search

langchain-ai / langchain

🦜🔗 Build context-aware reasoning applications
https://python.langchain.com
MIT License
95.74k stars 15.55k forks source link

Issue: <CSVLoader can't load> #15192

Closed AidPaike closed 11 months ago

AidPaike commented 11 months ago

Issue you'd like to raise.

why CSVLoader can't load? error:

AttributeError Traceback (most recent call last) Cell In[25], line 1 ----> 1 from langchain.document_loaders.csv_loader import CSVLoader 3 loader = CSVLoader(file_path='./data/bugreport.csv', csv_args={ 4 'delimiter': ',', 5 'quotechar': '"', 6 'fieldnames': ["URL","Resolved","Backport_of","Submitted","Status","CPU","Priority","Sub_Component","Updated","Fix_Versions","Affected_Version","OS","Type","Resolution","Component"] 7 }) 9 data = loader.load()

File D:\miniconda\lib\site-packages\langchain\document_loaders__init__.py:49 47 from langchain.document_loaders.bigquery import BigQueryLoader 48 from langchain.document_loaders.bilibili import BiliBiliLoader ---> 49 from langchain.document_loaders.blackboard import BlackboardLoader 50 from langchain.document_loaders.blob_loaders import ( 51 Blob, 52 BlobLoader, 53 FileSystemBlobLoader, 54 YoutubeAudioLoader, 55 ) 56 from langchain.document_loaders.blockchain import BlockchainDocumentLoader

File D:\miniconda\lib\site-packages\langchain\document_loaders\blackboard.py:1 ----> 1 from langchain_community.document_loaders.blackboard import BlackboardLoader 3 all = ["BlackboardLoader"]

File D:\miniconda\lib\site-packages\langchain_community\document_loaders__init__.py:51 49 from langchain_community.document_loaders.bigquery import BigQueryLoader 50 from langchain_community.document_loaders.bilibili import BiliBiliLoader ---> 51 from langchain_community.document_loaders.blackboard import BlackboardLoader 52 from langchain_community.document_loaders.blob_loaders import ( 53 Blob, 54 BlobLoader, 55 FileSystemBlobLoader, 56 YoutubeAudioLoader, 57 ) 58 from langchain_community.document_loaders.blockchain import BlockchainDocumentLoader

File D:\miniconda\lib\site-packages\langchain_community\document_loaders\blackboard.py:10 7 from langchain_core.documents import Document 9 from langchain_community.document_loaders.directory import DirectoryLoader ---> 10 from langchain_community.document_loaders.pdf import PyPDFLoader 11 from langchain_community.document_loaders.web_base import WebBaseLoader 14 class BlackboardLoader(WebBaseLoader):

File D:\miniconda\lib\site-packages\langchain_community\document_loaders\pdf.py:18 16 from langchain_community.document_loaders.base import BaseLoader 17 from langchain_community.document_loaders.blob_loaders import Blob ---> 18 from langchain_community.document_loaders.parsers.pdf import ( 19 AmazonTextractPDFParser, 20 DocumentIntelligenceParser, 21 PDFMinerParser, 22 PDFPlumberParser, 23 PyMuPDFParser, 24 PyPDFium2Parser, 25 PyPDFParser, 26 ) 27 from langchain_community.document_loaders.unstructured import UnstructuredFileLoader 29 logger = logging.getLogger(file)

File D:\miniconda\lib\site-packages\langchain_community\document_loaders\parsers__init.py:5 3 from langchain_community.document_loaders.parsers.grobid import GrobidParser 4 from langchain_community.document_loaders.parsers.html import BS4HTMLParser ----> 5 from langchain_community.document_loaders.parsers.language import LanguageParser 6 from langchain_community.document_loaders.parsers.pdf import ( 7 PDFMinerParser, 8 PDFPlumberParser, (...) 11 PyPDFParser, 12 ) 14 all__ = [ 15 "BS4HTMLParser", 16 "DocAIParser", (...) 24 "PyPDFParser", 25 ]

File D:\miniconda\lib\site-packages\langchain_community\document_loaders\parsers\language__init__.py:1 ----> 1 from langchain_community.document_loaders.parsers.language.language_parser import ( 2 LanguageParser, 3 ) 5 all = ["LanguageParser"]

File D:\miniconda\lib\site-packages\langchain_community\document_loaders\parsers\language\language_parser.py:24 18 try: 19 from langchain.text_splitter import Language 21 LANGUAGE_EXTENSIONS: Dict[str, str] = { 22 "py": Language.PYTHON, 23 "js": Language.JS, ---> 24 "cobol": Language.COBOL, 25 } 27 LANGUAGE_SEGMENTERS: Dict[str, Any] = { 28 Language.PYTHON: PythonSegmenter, 29 Language.JS: JavaScriptSegmenter, 30 Language.COBOL: CobolSegmenter, 31 } 32 except ImportError:

File D:\miniconda\lib\enum.py:437, in EnumMeta.getattr(cls, name) 435 return cls._membermap[name] 436 except KeyError: --> 437 raise AttributeError(name) from None

AttributeError: COBOL

Suggestion:

No response

dosubot[bot] commented 11 months ago

🤖

Hello @AidPaike,

Welcome! I'm Dosu, an AI here to assist you with bugs, answer your questions, and help you become a better contributor while we wait for a human maintainer. I understand you're having an issue with CSVLoader, don't worry, I'm going to look into this and will provide you with an answer shortly.

AidPaike commented 11 months ago

Issue you'd like to raise.

why CSVLoader can't load? error:

AttributeError Traceback (most recent call last) Cell In[25], line 1 ----> 1 from langchain.document_loaders.csv_loader import CSVLoader 3 loader = CSVLoader(file_path='./data/bugreport.csv', csv_args={ 4 'delimiter': ',', 5 'quotechar': '"', 6 'fieldnames': ["URL","Resolved","Backport_of","Submitted","Status","CPU","Priority","Sub_Component","Updated","Fix_Versions","Affected_Version","OS","Type","Resolution","Component"] 7 }) 9 data = loader.load()

File D:\miniconda\lib\site-packages\langchain\document_loadersinit.py:49 47 from langchain.document_loaders.bigquery import BigQueryLoader 48 from langchain.document_loaders.bilibili import BiliBiliLoader ---> 49 from langchain.document_loaders.blackboard import BlackboardLoader 50 from langchain.document_loaders.blob_loaders import ( 51 Blob, 52 BlobLoader, 53 FileSystemBlobLoader, 54 YoutubeAudioLoader, 55 ) 56 from langchain.document_loaders.blockchain import BlockchainDocumentLoader

File D:\miniconda\lib\site-packages\langchain\document_loaders\blackboard.py:1 ----> 1 from langchain_community.document_loaders.blackboard import BlackboardLoader 3 all = ["BlackboardLoader"]

File D:\miniconda\lib\site-packages\langchain_community\document_loadersinit.py:51 49 from langchain_community.document_loaders.bigquery import BigQueryLoader 50 from langchain_community.document_loaders.bilibili import BiliBiliLoader ---> 51 from langchain_community.document_loaders.blackboard import BlackboardLoader 52 from langchain_community.document_loaders.blob_loaders import ( 53 Blob, 54 BlobLoader, 55 FileSystemBlobLoader, 56 YoutubeAudioLoader, 57 ) 58 from langchain_community.document_loaders.blockchain import BlockchainDocumentLoader

File D:\miniconda\lib\site-packages\langchain_community\document_loaders\blackboard.py:10 7 from langchain_core.documents import Document 9 from langchain_community.document_loaders.directory import DirectoryLoader ---> 10 from langchain_community.document_loaders.pdf import PyPDFLoader 11 from langchain_community.document_loaders.web_base import WebBaseLoader 14 class BlackboardLoader(WebBaseLoader):

File D:\miniconda\lib\site-packages\langchain_community\document_loaders\pdf.py:18 16 from langchain_community.document_loaders.base import BaseLoader 17 from langchain_community.document_loaders.blob_loaders import Blob ---> 18 from langchain_community.document_loaders.parsers.pdf import ( 19 AmazonTextractPDFParser, 20 DocumentIntelligenceParser, 21 PDFMinerParser, 22 PDFPlumberParser, 23 PyMuPDFParser, 24 PyPDFium2Parser, 25 PyPDFParser, 26 ) 27 from langchain_community.document_loaders.unstructured import UnstructuredFileLoader 29 logger = logging.getLogger(file)

File D:\miniconda\lib\site-packages\langchain_community\document_loaders\parsersinit.py:5 3 from langchain_community.document_loaders.parsers.grobid import GrobidParser 4 from langchain_community.document_loaders.parsers.html import BS4HTMLParser ----> 5 from langchain_community.document_loaders.parsers.language import LanguageParser 6 from langchain_community.document_loaders.parsers.pdf import ( 7 PDFMinerParser, 8 PDFPlumberParser, (...) 11 PyPDFParser, 12 ) 14 all = [ 15 "BS4HTMLParser", 16 "DocAIParser", (...) 24 "PyPDFParser", 25 ]

File D:\miniconda\lib\site-packages\langchain_community\document_loaders\parsers\languageinit.py:1 ----> 1 from langchain_community.document_loaders.parsers.language.language_parser import ( 2 LanguageParser, 3 ) 5 all = ["LanguageParser"]

File D:\miniconda\lib\site-packages\langchain_community\document_loaders\parsers\language\language_parser.py:24 18 try: 19 from langchain.text_splitter import Language 21 LANGUAGE_EXTENSIONS: Dict[str, str] = { 22 "py": Language.PYTHON, 23 "js": Language.JS, ---> 24 "cobol": Language.COBOL, 25 } 27 LANGUAGE_SEGMENTERS: Dict[str, Any] = { 28 Language.PYTHON: PythonSegmenter, 29 Language.JS: JavaScriptSegmenter, 30 Language.COBOL: CobolSegmenter, 31 } 32 except ImportError:

File D:\miniconda\lib\enum.py:437, in EnumMeta.getattr(cls, name) 435 return cls._membermap[name] 436 except KeyError: --> 437 raise AttributeError(name) from None

AttributeError: COBOL

Suggestion:

No response

langchain 0.0.352

AidPaike commented 11 months ago

QAQ After reloading the Jupyter server, the error no longer persists.

sabatale commented 11 months ago

v0.1.0 fixed the issue for us.

1-0-Bhoomeendra commented 11 months ago

I am having similar Issue. I have restarted the notebook but still its not working. langchain 0.0.309 langchain-community 0.0.10 langchain-core 0.1.8 Python 3.8.10

from langchain_community.document_loaders import TextLoader

loader = TextLoader("data/data.txt")

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
Cell In[16], line 1
----> 1 from langchain_community.document_loaders import TextLoader
      3 loader = TextLoader("data/data.txt")

File ~/venvs/global/lib/python3.8/site-packages/langchain_community/document_loaders/__init__.py:51
     49 from langchain_community.document_loaders.bigquery import BigQueryLoader
     50 from langchain_community.document_loaders.bilibili import BiliBiliLoader
---> 51 from langchain_community.document_loaders.blackboard import BlackboardLoader
     52 from langchain_community.document_loaders.blob_loaders import (
     53     Blob,
     54     BlobLoader,
     55     FileSystemBlobLoader,
     56     YoutubeAudioLoader,
     57 )
     58 from langchain_community.document_loaders.blockchain import BlockchainDocumentLoader

File ~/venvs/global/lib/python3.8/site-packages/langchain_community/document_loaders/blackboard.py:10
      7 from langchain_core.documents import Document
      9 from langchain_community.document_loaders.directory import DirectoryLoader
---> 10 from langchain_community.document_loaders.pdf import PyPDFLoader
     11 from langchain_community.document_loaders.web_base import WebBaseLoader
     14 class BlackboardLoader(WebBaseLoader):

File ~/venvs/global/lib/python3.8/site-packages/langchain_community/document_loaders/pdf.py:18
     16 from langchain_community.document_loaders.base import BaseLoader
     17 from langchain_community.document_loaders.blob_loaders import Blob
---> 18 from langchain_community.document_loaders.parsers.pdf import (
     19     AmazonTextractPDFParser,
     20     DocumentIntelligenceParser,
     21     PDFMinerParser,
     22     PDFPlumberParser,
     23     PyMuPDFParser,
     24     PyPDFium2Parser,
     25     PyPDFParser,
     26 )
     27 from langchain_community.document_loaders.unstructured import UnstructuredFileLoader
     29 logger = logging.getLogger(__file__)

File ~/venvs/global/lib/python3.8/site-packages/langchain_community/document_loaders/parsers/__init__.py:8
      6 from langchain_community.document_loaders.parsers.grobid import GrobidParser
      7 from langchain_community.document_loaders.parsers.html import BS4HTMLParser
----> 8 from langchain_community.document_loaders.parsers.language import LanguageParser
      9 from langchain_community.document_loaders.parsers.pdf import (
     10     PDFMinerParser,
     11     PDFPlumberParser,
   (...)
     14     PyPDFParser,
     15 )
     17 __all__ = [
     18     "AzureAIDocumentIntelligenceParser",
     19     "BS4HTMLParser",
   (...)
     28     "PyPDFParser",
     29 ]

File ~/venvs/global/lib/python3.8/site-packages/langchain_community/document_loaders/parsers/language/__init__.py:1
----> 1 from langchain_community.document_loaders.parsers.language.language_parser import (
      2     LanguageParser,
      3 )
      5 __all__ = ["LanguageParser"]

File ~/venvs/global/lib/python3.8/site-packages/langchain_community/document_loaders/parsers/language/language_parser.py:24
     18 try:
     19     from langchain.text_splitter import Language
     21     LANGUAGE_EXTENSIONS: Dict[str, str] = {
     22         "py": Language.PYTHON,
     23         "js": Language.JS,
---> 24         "cobol": Language.COBOL,
     25     }
     27     LANGUAGE_SEGMENTERS: Dict[str, Any] = {
     28         Language.PYTHON: PythonSegmenter,
     29         Language.JS: JavaScriptSegmenter,
     30         Language.COBOL: CobolSegmenter,
     31     }
     32 except ImportError:

File /usr/lib/python3.8/enum.py:384, in EnumMeta.__getattr__(cls, name)
    382     return cls._member_map_[name]
    383 except KeyError:
--> 384     raise AttributeError(name) from None

AttributeError: COBOL
gokcenazakyol commented 10 months ago

I am having similar Issue. I have restarted the notebook but still its not working. langchain 0.0.309 langchain-community 0.0.10 langchain-core 0.1.8 Python 3.8.10

from langchain_community.document_loaders import TextLoader

loader = TextLoader("data/data.txt")

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
Cell In[16], line 1
----> 1 from langchain_community.document_loaders import TextLoader
      3 loader = TextLoader("data/data.txt")

File ~/venvs/global/lib/python3.8/site-packages/langchain_community/document_loaders/__init__.py:51
     49 from langchain_community.document_loaders.bigquery import BigQueryLoader
     50 from langchain_community.document_loaders.bilibili import BiliBiliLoader
---> 51 from langchain_community.document_loaders.blackboard import BlackboardLoader
     52 from langchain_community.document_loaders.blob_loaders import (
     53     Blob,
     54     BlobLoader,
     55     FileSystemBlobLoader,
     56     YoutubeAudioLoader,
     57 )
     58 from langchain_community.document_loaders.blockchain import BlockchainDocumentLoader

File ~/venvs/global/lib/python3.8/site-packages/langchain_community/document_loaders/blackboard.py:10
      7 from langchain_core.documents import Document
      9 from langchain_community.document_loaders.directory import DirectoryLoader
---> 10 from langchain_community.document_loaders.pdf import PyPDFLoader
     11 from langchain_community.document_loaders.web_base import WebBaseLoader
     14 class BlackboardLoader(WebBaseLoader):

File ~/venvs/global/lib/python3.8/site-packages/langchain_community/document_loaders/pdf.py:18
     16 from langchain_community.document_loaders.base import BaseLoader
     17 from langchain_community.document_loaders.blob_loaders import Blob
---> 18 from langchain_community.document_loaders.parsers.pdf import (
     19     AmazonTextractPDFParser,
     20     DocumentIntelligenceParser,
     21     PDFMinerParser,
     22     PDFPlumberParser,
     23     PyMuPDFParser,
     24     PyPDFium2Parser,
     25     PyPDFParser,
     26 )
     27 from langchain_community.document_loaders.unstructured import UnstructuredFileLoader
     29 logger = logging.getLogger(__file__)

File ~/venvs/global/lib/python3.8/site-packages/langchain_community/document_loaders/parsers/__init__.py:8
      6 from langchain_community.document_loaders.parsers.grobid import GrobidParser
      7 from langchain_community.document_loaders.parsers.html import BS4HTMLParser
----> 8 from langchain_community.document_loaders.parsers.language import LanguageParser
      9 from langchain_community.document_loaders.parsers.pdf import (
     10     PDFMinerParser,
     11     PDFPlumberParser,
   (...)
     14     PyPDFParser,
     15 )
     17 __all__ = [
     18     "AzureAIDocumentIntelligenceParser",
     19     "BS4HTMLParser",
   (...)
     28     "PyPDFParser",
     29 ]

File ~/venvs/global/lib/python3.8/site-packages/langchain_community/document_loaders/parsers/language/__init__.py:1
----> 1 from langchain_community.document_loaders.parsers.language.language_parser import (
      2     LanguageParser,
      3 )
      5 __all__ = ["LanguageParser"]

File ~/venvs/global/lib/python3.8/site-packages/langchain_community/document_loaders/parsers/language/language_parser.py:24
     18 try:
     19     from langchain.text_splitter import Language
     21     LANGUAGE_EXTENSIONS: Dict[str, str] = {
     22         "py": Language.PYTHON,
     23         "js": Language.JS,
---> 24         "cobol": Language.COBOL,
     25     }
     27     LANGUAGE_SEGMENTERS: Dict[str, Any] = {
     28         Language.PYTHON: PythonSegmenter,
     29         Language.JS: JavaScriptSegmenter,
     30         Language.COBOL: CobolSegmenter,
     31     }
     32 except ImportError:

File /usr/lib/python3.8/enum.py:384, in EnumMeta.__getattr__(cls, name)
    382     return cls._member_map_[name]
    383 except KeyError:
--> 384     raise AttributeError(name) from None

AttributeError: COBOL

same here. Any solution?

ShaneJIan commented 10 months ago

Python 3.9.12
from langchain_community.document_loaders import JSONLoader

raise AttributeError(name) from None AttributeError: COBOL

Anyone knows how to fix this?

kdsharmaai commented 10 months ago

Same issue while only importing "UnstructuredURLLoader" Checking in JP notebook with Anaconda (Windows 11) (Working fine in PyCharm, Individual setup for same machine)

from langchain_community.document_loaders import UnstructuredURLLoader

~\anaconda3\lib\enum.py in __getattr__(cls, name)
    427             return cls._member_map_[name]
    428         except KeyError:
--> 429             raise AttributeError(name) from None
    430 
    431     def __getitem__(cls, name):

AttributeError: COBOL
ajithkumar666 commented 9 months ago

I have same issue , I just upgrade langchain package and it worked for me pip3 install --upgrade langchain