does CSVReader exist in llama

COdXG · 2024-02-21T20:22:36.015Z

does CSVReader exist in llama_index:from llama_index.core.readers import CSVReader

from llama_index.readers.file import CSVReader

thanks G

@Logan M is this right way of importing this:
from llama_index.core.storage import StorageContext, VectorStoreIndex, load_index_from_storage

LLogan M

Negatory

LLogan M

Remove .storage from the import path

CCOdXG

am getting this error for hours any help annoying errorrrs :(!)

Traceback (most recent call last):
  File "/Users/ahmednadiir/Desktop/agency/app.py", line 11, in <module>
    from quran import quran_engine
  File "/Users/ahmednadiir/Desktop/agency/quran.py", line 21, in <module>
    quran_csv = CSVReader().load_data(file=csv_path);
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/ahmednadiir/Desktop/agency/localEvir/lib/python3.11/site-packages/llama_index/readers/file/tabular/base.py", line 48, in load_data
    return [Document(text="\n".join(text_list), metadata=extra_info)]
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/ahmednadiir/Desktop/agency/localEvir/lib/python3.11/site-packages/pydantic/v1/main.py", line 341, in __init__
    raise validation_error
pydantic.v1.error_wrappers.ValidationError: 1 validation error for Document
extra_info
  none is not an allowed value (type=type_error.none.not_allowed)

my code:

import os
from llama_index.core import StorageContext, VectorStoreIndex, load_index_from_storage
from llama_index.readers.file import CSVReader

def get_index(data, index_name):
    index = None
    if not os.path.exists(index_name):
        print("building index", index_name)
        index = VectorStoreIndex.from_documents(data, show_progress=True)
        index.storage_context.persist(persist_dir=index_name)
    else:
        index = load_index_from_storage(
            StorageContext.from_defaults(persist_dir=index_name)
        )

    return index

csv_path = os.path.join("data", "quran-english-tafsir.csv");
quran_csv = CSVReader().load_data(file=csv_path);
quran_index = get_index(quran_csv, "quran")
quran_engine = quran_index.as_query_engine()
quran_engine.query()

CCOdXG

@Logan M

Find answers from the community

does CSVReader exist in llama_index: