f3fi[+dZddlmZddlZddlZddlmZmZddlm Z m Z ddl m Z m Z mZmZddlmZmZmZddlmZe rdd lmZee zZGd d eZGd d eZGddeZy)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) GeneratorcNeZdZUdZeddZded< eeZded <y) BaseMediaaABase 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____doc__r r__annotations__rr[/var/www/auto_recruiter/arenv/lib/python3.12/site-packages/langchain_core/documents/base.pyrr!s34tDB D 40Hd09r rcHeZdZUdZdZded< dZded< dZded < dZd ed < e d d Z e ddZ e deddZddZddZej&ddZeddd dd ddZeddddd d dZddZy)!BlobaRaw 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_allowedfrozenc|jr'd|jvrtd|jdS|jrt|jSdS)a!The 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!r,z Blob.sourcesE ==X6 dmmH&=> >!%s499~44r before)modec0d|vrd|vr d}t||S)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_validzBlob.check_blob_is_valids'  F&$88CS/ ! r cz|j;|jr/t|jj|jSt |jt r%|jj|jSt |jtr |jSd|}t|)zRead data as a string. Raises: ValueError: If the blob cannot be represented as a string. Returns: The data as a string. )r'zUnable to get string for blob ) r$r(r read_textr' isinstancebytesdecoder&r2r.r5s r! as_stringzBlob.as_strings 99  ?,,dmm,D D dii '99##DMM2 2 dii %99 .tf5or cbt|jtr |jSt|jtr%|jj |j S|j/|j r#t|j jSd|}t|)zRead data as bytes. Raises: ValueError: If the blob cannot be represented as bytes. Returns: The data as bytes. zUnable to get bytes for blob ) r9r$r:r&encoder'r(r read_bytesr2r<s r!as_bytesz Blob.as_bytess dii '99  dii %99##DMM2 2 99  ?--/ /-dV4or c#:Kt|jtrt|jy|j>|jr2t |jj d5}|dddyd|}t|#1swYyxYww)zRead data as a byte stream. Raises: NotImplementedError: If the blob cannot be represented as a byte stream. Yields: The data as a byte stream. NrbzUnable to convert blob )r9r$r:rr(ropenNotImplementedError)r.fr5s r! as_bytes_iozBlob.as_bytes_ios dii '$))$ $ YY 499dii%%d+ q  ,D62C%c* *   sA/B1B6BBB)r' mime_type guess_typerct||r|rtj|dnd}n|}|d|||||SiS)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$r%r'r(r) mimetypesrI)r3r(r'rHrIrr%s r! from_pathzBlob.from_paths\.  8By++D1!4H H!)!5X   <>   r )r'rHr(rc.|||||||SiS)aInitialize the `Blob` from in-memory data. Args: data: The in-memory data associated with the `Blob` encoding: Encoding to use if decoding the bytes into a string mime_type: If provided, will be set as the MIME type of the data path: If provided, will be set as the source from which the data came metadata: Metadata to associate with the `Blob` Returns: `Blob` instance rKr)r3r$r'rHr(rs r! from_datazBlob.from_datas4,!)!5X   <>   r c^dt|}|jr|d|jz }|S)zReturn the blob representation.zBlob  )rr,)r.str_reprs r!__repr__z Blob.__repr__s32d8*% ;; !DKK=) )Hr )returnr)r4zdict[str, Any]rTr rTr&)rTr:)rTz/Generator[BytesIO | BufferedReader, None, None]) r(PathLiker'r&rHrrIboolr dict | NonerTr#) r$z str | bytesr'r&rHrr(rrrXrTr#)rrrrr$rr%r'r(r model_configpropertyr,r classmethodr6r=rA contextlibcontextmanagerrGrMrOrSrr r!r#r#9sj6p $D #.Hj>Hc!D/ 8 $L  5 5(#$$$++$  $ $" "  "  "  " "  " " H  $ $            :r r#cleZdZUdZded< dZded<d fd Zed dZed dZ d d Z xZ S)DocumentaClass 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 (t|dd|i|y)z0Pass page_content in as positional or named arg.r`Nr)super__init__)r.r`kwargs __class__s r!rdzDocument.__init__0s =l=f=r cy)z,Return `True` as this class is serializable.Trr3s r!is_lc_serializablezDocument.is_lc_serializable6sr c gdS)zuGet the namespace of the LangChain object. Returns: ["langchain", "schema", "document"] ) langchainschemadocumentrrhs r!get_lc_namespacezDocument.get_lc_namespace;s 32r cr|jrd|jd|jSd|jdS)zOverride `__str__` to restrict it to page_content and metadata. Returns: A string representation of the `Document`. zpage_content='z ' metadata=')rr`r-s r!__str__zDocument.__str__Ds? ==#D$5$5#6k$--Q Q 1 12!44r )r`r&rer rTNone)rTrW)rTz list[str]rU) rrrrrrardr[rirnrq __classcell__)rfs@r!r_r_sP  *D *> 335r r_)r __future__rr\rLiorrpathlibrrtypingrr r r pydanticr r r langchain_core.load.serializablercollections.abcrr&rVrr#r_rr r!r{s` #&"44779) >: :0_9_D95y95r