D_i[+SrSSKJr SSKrSSKrSSKJrJr SSKJ r J r SSK J r J r JrJr SSKJrJrJr SSKJr \ (aSS KJr \\ -r"S S \5r"S S \5r"SS\5rg)aDBase classes for media and documents. This module contains core abstractions for **data retrieval and processing workflows**: - `BaseMedia`: Base class providing `id` and `metadata` fields - `Blob`: Raw data loading (files, binary data) - used by document loaders - `Document`: Text content for retrieval (RAG, vector stores, semantic search) !!! note "Not for LLM chat messages" These classes are for data processing pipelines, not LLM I/O. For multimodal content in chat messages (images, audio in conversations), see `langchain.messages` content blocks instead. ) annotationsN)BufferedReaderBytesIO)PathPurePath) TYPE_CHECKINGAnyLiteralcast) ConfigDictFieldmodel_validator) Serializable) GeneratorcJ\rSrSr%Sr\"SSS9rS\S'\"\S9r S \S 'S r g) BaseMedia!a-Base class for content used in retrieval and data processing workflows. Provides common fields for content that needs to be stored, indexed, or searched. !!! note For multimodal content in **chat messages** (images, audio sent to/from LLMs), use `langchain.messages` content blocks instead. NT)defaultcoerce_numbers_to_str str | Noneid)default_factorydictmetadata) __name__ __module__ __qualname____firstlineno____doc__r r__annotations__rr__static_attributes__rW/home/james-whalen/.local/lib/python3.13/site-packages/langchain_core/documents/base.pyrr!s34tDB D 40Hd09r#rcX\rSrSr%SrSrS\S'SrS\S'SrS \S 'Sr S \S '\ "S S S9r \ SSj5r \"SS9\SSj55rSSjrSSjr\R(S Sj5r\SSS SS.S!Sjj5r\SSSSS.S"Sjj5rSSjrSrg)#Blob9a2Raw data abstraction for document loading and file processing. Represents raw bytes or text, either in-memory or by file reference. Used primarily by document loaders to decouple data loading from parsing. Inspired by [Mozilla's `Blob`](https://developer.mozilla.org/en-US/docs/Web/API/Blob) ???+ example "Initialize a blob from in-memory data" ```python from langchain_core.documents import Blob blob = Blob.from_data("Hello, world!") # Read the blob as a string print(blob.as_string()) # Read the blob as bytes print(blob.as_bytes()) # Read the blob as a byte stream with blob.as_bytes_io() as f: print(f.read()) ``` ??? example "Load from memory and specify MIME type and metadata" ```python from langchain_core.documents import Blob blob = Blob.from_data( data="Hello, world!", mime_type="text/plain", metadata={"source": "https://example.com"}, ) ``` ??? example "Load the blob from a file" ```python from langchain_core.documents import Blob blob = Blob.from_path("path/to/file.txt") # Read the blob as a string print(blob.as_string()) # Read the blob as bytes print(blob.as_bytes()) # Read the blob as a byte stream with blob.as_bytes_io() as f: print(f.read()) ``` Nzbytes | str | Nonedatarmimetypezutf-8strencodingzPathLike | NonepathT)arbitrary_types_allowedfrozencUR(a)SUR;a[SURS5$UR(a[UR5$S$)aThe source location of the blob as string if known otherwise none. If a path is associated with the `Blob`, it will default to the path location. Unless explicitly set via a metadata field called `'source'`, in which case that value will be used instead. sourcerN)rr r,r*selfs r$r0 Blob.sourcesE ==X6 dmmH&=> >!%s499~44r#before)modec8SU;aSU;a Sn[U5eU$)z,Verify that either data or path is provided.r(r,z$Either data or path must be provided) ValueError)clsvaluesmsgs r$check_blob_is_validBlob.check_blob_is_valids'  F&$88CS/ ! r#cURc=UR(a,[UR5RURS9$[ UR[ 5(a%URRUR5$[ UR[5(a UR$SU3n[U5e)zRead data as a string. Raises: ValueError: If the blob cannot be represented as a string. Returns: The data as a string. )r+zUnable to get string for blob ) r(r,r read_textr+ isinstancebytesdecoder*r7r2r:s r$ as_stringBlob.as_strings 99  ?,,dmm,D D dii ' '99##DMM2 2 dii % %99 .tf5or#c[UR[5(a UR$[UR[5(a%URR UR 5$URc4UR (a#[UR 5R5$SU3n[U5e)zzRead data as bytes. Raises: ValueError: If the blob cannot be represented as bytes. Returns: The data as bytes. zUnable to get bytes for blob ) r?r(r@r*encoder+r,r read_bytesr7rBs r$as_bytes Blob.as_bytess dii ' '99  dii % %99##DMM2 2 99  ?--/ /-dV4or#c#Z# [UR[5(a[UR5v gURcCUR(a2[ UR5R S5nUv SSS5 gSU3n[U5e!,(df  g=f7f)zRead data as a byte stream. Raises: NotImplementedError: If the blob cannot be represented as a byte stream. Yields: The data as a byte stream. NrbzUnable to convert blob )r?r(r@rr,ropenNotImplementedError)r2fr:s r$ as_bytes_ioBlob.as_bytes_ios} dii ' '$))$ $ YY 499dii%%d+q,+,D62C%c* * ,+sA:B+<BB+ B($B+)r+ mime_type guess_typercUc*U(a#U(a[R"U5SOSnOUnU"SUUUUbUS9$0S9$)aLoad the blob from a path like object. Args: path: Path-like object to file to be read encoding: Encoding to use if decoding the bytes into a string mime_type: If provided, will be set as the MIME type of the data guess_type: If `True`, the MIME type will be guessed from the file extension, if a MIME type was not provided metadata: Metadata to associate with the `Blob` Returns: `Blob` instance Nrr(r)r+r,r) mimetypesrR)r8r,r+rQrRrr)s r$ from_pathBlob.from_paths\.  8By++D1!4H H!)!5X   <>   r#)r+rQr,rc$U"UUUUUbUS9$0S9$)aInitialize the `Blob` from in-memory data. Args: data: The in-memory data associated with the `Blob` encoding: Encoding to use if decoding the bytes into a string mime_type: If provided, will be set as the MIME type of the data path: If provided, will be set as the source from which the data came metadata: Metadata to associate with the `Blob` Returns: `Blob` instance rTr)r8r(r+rQr,rs r$ from_dataBlob.from_datas4,!)!5X   <>   r#chS[U53nUR(aUSUR3- nU$)zReturn the blob representation.zBlob  )rr0)r2str_reprs r$__repr__ Blob.__repr__s32d8*% ;; !DKK=) )Hr#r)returnr)r9zdict[str, Any]r`r r`r*)r`r@)r`z/Generator[BytesIO | BufferedReader, None, None]) r,PathLiker+r*rQrrRboolr dict | Noner`r&) r(z str | bytesr+r*rQrr,rrrdr`r&)rrrrr r(r!r)r+r,r model_configpropertyr0r classmethodr;rCrH contextlibcontextmanagerrOrVrYr^r"rr#r$r&r&9sj6p $D #.Hj>Hc!D/ 8 $L  5 5(#$$$++$  $ $" "  "  "  " "  " " H  $ $            :r#r&c~^\rSrSr%SrS\S'SrS\S'S U4Sjjr\S Sj5r \SS j5r SS jr S r U=r $)DocumentiaClass for storing a piece of text and associated metadata. !!! note `Document` is for **retrieval workflows**, not chat I/O. For sending text to an LLM in a conversation, use message types from `langchain.messages`. Example: ```python from langchain_core.documents import Document document = Document( page_content="Hello, world!", metadata={"source": "https://example.com"} ) ``` r* page_contentzLiteral['Document']typec *>[TU]"SSU0UD6 g)z0Pass page_content in as positional or named arg.rlNr)super__init__)r2rlkwargs __class__s r$rpDocument.__init__0s =l=f=r#cg)z,Return `True` as this class is serializable.Trr8s r$is_lc_serializableDocument.is_lc_serializable6sr#c /SQ$)z]Get the namespace of the LangChain object. Returns: ["langchain", "schema", "document"] ) langchainschemadocumentrrus r$get_lc_namespaceDocument.get_lc_namespace;s 32r#c|UR(aSURSUR3$SURS3$)zyOverride `__str__` to restrict it to page_content and metadata. Returns: A string representation of the `Document`. zpage_content='z ' metadata=')rrlr1s r$__str__Document.__str__Ds? ==#D$5$5#6k$--Q Q 1 12!44r#r)rlr*rqr r`None)r`rc)r`z list[str]ra)rrrrr r!rmrprgrvr|rr" __classcell__)rrs@r$rkrksU  *D *> 3355r#rk)r __future__rrhrUiorrpathlibrrtypingrr r r pydanticr r r langchain_core.load.serializablercollections.abcrr*rbrr&rkrr#r$rs` #&"44779) >: :0_9_D95y95r#