j 5dZddlZddlZddlZddlZddlmZmZmZm Z m Z m Z m Z ddl Z ddlmZddlmZddlmZerddlmZe dZGd d ZdS) ziThis module contains the LangfuseMedia class, which is used to wrap media objects for upload to Langfuse.N) TYPE_CHECKINGAnyLiteralOptionalTupleTypeVarcast)MediaContentType)langfuse_logger)ParsedMediaReference)LangfuseTc$eZdZUdZeed<eeed<eeed<ee ed<ee ed<dddddddeed ee d eed eed ee f d Z d e deefdZ dee fdZ e deefdZe dee fdZe dee fdZede defdZde deeeeeffdZeddddeddded dededef dZdS) LangfuseMediaaA class for wrapping media objects for upload to Langfuse. This class handles the preparation and formatting of media content for Langfuse, supporting both base64 data URIs and raw content bytes. Args: obj (Optional[object]): The source object to be wrapped. Can be accessed via the `obj` attribute. base64_data_uri (Optional[str]): A base64-encoded data URI containing the media content and content type (e.g., "data:image/jpeg;base64,/9j/4AAQ..."). content_type (Optional[str]): The MIME type of the media content when providing raw bytes. content_bytes (Optional[bytes]): Raw bytes of the media content. file_path (Optional[str]): The path to the file containing the media content. For relative paths, the current working directory is used. Raises: ValueError: If neither base64_data_uri or the combination of content_bytes and content_type is provided. obj_content_bytes _content_type_source _media_idN)rbase64_data_uri content_type content_bytes file_pathrrrrc||_|,||}|\|_|_d|_n||||_||_d|_n|\|Zt j|r;|||_|jr|nd|_|jrdnd|_n)tj dd|_d|_d|_| |_ dS)aAInitialize a LangfuseMedia object. Args: obj: The object to wrap. base64_data_uri: A base64-encoded data URI containing the media content and content type (e.g., "data:image/jpeg;base64,/9j/4AAQ..."). content_type: The MIME type of the media content when providing raw bytes or reading from a file. content_bytes: Raw bytes of the media content. file_path: The path to the file containing the media content. For relative paths, the current working directory is used. Nrbytesfilezbbase64_data_uri, or content_bytes and content_type, or file_path must be provided to LangfuseMedia) r_parse_base64_data_urirrrospathexists _read_fileloggererror _get_media_idr)selfrrrrr parsed_datas X/lsinfo/ai/hellotax_ai/base_platform/venv/lib/python3.11/site-packages/langfuse/media.py__init__zLangfuseMedia.__init__0s *  &55oFFK6A 3D !3,DLL  &<+C!-D "/D "DLL  !(y)))#'//)"<" > F FsC P P$SbS))r)c<|jrt|jndSN)rlenr%s r'_content_lengthzLangfuseMedia._content_lengthws +/+>Hs4&'''DHr)c|jdStj|j}t j|dS)Nzutf-8)rhashlibsha256digestbase64 b64encodedecode)r%sha256_hash_bytess r'r9z"LangfuseMedia._content_sha256_hash{sO   &4#N4+>??FFHH 12299'BBBr)cf|j|j|jdSd|jd|jd|jdS)N@@@langfuseMedia:type=z|id=z|source=@@@)rrrr@s r'_reference_stringzLangfuseMedia._reference_stringsH   %)=AW4i(:iiiiX\Xdiiiir)reference_stringc |stdt|tstd|dstd|dstd|t ddd}|d }i|D] }|d d \}}||<!tfd d DstdtddttdS)aParse a media reference string into a ParsedMediaReference. Example reference string: "@@@langfuseMedia:type=image/jpeg|id=some-uuid|source=base64_data_uri@@@" Args: reference_string: The reference string to parse. Returns: A TypedDict with the media_id, source, and content_type. Raises: ValueError: If the reference string is empty or not a string. ValueError: If the reference string does not start with "@@@langfuseMedia:type=". ValueError: If the reference string does not end with "@@@". ValueError: If the reference string is missing required fields. zReference string is emptyz Reference string is not a stringrKz=Reference string does not start with '@@@langfuseMedia:type='rLz(Reference string does not end with '@@@'z@@@langfuseMedia:N|=c3 K|]}|vV dSr>).0keyr&s r' z7LangfuseMedia.parse_reference_string..s(JJ#3+%JJJJJJr))typeidsourcez+Missing required fields in reference stringrYrZrX)media_idrZr) ValueError isinstancestr startswithendswithr?rstripsplitallr r r )rNcontentpairspairrVvaluer&s @r'parse_reference_stringz$LangfuseMedia.parse_reference_stringsw&  :899 9*C00 A?@@ @**+CDD O  ((// IGHH H"3':#;#;#=#=>EEeLL c""  % %DC++JC$K  JJJJ1IJJJJJ LJKK K# &x(. F0CDD    r)datac0 |rt|tstd|dstd|dddd\}}|r|std|d}d |vrtd |d }|std t j|tt|fS#t$r!}tj d |Yd}~dSd}~wwxYw)NzData URI is not a stringdata:z$Data URI does not start with 'data:',rRz Invalid URI;rFzData is not base64 encodedrzContent type is emptyzError parsing base64 data URIr-)NN) r]r^r\r_rbrF b64decoder r r1r"r#)r%riheader actual_data header_partsrr2s r'rz$LangfuseMedia._parse_base64_data_urisB  =z$44 = !;<<<??7++ I !GHHH"&qrr(..a"8"8 FK 0 0 ///"<<,,L|++ !=>>>(?L : !8999#K00$7G2V2VV V    L81 E E E E::::: sC'C** D4DD ) max_depthcontent_fetch_timeout_secondslangfuse_clientr resolve_withrtrucdtdtdtffd tt|dS)aReplace media reference strings in an object with base64 data URIs. This method recursively traverses an object (up to max_depth) looking for media reference strings in the format "@@@langfuseMedia:...@@@". When found, it (synchronously) fetches the actual media content using the provided Langfuse client and replaces the reference string with a base64 data URI. If fetching media content fails for a reference string, a warning is logged and the reference string is left unchanged. Args: obj: The object to process. Can be a primitive value, array, or nested object. If the object has a __dict__ attribute, a dict will be returned instead of the original object type. langfuse_client: Langfuse client instance used to fetch media content. resolve_with: The representation of the media content to replace the media reference string with. Currently only "base64_data_uri" is supported. max_depth: Optional. Default is 10. The maximum depth to traverse the object. Returns: A deep copy of the input object with all media references replaced with base64 data URIs where possible. If the input object has a __dict__ attribute, a dict will be returned instead of the original object type. Example: obj = { "image": "@@@langfuseMedia:type=image/jpeg|id=123|source=bytes@@@", "nested": { "pdf": "@@@langfuseMedia:type=application/pdf|id=456|source=bytes@@@" } } result = await LangfuseMedia.resolve_media_references(obj, langfuse_client) # Result: # { # "image": "data:image/jpeg;base64,/9j/4AAQSkZJRg...", # "nested": { # "pdf": "data:application/pdf;base64,JVBERi0xLjcK..." # } # } rdepthr*cTkr|St|trwd}tj||}t |dkr|S|}i}j jjnd}|D]} t|}j j |d} || | j ntj | j } | tj| j} d| jd| } | ||<#t($r$} t+jd|d| Yd} ~ d} ~ wwxYw|D]\}}|||}|St|t2rfd |DSt|t4r!fd |DSt7|d r&fd |jDS|S) Nz@@@langfuseMedia:.+?@@@rr[)timeoutrkz;base64,z2Error fetching media content for reference string z: c.g|]}|dzSrRrT)rUitemrytraverses r' zLLangfuseMedia.resolve_media_references..traverse..Qs)BBBduqy11BBBr)c6i|]\}}||dzSr}rTrUrVrgryrs r' zLLangfuseMedia.resolve_media_references..traverse..Us/VVVJCXXeUQY77VVVr)__dict__c6i|]\}}||dzSr}rTrs r'rzLLangfuseMedia.resolve_media_references..traverse..Ys?"U%33r))r]r^refindallr? _resources httpx_clientrrhapimediageturlhttpxraise_for_statusrFrGrdrHrr1r"warningitemsr:listdicthasattrr)rryregexreference_string_matchesresult!reference_string_to_media_contentrrNparsed_media_reference media_data media_contentbase64_media_contentrr2ref_strmedia_content_strrurvrtrs ` r'rz8LangfuseMedia.resolve_media_references..traversesy   #s##7 2+-:eS+A+A(/00A55J461'1=$.;; )A!!!!$ !1>1U1U,22.&5%8%>%B%B2:>&&  ,7 ),, *(E- "' *8U""" &&66888/5/?)100 &((-+j*2I*i*iSg*i*i,::JKK%!!!hQahhefhh! !7<<>>HH%#^^G5FGGFF #t$$ CBBBBBcBBBB#t$$ WVVVVV#))++VVVVsJ'' &)l&8&8&:&: Js+C D55 E#?EE#r)rintr r)rrvrwrtrurs ` ``@r'resolve_media_referencesz&LangfuseMedia.resolve_media_referencesstbM #M cM cM M M M M M M M M ^AxxQ''(((r))__name__ __module__ __qualname____doc__object__annotations__rrr r^r(r!r$propertyrrAr9rM staticmethodr rhrrrrrrTr)r'rrs& KKKUO###,---- c]} !%)-37)-#'1.1.1.f 1."# 1. /0 1.   1.C=1.1.1.1.fCHUO *x} * * * *I#IIIXIChsmCCCXCj8C=jjjXj 2 2 9M2 2 2 \2 h x)9 :: ;@ -/ ))) )$)/0 )  ) (+ ) )))\)))r)r)rrFrCrrtypingrrrrrrr r langfuse.apir langfuse.loggerr r"langfuse.typesr langfuse._client.clientr rrrTr)r'rsoo  NNNNNNNNNNNNNNNNNN ))))))555555//////1000000 GCLLK)K)K)K)K)K)K)K)K)K)r)