Error running L4-QnA cell number 5

Trying to run above notebook cell 5. Have installed docarray and restarted kernel.

index = VectorstoreIndexCreator(
vectorstore_cls=DocArrayInMemorySearch
).from_loaders([loader])

Getting following error:

UnicodeDecodeError Traceback (most recent call last)
Cell In[5], line 3
1 index = VectorstoreIndexCreator(
2 vectorstore_cls=DocArrayInMemorySearch
----> 3 ).from_loaders([loader])

File ~\anaconda3\envs\openai\Lib\site-packages\langchain\indexes\vectorstore.py:81, in VectorstoreIndexCreator.from_loaders(self, loaders)
79 docs =
80 for loader in loaders:
—> 81 docs.extend(loader.load())
82 return self.from_documents(docs)

File ~\anaconda3\envs\openai\Lib\site-packages\langchain\document_loaders\csv_loader.py:61, in CSVLoader.load(self)
59 with open(self.file_path, newline=“”, encoding=self.encoding) as csvfile:
60 csv_reader = csv.DictReader(csvfile, **self.csv_args) # type: ignore
—> 61 for i, row in enumerate(csv_reader):
62 content = “\n”.join(f"{k.strip()}: {v.strip()}" for k, v in row.items())
63 try:

File ~\anaconda3\envs\openai\Lib\csv.py:111, in DictReader.next(self)
108 if self.line_num == 0:
109 # Used only for its side effect.
110 self.fieldnames
→ 111 row = next(self.reader)
112 self.line_num = self.reader.line_num
114 # unlike the basic reader, we prefer not to return blanks,
115 # because we will typically wind up with a dict full of None
116 # values

File ~\anaconda3\envs\openai\Lib\encodings\cp1252.py:23, in IncrementalDecoder.decode(self, input, final)
22 def decode(self, input, final=False):
—> 23 return codecs.charmap_decode(input,self.errors,decoding_table)[0]

UnicodeDecodeError: ‘charmap’ codec can’t decode byte 0x9d in position 4445: character maps to

Please help

Hi @bolt,

Are you trying to run the notebook on the platform or elsewhere ?

At my local machine

Should I upgrade langchain? openai I upgrades last week

Updated langchain from 0.0.279 to 0.0.285
Updated openai from 0.27.8 to 0.28.0

The same error persists

The cell runs on other csv file like Data.csv from L3-chains.

So the problem is with the file OutdoorClothingCatalog_1000.csv. It seems same file running at the platform. So don’t know what to do

Hi @bolt,

Have your properly downloaded the file ? Maybe it is corrupt ?

Please make sure you have downloaded everything from the workspace by clicking on File --> Open.... This should open things in a new tab where your workspace, including all of the files will be visible to you.

Best,
Mubsi

Hi All,
to resolve this issue make the following change to the loader line:

loader = CSVLoader(file_path=file)
loader = CSVLoader(file_path=file, encoding=‘utf8’)

Hope that helps.

ChuckM

Thanks Chuck, I was facing the same issue!