Python-解决SimpleDirectoryReader读取PDF乱码问题
一. 结论先行
缺少 llama-index-readers-file 和 pypdf 依赖
二. 示例代码
from llama_index.core import SimpleDirectoryReader path = "../file" # # 创建文档读取器 reader = SimpleDirectoryReader( input_dir = path, recursive=True, required_exts = [".pdf"] ) # 加载文档 documents = reader.load_data() # 返回的结果response 是 List[Document] 列表 for document in documents: print("="* 60) print(document.text) # 输出的文档内容 print("="* 60) print(document.metadata) # 输出文档元数据三. 错误原因解析
1.有 llama-index-readers 依赖缺少 pypdf 依赖时:
Failed to load file D:\Patrick\Study\PyCharmProjects\AgentStudy\LangChain\进阶 RAG\LlamaIndex\图文类型数据处理\L1SimpleDirectoryReader + VectorStoreIndex\..\file\公司季度财 报.pdf with error: RetryError[<Future at 0x2032dfd4190 state=finished raised ImportError>]. Skipping...2.有 pypdf 依赖缺少 llama-index-readers 依赖时:
============================================================ %PDF-1.7 %³ <</Filter /FlateDecode /Length 839>> stream xXj0}/\F]_>1JB҇~Gldw6aJkϙ3R@)SD("Ι`N?o߅ҔU~=}{,S.^Pv?GwHzZ2>-Xpftϥd d,:XlFV3o@W tUV5.b^]K|J.!~wԭfܚ:.W4/]r`Rr-.UDM>Lp%+vVks"b}>v%U'0JӁo~<7iJZG߭%lޞvqRXOȆ:@ 8hKU1sBa|Mi9zAScO4)k7"R.@.@gǙ8<R܄F9t*R݁[HzU0:p;̱+PYh75SpP;Ҥ{ <</Filter /FlateDecode /Length 266>> stream Yڿ_I <</Filter /FlateDecode /Length 21013 /Length1 74640>> stream xxTE9e7 %jBHB %$-*"bE@D@QQP;v*+=f΄>_{̙>9!FDt y]GM[xQJH{J? g4B~oU)yime? ==|/(Xxa\Fp- CU};53+kmŘvPshEy6N!Sh^L%}}Ne0!j4=N͵hMb6:wl~! ف٧h)Vh`b2|ծp6\?B SjmӘGOEzs\{^r&;)h1'86>Ό˰C/KPrȥڥB.bZGeXWqDr)ϳ|Mf6K{S`6QsޣG5j `60K,.qO`xPk"_bI^0. ue;aJP,>z5w)>t%__尵8icp!h 9NQd KAW|5;jN(F8-B<x醋Ye"nITѮmzmM3is5-99fڨ^cc*<eܾnU[8ޖvS?kvvPNI%慍G?"P# L&:υ}g!бEnvRM G}adF5MߏHjШ9 y` 0 GݬFec>GIT`GOX&'"g+uc 6%j|H.w>S#Wi,{@WN)ꨍ eꠥP3m,/4~+[Of!Zj6e;0 TX{Oĺ諈[K~sTu yb3e?a cu<U4':8{nl_χA :{>,E>zcͺ2 4CB.˴υqOxv9b<^}opγgrY4Rَ5D)(l4{A"Ik7Q+mgNc(m~&L~j9g}^?]w"s{x8}h}b<Iuj3#2[nB^Z$\LQ.AQM= vg^>g~(nӋlP=~'zȴ㉲ Ʈ{Qxy1G乴9?_lնWx?SS.y΅<ؽs3qKvvk0W~r y e| ;>S;}ϔ{ /ڗ/$_#Ym&B W%;[kQɟ\}|פ~_.ؿc_s!s2]Q{>>0S\c>[ȼ o˞]E sx_,@[Xn?BffOh3Bijϙ,튳"b{a?H{inWjBĭGzs:s G?Ny~.{u)&Ґ8h.璿'ʳZ>g@: )1SYIxy7B?L~^|W) ӿǏ^p;='Z ވ#[(8>\UiNs<m4S1O@~4[OB{cm7;lsDpc|DyΟ) E8`L!@jS<٨&~rx"ޯ6\Aю@aԀn=D_qG%4D;p]of]v!4F_Dx&ؗvY'3V9ٳh~I^;J8+ pɁU5T݈^xyM:xa>飼<~"$P^?ɒiw~~}m-Bfof58^֫<MeW͆}rD0'PUb0B;Q*di\Ψ%mKPmӥE6m۪ {&ŋwTEDZv"S&G~~oPAsiE^4ޱ<Wb䟍́j}%>|+N}2~5X\'&O2|h;:{p5vEp,DcnfFUUʥ;xȟ)lD$OC>CyE>&RosѴՉC<MoXCK=?V\ַ c@]BUX `l5GYg}l4>ߟϥb(LAV%CְպKSAO9ub?mF~G⽪v\F3&wShc|wce(杶~^#RQ~vl -aaXV(l3wCZgu!5 0gzmQ Y@v )t0kq#t<OcN`\ca =6pY7$>idtcMd'j9'ʸb_5 6ަnأ݇ب&t隋i>tNQ;&&SCGg(Kϫ(+/N1"[1碼Ov1L2WeeeTCDr؏63c]w$_/;kNѬG+5'`ZN.¼GC )P7I` K3}hI:aQ_I"S@csүF[ wtD&j;})YB<̲yZH# cPz O&0.s>h֟i4k3re(5v:.44,2hOB \+x<=<'inNC7s(M#ҏϐCe6ӖmWJXf4pho"*Я6%pXS[zks9t?b`6=@}$8 A-A#;^K$A 1'+5w2ăr6xH{tnZ{ad-WiMpCv6<pd|!cp¶3z=w&qZe: fs2$mn߷v8-vl5%KEk]:% 05 aW4D/@h!:E:vkؾцgɲw0Ylc|s}N~q3T1L q ^~(>yΆnUF.%MA/Gnvl%~49 /@uܿHH˂myC{.`O ;^sXM^;5v`nF5w]c;z=gusG˺"NhMI1$_=6@p_h˺v0vzlm6M`[z/6x<llm6<M`[U{vl:m8_LA;q!mF[օw8Qgo&ObNjnݷp7muWibn3c~Zosyϱk?wSkZ3ςN7WroT?83yڕΡYQMmTHD>0N]d~zk:w6yy:js}?ySľ߃}}a_k}}X}oF^騳}^Qo4CG[kIs!4ʟB^cy]v#`3Hp>?-=?u8ЮvzmokE4Db,e T+v~={巫W^|zvu=̎yNCγZ {OPcͳN Iܫv#^*u?]Ocp}x;?տ95ȱǶZcP)t9ՙ`h.uRKkRϰ{IFUb\f;QKKAwtsm,ж-{# 5};Mlĸjq4hDWiLijt#~Ʌi Dͦ{ mtq&q-4X=K.ߦ$7o3fh6B9Jo*?4Ksda̖is>4ݔ᷇Z韢.|0]8M?`mq_ 'Gc|Hl'P<E9r#iF]UmoN4oc8r3$ ~ጧI+li#/Oaq3}Ji O(LBw"/wG =7s~#5Cހ59ƨO} mqh4&#fPbV0nw;*)#&)Y?aSwKU|\ZZ<ݮ=C4ncoaLnۑ&j/S";i$9{;?ˍ w,/DV=(gi {J]t]N/#[b}l~=zXZ̟7wY3fL6uJ䒉 Əu5rDaCd4p@VfF~i}ճGJn]۷kۦeRbfQa!~Ni6 YEq"0p`[N(GG;^Y5øD!V42:$M۶LsWGB_>)B7#xĈˌfEqES32 'mCBsL˄_#`~[Y\'Hv<q._[JJJbD*3˯t%[%d[-, EnNN@b#ofbhB\/'<Qӧq$B\E&\W:!o!rueMýbDt Jk֊J_YTG/JMYd_45ʽbb\6}?q=έ'M4 F2eߡ=x5uOHH`ڨ\Ŏ廉Iv,wAV.q:Sp7FI,-)uEFǻP}y x+%[}ŋ;X([*0/3/.Wxk#.{B(K8yeѤ.H=@~IQϋ?h;Of+PxTIYyZeN`DM;vjuSua1xsTD\iHFxVsSN\n䄼\^6^ע}G%dm5\zt)C>Uws`˃' u{xr^{brB<g6((~tQ,Lw Y qqYŕ֊dMqQ0<aTnhˣ{S64Jߟ؟} (n i7ǵ` _rOH8D҈VIc4R~FIFi! WB g? ~uG\-8 ÉɗʄaB2!'`90tt< Ysy1@|R.fdctNvfq`&6Z2LH\y\hBKD)B#Ut:>hVL˝Ύʳʹ:خ6NY5ĸ`<Hǽ"'()W !_|QG &{zVv7I3@g=A, n8Ql0tRV*2PʥJD)˕rR)eR.R,V",TW\QlRL)eR+eR*eRJ2Y)%JJ)VJR RlbA^뤸VkX'Zj**)HqWTDq*"K!VJqYEbEE$&cviEd7KX._,-biEd E2)KHR,bLz>W9 ffɐ3(bӥ&MbY>Yr(HB)&BȜb,tL:O(W2c\2Rb#*" r*"WD="bЊCdl)WD.`kgVE%WBdTD\ ѿ"bDzExD?)ҤHoE8wGzWAgE= ѽ",[EX>DWy+@t!;VcdmHL-H""Rs)dd28J12^S)H-Ec)U@DUNhX@H)"/E&#J)I,E(CHO)pJ!MҐL N?;~_ k?=|N+p| 7%zSc?CCc3b7b C-89U x_ߋ3c_< lg><%)}=ia~< pм؇> P ~pĵ xQ=Kc8v_ؽ{vp[`ݐ[g;}; 6u#ڊo3lGz6`x5Sb6zbzJ*ҵuK]]] \G/^l-Ow\ZZw"bג]jWP:kޅ.caYBa!ha¸z<\4/gފyyF/i4TZ̋ɂLr^ph\lל]Jg#R*M)qM[ )i_MJ*N)r&-pOwۛ O)ٮ!{]SD=P&qMPaM)fӢ?>ڠhwh=<qlcUH#x#6ѥmDEj6Q?avY A\=YBfHٱ(vlHe~ɮ 1F,BC,26K?G`cJ?fk܉n7g<z;_"ܫr+;eWp=-M A'_8?97}}X+Z Bd>^l=i:v /+Xo^A9Bc5Wj@--0VZ`Y /s 5ad<;/?B?<6PY8??;{=,r*V2\ .`X f 40L_XM%`A(@Ɓ|rX0ėhH0` l0 2AA?RA_@O Π:hڀd-AAs xbAh h4Q!h "AA!A L`[`y@8NS; ~?=|N3_%5 _/3)|>=.xoQ&x^W%"x<G4x < 1(x<@%8 w}`/ ;6 nN6p# 'ȌGY(&?bZj85PW:=lP%k{0չN(ꃪW}p2G>^Ѿo~ܱCtZDCe5PYWݱLKR42$'d;tcaazHhN"[Νj]$%4 .ݺ;Wn~&_^.IHٌi0&Qm{'ػ]St覟efeu5l4/iȦaΪz~4oި;zOmo 2&Q^Ƅ5뇆5s_uEdFHVPbj>Bq3A^BE4O%7KB:ǣ,Z0τp[MGؤGXc4G]h =S~[hC䅩4Oe]RYTZj$hiW6+zve]YW\8d 'Lm:!5mBߦV\V{¨nzJo7dŝCbBzLgaz3m1F4ullnCؐnPِOWEtQ>cCD;ϛs%$Vl*Fi"Zrϖ<jJ-*qLHB PAś7"kim(:[3~_V@l*5qԁHhĻw.sX@mDWQ1lLgT6j?G?X2 `#[VH9Og/[zGir2ezɽvpM )>-M/{o;7&7Yp/ټy S=D!cA7a͛MXB4kޘ5oĒXRCJNx\(` ʧV[U.d!äUV/&G qޞ~W_a i>E8oF9Zñn6H ד1bYIIRI$)Mɾ)Mɵ|{։*k8]8W$<δh2`-\{8L!Z X+Pg~( ]G'7k( EPNJ.! q<2 E"Pw onhy[!N2V0STTBUL-H}u,PFjiQs00FSENRǀP%@==~uPs[bX_`≣WkTΙT22S=z*Ϯ<oaAN9/Vw}$O{'4?lo+H/уg7WQ <</Filter /FlateDecode /Length 522>> stream 4sxϭ5-VB;2Nsya)~Ww <</Filter /FlateDecode /Length 31734 /Length1 233784>> stream xkduvUutt<vwvfEcwg]ę@ĂIq < Otct]\k_wLqwGq??`E>ckgO4SksJ}ha㬣aϨeWߍͦ㷙_pxᯜvx?G3j.ہ/{Ep;GRq}dۍ9Uگ{OjqJ=fS7&G긼7]C/ C^g1p|qV'i๋5qEǚ(㡨5#1N~x!L=mwqlG|84qJyse4R_y1J9'd2eۧ/ڢ>˙Li<bQ_\cC1X"cd>{',u: |.$H|yV22<-Ƈ+hgN|!Xs#SվxGT`1\561r;R;aAdz9MGLcl/:C rOLM)G#eg@ܮo~$l[ʩ\<>$&.#}sw{v-*#^Mr<$)?ُ<z7^r<}~tI'OAq^&r+}%ٗ+>qɋ,%"(|#ߘh;,u7&Gl9Pϳ:=Y}Xc˵Ԭ m1u}A&@LEo/k㜈Y3>'[yޔ0djLҦ0-3*Flܡ*߉2gvχ!]59 nR=Kkc }nWE]6 cQ5l]DN}L>Wq鉚՝ H}3L>=]MΫa{A5+'ɽfi}B8"?c sH{,әl?Rjyn9f$% Ƅ䯩j~C'Gsl5z~f"g~eX0lWVU?7Tf=5{y}193϶\M5k7Xb7^ѽ*v@#tp'S4ΐ5;9 ?h-dX<\_{SS K>4@E/dH>U6`?;.c,'(1Psr*gArk'WWr},(-4K,pߺ:'tM]Q/+CF8n.yQm;@7y]C^d}dblÑkaGc]gjN *ɹ\+u"×a$.q6JcB;a>THg\`?L/}bY``3ZT|\ԥ,wsCyPȚ!VƺPջzNլo 25זg:]icsmfDz2ymlwWcrROE9(XWd|^ƹj. 19neTu?!I"4H,r͉s5V| _X0A빂1RfQsBmUz瞤SRorJN r<7ܟDͮ|cXrNlomٹo"FyfZT;=嚮NMjq&AӜW\JD_kG__uF?)+,ouEOUoѢv1p}H}[O8^/uN) KX6YIA |6/<%O;v$mў̧Da_y_[R^K\C|r9: ]'UTFxw Q=| G1Wlwϣ|mϞg:yzpZ91/81.瑜?hאkH|㽫T\o>dL噷{IZ\kDӐzK>?W8q|uL,q{,32^=gUFgW3aч3;KΊ@GUP>Wu]r+"9S;|%߅*>?:ig8N+bgQ!7go{ ~ہ[P9{W3vt$zG Mɩ6C|>aD_>; lpBGj,p`:) Om`Ӂ[PǀƞdO_ eN~ʲ6sn$p (|GφEۇFHJu}V+d?awU>ZSQ$\_n3uYηv)U}߱=IJSy;rOuSʵܧuεbdܦbq/f%i<|6& ˲S }@I]{uylNI<[9PI/ޞuq@f/Ąq>Aylg7|2 go~c=ĸ܈l+ڪS#pJY=_#1/rѦVsBWy>#_;.+텯O%|u|q~G5g_CGfW{X!&q[+pbIҁ6wGهE.1nOԕv]]HվS9('Ɣ2!eV(tB7s(:L[ʍD9ޣ|o"e[Su=m'@)':L@-ؓB'-ӚQbP--ہng<̴W!9LL+?~}KuAey~KYB=^|֙_}֤C&bQƕu>LVf?v{#b>ujeO 3<qcUͷ:Km&p9H[ק[J+oǶ\zS)K+x ˨:P~|fǑ?AW6:Q,wl9,R9Ce,pUKm}kq/6,}\v[K^˘ {g|ϒ_uڈa9d'+߹&ᐿStSr6n3r*3V}[xlۧWd|H~vH ˸-w{iP[) t3t Kg;d\\~=ugvX:C zG"bpp٥4Sg*}]@ߘWWc/\h<F;6lsqed{n :kM^O:x_B͎\Z۷.dxꤔ/㩧_O?ӹDu;Mߜw}TfK^2?x-}OU#nxR)<>s76g'auP~X16/ t!>!8ΰ.`Icؠ+8l[w2u"o.96qG=u>u8L#Nx 5=q#.+y<uťSoA[s\U=Vՙ1SX;GTfц/e/˔Ͽ= >и$_>E[ƿKc77 OX/)pI>$v>:)|a|-iلg[;'czь,:bҷ'ۖvQߟ|LI{KϺnLt ^'Kۍ>%}mG~W sllז]3&|͔stozxMLe}?|dkA/m>-;Srl}h |;(U>%|nR5;}9fܣv"嘪9h:4-sUͱB&?K@|4hxwLX;;Ey<{q9NLU:|a R_AK\9-c<ti[36l2x(S~bQ2ua%slJ9ƖLB~*9J8hTV?ۚݺA\hts*'r0W3xښ^ckcz`Nn.?ru]γ|:o8?9WAM%+L\4Z̦{GZ-S8Ҳs r،J?ʕFf! EQ,}ܶ[3oHOR:Z.%Je[˦)vS;ndN;/AJ1S3M|&;.Uz%ber˯lVeԤJT|%SdSya'5ŏF-"(HVtL-Tԭ$Y#Q<J<mlYTa0齡A#QAuó~TE+O*ul:;inx7#iUz3;UҌ/㙻ĭJͧ~t:쫔R۞F@S[xaI:ԐlWS"XCv+oLc)3|kEB4 Ww不Y.i^Nu`WeӾ$Vlcfg;H\5%-c[uաj}1{.RX~kb(c1%^z.ki-˖ў[\K>/d=]JE2.8lzn%v}[ WBQ3~¢fV9K͏֊fk#*-ZUqg\i6t}-gwb^ic{e*;2ܚ-I+TŔnkazua> 'Um;e sqȎ:N*}ʝk=+WVm[ogLa_tWFl<o)o;}+#ihߎ7mANy^l թk:mMp.{N~J vXKeKOiXv;58J<݊{]e\peV]۞5JmNԙ>~yz<MwVzYƣ\q^dUtK~)>S^#3Չc)AͩfE /w?Skәk;؝8솔ȧr6$WqtJyeg˽PXWU+Dajo5ZNvXME'jVU|ZVRmRwD)gFYAMzkʭ&p\LC31V\dtLǭ;Q>3jULNUL%Um4)=NVQjp9mU;A֠'HiNܘVчNɗTqҹ<YJ.,UV/<8x1q+|lmx+xN|w#E+q0M,>iQpů|`%wLX#Wi3+Bd֜Yt"*Ol)0ǐ<Zt?1,fM[Õy}O2n`ycіSS+nUʝ\}4DEwG'Gt]tt!G?A?==5Cѫ3vttQߥKm꾯Ewŝ_ſ?ΏG/|~o?O~oׯ]?|_z=y'|Z'Oi7ӧIoӧ^㱽MW6yʥW76vW'{;{\{udjQ<^~US^y*湻^wy[?y~ ٓ7o՛,>vuOv'{oO6&Weoxc.ÝZBc\G&*wꕽo>KGs{KF'_,___klN^ʍ=uu_9ؘlKGLɆ5=zs^N+?7:7֣hǦΙThC#ss-[~;Q] Mk!MEߝ+:eC[-](svPzAʴwly,vl.6I?SY~3՛6]xg,.SRW_yZuCO]9h_۾jer~ҺƽWWD>~+7W'7o_&75n(ÈäͧO._5%pO^m}|kt497yS-lGGt^2yѽt4˜iNSs&֗>yu-';_[4ɵɣ7GT/)݉K7uoђ_S|ƍo,l]~<?9qeM|j\ZsU]Ү-N4fK}ꫦ˯^1ycs-u}MZtbC ԱFaL<ܜ^vQn``2Եc[cqV-FT'\ٴ-=8\TQ¿/¿/¿/~W~ۄ%@ o8.?[{_և @ |ɀCwɯ^ w'd'/0( (@ @ @ ށ @ w @ 30 w'F(@,E @ G |/7ǁխ2}8 @ @ @ ؉ @ @ VX; @ @op W @ ;' @ ;# @ @ @ @ @ @ @ pz2@ @ _ @ @ T8 @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ Vcu何ag0lݣͅ`p%_D2\ډdy{w*v3Q>=YNoӝ^\NwԹ{N/y(5n/bkI;oE)ɛ}ZG?P#vHֆ϶>ϴz^o0lln.OI*:ت(+I+TŹŅ8o9x=s̝WKܱ#v矲rx_i~-GZǛgN6/l=ovn||;}>_qq9]?粞Srgh%+RL+[4]l3i6Nemt8ٍ毮4ҝQ97N7on^;#w6sc+F̚p呥ݸ<<6l=gmM_;Z~Cks=48{l)^:rB XRE\=E+cZ.s8::5_֗ݺ/'VCj哫VGϟ asuVR^?R<8[7G^saNY;i{Z;nh{R*\zҹsO]VLsÆa}܌Gc~OlwV`w7{iwe?~߸k-Fq̛EZL?/k<0l?86tno}Z[$WySn9u_gggz=Y찻k׀16kD\B"l x0 <D` )s( WA@uWezfjg{g|}ߩX*:~ݴSIUQ \_dUKK+ss%R+USRRiZPsIG|9>f]^N#~?X4&E:l_+P)yQ8Km$?j @Tһљ*ބ BZq],<<hl.֥` ]\]BYi:IKKm[2=ioZO@xDž;`O}v}͐_aޭE97;GV{,1NE/=WTƼ鄦b䜦`o#m2Jaxcif +B S@Z[5E<()3uz!CO I}xDm]5pc(?0B=pN 8ikؔ"&YTff+3KM^K` XX݃K͵5/cL]?/j}M1&:Dp!Cgui4quu?n DVZ&gˠ[~pk(ڋ'38ѱ+lM*s؇}hhʓ ЭO;`8AS[@G!qE5J=/7Z:nzl}P˼!q躗5ms]'`<y%IU%=Ds|~CWu)*6<z*}π\ 4 MAI`7xzCׯ\=93uF~>-BtD-WVjA[C61CzpÔ; Vh,f0%Q}%hp>p3$LTv0̛Z.5XG~!a)]#\y9KOTÏCq+T"#j崡6{Ic=,%ǞM2srʣ8.vOYj$r_-ЈZ*bTJ+P6g {즩;nlZZ/ŕ-7ԛC{Skme8wvo%h(Wʆ}<Av_c%5ApOK}&%YZ:bxCO vȱ3H B(..{3Cqopn|{0q;Fh5q B-%6'_nl,"OY.SI7|zC WV p|SM(aPxw;_ίw_ѷO^?yW'&O.^8HcH xLP3l^ tK4)|zІm~9?:J[@)d.5pJٖdWy]?;2Gw}?*13`NJDE`ZjJM`v]b/xrA0USݖ@[B3NR ]O=PL(ruNRC%FUTi`0]dTf\eGUZ' K1ė@>|;NNdɜQFϛ;5Kz2\zΞ?e#T,LGQcmUw&`yqB=*{լr4vR mLf3bs wf3,*<NnPǃ<ު?zneRʊ}W=CD[Xt\}6M M5p4vg,zq}]@ClR@ momQ6;Qr"+dXt$ Lz,9cS:.H6eؗyfyٳ4Wٻb"Ƣٙϸ8[M[/vRL5 ǬlF}ϳĠ_Z ե%!@O}aP4++b1-@&DlU*l}wW e+hhͥ2,"<2_zhY&bum"Ԁ1h&l)W1d&Baq m 4DNZ6 ի[VYFkffZ{mWbt Ә Нbюʯ^3i)e;ml˘NkCr:>xcųlFg`ȍ"r-*"1p8Ξų3(/8NMU6^ko^oh8RQ⚞%:pS60 dNӭeqv.B3KN,?RPey{/<Om=YsQ e%gJV#I&0TyY湟 BFu},vh@ QQˆflYbF\ B7SAk 3E?xyZbALE^JIOVC딙J,3~ =۵,=vGݾоqr g2=r+ﴱw}к~uо)<PϊB,k4(Lhy#r#V1o|.RpZ5flGdgX]g\!k3퍸֬k7"]ۂaG-ٻ9}QY6u(1,%gKW%)6L!Qi҉\OU]pm=Vf%Op HQPw4hb`opSRs~6 )w./X xref 0 22 0000000000 65535 f 0000056710 00000 n 0000056655 00000 n 0000000016 00000 n 0000056797 00000 n 0000056926 00000 n 0000000358 00000 n 0000000524 00000 n 0000023625 00000 n 0000023762 00000 n 0000024357 00000 n 0000024520 00000 n 0000024829 00000 n 0000000286 00000 n 0000001476 00000 n 0000001616 00000 n 0000002029 00000 n 0000002207 00000 n 0000002521 00000 n 0000056838 00000 n 0000001436 00000 n 0000001956 00000 n %%EOF ============================================================ {'file_path': 'D:\\Patrick\\Study\\PyCharmProjects\\AgentStudy\\LangChain\\进阶RAG\\LlamaIndex\\图文类型数据处理\\L1SimpleDirectoryReader + VectorStoreIndex\\..\\file\\公司季度财报.pdf', 'file_name': '公司季度财报.pdf', 'file_type': 'application/pdf', 'file_size': 57574, 'creation_date': '2026-08-03', 'last_modified_date': '2026-07-31'} Process finished with exit code 0四. 解决方案
同时安装 llama-index-readers 和 pypdf 依赖
1. 结果展示
============================================================ 公司季度财报 以下是我们在 2026 年第三季度的详细财务表现: 部门 收入(万元) 成本(万元) 利润(万元) 研发部 0 500 -500 销售部 2000 800 1200 产品部 500 200 300 总结来看,销售部表现最为亮眼 ============================================================ {'page_label': '1', 'file_name': '公司季度财报.pdf', 'file_path': 'D:\\Patrick\\Study\\PyCharmProjects\\AgentStudy\\LangChain\\进阶RAG\\LlamaIndex\\图文类型数据处理\\L1SimpleDirectoryReader + VectorStoreIndex\\..\\file\\公司季度财报.pdf', 'file_type': 'application/pdf', 'file_size': 57574, 'creation_date': '2026-08-03', 'last_modified_date': '2026-07-31'}