Ci ddlZddlZddlmZmZmZmZddlmZddlm Z GddeZ dZ dZ d d gfd Zd"d Zd d gfd ZdZdZdZdZdZdZdZd d gfdZdZdZdZdZdZdZdZdZ dZ!d#dZ"d Z#d!Z$y)$N)AnyCallable NamedTupleOptional)assert_has_pandas)pandasceZdZUeed<dZeeed<dZeeed<dZee e ge fed<dZ eeed<dZ ee e ge fed<dZ eeed<y) RemediationnameN immediate_msg necessary_msg necessary_fn optional_msg optional_fn error_msg)__name__ __module__ __qualname__str__annotations__r rr rrrrrrK/var/www/html/aiagents/fe/lib/python3.12/site-packages/openai/validators.pyr r ss I#'M8C='#'M8C='37L(8SE3J/07"&L(3-&26K(C5#:./6#Ix}#rr cfd}t||k\rdnd}dt|d|}td|S)z This validator will only print out the number of examples and recommend to the user to increase the number of examples if less than 100. dz. In general, we recommend having at least a few hundred examples. We've found that performance tends to linearly increase for every doubling of the number of examplesz - Your file contains z prompt-completion pairs num_examplesr r )lenr )df MIN_EXAMPLESoptional_suggestionr s rnum_examples_validatorr#sTL r7l " w "#b'*BCVBWX N- HHrcdd}d}d}d}|jvrN|jDcgc]}t|jc}vrfd}|}dd}dd}ndd}td |||| Scc}w) z[ This validator will ensure that the necessary column is present in the dataframe. c|jDcgc]!}t|j|k(s |#}}|j|d|jid|Scc}w)NrT)columnsinplace)r&rlowerrename)r columnccolss rlower_case_columnz5necessary_column_validator..lower_case_column(sT::BaQ6)ABB 47FLLN3T B Cs !AANc|SNr)r r-necessary_columns rlower_case_column_creatorz=necessary_column_validator..lower_case_column_creator5s(-=>>rz - The `z ` column/key should be lowercasezLower case column name to ``z^` column/key is missing. Please make sure you name your columns/keys appropriately, then retryr0)r r r rr)r&rr(r ) r r0r rr rr+r1r-s ` @rnecessary_column_validatorr3#s  MLMIrzz)  C1A C C ?5L,--MN ::J9K1MM,-.LMI  ##!   Ds A:prompt completioncDg}d}d}d}t|jdkDrg|jDcgc] }|vs| }}d}|D]1}|Dcgc] }||vs| } }t| dkDs&|d|d|dz }3d||}d |}fd }td ||| Scc}wcc}w) zK This validator will remove additional columns from the dataframe. Nrrz9 WARNING: Some of the additional columns/keys contain `z<` in their name. These will be ignored, and the column/key `z`` will be used instead. This could also result from a duplicate column/key in the provided file.zh - The input file should contain exactly two columns/keys per row. Additional columns/keys present are: z Remove additional columns/keys: c|Sr/rxfieldss rrz1additional_column_validator..necessary_fn[s V9 radditional_columnr r r r)rr&r ) r r;additional_columnsr r rr+ warn_messageacdupss ` radditional_column_validatorrBIsMML 2::)+GAqaGG $ BB1=!R1WA=D=4y1}"\]_\`a]^`]aaA!BB  BDEWDXYeXfg :;M:NO    ##!  H>s BB BBcd}d}d}|jdjs!|jjrf|dk(|jz}|jj|j }dd|}fd}dt |dd }td ||| S) zA This validator will ensure that no completion is empty. Nc |dk(S)Nrrr:s rz+non_empty_field_validator..ns brrz - `z?` column/key should not contain empty strings. These are rows: c<||dk7jgS)Nrsubset)dropna)r:fields rrz/non_empty_field_validator..necessary_fnss&QuX^$++E7+; ;rRemove z rows with empty sempty_r=)applyanyisnull reset_indexindextolistrr )r rKr rr empty_rows empty_indexess ` rnon_empty_field_validatorrWfsMLM %y()--/2e93C3C3E3I3I3Ki2o"U)*:*:*<= (..z:AAC w&efsetu  <"#m"4!55FugQO eW ##!  rc2|j}|jj|j}d}d}d}t |dkDr7dt |ddj d|}dt |d }fd }t d ||| S) zY This validator will suggest to the user to remove duplicate rows if they exist. rHNr - There are z duplicated -z sets. These are rows: rLz duplicate rowsc(|jS)NrH)drop_duplicatesr9s rrz.duplicated_rows_validator..optional_fns$$F$3 3rduplicated_rowsr r rr) duplicatedrRrSrTrjoinr )r r;r]duplicated_indexesr rrs ` rduplicated_rows_validatorrbsmm6m2O)//@GGIMLK "(-?)@(AchhW]N^M__vxJwKL  %7!8 9I  4  #!  rcd}d}d}t|}|dk7r@d|tdkDr'dtdd}dtd }fd }td ||| S) zW This validator will suggest to the user to remove examples that are too long. Nopen-ended generationc|jdd}|jj|jS)Nc^t|jt|jzdkDS)Ni')rr4r5rEs rrFzClong_examples_validator..get_long_indexes..s!#ahh-#all*;;eCr)axis)rOrRrSrT)d long_exampless rget_long_indexesz1long_examples_validator..get_long_indexess<GGC!$M==?((7>>@ @rrrYz. examples that are very long. These are rows: zf For conditional generation, and for classification the examples shouldn't be longer than 2048 tokens.rLz long examplesc|}|k7r/tjjdt|d|d|j |S)NzeThe indices of the long examples has changed as a result of a previously applied recommendation. The z? long examples to be dropped are now at the following indices:  )sysstdoutwriterdrop)r:long_indexes_to_droprk long_indexess rrz,long_examples_validator..optional_fns'7':$#77JJ$$ABEFZB[A\\[\p[qqstvv233rrjr^)infer_task_typerr )r r rrft_typerkrss @@rlong_examples_validatorrvsMLKb!G)) A (+ | q ,S->,??mnzm{|cdM$S%6$7~FL 4  #!  rc^ d}d}d}d}d gd}|D]t}|dk(r4|jjjdjr<|jjj|djrr| n j dd}t |}|d k(r t d Sd t|jd } |j| k(jrd| d}t d |S| dk7r| j dd} d| d}t| dkDr |d|dz }|jjdt|  jj| djr |d| dz }nd}| dk(r d|d} fd}t d||||S)z This validator will suggest to add a common suffix to the prompt if one doesn't already exist in case of classification or conditional generation. Nz ### => ) ->z ### z === z --- z ===> z ---> rxrmFregex\nrd common_suffixr c |dxx|z cc<|SNr4rr:suffixs r add_suffixz2common_prompt_suffix_validator..add_suffixs ( v rrxfixzAll prompts are identical: `zt` Consider leaving the prompts blank if you want to do open-ended generation, otherwise ensure prompts are differentr rrz - All prompts end with suffix `r2 R. This suffix seems very long. Consider replacing with a shorter suffix, such as `z5 WARNING: Some of your prompts contain the suffix `zZ` more than once. We strongly suggest that you review your prompts and add a unique suffixa - Your data does not contain a common separator at the end of your prompts. Having a separator string appended to the end of the prompt makes it clearer to the fine-tuned model where the completion should begin. See https://platform.openai.com/docs/guides/fine-tuning/preparing-your-dataset for more detail and examples. If you intend to do open-ended generation, then you should leave the prompts emptyzAdd a suffix separator `z` to all promptsc|Sr/rr:rsuggested_suffixs rrz3common_prompt_suffix_validator..optional_fna!12 2rcommon_completion_suffixr r rrr) r4rcontainsrPreplacertr get_common_xfixallr) r rr rrsuffix_options suffix_optiondisplay_suggested_suffixrur|common_suffix_new_line_handledrrs @@rcommon_prompt_suffix_validatorrsIMLK(N( E !yy}}%%d+//1 99== ! !-u ! = A A C (  077eDb!G))00$BIIH=M ]"'')2=/Bwx 9EE)6)>)>tU)K&/0N/Oq Q  }  " qsKrLLMN NM IIMM/S// 0 S-u5 SU  UVcUde@ @Mp &'?&@@P Q  3  '#!  rc0d}d}d}d}t|jddk(r tdSd|jk(jr tdSdk7r%d d }|t kr|d z }d d }fd}td|||S)zd This validator will suggest to remove a common prefix from the prompt if a long one exist. Nprefixrr common_prefixr}cB|djt|d|d<|Srrr)r:rs rremove_common_prefixz.remove_common_prefixs#kooc&km4( rz" - All prompts start with prefix `r2z. Fine-tuning doesn't require the instruction specifying the task, or a few-shot example scenario. Most of the time you should only add the input data into the prompt, and the desired output into the completionRemove prefix `z` from all promptsc|Sr/r)r:rrs rrz3common_prompt_prefix_validator..optional_fn(s+A}==rcommon_prompt_prefixr^)rr4r rr)r MAX_PREFIX_LENr rrrrs @@rcommon_prompt_prefix_validatorr sNMLK#BIIH=M00 ]"'')00=m_AN C . . r rM,]O;MNL >  ##!  rc:d}t|jdtdkDxrddk(t|kr tdSd|jk(j r tdSd d }d d }fd }td|||S)zh This validator will suggest to remove a common prefix from the completion if a long one exist. rrr rr}c\|djt|d|d<|r d|dz|d<|S)Nr5rr)r:r ws_prefixs rrz@common_completion_prefix_validator..remove_common_prefix>s:L/--c&km<, !AlO3AlOrz& - All completions start with prefix `z_`. Most of the time you should only add the output data into the completion, without any prefixrz` from all completionsc|Sr/r)r:rrrs rrz7common_completion_prefix_validator..optional_fnLs#A}i@@rcommon_completion_prefixr^)rr5rr r)r rr rrrrrs @@@r"common_completion_prefix_validatorr3sN#BMMAMM"Q&B=+;s+BI =N*00 &++-00=m_MlmM$]O3IJLA  '#!  rc d}d}d}d}t|}|dk(s|dk(r tdSt|jd}|j|k(j rd|d |d }td| Sd gd }|D];}|jj j |djr9| n jdd} d |dk7r|jdd} d| d }t|dkDr |d| d z }|jj dt| j j |djr |d|dz }nd}|dk(r d| d} fd}td||||S)z This validator will suggest to add a common suffix to the completion if one doesn't already exist in case of classification or conditional generation. Nrdclassificationr|r}rrz All completions are identical: `zJ` Ensure completions are different, otherwise the model will just repeat `r2rz [END]) rm.z ENDz***z+++z&&&z$$$z@@@z%%%Fryrmr{c |dxx|z cc<|SNr5rrs rrz6common_completion_suffix_validator..add_suffix}s ,6!rrz$ - All completions end with suffix `rrz9 WARNING: Some of your completions contain the suffix `zU` more than once. We suggest that you review your completions and add a unique endingaH - Your data does not contain a common ending at the end of your completions. Having a common ending string appended to the end of the completion makes it clearer to the fine-tuned model where the completion should end. See https://platform.openai.com/docs/guides/fine-tuning/preparing-your-dataset for more detail and examples.zAdd a suffix ending `z` to all completionsc|Sr/rrs rrz7common_completion_suffix_validator..optional_fnrrrr) rtr rr5rrrrPrr) r rr rrrur|rrrrrrs @@r"common_completion_suffix_validatorrWsIMLKb!G))W8H-H00#BMMAM &++-6}oFQR_Q``ab 9EE  N( ==   % %m5 % A E E G (  077eD)6)>)>tU)K&34R3SST U  }  " qsKrLLMN NM MM  3]!3 3 4 S-u5 SU  YZgYhi~ Md #$<#==Q R  3  '#!  rcd}d}d}d}|jjddjdk7s|jjdddk7rd}d}|}t d||| S) z This validator will suggest to add a space at the start of the completion if it doesn't already exist. This helps with tokenization. c6|djd|d<|S)Nr5c&|ddk(rd|zSd|zS)NrrrrrEs rrFzLcompletions_space_start_validator..add_space_start..sQqTS[rQ6cQ6r)rOrEs radd_space_startz:completions_space_start_validator..add_space_starts$L/// 6 ,rNrgrrz - The completion should start with a whitespace character (` `). This tends to produce better results due to the tokenization we use. See https://platform.openai.com/docs/guides/fine-tuning/preparing-your-dataset for more detailsz=Add a whitespace character to the beginning of the completioncompletion_space_startr^)r5rnuniquevaluesr )r rrrr s r!completions_space_start_validatorrs  LKM }}!$$&!+r}}/C/CA/Fq/IS/PB V %  %#!  rcfd}|jdj}|jdj}|dz|kDrtddddd d | Sy ) zt This validator will suggest to lowercase the column values, if more than a third of letters are uppercase. cH|jj|<|Sr/)rr()r:r*s r lower_casez(lower_case_validator..lower_cases"fIMM'')& rc&td|DS)Nc3dK|](}|js|js%d*ywrgN)isalphaisupper.0r+s r z9lower_case_validator.... I1QYY[QYY[QI 000sumrEs rrFz&lower_case_validator..IIIrc&td|DS)Nc3dK|](}|js|js%d*ywr)rislowerrs rrz9lower_case_validator....rrrrEs rrFz&lower_case_validator..rrr7rz - More than a third of your `z%` column/key is uppercase. Uppercase zs tends to perform worse than a mixture of case encountered in normal language. We recommend to lower case the data if that makes sense in your domain. See https://platform.openai.com/docs/guides/fine-tuning/preparing-your-dataset for more detailsz'Lowercase all your data in column/key `r2r^N)rOrr )r r*r count_upper count_lowers ` rlower_case_validatorrs  6 I J  6 I J  Q$;F8ChiohpqhiB6(!L"   %rctd}d}d}d}d}tjj|r |j j ds|j j dr_|j j drdnd\}}d|d}d|d }t j||t jd }nV|j j d rdd }d}t j|} | j} t| dkDr|dz }t j|tjd }n|j j drud}d}t|d5} | j} t j | j#dD cgc]} d | gc} |tjd }dddn?|j j drit j$|dtjd }t|dk(r/d}d}t j$|tjd }nn|j j drj t j$|dtjd }t|dk(r+t j$|tjd }nd}d}n.d}d |vr|d!|d"|j#d d#d$z }n |d!|d%z }nd*|d+}t-d,|||-}||fScc} w#1swY(xYw#t&$r-t j$|tjd }Y`wxYw#t&t(f$r1|j#d d#j+}d&|d'|d(|d)}YwxYw).z This function will read a file saved in .csv, .json, .txt, .xlsx or .tsv format using pandas. - for .xlsx it will read the first sheet - for .txt it will assume completions and split on newline Nz.csvz.tsv)CSV,)TSV z= - Based on your file extension, your file is formatted as a z filez Your format `z` will be converted to `JSONL`)sepdtyperz.xlsxzH - Based on your file extension, your file is formatted as an Excel filez/Your format `XLSX` will be converted to `JSONL`rgz - Your Excel file contains more than one sheet. Please either save as csv or ensure all data is present in the first sheet. WARNING: Reading only the first sheet...)rz.txtz9 - Based on your file extension, you provided a text filez.Your format `TXT` will be converted to `JSONL`rrm)r&r.jsonlT)linesrz^ - Your JSONL file appears to be in a JSON format. Your file will be converted to JSONL formatz/Your format `JSON` will be converted to `JSONL`z.jsonz^ - Your JSON file appears to be in a JSONL format. Your file will be converted to JSONL formatz]Your file must have one of the following extensions: .CSV, .TSV, .XLSX, .TXT, .JSON or .JSONLrz Your file `z` ends with the extension `.z` which is not supported.z` is missing a file extension.z Your file `z!` does not appear to be in valid z9 format. Please ensure your file is formatted as a valid z file.zFile z does not exist.read_any_format)r r r r)rospathisfiler(endswithpdread_csvrfillna ExcelFile sheet_namesr read_excelopenread DataFramesplit read_json ValueError TypeErrorupperr )fnamer; remediationr r rr file_extension_str separatorxlssheetsfcontentlines rrrs KMMI B ww~~e@ v{{}%%f-1G1G1O$)KKM$:$:6$BL ."I#aas`tty z #$6#77UV[[ISAHHL''0 k Q ll5)v;?!&NNM]]54;;B?''/P!Q %%!ffhG07 d0CD"dD &!fRj !!''1\\%t3?FFrJr7a<%FM$UMe37>>rBB''0Ce4sCJJ2NB2w!|\\%s;BB2F)J M&| %<<w6RSXS^S^_bScdfSgRhiB"CCI<w6T!UUIE7"23  ## K {?cE!!:"Ce37>>rBBCI& v!&S!1"!5!;!;!= %eW,MN`Mab[\n[oouvI vsbEN 3M8 M M B1N A(M:/N MM N 3N N N  N =O  O cLt|}d}|dk(rd|d}td|S)z This validator will infer the likely fine-tuning format of the data, and display it to the user if it is classification. It will also suggest to use ada and explain train/validation split benefits. NrzK - Based on your data it seems like you're trying to fine-tune a model for z - For classification, we recommend you try one of the faster and cheaper models, such as `ada` - For classification, you can estimate the expected model performance by keeping a held out dataset, which is not used for trainingrr)rtr )r rur s rformat_inferrer_validatorr7sA b!GM""fgnfopUV N- HHrc`|jOtjjd|jd|jdtj d|j )tjj|j |j|j|}|S)zs This function will apply a necessary remediation to a dataframe, or print an error message if one exists. z ERROR in z validator: z Aborting...rg) rrnstderrrpr exitr ror)r rs rapply_necessary_remediationrCs( K,,-\+:O:O9PP_ `     , 223+  % %b ) Irctjj||r tjjdytj dk7S)NzY Tn)rnrorpinputr() input_text auto_accepts raccept_suggestionrSs?JJZ   7==?c !!rcd}d|jd}|jt||r|j|}d}|j-tj j d|jd||fS)zc This function will apply an optional remediation to a dataframe, based on the user input. Fz- [Recommended] z [Y/n]: Tz- [Necessary] rm)rrrr rnrorp)r rroptional_appliedrs rapply_optional_remediationr[s#K$<$<#=XFJ+ Z 5((,B#   , >+*C*C)DBGH  rct|}d}|dk(rt|}|dz}n%|jdj}|dz}d}||dz}tj j d |d y ) z? Estimate the time it'll take to fine-tune the dataset g?rg ףp= ?T)rSg|?5^?c|dkrt|ddS|dkrt|dz ddS|dkrt|dz ddSt|dz ddS) N<r7z secondsiz minutesiQz hoursz days)round)times r format_timez.estimate_fine_tuning_time..format_timewsv "9D!n%X. . D[D2Iq)*(3 3 E\D4K+,F3 3D5L!,-U3 3rz:Once your model starts training, it'll approximately take z~ to train a `curie` model, and less for `ada` and `babbage`. Queue will approximately take half an hour per job ahead of you. N)rtr memory_usagerrnrorp)r ft_format expected_timersizer  time_strings restimate_fine_tuning_timerjs #IM$$2w $t+ T*..0v 4mc12KJJ D[MRQ Rrc|rddgndg}d} |dkDrd|dnd}|Dcgc]0}tjj|ddz|z|zdz2}}td |Ds|S|d z }bcc}w) N_train_validrrz () _preparedrc3ZK|]#}tjj|%ywr/)rrr)rrs rrz get_outfnames..s?277>>!$?s)+rg)rrsplitextrP)rrsuffixesi index_suffixrcandidate_fnamess r get_outfnamesrs',(#2$H A $%EA3ayr #  GG  U #A & 4v = Lx W  ?.>??# # Q  s5A/c|jj}d}|dk(r'|jjjd}||fS)Nr7r)r5r value_countsrS)r n_classes pos_classs rget_classification_hyperparamsr#sH %%'IIA~MM..066q9 i rc  t|}t|jd}t|jd}d}d}|dk(rt ||rd}d} |j dd } |j dd } t | d kDrd | d nd} d }|s:|s8tjjd|d| d| d| d t|y*t ||rt||} |rt | dk(rd| d vrd| dvsJd}tt ||z tt |dz}|j|d}|j|j }|ddgj#| d ddd|ddgj#| ddddt%|\}}| dz } |dk(r | d|dz } n6| d |z } n-t | dk(sJ|ddgj#| d ddd|rd!ndd"zd#j'| z}|r d$| ddnd}t | d k(rdnd%| d}tjjd&|d'| d d|| d(|| d t|y*tjjd)y*)+aQ This function will write out a dataframe to a file, if the user would like to proceed, and also offer a fine-tuning command with the newly created file. For classification it will optionally ask the user if they would like to split the data into train/valid files, and modify the suggested command to include the valid set. rrFzQ- [Recommended] Would you like to split into training and validation set? [Y/n]: rTrrmr{rz Make sure to include `stop=["z;"]` so that the generated texts ends at the expected place.z@ Your data will be written to a new JSONL file. Proceed [Y/n]: zK You can use your file for fine-tuning: > openai api fine_tunes.create -t ""ue After you’ve fine-tuned a model, remember that your prompt has to end with the indicator string `zX` for the model to start generating completions, rather than continuing with the prompt.r7trainvalidrgig?*)r random_stater4r5records)rorient force_asciiz! --compute_classification_metricsz" --classification_positive_class "z --classification_n_classes rMz to `z` and `z -v "ucAfter you’ve fine-tuned a model, remember that your prompt has to end with the indicator string `z Wrote modified filezd` Feel free to take a look! Now use that file when fine-tuning: > openai api fine_tunes.create -t "z z#Aborting... did not write the file N)rtrr4r5rrrrnrorprrmaxintsamplerqrSto_jsonr#r`)r rany_remediationsrrcommon_prompt_suffixrrradditional_params%common_prompt_suffix_new_line_handled)common_completion_suffix_new_line_handledoptional_ending_stringfnamesMAX_VALID_EXAMPLESn_traindf_traindf_validr!r" files_string valid_stringseparator_reminders rwrite_out_filer?s  #I*2998D.r}}8L EdJ$$ Z 5E,@,H,Hu,U)0H0P0P e1- 8 9A = ))R(STO P  VJ E [\a[bbcducvw^_D^EE]^t]uuw x  ""% :{ 3ue, v;!#6!9(<FSTIAU UU!% #b'$66CGcM8JKGyy7y>&;QR /4vayk+" 89Q> vx]w^^vw  #L>2Z[abc[dZeefgsftuFtGGKL^K_`v_wwy z  ""% ?@rcd}t|jjjdk(ryt|jj t||z kryy)z> Infer the likely fine-tuning task type from the data rrdrzconditional generation)rr4rrr5unique)r CLASSIFICATION_THRESHOLDs rrtrtsU ! 299==   1$& 2==   !"SW/G%GG #rcd} |dk(r|jt|dz dn|jdt|dz}|jdk7r |S||jdk(r |S|jd}w)zQ Finds the longest common suffix or prefix of all the values in a series rrrgNr)rrrr)seriesr common_xfix common_xfixess rrrsK x JJ[)A-.0 12c+.23   ! ! #q (   =//2 2  (..q1K rctddttttt ddt ttttgS)Nct|dSrr3rEs rrFz get_validators..s,Q9rct|dSrrJrEs rrFz get_validators..s,Q =rct|dSrrrEs rrFz get_validators..s&q(3rct|dSrrMrEs rrFz get_validators..s&q,7r) r#rBrWrrbrvrrrrrrrrget_validatorsrOs99=#!!!37&&**) rc.g}||j||D]*}||}||j|t||},t|Dcgc]}|j |j|c}}t|Dcgc]}|j|c}} d} |r=t j jd|D]}t|||\}} | xs| } nt j jd| xs| } |||| |ycc}wcc}w)NFz? Based on the analysis we will perform the following actions: z No remediations found. ) appendrrPrr rnrorpr) r rr validatorsrwrite_out_file_funcoptional_remediations validator&any_optional_or_necessary_remediationsany_necessary_appliedany_optional_appliedr!any_optional_or_necessary_applieds rapply_validatorsrZ$sV$$[1> m  " ! ( ( 5,R=B > .1 5 ''3((4  .*  5 ((4  !-  P 1 LK#=K$ B $8#K;K  L 78(<(U@U%E#DkR=  s !D ?D)r5)r)%rrntypingrrrropenai.datalib.pandas_helperrrrr r#r3rBrWrbrvrrrrrrrrrrrrrr#r?rtrrOrZrrrr]s 66:5$*$ I #L-5l+C:2+3L)A2%PIX$N!HIX6 :$,\":Yx I  "  :  JAZ $0(0Sr