dhSSSKrSSKJr SSKJr SSKJrJrJrJ r J r J r J r SSK Jr SSKJr SSKJr SSKJrJr "S S \5r"S S \5rg) N) TextIOWrapper)Path)AnyDictIteratorListOptionalSequenceUnion)Document) BaseLoader)detect_file_encodings)UnstructuredFileLoadervalidate_unstructured_versionc\rSrSrSrSSS.S\\\4S\\S\ \S \\ S \\S \ S \ \4S jjjr S\ \4SjrS\S\ \4SjrSrg) CSVLoaderaLoad a `CSV` file into a list of Documents. Each document represents one row of the CSV file. Every row is converted into a key/value pair and outputted to a new line in the document's page_content. The source for each document loaded from csv is set to the value of the `file_path` argument for all documents by default. You can override this by setting the `source_column` argument to the name of a column in the CSV file. The source of each document will then be set to the value of the column with the name specified in `source_column`. Output Example: .. code-block:: txt column1: value1 column2: value2 column3: value3 Instantiate: .. code-block:: python from langchain_community.document_loaders import CSVLoader loader = CSVLoader(file_path='./hw_200.csv', csv_args={ 'delimiter': ',', 'quotechar': '"', 'fieldnames': ['Index', 'Height', 'Weight'] }) Load: .. code-block:: python docs = loader.load() print(docs[0].page_content[:100]) print(docs[0].metadata) .. code-block:: python Index: Index Height: Height(Inches)" Weight: "Weight(Pounds)" {'source': './hw_200.csv', 'row': 0} Async load: .. code-block:: python docs = await loader.aload() print(docs[0].page_content[:100]) print(docs[0].metadata) .. code-block:: python Index: Index Height: Height(Inches)" Weight: "Weight(Pounds)" {'source': './hw_200.csv', 'row': 0} Lazy load: .. code-block:: python docs = [] docs_lazy = loader.lazy_load() # async variant: # docs_lazy = await loader.alazy_load() for doc in docs_lazy: docs.append(doc) print(docs[0].page_content[:100]) print(docs[0].metadata) .. code-block:: python Index: Index Height: Height(Inches)" Weight: "Weight(Pounds)" {'source': './hw_200.csv', 'row': 0} N)content_columns file_path source_columnmetadata_columnscsv_argsencodingautodetect_encodingrclXlX lX0lXPlU=(d 0UlX`lXplg)a Args: file_path: The path to the CSV file. source_column: The name of the column in the CSV file to use as the source. Optional. Defaults to None. metadata_columns: A sequence of column names to use as metadata. Optional. csv_args: A dictionary of arguments to pass to the csv.DictReader. Optional. Defaults to None. encoding: The encoding of the CSV file. Optional. Defaults to None. autodetect_encoding: Whether to try to autodetect the file encoding. content_columns: A sequence of column names to use for the document content. If not present, use all columns that are not part of the metadata. N)rrrrrrr)selfrrrrrrrs g/var/www/html/shao/venv/lib/python3.13/site-packages/langchain_community/document_loaders/csv_loader.py__init__CSVLoader.__init__cs12#* 0  B #6 .returnc## [URSURS9nURU5ShvN SSS5 gN !,(df  g=f![anUR (a[ UR5nUHnn[URSURS9nURU5ShvN SSS5 SnAg!,(df  M\=f![a Mlf=f SnAg[SUR35UeSnAf[an[SUR35UeSnAff=f7f)N)newlinerzError loading ) openrr_CSVLoader__read_fileUnicodeDecodeErrorrr RuntimeError Exception)rcsvfileedetected_encodingsrs r lazy_loadCSVLoader.lazy_loads Idnnb4==IW++G444JI4JI! M''%:4>>%J" 2H!! NNBARAR$'+'7'7'@@@!  .! !!3#^DNN3C#DE1L I/?@Aq H IsE AAAAAE A AAE A E#+DC*.CC C C*DE  C' "C*%D'C** C84D7C88D=E D E(EEE r+c#^# [R"U40TRD6n[U5Hup4TRbUTRO[ TR 5nSRU4SjUR555nXSS.nTRH nXHXx'M [XgS9v M g![a [STRS35ef=f![a [SUS35ef=f7f)NzSource column 'z' not found in CSV file. c 3># UHupTR(aUTR;dM(OUTR;dM;UbUR5OUS[U[5(aUR5O?[U[ 5(a)SR [[RU55OU3v M g7f)Nz: ,)rrstrip isinstancestrlistjoinmap).0kvrs r (CSVLoader.__read_file..s (DA++---.$"7"77!-QWWYQ7r!!S))GGI"!T**#cii"34 :(s&CCBC)sourcerowzMetadata column ') page_contentmetadata) csv DictReaderr enumeraterr6rKeyError ValueErrorr8itemsrr ) rr+ csv_readerir@r?contentrBcols ` r __read_fileCSVLoader.__read_files^^G=t}}=  +FA ))5**+T^^,ii  IIK G#)3H,,X$'HHM- C CA,  %d&8&8%99QR . X$'8=U%VWWXs42D1B>'$C""D%C??D)rrrrrrr)NrNNF)__name__ __module__ __qualname____firstlineno____doc__r r6rr r rboolrrr r.rr'__static_attributes__rr!rrrsPj(,*,#'"&$)/*,/d#/ }/#3- / 4. / 3- /"/"#/BI8H-I*"D="DXh5G"Dr!rcP^\rSrSrSrS S\S\S\4U4SjjjrS\4Sjr S r U=r $) UnstructuredCSVLoaderaHLoad `CSV` files using `Unstructured`. Like other Unstructured loaders, UnstructuredCSVLoader can be used in both "single" and "elements" mode. If you use the loader in "elements" mode, the CSV file will be a single Unstructured Table element. If you use the loader in "elements" mode, an HTML representation of the table will be available in the "text_as_html" key in the document metadata. Examples -------- from langchain_community.document_loaders.csv_loader import UnstructuredCSVLoader loader = UnstructuredCSVLoader("stanley-cups.csv", mode="elements") docs = loader.load() rmodeunstructured_kwargsc <>[SS9 [TU]"SXS.UD6 g)z Args: file_path: The path to the CSV file. mode: The mode to use when loading the CSV file. Optional. Defaults to "single". **unstructured_kwargs: Keyword arguments to pass to unstructured. z0.6.8)min_unstructured_version)rrYNr)rsuperr)rrrYrZ __class__s rrUnstructuredCSVLoader.__init__s# &wG O9O;NOr!r"cJSSKJn U"SSUR0URD6$)Nr) partition_csvfilenamer)unstructured.partition.csvrarrZ)rras r _get_elements#UnstructuredCSVLoader._get_elementss"<QdnnQ8P8PQQr!r)single) rOrPrQrRrSr6rrrrdrU __classcell__)r^s@rrWrWsH&+3 P P$' PKN P PRtRRr!rW)rCiorpathlibrtypingrrrrr r r langchain_core.documentsr )langchain_community.document_loaders.baser ,langchain_community.document_loaders.helpersr1langchain_community.document_loaders.unstructuredrrrrWrr!rrosE GGG-@N kD kD\$R2$Rr!