change the outcome

[sway4em]

I'm having a similar issue, on M2.

❯ python3 main.py
[Jan 17, 23:40:44] Loading segmented_maxsim_cpp extension (set COLBERT_LOAD_TORCH_EXTENSION_VERBOSE=True for more info)...
/Users/swayamchidrawar/anaconda3/lib/python3.11/site-packages/torch/cuda/amp/grad_scaler.py:125: UserWarning: torch.cuda.amp.GradScaler is enabled, but CUDA is not available.  Disabling.
  warnings.warn(


[Jan 17, 23:40:51] #> Note: Output directory .ragatouille/colbert/indexes/my_index already exists


[Jan 17, 23:40:55] Loading segmented_maxsim_cpp extension (set COLBERT_LOAD_TORCH_EXTENSION_VERBOSE=True for more info)...
/Users/swayamchidrawar/anaconda3/lib/python3.11/site-packages/torch/cuda/amp/grad_scaler.py:125: UserWarning: torch.cuda.amp.GradScaler is enabled, but CUDA is not available.  Disabling.
  warnings.warn(


[Jan 17, 23:40:56] #> Note: Output directory .ragatouille/colbert/indexes/my_index already exists


Traceback (most recent call last):
  File "<string>", line 1, in <module>
  File "/Users/swayamchidrawar/anaconda3/lib/python3.11/multiprocessing/spawn.py", line 122, in spawn_main
    exitcode = _main(fd, parent_sentinel)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/swayamchidrawar/anaconda3/lib/python3.11/multiprocessing/spawn.py", line 131, in _main
    prepare(preparation_data)
  File "/Users/swayamchidrawar/anaconda3/lib/python3.11/multiprocessing/spawn.py", line 246, in prepare
    _fixup_main_from_path(data['init_main_from_path'])
  File "/Users/swayamchidrawar/anaconda3/lib/python3.11/multiprocessing/spawn.py", line 297, in _fixup_main_from_path
    main_content = runpy.run_path(main_path,
                   ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "<frozen runpy>", line 291, in run_path
  File "<frozen runpy>", line 98, in _run_module_code
  File "<frozen runpy>", line 88, in _run_code
  File "/Users/swayamchidrawar/repos/ragtest/main.py", line 10, in <module>
    index_path = RAG.index(index_name="my_index", collection=my_documents)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/swayamchidrawar/anaconda3/lib/python3.11/site-packages/ragatouille/RAGPretrainedModel.py", line 125, in index
    return self.model.index(
           ^^^^^^^^^^^^^^^^^
  File "/Users/swayamchidrawar/anaconda3/lib/python3.11/site-packages/ragatouille/models/colbert.py", line 204, in index
    self.indexer.index(
  File "/Users/swayamchidrawar/anaconda3/lib/python3.11/site-packages/colbert/indexer.py", line 78, in index
    self.__launch(collection)
  File "/Users/swayamchidrawar/anaconda3/lib/python3.11/site-packages/colbert/indexer.py", line 83, in __launch
    manager = mp.Manager()
              ^^^^^^^^^^^^
  File "/Users/swayamchidrawar/anaconda3/lib/python3.11/multiprocessing/context.py", line 57, in Manager
    m.start()
  File "/Users/swayamchidrawar/anaconda3/lib/python3.11/multiprocessing/managers.py", line 563, in start
    self._process.start()
  File "/Users/swayamchidrawar/anaconda3/lib/python3.11/multiprocessing/process.py", line 121, in start
    self._popen = self._Popen(self)
                  ^^^^^^^^^^^^^^^^^
  File "/Users/swayamchidrawar/anaconda3/lib/python3.11/multiprocessing/context.py", line 288, in _Popen
    return Popen(process_obj)
           ^^^^^^^^^^^^^^^^^^
  File "/Users/swayamchidrawar/anaconda3/lib/python3.11/multiprocessing/popen_spawn_posix.py", line 32, in __init__
    super().__init__(process_obj)
  File "/Users/swayamchidrawar/anaconda3/lib/python3.11/multiprocessing/popen_fork.py", line 19, in __init__
    self._launch(process_obj)
  File "/Users/swayamchidrawar/anaconda3/lib/python3.11/multiprocessing/popen_spawn_posix.py", line 42, in _launch
    prep_data = spawn.get_preparation_data(process_obj._name)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/swayamchidrawar/anaconda3/lib/python3.11/multiprocessing/spawn.py", line 164, in get_preparation_data
    _check_not_importing_main()
  File "/Users/swayamchidrawar/anaconda3/lib/python3.11/multiprocessing/spawn.py", line 140, in _check_not_importing_main
    raise RuntimeError('''
RuntimeError: 
        An attempt has been made to start a new process before the
        current process has finished its bootstrapping phase.

        This probably means that you are not using fork to start your
        child processes and you have forgotten to use the proper idiom
        in the main module:

            if __name__ == '__main__':
                freeze_support()
                ...

        The "freeze_support()" line can be omitted if the program
        is not going to be frozen to produce an executable.

        To fix this issue, refer to the "Safe importing of main module"
        section in https://docs.python.org/3/library/multiprocessing.html
        
Traceback (most recent call last):
  File "/Users/swayamchidrawar/repos/ragtest/main.py", line 10, in <module>
    index_path = RAG.index(index_name="my_index", collection=my_documents)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/swayamchidrawar/anaconda3/lib/python3.11/site-packages/ragatouille/RAGPretrainedModel.py", line 125, in index
    return self.model.index(
           ^^^^^^^^^^^^^^^^^
  File "/Users/swayamchidrawar/anaconda3/lib/python3.11/site-packages/ragatouille/models/colbert.py", line 204, in index
    self.indexer.index(
  File "/Users/swayamchidrawar/anaconda3/lib/python3.11/site-packages/colbert/indexer.py", line 78, in index
    self.__launch(collection)
  File "/Users/swayamchidrawar/anaconda3/lib/python3.11/site-packages/colbert/indexer.py", line 83, in __launch
    manager = mp.Manager()
              ^^^^^^^^^^^^
  File "/Users/swayamchidrawar/anaconda3/lib/python3.11/multiprocessing/context.py", line 57, in Manager
    m.start()
  File "/Users/swayamchidrawar/anaconda3/lib/python3.11/multiprocessing/managers.py", line 567, in start
    self._address = reader.recv()
                    ^^^^^^^^^^^^^
  File "/Users/swayamchidrawar/anaconda3/lib/python3.11/multiprocessing/connection.py", line 249, in recv
    buf = self._recv_bytes()
          ^^^^^^^^^^^^^^^^^^
  File "/Users/swayamchidrawar/anaconda3/lib/python3.11/multiprocessing/connection.py", line 413, in _recv_bytes
    buf = self._recv(4)
          ^^^^^^^^^^^^^
  File "/Users/swayamchidrawar/anaconda3/lib/python3.11/multiprocessing/connection.py", line 382, in _recv
    raise EOFError
EOFError

[bclavie]

Hey,

Appreciate the feedback guys! I've got less time than I'd like to track it down (and big thanks to @Anmol6 for helping) because of health, but so far we're strongly suspecting a dependency issue and are trying to pinpoint exactly why it only happens to a (currently seemingly) random subset of users.

Would you be able to:

• Try once again with a downgraded Colbert version, to 0.2.15 this time? (pip uninstall --y colbert-ai && pip install colbert-ai==0.2.15)
• Could you send us your full pip freeze? Via https://pastebin.com if possible!

Thanks a lot

[excubo-jg]

Oh, sorry to hear that. I hope you get well soon!

• downgrade down to .15 has no impact

here is the output from pip freeze:
aiohttp==3.9.1
aiosignal==1.3.1
annotated-types==0.6.0
anyio==4.2.0
attrs==23.2.0
beautifulsoup4==4.12.2
bitarray==2.9.2
blinker==1.7.0
blis==0.7.11
catalogue==2.0.10
certifi==2023.11.17
charset-normalizer==3.3.2
click==8.1.7
cloudpathlib==0.16.0
colbert-ai==0.2.17
confection==0.1.4
cymem==2.0.8
dataclasses-json==0.6.3
datasets==2.16.1
Deprecated==1.2.14
dill==0.3.7
distro==1.9.0
faiss-cpu==1.7.4
filelock==3.13.1
Flask==3.0.0
frozenlist==1.4.1
fsspec==2023.10.0
git-python==1.0.3
gitdb==4.0.11
GitPython==3.1.41
greenlet==3.0.3
h11==0.14.0
httpcore==1.0.2
httpx==0.26.0
huggingface-hub==0.20.2
idna==3.6
itsdangerous==2.1.2
Jinja2==3.1.3
joblib==1.3.2
jsonpatch==1.33
jsonpointer==2.4
langchain==0.1.0
langchain-community==0.0.13
langchain-core==0.1.11
langcodes==3.3.0
langsmith==0.0.80
llama-index==0.9.32
MarkupSafe==2.1.3
marshmallow==3.20.2
mpmath==1.3.0
multidict==6.0.4
multiprocess==0.70.15
murmurhash==1.0.10
mypy-extensions==1.0.0
nest-asyncio==1.5.9
networkx==3.2.1
ninja==1.11.1.1
nltk==3.8.1
numpy==1.26.3
nvidia-cublas-cu12==12.1.3.1
nvidia-cuda-cupti-cu12==12.1.105
nvidia-cuda-nvrtc-cu12==12.1.105
nvidia-cuda-runtime-cu12==12.1.105
nvidia-cudnn-cu12==8.9.2.26
nvidia-cufft-cu12==11.0.2.54
nvidia-curand-cu12==10.3.2.106
nvidia-cusolver-cu12==11.4.5.107
nvidia-cusparse-cu12==12.1.0.106
nvidia-nccl-cu12==2.18.1
nvidia-nvjitlink-cu12==12.3.101
nvidia-nvtx-cu12==12.1.105
onnx==1.15.0
openai==1.7.2
packaging==23.2
pandas==2.1.4
pillow==10.2.0
preshed==3.0.9
protobuf==4.25.2
psutil==5.9.7
pyarrow==14.0.2
pyarrow-hotfix==0.6
pydantic==2.5.3
pydantic_core==2.14.6
python-dateutil==2.8.2
python-dotenv==1.0.0
pytz==2023.3.post1
PyYAML==6.0.1
RAGatouille==0.0.4b2
regex==2023.12.25
requests==2.31.0
ruff==0.1.13
safetensors==0.4.1
scikit-learn==1.3.2
scipy==1.11.4
sentence-transformers==2.2.2
sentencepiece==0.1.99
six==1.16.0
smart-open==6.4.0
smmap==5.0.1
sniffio==1.3.0
soupsieve==2.5
spacy==3.7.2
spacy-legacy==3.0.12
spacy-loggers==1.0.5
SQLAlchemy==2.0.25
srsly==2.4.8
sympy==1.12
tenacity==8.2.3
thinc==8.2.2
threadpoolctl==3.2.0
tiktoken==0.5.2
tokenizers==0.15.0
torch==2.1.2
torchvision==0.16.2
tqdm==4.66.1
transformers==4.36.2
triton==2.1.0
typer==0.9.0
typing-inspect==0.9.0
typing_extensions==4.9.0
tzdata==2023.4
ujson==5.9.0
urllib3==2.1.0
voyager==2.0.2
wasabi==1.1.2
weasel==0.3.4
Werkzeug==3.0.1
wrapt==1.16.0
xxhash==3.4.1
yarl==1.9.4

[sway4em]

Hey,

Appreciate the feedback guys! I've got less time than I'd like to track it down (and big thanks to @Anmol6 for helping) because of health, but so far we're strongly suspecting a dependency issue and are trying to pinpoint exactly why it only happens to a (currently seemingly) random subset of users.

Would you be able to:

• Try once again with a downgraded Colbert version, to 0.2.15 this time? (pip uninstall --y colbert-ai && pip install colbert-ai==0.2.15)
• Could you send us your full pip freeze? Via https://pastebin.com if possible!

Thanks a lot

https://pastebin.com/L7gPAT5a

[GMartin-dev]

+1 to this i'm experiencing a similar issue on Ubuntu 22.04 + langchain, but I was trying the library apart from the langchain integration too.
If this detail helps narrowing this down:
On memory indexing and Rerank works, the problem is creating the index files it seems that flow gets interrupted

[bjsi]

@VidyasagarDudekula Nice, this worked for me 👍

[excubo-jg]

I just checked with the current version and the error persists.

@VidyasagarDudekula describes how to fix https://python.langchain.com/docs/integrations/retrievers/ragatouille which is not the indexing example.

[Anmol6]

@excubo-jg could you try again with the newer version?

[excubo-jg]

Did try with 6b0 and still got the same error